from __future__ import print_function
import pandas as pd
import seaborn as sns
from matplotlib import pyplot
import warnings
warnings.filterwarnings('ignore')
sns.set_style('darkgrid')
sns.set_context('paper')
def print_ln():
print('-' * 80, '\n')
import h2o
h2o.init(min_mem_size='25G')
DATA_LOCATION = "../../data/"
MODELS_LOCATION = "../../models/"
MAX_MODELS = 10
Checking whether there is an H2O instance running at http://localhost:54321 ..... not found. Attempting to start a local H2O server... Java Version: openjdk version "1.8.0_265"; OpenJDK Runtime Environment (build 1.8.0_265-8u265-b01-0ubuntu2~16.04-b01); OpenJDK 64-Bit Server VM (build 25.265-b01, mixed mode) Starting server from /anaconda/envs/azureml_py36/lib/python3.6/site-packages/h2o/backend/bin/h2o.jar Ice root: /tmp/tmpp91hy6gk JVM stdout: /tmp/tmpp91hy6gk/h2o_azureuser_started_from_python.out JVM stderr: /tmp/tmpp91hy6gk/h2o_azureuser_started_from_python.err Server is running at http://127.0.0.1:54321 Connecting to H2O server at http://127.0.0.1:54321 ... successful. Warning: Your H2O cluster version is too old (5 months and 14 days)! Please download and install the latest version from http://h2o.ai/download/
H2O_cluster_uptime: | 09 secs |
H2O_cluster_timezone: | Etc/UTC |
H2O_data_parsing_timezone: | UTC |
H2O_cluster_version: | 3.30.0.4 |
H2O_cluster_version_age: | 5 months and 14 days !!! |
H2O_cluster_name: | H2O_from_python_azureuser_zrfkrh |
H2O_cluster_total_nodes: | 1 |
H2O_cluster_free_memory: | 23.57 Gb |
H2O_cluster_total_cores: | 4 |
H2O_cluster_allowed_cores: | 4 |
H2O_cluster_status: | accepting new members, healthy |
H2O_connection_url: | http://127.0.0.1:54321 |
H2O_connection_proxy: | {"http": null, "https": null} |
H2O_internal_security: | False |
H2O_API_Extensions: | Amazon S3, XGBoost, Algos, AutoML, Core V3, TargetEncoder, Core V4 |
Python_version: | 3.6.9 final |
binarized_final_df = pd.read_csv(DATA_LOCATION + "processed/final.binarized_final_monolabel_df.tsv", "\t", index_col= 'SampleID')
binarized_final_df.head()
NC000962_3.22 | NC000962_3.434 | NC000962_3.524 | NC000962_3.645 | NC000962_3.648 | NC000962_3.654 | NC000962_3.666 | NC000962_3.675 | NC000962_3.678 | NC000962_3.693 | ... | NC000962_3.4410251 | NC000962_3.4410260 | NC000962_3.4410272 | NC000962_3.4410278 | NC000962_3.4410728 | NC000962_3.4410850 | NC000962_3.4411016 | NC000962_3.4411170 | NC000962_3.4411327 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
ERR027458 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
ERR027459 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
ERR027460 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 |
ERR027461 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 |
ERR027462 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 |
5 rows × 52683 columns
binarized_final_frame = h2o.import_file(DATA_LOCATION + "processed/final.binarized_final_monolabel_df.tsv")
Parse progress: |█████████████████████████████████████████████████████████| 100%
train_df = pd.read_csv(DATA_LOCATION + "processed/final.train.tsv", "\t", index_col= 'SampleID')
train_df.head()
NC000962_3.22 | NC000962_3.434 | NC000962_3.524 | NC000962_3.645 | NC000962_3.648 | NC000962_3.654 | NC000962_3.666 | NC000962_3.675 | NC000962_3.678 | NC000962_3.693 | ... | NC000962_3.4410251 | NC000962_3.4410260 | NC000962_3.4410272 | NC000962_3.4410278 | NC000962_3.4410728 | NC000962_3.4410850 | NC000962_3.4411016 | NC000962_3.4411170 | NC000962_3.4411327 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
SRR10525336 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR10380004 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR6807701 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR11033700 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR1163101 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
5 rows × 52683 columns
train_frame = h2o.import_file(DATA_LOCATION + "processed/final.train.tsv")
Parse progress: |█████████████████████████████████████████████████████████| 100%
test_df = pd.read_csv(DATA_LOCATION + "processed/final.test.tsv", "\t", index_col= 'SampleID')
test_df.head()
NC000962_3.22 | NC000962_3.434 | NC000962_3.524 | NC000962_3.645 | NC000962_3.648 | NC000962_3.654 | NC000962_3.666 | NC000962_3.675 | NC000962_3.678 | NC000962_3.693 | ... | NC000962_3.4410251 | NC000962_3.4410260 | NC000962_3.4410272 | NC000962_3.4410278 | NC000962_3.4410728 | NC000962_3.4410850 | NC000962_3.4411016 | NC000962_3.4411170 | NC000962_3.4411327 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
ERR3335735 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR8552929 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
ERR067629 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
ERR067714 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
SRR5065314 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 |
5 rows × 52683 columns
test_frame = h2o.import_file(DATA_LOCATION + "processed/final.test.tsv")
Parse progress: |█████████████████████████████████████████████████████████| 100%
index_col = 'SampleID'
# Identify predictors and response columns
predictor_cols = train_frame.columns
response_col = "Resistance_Status"
# Remove the index and response columns from predictor_columns list
predictor_cols.remove(index_col)
predictor_cols.remove(response_col)
# print("train frame - predictor column: ", predictor_cols[0], predictor_cols[-1])
# print("train frame - response column: ", response_col)
# print("test frame - predictor columns: ", predictor_cols[0], predictor_cols[-1])
# print("test frame - response column: ", response_col)
# For binary classification, response should be a factor
train_frame[response_col] = train_frame[response_col].asfactor()
test_frame[response_col] = test_frame[response_col].asfactor()
x = predictor_cols
y = response_col
from h2o.estimators import H2OPrincipalComponentAnalysisEstimator
pca300 = H2OPrincipalComponentAnalysisEstimator(
k = 300,
)
pca300.train(x=x, y=y, training_frame=binarized_final_df)
# save the model
# model_path = h2o.save_model(model= my_pca, path="../models/my_pca_model", force=True)
model_path = MODELS_LOCATION + "PCA300/PCA_model_python_1603962989759_1_k300"
# load the model
pca300 = h2o.load_model(model_path)
pca300_df = pca300.summary().as_data_frame().set_index("")
pca300_df
pc1 | pc2 | pc3 | pc4 | pc5 | pc6 | pc7 | pc8 | pc9 | pc10 | ... | pc291 | pc292 | pc293 | pc294 | pc295 | pc296 | pc297 | pc298 | pc299 | pc300 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Standard deviation | 8.748536 | 4.715628 | 3.877237 | 3.107335 | 2.784571 | 2.583031 | 2.371838 | 1.989349 | 1.914256 | 1.835004 | ... | 0.241208 | 0.240459 | 0.239932 | 0.239419 | 0.238373 | 0.237840 | 0.237656 | 0.237487 | 0.236259 | 0.236189 |
Proportion of Variance | 0.319086 | 0.092708 | 0.062673 | 0.040254 | 0.032326 | 0.027816 | 0.023453 | 0.016499 | 0.015277 | 0.014038 | ... | 0.000243 | 0.000241 | 0.000240 | 0.000239 | 0.000237 | 0.000236 | 0.000235 | 0.000235 | 0.000233 | 0.000233 |
Cumulative Proportion | 0.319086 | 0.411794 | 0.474467 | 0.514722 | 0.547048 | 0.574864 | 0.598318 | 0.614817 | 0.630094 | 0.644132 | ... | 0.931150 | 0.931391 | 0.931631 | 0.931870 | 0.932107 | 0.932342 | 0.932578 | 0.932813 | 0.933046 | 0.933278 |
3 rows × 300 columns
a4_dims = (15, 10)
fig, ax = pyplot.subplots(figsize=a4_dims)
ax.set_xticks([49,99,149, 199, 249, 299])
sns.lineplot(ax=ax, data= pca300_df.loc['Cumulative Proportion'])
<AxesSubplot:ylabel='Cumulative Proportion'>
# Export the overall PCA transformed dataset - only for Predictors
binarized_final_pca300_frame = pca300.predict(binarized_final_frame[predictor_cols])
h2o.export_file(frame=binarized_final_pca300_frame, path= DATA_LOCATION + "processed/final.binarized_final_monolabel_frame.pc300.tsv", force=True)
pca prediction progress: |████████████████████████████████████████████████| 100% Export File progress: |███████████████████████████████████████████████████| 100%
binarized_final_pca300_frame_df = binarized_final_pca300_frame.as_data_frame()
binarized_final_pca300_frame_df.to_csv(DATA_LOCATION + "processed/final.binarized_final_monolabel_df.pc300.tsv", "\t")
# train_frame_pca = pca300.predict(train_frame[predictor_cols])
# h2o.export_file(frame=train_frame_pca, path= DATA_LOCATION + "processed/final.train_frame.pca300.tsv", force=True)
train_frame_pca = h2o.import_file(DATA_LOCATION + "processed/final.train_frame.pca300.tsv")
train_frame_pca.head()
Parse progress: |█████████████████████████████████████████████████████████| 100%
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | PC11 | PC12 | PC13 | PC14 | PC15 | PC16 | PC17 | PC18 | PC19 | PC20 | PC21 | PC22 | PC23 | PC24 | PC25 | PC26 | PC27 | PC28 | PC29 | PC30 | PC31 | PC32 | PC33 | PC34 | PC35 | PC36 | PC37 | PC38 | PC39 | PC40 | PC41 | PC42 | PC43 | PC44 | PC45 | PC46 | PC47 | PC48 | PC49 | PC50 | PC51 | PC52 | PC53 | PC54 | PC55 | PC56 | PC57 | PC58 | PC59 | PC60 | PC61 | PC62 | PC63 | PC64 | PC65 | PC66 | PC67 | PC68 | PC69 | PC70 | PC71 | PC72 | PC73 | PC74 | PC75 | PC76 | PC77 | PC78 | PC79 | PC80 | PC81 | PC82 | PC83 | PC84 | PC85 | PC86 | PC87 | PC88 | PC89 | PC90 | PC91 | PC92 | PC93 | PC94 | PC95 | PC96 | PC97 | PC98 | PC99 | PC100 | PC101 | PC102 | PC103 | PC104 | PC105 | PC106 | PC107 | PC108 | PC109 | PC110 | PC111 | PC112 | PC113 | PC114 | PC115 | PC116 | PC117 | PC118 | PC119 | PC120 | PC121 | PC122 | PC123 | PC124 | PC125 | PC126 | PC127 | PC128 | PC129 | PC130 | PC131 | PC132 | PC133 | PC134 | PC135 | PC136 | PC137 | PC138 | PC139 | PC140 | PC141 | PC142 | PC143 | PC144 | PC145 | PC146 | PC147 | PC148 | PC149 | PC150 | PC151 | PC152 | PC153 | PC154 | PC155 | PC156 | PC157 | PC158 | PC159 | PC160 | PC161 | PC162 | PC163 | PC164 | PC165 | PC166 | PC167 | PC168 | PC169 | PC170 | PC171 | PC172 | PC173 | PC174 | PC175 | PC176 | PC177 | PC178 | PC179 | PC180 | PC181 | PC182 | PC183 | PC184 | PC185 | PC186 | PC187 | PC188 | PC189 | PC190 | PC191 | PC192 | PC193 | PC194 | PC195 | PC196 | PC197 | PC198 | PC199 | PC200 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
-7.21528 | 5.48779 | -0.0457426 | -3.29582 | -8.02517 | -2.94974 | -2.96759 | -2.26629 | -0.652408 | 0.578522 | 0.182181 | 0.434753 | 2.51645 | -2.40717 | -0.0528002 | -0.867347 | -0.77548 | 0.779273 | -0.362249 | -0.189216 | -1.43005 | 0.0339925 | 0.0361673 | -0.59373 | 0.642088 | -0.0192343 | 0.0159929 | 0.10032 | -2.14885 | 0.72847 | -0.426612 | -2.17743 | 0.564177 | -0.419728 | -0.040311 | 0.174175 | 0.0958375 | -0.840905 | -0.412918 | 0.0362403 | -1.12543 | 1.47642 | -0.288826 | 0.204485 | 0.970888 | 0.830999 | 0.392813 | -0.160212 | 0.045166 | -0.775327 | 0.854433 | 3.10933 | 1.62966 | -0.403796 | 2.37824 | -1.07053 | 1.22014 | -0.0348898 | 0.709709 | -1.60722 | -0.537093 | -0.519959 | -0.607373 | 1.96028 | -1.37502 | 0.788434 | 0.623542 | 0.117146 | -0.662954 | -0.788601 | 0.0349831 | -0.104036 | 0.64312 | 0.498023 | 1.10188 | 1.07592 | 0.471287 | -0.870997 | 0.134068 | 0.192699 | 0.590267 | 1.93532 | 1.70993 | 0.0663423 | -0.0086952 | -0.131918 | 0.4172 | -1.12597 | 0.123066 | -2.76761 | -0.0105532 | -0.186149 | -0.528908 | -0.59734 | -0.125254 | 0.853391 | -0.353671 | 0.527961 | -1.19337 | 0.320649 | -0.910347 | 0.726797 | -1.19437 | 0.643785 | 2.2666 | 1.23807 | -1.71336 | 1.6379 | -1.35046 | -0.0621283 | -2.1299 | 0.338774 | -0.294789 | 0.635849 | 0.393347 | 0.461294 | 0.799493 | 0.182817 | -0.0629657 | -0.0312119 | 0.38403 | -0.29482 | 0.102779 | -0.0105114 | -0.613126 | -0.635172 | 0.318172 | -0.604303 | -1.23884 | -0.367584 | 0.13739 | 0.403578 | 1.11971 | -1.58696 | 0.0275307 | 1.58684 | -0.519128 | 0.250662 | -0.731469 | 1.03236 | -0.272874 | -0.146155 | -1.12871 | 0.518941 | -0.731375 | -0.186096 | 0.206038 | -0.129464 | 0.20192 | 0.0572525 | 0.337063 | 1.8732 | 0.718144 | 0.609294 | -0.0976525 | 1.02692 | 1.16342 | -0.027039 | -0.366797 | -0.126558 | 0.145244 | 0.0541146 | -0.293231 | -0.430163 | -0.623036 | 0.119761 | 0.0857521 | 0.654185 | -0.597948 | 0.906505 | 0.00763198 | 0.760529 | -0.196652 | 1.37364 | 0.38687 | 1.06562 | -0.592595 | 0.096302 | -0.982776 | 0.205194 | 0.795516 | 1.4415 | 0.103181 | 0.958078 | -0.024321 | 0.423626 | 0.416048 | -0.422432 | -0.822004 | 0.286042 | -0.334727 | 0.236006 | 0.430699 | -1.99712 | 0.0612397 | -0.281902 | 0.561714 | -0.545934 | 0.920071 | -0.603047 |
-11.6 | 5.53472 | -0.0676378 | 0.442869 | 6.54339 | 0.485848 | -2.2913 | -1.48508 | -1.26789 | 2.48786 | 1.61519 | -1.82951 | -1.14724 | -0.686728 | 0.0791433 | 0.244093 | -0.673544 | -0.298431 | 0.569891 | 1.3156 | 0.936164 | -1.74636 | -1.05101 | 0.351799 | -0.744067 | 0.26847 | -0.322997 | -0.0033458 | 0.139044 | 0.83802 | 0.0462784 | 0.18821 | 0.0188327 | 0.311519 | -0.103977 | 0.924853 | 1.06325 | -0.617407 | 0.416026 | 0.152573 | -0.00922459 | -0.540769 | -0.42493 | 0.224336 | 0.842236 | -0.0829223 | 0.104743 | -0.249455 | -0.237306 | 0.123351 | 0.373262 | 0.402359 | 0.0419783 | -1.21117 | -0.482892 | -0.974701 | -0.132585 | 0.422715 | -0.532571 | -0.512553 | -0.417771 | 0.55964 | -0.123657 | -0.481367 | -0.395624 | 0.235399 | -0.338215 | -0.311371 | 0.25003 | -0.187722 | -0.145724 | 0.0526789 | 0.49318 | 0.0865632 | -0.12011 | -0.482305 | 0.176727 | -0.126995 | -0.1996 | -0.169428 | 0.0459824 | -0.10309 | -0.100268 | -0.066558 | 0.290223 | 0.0640084 | 0.192294 | 0.367173 | -0.726469 | -0.255324 | 0.376527 | 0.0864552 | 0.429294 | 0.361994 | -0.0955574 | 0.10195 | 0.101228 | -0.164574 | 0.105739 | 0.0161596 | -0.309447 | -0.148715 | 0.0122466 | 0.408371 | -0.140452 | 0.34785 | 0.134036 | 0.312078 | 0.0964443 | 0.262582 | 0.0372175 | 0.103305 | 0.0706207 | 0.0719518 | 0.171051 | -0.0878448 | 0.0998239 | -0.0338992 | 0.00544983 | 0.186707 | 0.281369 | -0.021923 | 0.384559 | -0.145023 | 0.107315 | -0.314057 | 0.0957007 | -0.178865 | -0.00989666 | -0.151766 | 0.141986 | -0.228017 | -0.237458 | -0.12697 | -0.318449 | 0.113567 | 0.30737 | -0.20337 | 0.202596 | 0.386656 | -0.266906 | 0.164085 | 0.318025 | 0.0820759 | 0.14793 | 0.01882 | 0.495149 | -0.260415 | -0.0617778 | 0.362951 | 0.0325297 | 0.117637 | 0.113324 | 0.429079 | -0.334004 | 0.0182072 | -0.187317 | 0.081209 | 0.0555776 | -0.100039 | 0.183181 | -0.027631 | 0.00739474 | 0.274455 | -0.186653 | 0.177429 | -0.178171 | 0.108237 | 0.214357 | 0.279921 | -0.100227 | 0.434997 | 0.0841473 | 0.0511457 | -0.231324 | -0.0408152 | 0.0517595 | -0.00591222 | -0.212198 | -0.0753098 | -0.0714339 | 0.0261387 | 0.463119 | -0.0376576 | -0.0828916 | 0.152708 | -0.111939 | -0.132567 | 0.0222411 | -0.0039838 | -0.211777 | -0.19423 | -0.156346 | -0.166492 | 0.121824 | -0.110317 | 0.217815 | -0.0654254 | -0.119042 | -0.0851808 |
-9.1499 | -4.45121 | -0.000560915 | -0.211492 | 0.891811 | -1.61937 | -0.0314806 | -1.11622 | -0.521429 | 0.226712 | -0.650277 | -0.479117 | -0.996814 | -1.1133 | -1.26154 | -0.974177 | -0.00247332 | -0.0530825 | -0.201434 | -1.98052 | -1.29959 | -0.260899 | 0.78139 | -0.048447 | 0.238562 | -0.334514 | -0.853045 | 0.0713396 | -0.484966 | -0.619925 | -0.21595 | 0.653184 | -1.5664 | 0.0428643 | -1.3497 | 0.0193528 | -0.51782 | 0.820135 | 0.293265 | -0.509604 | 0.134869 | 0.00260967 | -0.452535 | -0.293624 | -0.00177784 | -0.149006 | -0.594837 | 0.165374 | 0.351211 | -0.462701 | -1.30318 | 0.00425985 | -1.19819 | 0.371879 | 0.325116 | -0.123847 | 0.937828 | 0.263567 | 0.0863833 | 0.268786 | 0.402629 | -0.26627 | 0.384837 | 0.60637 | -0.152096 | -0.0725101 | 0.792331 | -0.0321351 | -0.481089 | -0.42079 | -0.0660262 | -0.148211 | 0.378529 | 0.02314 | -0.0201441 | 0.487322 | -0.194526 | -0.0200701 | -0.29859 | 0.0686552 | -0.199198 | -0.241327 | -0.263722 | 0.519523 | -0.0661203 | -0.386223 | 0.337415 | -0.0933436 | -0.738899 | 0.41998 | -0.180534 | 0.162631 | 0.0589995 | -0.343279 | -0.141084 | -0.00846396 | -0.494676 | 0.062485 | 0.143639 | -0.154256 | 0.100058 | 0.0459747 | -0.10124 | 0.0749152 | 0.0433454 | 0.407651 | -0.00085629 | 0.272083 | -0.36515 | 0.186306 | -0.106947 | -0.179909 | -0.154551 | -0.239001 | 0.390033 | 0.103301 | -0.179483 | 0.22951 | -0.0668002 | -0.0825495 | 0.0340617 | 0.203809 | -0.275612 | 0.310813 | -0.0216203 | 0.0308512 | 0.295299 | 0.0617808 | 0.233424 | -0.602807 | -0.264453 | -0.0983916 | -0.367157 | 0.33488 | -0.248688 | -0.0103886 | 0.0212966 | -0.139436 | 0.126407 | 0.163799 | -0.0999936 | 0.159078 | 0.326816 | -0.422006 | 0.328108 | -0.12589 | -0.224009 | 0.165427 | 0.00736128 | 0.273949 | -0.432772 | 0.261663 | -0.032972 | -0.417354 | -0.222135 | -0.277632 | -0.151629 | 0.199935 | -0.109284 | 0.0932435 | 0.435215 | -0.0667091 | -0.0196309 | 0.346601 | -0.0825501 | 0.154359 | -0.164206 | 0.37597 | -0.136508 | 0.229612 | 0.213105 | 0.086485 | -0.0631953 | 0.159335 | -0.214413 | -0.114718 | 0.0446415 | -0.0986768 | 0.0589636 | -0.27537 | -0.470475 | -0.071911 | 0.185972 | -0.316124 | 0.204503 | -0.435719 | 0.31322 | 0.379372 | -0.0453729 | -0.167095 | -0.0395213 | 0.064882 | 0.348529 | 0.41005 | 0.0878616 | -0.0791032 | 0.187943 | 0.105175 | 0.19989 | -0.0378579 |
-4.59049 | 5.31294 | -0.043539 | -1.58611 | -3.70249 | -0.156249 | 2.93034 | -4.97455 | -0.930162 | -0.817911 | 1.69132 | 0.357042 | -1.68802 | 1.82346 | 1.65873 | 0.993338 | -0.769028 | 0.648757 | 0.739181 | 0.40869 | 1.46154 | -1.07547 | -0.412326 | -1.15372 | 0.033482 | -0.399165 | -1.04086 | 0.0623232 | 0.0584557 | 0.287642 | 0.441088 | 1.40573 | 0.373167 | 0.595857 | 0.777845 | -0.284434 | 0.893216 | 0.0325202 | -0.253651 | -0.256632 | 0.216368 | -1.11769 | 0.182434 | -0.300572 | -0.090939 | -0.220814 | 0.592161 | 0.422401 | 0.615093 | -0.910159 | -0.441763 | 0.315778 | 0.165484 | 0.419825 | -0.294703 | 0.0210309 | 0.213716 | -0.211021 | 0.879258 | 0.0419514 | -0.500143 | -0.0916183 | 0.199057 | -0.275862 | -0.313245 | 0.239273 | 0.113842 | -0.159077 | 0.669248 | -0.49075 | -0.165403 | 0.175773 | 0.49225 | -0.407117 | -0.818282 | -0.758563 | -0.0963912 | -0.253328 | -0.544874 | 0.221636 | 0.406422 | -0.219667 | 0.195245 | -0.149426 | -0.317279 | 0.582046 | -0.210104 | 0.849998 | -0.506772 | 0.455948 | 0.468586 | -0.264578 | -0.197681 | 0.321523 | -0.0873612 | 0.234735 | -0.205255 | -0.356656 | 0.246365 | -0.374521 | 0.216978 | -0.184585 | -0.550619 | -0.202771 | -0.722441 | 0.21047 | -0.227439 | 0.408528 | 0.615943 | 0.0445044 | -0.0414433 | 0.340925 | 0.294431 | 0.648748 | -0.191099 | 0.322158 | 0.419815 | 0.598406 | 0.141637 | -0.274665 | 0.482582 | -0.0160315 | 0.0962388 | -0.450854 | -0.0831487 | 0.363272 | 0.0283987 | -0.304109 | 0.0881775 | -0.281148 | -0.347671 | 0.48956 | -0.679409 | -0.0465728 | -0.0229669 | 0.305086 | 0.630215 | -0.247286 | 0.0045951 | -0.607346 | -0.00771802 | 0.229427 | -0.398598 | -0.666365 | -0.153768 | -0.323856 | -0.209572 | -0.241635 | -0.302749 | 0.194522 | 0.685216 | 0.00430719 | 0.027653 | 0.318633 | 0.318989 | 0.333135 | 0.345507 | -0.145466 | 0.0686151 | 0.115055 | -0.362267 | -0.616801 | 0.104639 | -0.34185 | -0.354017 | -0.435519 | -0.169556 | 0.060568 | 0.530617 | 0.252677 | -0.0308713 | -0.401517 | 0.370231 | 0.193731 | -0.212494 | 0.212407 | 0.0962742 | -0.0251926 | 0.013189 | 0.237966 | -0.0909133 | -0.31605 | -0.045298 | 0.43653 | 0.0797025 | -0.598752 | 0.219091 | -0.246436 | 0.355176 | -0.615051 | 0.214979 | -0.228767 | 0.174032 | -0.347543 | 0.355885 | -0.970259 | 0.529508 | 0.348943 | -0.0221957 | 0.282418 |
-8.68246 | -4.77252 | 0.00352481 | 0.0944094 | 0.517031 | -3.71639 | 0.988545 | 0.65286 | -0.217747 | 0.573477 | 0.52632 | -0.683847 | -0.328461 | -0.396951 | -0.832451 | 0.354952 | -2.34578 | 1.25273 | -0.0812596 | -0.894451 | 1.79601 | -0.755556 | -1.18765 | -0.329411 | 0.130982 | 0.0222099 | -0.690187 | 0.0358821 | 0.24405 | -0.157876 | 0.157296 | -0.45587 | -0.32256 | 0.496656 | -0.321544 | -0.447171 | 0.0159054 | -0.071811 | -0.527262 | 0.294327 | 0.0221319 | -0.44001 | -0.17165 | -0.0971737 | 0.0824659 | -0.32426 | 0.175003 | -0.121623 | -0.332931 | -0.109857 | 0.113921 | 0.185016 | -0.172949 | -0.146797 | 0.0518847 | -0.241559 | -0.0679523 | 0.0335394 | -0.397274 | -0.122382 | -1.07938 | 0.804987 | -0.784403 | 0.049347 | 0.0892695 | -0.234216 | -0.393779 | 0.12618 | 0.110403 | -0.293747 | -0.196784 | -0.247168 | 0.097565 | 0.275938 | -0.0729131 | 0.12785 | 0.167029 | -0.0804026 | 0.13433 | -0.384247 | 0.0972462 | -0.068248 | -0.183705 | 0.00138043 | 0.345901 | 0.314085 | 0.432695 | 0.0817047 | -0.247884 | -0.405813 | 0.264043 | -0.181348 | -0.0680196 | 0.263482 | -0.070708 | 0.145009 | -0.180823 | 0.155849 | -0.31145 | -0.0989632 | -0.0866583 | 0.464757 | 0.0708443 | 0.177191 | 0.00976185 | 0.113518 | -0.0383682 | 0.0381381 | 0.0265574 | -0.12861 | 0.16697 | -0.331246 | 0.162963 | 0.3131 | 0.0116855 | -0.170562 | 0.0675353 | -0.135805 | 0.1076 | -0.367674 | -0.00944606 | 0.664511 | -0.0524581 | 0.149948 | -0.37418 | -0.173271 | 0.374806 | 0.322866 | 0.0653631 | 0.117941 | 0.0171137 | -0.196438 | 0.183118 | -0.184732 | -0.196132 | 0.0925266 | -0.0897482 | 0.0666219 | -0.00172925 | 0.00750581 | 0.0064723 | 0.157167 | -0.30515 | 0.0055818 | -0.0963982 | 0.110583 | -0.139017 | -0.0481604 | -0.232714 | -0.160162 | 0.173199 | -0.0826625 | -0.241485 | -0.0495134 | 0.151465 | 0.0346363 | -0.148535 | -0.144367 | 0.0784351 | 0.09193 | 0.0801042 | 0.103298 | -0.0168575 | -0.121607 | 0.137488 | -0.080562 | -0.0122179 | 0.278007 | 0.300971 | 0.0471241 | -0.0783548 | 0.0483359 | 0.26833 | -0.148815 | 0.0062242 | 0.41095 | 0.1374 | -0.0122015 | -0.0344289 | -0.261423 | -0.131396 | -0.211338 | 0.00387303 | 0.082486 | -0.130322 | -0.137823 | 0.0903963 | 0.00290438 | 0.0638734 | 0.117863 | 0.00904495 | -0.0510632 | -0.0925759 | -0.00737436 | -0.108323 | -0.00531824 | 0.00543457 | 0.276971 | 0.245328 | 0.10757 |
-9.19672 | 7.94682 | -0.0615294 | -1.82745 | -4.61263 | -2.20144 | -6.78272 | 0.342489 | 0.726244 | -2.52807 | 2.35922 | -0.920174 | 1.58982 | 1.77681 | -1.02456 | -0.135104 | -1.06266 | -1.23535 | -1.06946 | 0.256949 | -0.135148 | 0.0709823 | 0.120553 | -0.212403 | 0.314243 | -0.718003 | -0.0869338 | 0.124004 | -2.44493 | 0.276341 | 0.149156 | -0.887986 | 0.74151 | -0.488781 | -0.0879999 | -0.646071 | 0.247737 | 2.36842 | -0.191677 | -0.843649 | 0.932515 | -0.412667 | -1.76671 | 1.40751 | 0.31721 | 0.412233 | 0.636046 | 0.482982 | -1.7244 | -1.14457 | -1.8538 | -0.382721 | -0.100829 | 1.13878 | -0.671918 | -1.06497 | -1.17288 | -0.097851 | -0.69384 | 1.24439 | -0.048193 | -0.645799 | -0.132279 | -2.03033 | 2.31706 | 0.017334 | 0.431449 | -1.51772 | 0.162575 | 0.758915 | -0.138466 | 0.136531 | -0.49254 | -0.298467 | -1.42526 | -0.740595 | -1.18069 | 0.513582 | -0.586936 | -0.203759 | 0.627928 | 1.36234 | -0.866153 | -1.29616 | 0.535693 | 0.415754 | 0.570849 | -1.48843 | 0.270096 | 0.543689 | -0.908162 | -0.105914 | 0.339703 | 0.496366 | 0.925362 | -0.933789 | -1.00079 | 0.00877185 | 0.322465 | 0.91807 | -1.99269 | 0.165965 | 0.353154 | 0.306088 | 0.326838 | -0.952772 | -0.146353 | 0.434984 | -0.340664 | 2.29767 | 0.0678048 | 0.420068 | -1.27611 | 0.259335 | 0.302944 | 0.911172 | -0.762877 | 0.00954014 | 1.78079 | -0.326688 | -0.603852 | 1.44774 | 0.267919 | -0.226292 | 1.30767 | 0.233281 | 0.24383 | 0.0630102 | 0.122896 | 1.05555 | 0.280146 | -0.134538 | -0.731806 | -0.285732 | -1.32877 | -0.335229 | -0.519341 | -0.643283 | 0.897955 | 0.672274 | 0.294411 | 0.143189 | -0.0573502 | 0.451826 | 0.42029 | -0.324798 | -1.14813 | 1.55177 | 0.302485 | 0.0641582 | -0.128799 | -1.17716 | -0.648077 | -0.761746 | 0.782809 | -1.34186 | -0.948957 | 0.617957 | 0.691935 | -0.00794323 | -0.36627 | 0.5934 | 0.669587 | 0.0575043 | -0.668937 | -0.208462 | -0.475375 | -0.114637 | -0.712252 | 0.706196 | 0.393449 | -0.0882379 | -0.215291 | 0.000254881 | -1.08491 | 0.26807 | -1.35235 | 0.83783 | 0.559586 | -0.905636 | 0.771805 | -0.450792 | -0.428496 | 0.0861287 | 0.379909 | -0.448908 | -0.729855 | -1.16339 | 0.153952 | 0.492471 | 0.122041 | 0.834458 | 0.341664 | -0.329075 | -1.22 | 0.723765 | -0.649107 | -0.778855 | 2.10345 | -0.932384 |
-8.97007 | -5.43213 | 0.00272524 | 0.28841 | 0.0794467 | -3.89085 | 0.632721 | 0.5904 | -0.127595 | 0.102558 | 0.71127 | -0.632055 | -0.726413 | -0.124563 | -0.851183 | -0.054087 | -1.16743 | 0.376756 | -0.485514 | 1.74656 | 1.82665 | -0.158678 | -0.241553 | -0.364044 | -0.217666 | 0.325344 | -0.32731 | -0.00430132 | 0.631429 | 0.602307 | 0.00693307 | -0.100303 | -0.522723 | 0.60247 | 0.181705 | -0.255738 | 0.049287 | -0.0754982 | -0.0537969 | 0.434123 | 0.0349033 | 0.0485308 | -0.263522 | -0.0376923 | 0.143516 | -0.22031 | 0.29255 | 0.0904726 | -0.0917416 | -0.0518825 | -0.134846 | -0.0404059 | 0.205374 | 0.4644 | 0.010876 | 0.265961 | -0.48591 | -0.116062 | 0.246857 | 0.0471285 | -0.153093 | -0.000917792 | 0.0952652 | -0.0410535 | 0.107979 | 0.0804973 | -0.144514 | 0.118716 | -0.216696 | 0.210607 | 0.135711 | 0.125965 | 0.0628714 | 0.127415 | 0.469845 | -0.0667844 | 0.299821 | -0.12846 | -0.310889 | -0.0219621 | -0.0634152 | 0.280179 | -0.190406 | 0.080822 | 0.505054 | -0.274689 | 0.0995224 | 0.129501 | -0.0746645 | -0.280162 | -0.00093445 | 0.325553 | 0.298584 | 0.290192 | -0.221259 | -0.316362 | -0.0866782 | 0.50856 | 0.115006 | 0.386605 | -0.0275449 | 0.325659 | 0.125141 | 0.1233 | 0.118446 | 0.213108 | -0.21447 | 0.103515 | -0.162711 | -0.146634 | 0.207015 | -0.172975 | 0.369363 | -0.117679 | 0.127677 | -0.0634523 | -0.0536918 | 0.192478 | 0.198908 | 0.342845 | 0.0431692 | -0.328894 | 0.326333 | -0.0311168 | -0.245055 | 0.268527 | 0.193657 | -0.103903 | -0.0323027 | 0.321355 | -0.0616184 | -0.0753923 | -0.0921688 | -0.204716 | -0.410808 | 0.132522 | 0.0881262 | -0.0974992 | -0.0268259 | 0.118561 | 0.39624 | -0.422308 | -0.047406 | 0.0247631 | -0.0875903 | 0.0627485 | -0.287498 | -0.0175366 | -0.152858 | -0.0592951 | 0.206058 | 0.0673219 | 0.0939456 | 0.0170619 | -0.254741 | -0.0368757 | 0.161321 | -0.00412753 | -0.240887 | 0.0474343 | 0.199414 | -0.133641 | 0.165681 | 0.0410559 | -0.242758 | 0.0618847 | 0.129121 | -0.0017245 | -0.135786 | -0.104665 | -0.0768873 | 0.155628 | -0.226643 | -0.311717 | -0.00275112 | -0.265139 | -0.243158 | 0.0752308 | -0.0870046 | -0.183222 | -0.145014 | 0.0244057 | 0.0655492 | -0.153869 | -0.140731 | -0.0511595 | 0.305929 | 0.215741 | 0.0643249 | -0.111242 | 0.0574274 | 0.0537022 | -0.31474 | -0.21632 | 0.0157848 | 0.109514 | 0.0300488 | -0.104866 | -0.133928 | 0.277623 |
-6.99841 | -2.98309 | -0.00022671 | -1.11203 | -1.20356 | 2.99938 | 0.792167 | 1.05258 | 0.65212 | -0.31234 | -0.192416 | 0.710371 | 1.59316 | 0.206608 | -0.346359 | 0.485749 | 0.635867 | -0.896472 | 0.680551 | -2.08688 | 0.475259 | -1.7706 | -0.62088 | 0.612203 | -0.14104 | -0.699463 | 0.650789 | -0.0262048 | -0.877455 | -1.0542 | 0.856707 | 0.541396 | 0.349956 | 0.331304 | -0.213139 | 0.774679 | -0.139329 | -0.975618 | 0.463806 | 0.715431 | -0.113045 | 0.272788 | 0.319152 | -0.40954 | 0.27471 | 0.268401 | -0.259543 | 0.272648 | -0.40678 | 0.375968 | -0.188106 | -0.108689 | -0.192379 | 0.104581 | 0.262699 | -0.559073 | 0.27288 | 0.414692 | 0.290314 | -0.357249 | 0.0937383 | -0.141974 | 0.278577 | 0.301905 | -0.266512 | 0.455196 | 0.227363 | 0.135629 | 0.354646 | 0.354206 | -0.110135 | 0.046093 | -0.536456 | 0.411382 | -0.566792 | 0.125481 | 0.255462 | 0.0793334 | -0.157157 | 0.179331 | -0.243474 | 0.172762 | -0.341583 | 0.134515 | 0.140128 | -0.0330968 | -0.587655 | 0.0485561 | 0.235821 | -0.0395163 | -0.205601 | 0.0350589 | 0.101773 | -0.0747391 | 0.271811 | -0.0368525 | 0.215494 | 0.00417177 | 0.11549 | 0.249065 | -0.0919896 | 0.147014 | 0.454241 | 0.0631964 | -0.0799047 | -0.206424 | 0.0626648 | 0.254552 | -0.126758 | -0.0135385 | 0.103113 | -0.0470452 | -0.0234869 | 0.0569321 | 0.302449 | 0.107023 | 0.197454 | 0.105974 | -0.0316742 | -0.0724548 | -0.143969 | 0.0551029 | -0.152243 | -0.124432 | -0.1107 | -0.0454275 | 0.375159 | -0.13424 | 0.113136 | 0.0845437 | -0.0824407 | -0.0427799 | 0.0288591 | 0.0546468 | 0.0112691 | 0.254756 | -0.0664561 | -0.0944385 | -0.0845776 | -0.348813 | -0.388426 | 0.331286 | 0.214688 | 0.12623 | 0.078729 | 0.133513 | -0.055878 | 0.361878 | 0.0198201 | 0.129158 | -0.133021 | -0.0430224 | -0.104172 | -0.0844451 | 0.123224 | 0.0786226 | -0.154249 | -0.234724 | 0.214356 | -0.176343 | -0.04811 | -0.278694 | 0.0631813 | -0.00826134 | -0.0339437 | 0.147426 | 0.21716 | 0.0806935 | 0.0963404 | -0.123161 | 0.206812 | -0.384298 | 0.0548116 | 0.0746361 | 0.0921111 | 0.371321 | 0.292604 | 0.190858 | 0.205624 | -0.305565 | 0.0741434 | 0.0436073 | -0.0483075 | 0.129479 | 0.0881774 | 0.144502 | -0.156171 | 0.154395 | -0.0339808 | 0.0232897 | 0.070536 | 0.143951 | -0.136796 | 0.311865 | -0.0452586 | -0.127641 | -0.00310456 | -0.0674689 | -0.220191 | 0.154635 |
-11.4408 | 3.91069 | -0.0533963 | 1.10893 | 5.12126 | -4.0803 | -0.0529325 | -0.577976 | -0.522176 | 1.24176 | 2.51208 | -0.801427 | 1.1297 | 0.173791 | 1.67921 | 1.44797 | -2.08321 | -0.945879 | 0.125994 | 1.41064 | 0.325474 | -1.19619 | 1.39569 | -0.668194 | 0.101959 | -0.806764 | -1.06909 | 0.0805773 | -0.168554 | -0.207682 | -0.179091 | 0.891167 | 1.12312 | -1.44565 | -0.22525 | -0.781858 | 0.780147 | 1.30059 | 0.0663721 | 0.0359448 | -0.750649 | 0.958028 | 1.12601 | -1.40816 | 0.400875 | -0.107926 | 0.268149 | 0.303018 | -0.481072 | -0.102791 | -0.0510634 | -0.824892 | 0.922151 | -0.337871 | -1.3525 | -0.644757 | 1.3427 | 0.283754 | -0.57398 | -0.602533 | 0.881829 | -0.876745 | -0.584974 | 0.0359255 | -0.32868 | -0.391202 | -0.447582 | 0.274852 | 0.142741 | -0.667909 | -0.863052 | 0.150856 | -0.438702 | 0.750841 | -0.385989 | -0.310674 | -0.0790464 | -0.0680184 | 0.222167 | 0.557807 | -0.11575 | 0.387843 | 0.725434 | -0.402882 | -0.535717 | -0.0202945 | 0.117413 | 0.429501 | 0.153339 | 0.107547 | 0.427923 | -0.50234 | 0.129575 | -0.141354 | 0.0388434 | -0.0238002 | -0.290518 | 0.0415737 | 0.249019 | -0.536361 | 0.304088 | 0.0245802 | 0.135671 | 0.179917 | 0.45321 | 0.63413 | 0.424292 | -0.215174 | 0.247985 | 0.175937 | -0.139369 | -0.00493264 | 0.377265 | 0.0013446 | -0.144286 | -0.400853 | 0.245314 | -0.0452821 | -0.565764 | -0.306721 | 0.324002 | 0.370195 | -0.194664 | -0.0298646 | 0.376266 | 0.237367 | 0.290039 | 0.000584293 | -0.080829 | -0.379429 | -0.182291 | 0.984333 | 0.0874452 | 0.135156 | 0.139681 | 0.240714 | -0.0559758 | -0.148529 | 0.0806939 | -0.633445 | 0.123141 | -0.271885 | 0.196269 | 0.205204 | -0.336892 | 0.410195 | -0.165723 | 0.561479 | -0.59274 | -0.224254 | -0.325978 | -0.140057 | -0.193693 | -0.0940802 | -0.162493 | 0.140356 | 0.183163 | -0.381249 | 0.251974 | -0.334173 | 0.0931959 | -0.000737978 | 0.117114 | -0.206884 | 0.101043 | -0.132863 | 0.152506 | -0.134385 | 0.452986 | 0.152312 | 0.0582496 | 0.0839865 | -0.260468 | 0.478922 | -0.232389 | -0.137869 | 0.0222461 | 0.0882454 | 0.173291 | -0.206527 | 0.0762306 | 0.114507 | 0.165444 | -0.0534536 | -0.0920498 | -0.0482851 | 0.156824 | 0.278767 | -0.235759 | -0.103127 | 0.351468 | 0.0567588 | -0.0251241 | 0.47271 | -0.35859 | -0.0731565 | -0.128044 | 0.148674 | 0.234844 | 0.228908 |
-9.28681 | -4.90312 | -0.00260397 | -0.0484381 | 0.264835 | -4.63516 | 1.50224 | 0.357337 | -0.17422 | 0.359103 | -0.99246 | 0.0470872 | 0.236459 | -0.685021 | -0.497964 | 0.286454 | -1.0784 | 0.287785 | 0.142118 | -1.95973 | 0.474228 | -0.131709 | -0.65227 | -0.0330496 | -0.160879 | 0.0376077 | -0.284 | -0.00654314 | 0.860162 | 0.59502 | -0.0143426 | -0.310572 | 1.18587 | -0.76121 | 0.469566 | -0.461658 | 0.66815 | 0.376559 | 0.294312 | -0.52857 | -0.0855447 | 0.393372 | -0.0614584 | 0.466387 | 0.167627 | -0.166838 | -0.0566179 | 0.261778 | 0.23537 | -0.023874 | -0.269284 | -0.301234 | 0.514908 | 0.0554866 | 0.213697 | 0.17933 | 0.155894 | 0.168836 | -0.581615 | 0.782444 | -0.508643 | 0.309706 | -0.0866412 | 0.319645 | -0.255015 | 0.373621 | 0.13159 | 0.355665 | -0.0152177 | 0.0343728 | -0.226289 | -0.0396509 | 0.0890247 | -0.314686 | 0.254015 | -0.00557643 | -0.073443 | 0.0256341 | -0.0160978 | -0.194006 | -0.0268144 | 0.115604 | 0.246627 | -0.255683 | 0.108665 | 0.26341 | 0.057678 | 0.14296 | 0.111766 | -0.331197 | -0.0193557 | -0.00387406 | -0.124914 | 0.0608201 | -0.222559 | -0.225016 | 0.0165621 | -0.0301462 | -0.088343 | 0.0176888 | -0.133887 | 0.13669 | 0.00392239 | -0.0276523 | -0.343728 | -0.10763 | -0.286567 | -0.199684 | 0.0126868 | -0.17505 | 0.224408 | -0.00865879 | 0.20032 | 0.0144414 | -0.162134 | 0.0565026 | -0.0137815 | 0.0879913 | 0.214719 | 0.086483 | 0.241405 | 0.307029 | -0.188092 | 0.130884 | -0.160446 | 0.00855652 | -0.345006 | 0.060206 | 0.0967177 | 0.109908 | -0.0354725 | 0.0919997 | -0.151296 | -0.127584 | -0.195341 | 0.168563 | 0.0190496 | 0.0890706 | 0.115683 | 0.112105 | -0.115679 | -0.0499728 | -0.0841381 | -0.15374 | 0.0492803 | -0.0540748 | 0.111392 | 0.137551 | -0.27198 | 0.0150838 | -0.259813 | -0.148247 | -0.00539514 | 0.0489178 | -0.063976 | 0.202161 | -0.171876 | 0.12256 | -0.0702188 | 0.254428 | -0.19253 | 0.200451 | 0.010829 | -0.0996432 | 0.112846 | 0.0234955 | 0.0498658 | 0.138928 | -0.0556585 | -0.0764542 | -0.341671 | -0.111084 | 0.141304 | -0.0660777 | 0.0418051 | -0.0573906 | 0.148952 | 0.108492 | -0.282072 | 0.164999 | 0.156052 | -0.0552209 | -0.149022 | 0.0272333 | -0.00249091 | -0.195615 | 0.248751 | -0.0022166 | -0.204083 | 0.100609 | 0.150012 | -0.12504 | 0.176794 | -0.0911637 | -0.0638807 | 0.209557 | -0.0724328 | -0.186826 | 0.0963438 | 0.144141 |
# test_frame_pca = pca300.predict(test_frame[predictor_cols])
# h2o.export_file(frame=test_frame_pca, path= DATA_LOCATION + "processed/final.test_frame.pca300.tsv", force=True)
test_frame_pca = h2o.import_file(DATA_LOCATION + "processed/final.test_frame.pca300.tsv")
test_frame_pca.head()
Parse progress: |█████████████████████████████████████████████████████████| 100%
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | PC11 | PC12 | PC13 | PC14 | PC15 | PC16 | PC17 | PC18 | PC19 | PC20 | PC21 | PC22 | PC23 | PC24 | PC25 | PC26 | PC27 | PC28 | PC29 | PC30 | PC31 | PC32 | PC33 | PC34 | PC35 | PC36 | PC37 | PC38 | PC39 | PC40 | PC41 | PC42 | PC43 | PC44 | PC45 | PC46 | PC47 | PC48 | PC49 | PC50 | PC51 | PC52 | PC53 | PC54 | PC55 | PC56 | PC57 | PC58 | PC59 | PC60 | PC61 | PC62 | PC63 | PC64 | PC65 | PC66 | PC67 | PC68 | PC69 | PC70 | PC71 | PC72 | PC73 | PC74 | PC75 | PC76 | PC77 | PC78 | PC79 | PC80 | PC81 | PC82 | PC83 | PC84 | PC85 | PC86 | PC87 | PC88 | PC89 | PC90 | PC91 | PC92 | PC93 | PC94 | PC95 | PC96 | PC97 | PC98 | PC99 | PC100 | PC101 | PC102 | PC103 | PC104 | PC105 | PC106 | PC107 | PC108 | PC109 | PC110 | PC111 | PC112 | PC113 | PC114 | PC115 | PC116 | PC117 | PC118 | PC119 | PC120 | PC121 | PC122 | PC123 | PC124 | PC125 | PC126 | PC127 | PC128 | PC129 | PC130 | PC131 | PC132 | PC133 | PC134 | PC135 | PC136 | PC137 | PC138 | PC139 | PC140 | PC141 | PC142 | PC143 | PC144 | PC145 | PC146 | PC147 | PC148 | PC149 | PC150 | PC151 | PC152 | PC153 | PC154 | PC155 | PC156 | PC157 | PC158 | PC159 | PC160 | PC161 | PC162 | PC163 | PC164 | PC165 | PC166 | PC167 | PC168 | PC169 | PC170 | PC171 | PC172 | PC173 | PC174 | PC175 | PC176 | PC177 | PC178 | PC179 | PC180 | PC181 | PC182 | PC183 | PC184 | PC185 | PC186 | PC187 | PC188 | PC189 | PC190 | PC191 | PC192 | PC193 | PC194 | PC195 | PC196 | PC197 | PC198 | PC199 | PC200 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
-9.62946 | 3.42749 | -0.0544876 | -1.99728 | -0.501536 | 5.33675 | 1.88318 | 2.34222 | 0.550157 | 2.24487 | 1.01714 | -0.274509 | 0.473391 | -1.15809 | 0.0800588 | -1.07554 | 1.76168 | 2.19104 | -0.0812096 | -1.188 | 0.480369 | 1.51523 | -0.73458 | 0.856701 | -0.463986 | 1.1826 | -0.756524 | 0.0237812 | 0.516223 | 1.13772 | -0.564756 | 0.633247 | -0.349465 | -0.067741 | 0.234908 | -0.444675 | 0.17611 | -0.532194 | 0.0915564 | -0.113063 | 1.13146 | -0.302093 | 0.490816 | -0.493271 | -0.585398 | 0.8064 | -0.424099 | -0.672412 | 0.236234 | 0.621226 | 0.421086 | -0.957542 | 0.609662 | -0.625019 | 0.188252 | 0.878188 | -0.0257143 | -0.138875 | -0.0223257 | 1.23374 | -0.363303 | -0.19214 | 0.637254 | 0.567913 | 0.199097 | -0.825055 | 0.482516 | 0.0236314 | -0.274883 | -0.26622 | 0.389476 | -0.254482 | 0.476774 | 0.806681 | -0.515323 | -0.268944 | -0.521861 | -0.0541904 | 0.0623078 | -0.427573 | 0.209428 | 0.675307 | -0.156747 | -0.488074 | 0.266841 | 0.216901 | -0.365613 | -0.483448 | -0.16199 | -0.311047 | -0.877527 | -0.30912 | -0.48697 | 0.149168 | -0.372397 | -0.163269 | -0.117403 | 0.138337 | -0.19628 | 0.201152 | -0.0601995 | 0.192374 | -0.52172 | -0.127364 | -0.232277 | -0.0896376 | -0.125402 | 0.187321 | -0.271664 | -0.2616 | 0.0108175 | 0.43486 | -0.319592 | 0.198224 | -0.258672 | -0.383842 | -0.435208 | 0.323674 | -0.708164 | -0.422046 | -0.207349 | -0.780153 | 0.00302298 | 0.213339 | 0.0179504 | 0.450774 | -0.478498 | -0.0366665 | 0.0296298 | 0.283827 | -0.472738 | 0.0141913 | 0.275673 | 0.052553 | 0.255064 | 0.240547 | 0.15366 | -0.170729 | 0.243725 | 0.588446 | 0.528715 | -0.147671 | -0.216204 | 0.56448 | -0.525028 | 0.0715956 | 0.332453 | -0.223248 | 0.61728 | 0.123985 | -0.0749367 | 0.0996517 | -0.257484 | -0.405051 | 0.293621 | -0.227607 | -0.427547 | -0.384105 | 0.20133 | -0.0139542 | -0.396255 | 0.0760807 | 0.15238 | 0.0874545 | 0.195867 | 0.241876 | 0.124269 | -0.272356 | 0.188318 | 0.0350412 | 0.100087 | 0.0796334 | -0.349118 | 0.14185 | -0.00669717 | 0.19513 | 0.223768 | -0.268808 | -0.19858 | -0.134069 | 0.213021 | -0.0708481 | -0.370438 | -0.42775 | -0.0108664 | -0.189859 | -0.370499 | -0.286406 | 0.192455 | 0.252574 | -0.241866 | -0.0577385 | 0.207005 | -0.373174 | -0.254423 | 0.370247 | 0.0748705 | 0.00531612 | 0.150201 | 0.0503638 |
-6.50059 | 5.03212 | 9.89964 | -1.75115 | -1.99842 | 5.18436 | 5.72881 | 22.9759 | -72.9113 | -19.4345 | 3.5075 | 0.688388 | 1.69246 | -0.351719 | 0.807579 | 0.162097 | 0.751626 | -0.18388 | 0.114748 | -0.708287 | -0.431597 | 0.0908924 | 0.351024 | -0.106659 | -0.333741 | -0.275902 | -0.0169099 | 0.738175 | 0.298389 | 0.173786 | -0.232006 | -0.157514 | -0.0104423 | -0.0416099 | 0.00259742 | 0.153628 | -0.130673 | -0.0629438 | 0.103533 | 0.00953883 | -0.0284005 | 0.101688 | -0.15913 | 0.126722 | -0.0756605 | -0.0757435 | 0.0441156 | 0.0158992 | 0.0966239 | -0.0160974 | -0.00503431 | 0.0116024 | 0.0095455 | -0.0067565 | -0.026261 | -0.0215083 | 0.0502305 | -0.0297334 | 0.00990971 | -0.0598099 | 0.0232784 | -0.0248749 | -0.0285802 | 0.00209873 | 0.0368059 | 0.0434571 | -0.0579956 | -0.000134279 | 0.0298716 | -0.0178984 | 0.0093227 | -0.0204604 | -0.0540928 | 0.0371086 | 0.00754352 | -0.0336085 | -0.0019139 | 0.00628899 | -0.0455008 | 0.052359 | 0.0163493 | 0.00218547 | 0.0132377 | 0.00211587 | -0.0146862 | -0.00559338 | -0.000155938 | 0.00755395 | 0.0033325 | 0.00209277 | 0.00105389 | -0.0748952 | 0.0101986 | -0.0145325 | -0.00125014 | -0.0258381 | -0.0540903 | -0.0410478 | 0.0387674 | 0.00351536 | 0.0128107 | 0.00557929 | -0.0619911 | 0.0247265 | 0.0154274 | -0.0321825 | -0.00951977 | 0.00769412 | -0.0357834 | -0.0591719 | -0.00457642 | -0.00606525 | 0.00840811 | 0.0210038 | 0.004185 | -0.014654 | 0.0225778 | -0.00183399 | 0.00217674 | 0.0351158 | -0.00135192 | -0.0150031 | 0.0036849 | -0.00310188 | 0.000879287 | 0.00355384 | -0.0084746 | -0.00534059 | -0.0105895 | 0.00742139 | 0.011533 | -0.00614121 | -0.0129047 | 0.020875 | -0.0049962 | -0.00231064 | 0.00582987 | -0.00690987 | -0.00203907 | 0.00527454 | 0.00045267 | 0.00388553 | -0.0197361 | 0.00423608 | 0.00979886 | 0.000483858 | -0.00017943 | -0.00964616 | 0.0194447 | 0.0148543 | 0.00513786 | -0.0106696 | -0.00341618 | 0.00174641 | 0.0118982 | 0.00116556 | 0.0209835 | 0.00243423 | -0.000339955 | 0.00521808 | -0.00359017 | -0.0172559 | -0.00280436 | -0.00727958 | 0.026531 | 0.00720347 | 0.00123806 | 0.0154357 | 0.00556288 | 0.00342277 | 0.0102327 | -0.0109282 | -0.00307871 | -0.00308189 | -0.00206439 | 0.0103463 | -0.00746865 | -0.00659294 | 0.0021469 | 0.00023555 | 0.0107691 | -0.00834449 | 0.0171208 | 0.00355487 | 0.0104005 | 0.00500246 | 0.000461584 | 0.000601585 | 0.00443169 | 0.016988 | -0.00255609 | 0.0107808 | 0.00364382 | -0.00654571 | -0.0063882 | -0.00536978 | 0.000630954 | 0.0107065 | 0.0136769 | -0.000218748 |
-12.9479 | 4.52013 | -0.0727567 | 0.795501 | 5.60493 | -3.83393 | -0.123111 | 0.276374 | -0.394928 | 1.5134 | 0.0998441 | -0.160441 | 0.875783 | 0.144141 | 1.50295 | 0.662061 | -0.152918 | -1.32294 | 0.494843 | 0.120914 | 0.409421 | 1.27984 | 0.89714 | -0.4064 | 0.436947 | -0.264961 | -0.504652 | 0.0964939 | -0.857363 | 0.640224 | 0.00723726 | -0.427967 | 0.128956 | -0.386457 | -0.294656 | -0.138751 | -0.556036 | -0.0155012 | -0.478571 | 0.665948 | -0.00757544 | 0.0321201 | -0.430406 | -0.53032 | 1.22734 | 0.12203 | 1.33503 | 0.968721 | -0.417973 | 0.607955 | -0.330774 | 0.561572 | 0.352208 | 1.5755 | -0.707895 | -0.909152 | 0.28725 | 0.0648046 | -0.0253563 | -0.217064 | 0.413599 | 0.61586 | 0.537453 | 0.0908139 | -0.675122 | -0.489732 | 0.581519 | 0.330403 | -0.240445 | 0.167285 | -0.323837 | -0.203957 | 0.662979 | -0.2441 | 0.212523 | -0.801479 | -0.320418 | -0.0492246 | 0.0482084 | -0.143322 | 0.540529 | 0.84252 | 0.304992 | 0.255836 | 0.296174 | -0.203431 | 0.15144 | 0.0989564 | 0.231816 | -0.0948375 | 0.383431 | -0.130254 | 0.368513 | 0.10371 | 0.252825 | -0.265766 | 0.268541 | 0.4523 | -0.0431464 | -0.282415 | 0.455213 | -0.159996 | 0.361028 | -0.260988 | 0.186677 | 0.0308555 | 0.137222 | -0.0186495 | 0.273489 | -0.342984 | 0.101656 | -0.162863 | -0.0422177 | 0.0131981 | 0.0687778 | -0.845328 | -0.289969 | 0.162009 | -0.372335 | 0.472539 | 0.335047 | -0.259656 | -0.0743039 | 0.104449 | -0.44302 | -0.00990119 | -0.361591 | 0.0910314 | 0.184432 | -0.366909 | 0.100612 | -0.201271 | -0.0203719 | 0.0346376 | -0.0766412 | 0.771028 | -0.373069 | -0.510017 | -0.192733 | 0.511328 | -0.358742 | 0.781616 | -0.0907365 | -0.162883 | 0.418575 | 0.385409 | 0.392492 | 0.235851 | 0.408559 | 0.663412 | -0.288445 | -0.388877 | -0.377931 | 0.790468 | -0.21487 | 0.369718 | 0.249138 | -0.0841726 | 0.257572 | 0.43072 | -0.0510586 | -0.0270357 | 0.427252 | 0.108473 | -0.256147 | -0.425715 | -0.244946 | -0.0475409 | 0.134611 | -0.35111 | -0.00822583 | -0.169693 | -0.156576 | 0.370779 | -0.390898 | 0.140082 | -0.15994 | -0.218447 | -0.174837 | -0.127382 | 0.27608 | 0.102577 | 0.085631 | -0.51676 | 0.410059 | 0.401514 | -0.0918516 | -0.368146 | 0.445533 | 0.517653 | 0.124488 | 0.10141 | 0.1146 | 0.217356 | 0.631302 | -0.333418 | 0.342894 | -0.226901 | -0.293725 | -0.149337 |
-8.94528 | -5.01545 | 0.00218169 | 0.19758 | 0.776913 | -3.34027 | 0.435418 | -0.418539 | -0.392206 | 0.0628038 | 0.194703 | -0.470089 | -0.505175 | -0.666116 | -1.32472 | -1.18856 | -0.0948413 | 0.846526 | -0.351893 | 0.994438 | 0.709866 | 0.0946708 | 0.730704 | -0.415959 | 0.20027 | -0.0269342 | -0.0357076 | 0.00894854 | -0.396809 | -0.561537 | 0.0696797 | 1.07964 | -1.27838 | -0.177258 | -0.92883 | -0.129073 | -0.399533 | 0.0544567 | -0.503208 | 0.225213 | -0.125742 | -0.401784 | 0.0836486 | -0.0663367 | -0.339606 | -0.0227511 | 0.314145 | -0.698153 | -0.384385 | -0.482622 | 0.123586 | 0.035008 | 0.0553435 | 0.375374 | -0.165647 | 0.576548 | -0.148979 | -0.522299 | 0.35583 | -0.475503 | -0.117024 | -0.0363074 | 0.171169 | -0.0971223 | 0.175799 | -0.0940921 | -0.145786 | -0.0449375 | -0.0327391 | 0.266942 | 0.371082 | 0.148319 | -0.192359 | 0.114621 | 0.0116713 | -0.0226767 | -0.0395446 | 0.123841 | 0.0915411 | -0.368156 | 0.142615 | 0.0449073 | -0.0961354 | -0.285895 | -0.399253 | 0.336092 | 0.151977 | 0.227483 | 0.1069 | -0.141486 | -0.397814 | -0.352355 | -0.152311 | -0.125061 | -0.030034 | 0.219326 | 0.22168 | -0.274953 | 0.037017 | -0.214727 | -0.0662301 | 0.107729 | 0.27112 | 0.0018463 | 0.0442201 | -0.279706 | -0.0151437 | -0.0484053 | 0.0693774 | -0.150624 | -0.0293918 | 0.0167988 | -0.0950179 | -0.343762 | -0.0134441 | -0.0923724 | 0.0734659 | -0.1104 | -0.0647773 | -0.27454 | 0.16298 | 0.160289 | -0.337939 | 0.134666 | 0.0826234 | -0.0991061 | 0.00194032 | -0.0835894 | 0.0239177 | 0.1042 | 0.0224501 | 0.264522 | -0.0986982 | 0.0640312 | -0.155391 | 0.038349 | -0.0327791 | 0.052411 | 0.0375473 | 0.042954 | -0.334741 | 0.101777 | -0.00269391 | -0.0725712 | 0.142811 | -0.197656 | 0.226308 | 0.21958 | 0.104074 | 0.0606405 | 0.151589 | -0.0177989 | -0.0394543 | -0.060618 | 0.034742 | 0.117939 | -0.0518007 | -0.0837149 | -0.0975527 | -0.203868 | -0.169478 | -0.268492 | -0.051744 | 0.0340075 | -0.114194 | -0.0014794 | 0.184438 | -0.115449 | 0.0871521 | 0.125626 | -0.0201496 | -0.211015 | 0.370505 | 0.161568 | -0.0331975 | 0.115279 | -0.0729038 | 0.167561 | 0.0427467 | -0.238144 | 0.0151419 | -0.158566 | -0.0342529 | -0.140659 | 0.0779365 | 0.0792503 | -0.208821 | -0.0337909 | 0.168655 | -0.0670168 | -0.0351762 | 0.178609 | -0.0471835 | 0.136935 | -0.0638909 | -0.146832 | 0.177575 | 0.0438678 | 0.0781435 | -0.19136 |
-8.61603 | -5.40221 | 0.00811241 | -0.470638 | -0.436735 | 2.80297 | -0.717564 | 0.0320249 | 0.384208 | -0.915967 | 0.109527 | 0.47088 | 0.56927 | 0.160269 | 1.68617 | 1.00034 | -0.268822 | 0.0977931 | 0.296411 | 0.619891 | -0.622163 | 0.976312 | -0.49164 | 0.403487 | -0.389032 | 0.472982 | 1.40307 | -0.0736759 | -0.46472 | -0.184554 | 0.0479997 | -0.334994 | 0.160773 | -0.313563 | -0.234564 | 0.0904426 | 0.187123 | -0.1894 | -0.382194 | -0.201534 | -0.192287 | -0.369397 | 0.24313 | 0.378067 | -0.0988708 | 0.0338374 | 0.457246 | -0.188525 | 0.658951 | -0.130829 | 0.298092 | 0.200871 | -0.00588034 | -0.0506975 | 0.202035 | 0.0840065 | -0.336172 | -0.217707 | 0.159621 | -0.113108 | -0.260194 | 0.210903 | -0.297812 | 0.191484 | 0.329767 | 0.134989 | -0.0103842 | 0.0685854 | -0.00680479 | 0.266239 | 0.0298477 | -0.0748851 | -0.226567 | 0.255102 | -0.46267 | -0.0558517 | 0.335046 | -0.145945 | 0.20236 | 0.304878 | -0.078967 | 0.0183667 | 0.273161 | -0.335248 | -0.254011 | 0.118854 | 0.307712 | -0.262988 | 0.00616952 | 0.29753 | -0.202918 | 0.468733 | -0.188677 | -0.11437 | 0.11525 | 0.48977 | 0.386582 | -0.0465705 | -0.213999 | -0.186912 | -0.0642073 | 0.258249 | 0.0956704 | -0.0400266 | 0.295486 | -0.194503 | 0.270661 | -0.132432 | -0.00319387 | -0.0266163 | -0.135375 | -0.1325 | -0.198468 | -0.130475 | -0.0800707 | -0.0386215 | 0.249876 | -0.126518 | 0.219047 | 0.0443893 | 0.224987 | 0.300631 | -0.0520516 | -0.21036 | 0.354681 | 0.0235207 | 0.0676734 | -0.0435437 | 0.000305147 | 0.11257 | 0.0879637 | -0.238431 | -0.137048 | 0.119859 | 0.538576 | -0.0492506 | 0.132892 | 0.171543 | -0.207903 | -0.220583 | -0.0663057 | -0.249994 | -0.106164 | -0.0968478 | -0.0368319 | -0.0663302 | 0.0632253 | 0.437415 | -0.104386 | 0.335587 | -0.24875 | -0.0855293 | 0.066421 | 0.119544 | 0.0120892 | 0.0322334 | -0.112484 | 0.199125 | -0.284355 | -0.180984 | 0.00111741 | -0.28127 | 0.0789765 | 0.0622286 | 0.100738 | -0.213872 | 0.0294017 | -0.0373952 | -0.237339 | 0.034477 | 0.103067 | 0.11292 | -0.182185 | -0.161504 | 0.0491328 | 0.532505 | 0.175996 | 0.078395 | -0.0769586 | -0.0977332 | 0.0300075 | 0.148379 | -0.277488 | -0.140362 | 0.0533468 | -0.216524 | -0.224543 | 0.13969 | 0.0212791 | 0.189716 | 0.263188 | -0.333152 | 0.490811 | -0.00826002 | 0.250755 | -0.0532916 | 0.420241 | -0.003078 | 0.00691849 | -0.290798 |
-9.48605 | -4.62876 | -0.0113746 | 0.00264897 | 0.775464 | -3.74757 | 0.77578 | -0.347808 | -0.456373 | 0.557025 | -0.34515 | -0.525534 | -0.770694 | -0.893606 | -1.36622 | -0.886175 | -0.660253 | 0.680601 | 0.087117 | -1.99732 | 0.109212 | -0.287926 | 0.0916569 | -0.337078 | 0.529247 | -0.370455 | -0.353317 | 0.0351915 | -0.315187 | -1.04475 | 0.0678574 | 0.129865 | -0.294966 | -0.138945 | -1.23803 | -0.174998 | -1.22771 | -0.148812 | -0.438866 | 0.67779 | 0.609984 | -0.491248 | -0.811174 | -0.267217 | -0.687741 | -0.44685 | -0.208941 | 0.598894 | -0.0131963 | -0.506304 | 0.214687 | -0.442467 | -0.0567995 | 0.638434 | -0.290937 | 0.225813 | -0.770266 | -0.177163 | 0.494052 | -0.00251475 | -0.551776 | 0.555569 | -0.672519 | 0.0681414 | 0.143526 | -0.141077 | -0.12622 | -1.1825 | -0.890815 | 0.809135 | -0.0734005 | -0.352972 | -0.23503 | 0.146524 | 0.391508 | 0.223599 | 0.208097 | -0.505177 | 0.0281984 | -0.184417 | 0.462344 | -0.3132 | 0.0922791 | -0.260115 | -0.502435 | 0.635807 | -0.18061 | -0.559209 | 0.172449 | -0.236082 | 0.294326 | -0.0327853 | -0.110448 | 0.316669 | -0.50329 | -0.467994 | -0.386507 | 0.128248 | -0.195392 | 0.214672 | -0.433561 | -0.17302 | -0.418322 | -0.225325 | -0.198205 | -0.409893 | 0.0723651 | 0.0195491 | -0.119501 | 0.53044 | -0.208966 | -0.0434626 | 0.335261 | -0.0186331 | -0.197542 | 0.542854 | 0.431388 | -0.0885179 | -0.0761147 | 0.34833 | -0.286945 | 0.121582 | 0.163274 | 0.202084 | 0.0408521 | -0.0559559 | -0.00372374 | -0.405219 | 0.0149087 | 0.191357 | -0.0619767 | -0.0499176 | 0.163253 | -0.177005 | -0.693782 | -0.0374278 | -0.000758044 | 0.0458899 | 0.0892009 | -0.0336944 | 0.027149 | -0.236796 | 0.165388 | 0.328765 | -0.420372 | -0.0441485 | -0.541111 | 0.364678 | -0.200678 | -0.325924 | 0.434868 | -0.0713203 | -0.308079 | 0.546199 | 0.208701 | -0.428515 | 0.3897 | -0.268265 | 0.0722884 | -0.242711 | -0.154381 | -0.478868 | 0.111516 | 0.110804 | 0.013939 | -0.561829 | 0.421027 | 0.396893 | -0.509855 | 0.0646768 | -0.29089 | 0.16559 | -0.521093 | 0.611326 | 0.237163 | 0.185881 | 0.254386 | 0.363215 | -0.119303 | 0.496844 | 0.139088 | 0.331454 | 0.210057 | -0.419926 | 0.236703 | -0.185421 | 0.14139 | -0.0706251 | -0.118829 | 0.00907507 | 0.220119 | 0.233469 | -0.210597 | -0.422977 | 0.278417 | -0.125613 | -0.117672 | 0.204266 | 0.100809 | -0.124034 |
-9.76658 | -5.5994 | -3.89829e-05 | 0.128426 | 0.275775 | -3.69459 | 0.934526 | -0.210841 | -0.167749 | 0.01654 | -0.435993 | -0.0865435 | -0.0988782 | -0.916727 | -1.00726 | -0.965776 | 0.394868 | 0.0572899 | -0.25157 | 0.346353 | 0.402495 | 0.564993 | 1.01356 | -0.282266 | -0.191537 | 0.143237 | 0.192089 | -0.0401013 | 0.592642 | 0.307771 | -0.210301 | 0.885181 | 0.623763 | -1.24509 | 0.308801 | -0.390058 | 0.0322479 | -0.378667 | -0.171962 | -0.388523 | -0.203368 | 0.150018 | -0.311775 | 0.716699 | -0.34096 | -0.123057 | 0.343106 | 0.0780912 | 0.0999492 | -0.21739 | -0.439137 | -0.641553 | 0.63747 | 0.212651 | 0.00023834 | 0.752072 | -0.35732 | -0.0844205 | -0.05655 | 0.486645 | -0.144824 | 0.00930026 | 0.509781 | 0.955677 | 0.156868 | 0.338637 | 0.235263 | 0.409853 | -0.0224862 | 0.414458 | -0.0496435 | 0.25 | 0.0278119 | 0.09181 | 0.325807 | 0.113944 | -0.512569 | 0.211964 | -0.40525 | -0.00559174 | -0.335272 | -0.0507388 | -0.271236 | 0.506507 | -0.0271158 | 0.0993435 | -0.264506 | 0.13633 | 0.0295806 | -0.029975 | -0.20447 | -0.357801 | -0.234231 | 0.271066 | 0.0340541 | 0.0197665 | -0.0858676 | -0.0685943 | -0.223353 | -0.140029 | -0.0177669 | 0.13616 | -0.0288363 | -0.144437 | -0.216546 | -0.481661 | -0.241355 | 0.57967 | 0.381273 | 0.199381 | 0.0247126 | -0.293661 | 0.0366443 | -0.0894075 | 0.284502 | 0.0516168 | 0.392418 | 0.277646 | -0.290867 | 0.181913 | -0.253747 | -0.172934 | 0.115745 | -0.169049 | -0.168836 | -0.108469 | 0.060913 | 0.0477332 | 0.153886 | 0.17978 | -0.390308 | -0.000594149 | -0.0922742 | 0.0948177 | 0.1513 | 0.0629856 | -0.0766572 | 0.0214414 | -0.0950004 | 0.0877746 | 0.141019 | 0.0743689 | 0.0662412 | 0.520284 | -0.303057 | 0.183541 | 0.166094 | 0.421861 | 0.136801 | -0.11681 | -0.163334 | -0.0581083 | -0.158864 | 0.0991802 | -0.157009 | 0.299469 | -0.0443993 | -0.0668477 | -0.0397008 | 0.0152228 | 0.0125098 | -0.229027 | -0.0256575 | -0.152536 | 0.0809117 | -0.182133 | 0.0761649 | -0.106114 | 0.112669 | 0.0769044 | 0.290035 | 0.082249 | -0.161454 | -0.23842 | 0.0490028 | 0.227777 | 0.0811296 | -0.172135 | 0.198609 | -0.048791 | 0.39733 | -0.0440375 | -0.302422 | 0.121435 | -0.0814581 | -0.457707 | -0.111481 | 0.157116 | -0.261661 | -0.0290202 | -0.0832653 | -0.15217 | 0.346027 | -0.12647 | 0.101427 | -0.0278872 | 0.0469565 | -0.0606447 | 0.0924889 | -0.0066635 |
-6.8708 | 2.68057 | -0.0355698 | -0.699036 | 0.736729 | 0.257921 | 3.02569 | 1.1828 | 0.413017 | 1.53433 | 5.12066 | -1.7532 | -0.738115 | -2.14663 | -0.683129 | -0.654376 | -0.61325 | 0.185093 | 0.415841 | -0.534862 | -0.220786 | 1.42245 | 0.176689 | 0.0192469 | 0.396607 | -0.005357 | 1.40927 | -0.0209309 | -1.71154 | -0.270967 | 0.503112 | -0.453672 | -0.834217 | 1.10271 | 0.392462 | 1.47327 | 0.559773 | -1.06503 | -0.155041 | -0.281089 | 0.336117 | 0.527712 | -0.547592 | 0.625531 | -0.584138 | -0.408617 | 0.212724 | -1.05129 | 0.307422 | 0.597414 | 0.308627 | 0.0839721 | 1.0917 | -0.797267 | 0.0857386 | 0.0500546 | -0.187399 | 0.159411 | -0.0430745 | 0.0136178 | 0.29476 | -0.168814 | -0.2206 | 0.0783109 | -0.132235 | 0.220012 | -0.188318 | 0.24743 | 0.464853 | 0.0383091 | -0.686787 | 0.111268 | 0.0162829 | 0.325926 | -0.0904145 | 0.465747 | -0.016556 | -0.15027 | 0.207866 | 0.572747 | -0.0418297 | -0.545091 | -0.173507 | 0.15963 | 0.1852 | 0.314861 | -0.299225 | 0.0272655 | -0.134234 | 0.0170405 | 0.336794 | 0.288353 | -0.139473 | 0.166308 | -0.121751 | -0.161998 | 0.0468824 | -0.132319 | 0.138868 | 0.0860348 | 0.200801 | 0.107458 | -0.21358 | -0.106988 | -0.633656 | 0.121946 | -0.123863 | -0.320828 | -0.344134 | 0.251929 | 0.0805143 | -0.221949 | -0.180121 | -0.120502 | -0.22436 | 0.204527 | 0.521209 | -0.0929853 | -0.116271 | 0.0938814 | -0.0186209 | -0.122752 | -0.0490904 | 0.221927 | 0.0744466 | 0.122014 | -0.073049 | -0.115816 | 0.0574372 | 0.277756 | -0.00358919 | 0.0481752 | -0.341583 | 0.250432 | 0.0920894 | 0.10257 | -0.113817 | 0.10745 | 0.176046 | -0.149467 | -0.0509981 | 0.024196 | 0.00076316 | -0.0449122 | 0.091909 | -0.0479243 | 0.214462 | 0.13844 | -0.240763 | 0.269624 | -0.194052 | -0.209013 | 0.113906 | -0.194578 | 0.140454 | -0.1064 | -0.581816 | -0.131183 | -0.349921 | -0.168237 | -0.0816458 | -0.226236 | 0.150529 | 0.274294 | -0.165284 | 0.00747436 | -0.0591628 | 0.0272055 | -0.0140462 | 0.0427684 | -0.16886 | -0.0207045 | 0.186032 | -0.264496 | 0.177216 | -0.00905544 | 0.0825891 | 0.246186 | 0.111854 | 0.448187 | 0.0607458 | -0.189043 | 0.0269027 | 0.299077 | -0.141073 | -0.0316477 | 0.048967 | 0.270196 | -0.204264 | -0.0493952 | -0.116593 | 0.0616901 | 0.229456 | 0.0879137 | -0.0471718 | -0.0450974 | -0.34514 | -0.115519 | 0.108102 | 0.00262333 |
-9.7002 | 2.01993 | -0.0419022 | -1.78693 | -0.868938 | 4.90576 | 3.07665 | 1.46937 | 0.497968 | 2.8248 | 4.23813 | -0.6334 | 1.22995 | -1.28486 | 1.02514 | -0.576321 | 1.38022 | 1.20001 | 0.389443 | -1.77273 | -1.24207 | 1.16477 | 0.697286 | -0.368327 | -0.00249318 | -0.127154 | -0.250148 | 0.0167133 | 0.617982 | 0.592714 | -0.570079 | -0.0316759 | 0.315347 | -0.637864 | 0.943744 | -0.95563 | 0.0187535 | 0.840864 | 0.614452 | 0.703567 | 0.732973 | -0.135743 | 0.614975 | -0.575716 | -0.0218175 | 0.879477 | -0.0555101 | 0.987613 | 0.5341 | 0.544382 | 0.144836 | -0.530193 | 0.55032 | 0.189941 | 0.568939 | 0.555888 | -1.45468 | 0.100443 | 0.243123 | -0.106879 | -0.545287 | 0.300738 | 0.213071 | 0.418881 | 0.230577 | -0.797578 | 0.00839976 | -0.514347 | -0.397928 | 0.251805 | 0.0655922 | -0.284184 | -0.244452 | 0.0890336 | -0.235954 | 0.0687547 | 0.59685 | -0.381562 | 0.217461 | -0.115784 | -0.220976 | 0.135589 | 0.380991 | -0.376626 | 0.153256 | 0.124564 | -0.0237586 | 0.156169 | -0.0594366 | 0.0874143 | -0.296594 | -0.0797775 | 0.115377 | -0.17258 | -0.20333 | -0.390256 | 0.61364 | 0.208968 | 0.196587 | 0.462276 | -0.519164 | 0.158059 | 0.155647 | -0.12425 | 0.0731028 | 0.142651 | -0.130596 | 0.217428 | 0.325612 | 0.215072 | -0.101754 | -0.514854 | 0.0425049 | 0.430603 | -0.568491 | -0.265812 | -0.560729 | 0.140233 | -0.331596 | 0.399495 | 0.0114895 | -0.380821 | 0.0857853 | 0.476789 | 0.117023 | 0.0347636 | -0.321351 | 0.0941885 | -0.13162 | -0.303511 | -0.215142 | -0.122692 | 0.898417 | -0.0212619 | -0.231751 | 0.00636333 | -0.107066 | -0.302672 | 0.21904 | -0.264316 | -0.114049 | -0.359548 | 0.043984 | -0.417547 | -0.0733333 | 0.219099 | 0.00445267 | -0.24492 | -0.00254248 | 0.270459 | 0.258728 | 0.0124197 | 0.0574718 | 0.118086 | 0.100874 | -0.287752 | 0.216107 | -0.524942 | -0.188604 | 0.222052 | -0.288676 | 0.0389674 | -0.039381 | -0.0241603 | 0.131161 | 0.149168 | -0.50884 | 0.314479 | 0.325975 | -0.0304763 | 0.597556 | -0.0751168 | 0.285042 | 0.404374 | 0.340443 | -0.246579 | 0.248091 | 0.225155 | -0.158595 | -0.219442 | -0.00982387 | -0.0913876 | 0.116182 | 0.0220935 | -0.179899 | 0.118903 | 0.164548 | -0.103457 | -0.324 | -0.194148 | 0.205753 | 0.277896 | -0.429106 | 0.325799 | -0.452503 | -0.35914 | 0.0457975 | -0.103766 | -0.226946 | -0.345405 |
-8.54219 | 1.20221 | -0.0337894 | -1.70933 | -1.31788 | 4.43432 | 2.78561 | 1.62459 | 0.844757 | 1.30749 | 3.03594 | -0.389582 | 1.38847 | -0.790943 | 0.411406 | -0.215496 | 0.0373483 | 0.888375 | 0.217075 | -1.25865 | -0.840179 | 0.762913 | 0.464845 | -0.653663 | -0.140936 | -0.0993573 | 0.698259 | -0.0461487 | 0.244734 | -0.219995 | 0.0686529 | -0.408289 | -0.0627849 | -0.532491 | 1.05035 | -0.830271 | -0.37178 | 0.551295 | -0.0337151 | 0.0254299 | -0.739716 | -0.237236 | -0.268804 | 0.0528469 | 0.253406 | -0.314882 | 0.63836 | 0.479703 | -0.512762 | 0.00980382 | 0.0365693 | 0.283264 | 0.385486 | 0.844663 | -0.722482 | 0.389155 | 0.518976 | 0.140026 | 0.367951 | 0.0578155 | -0.237808 | 0.726078 | 0.0794338 | -0.396036 | 0.223692 | 0.564151 | 0.0105188 | -0.751705 | -0.127846 | 0.0994481 | -0.601196 | -0.17901 | -0.440456 | -0.424434 | -0.0342483 | -0.281859 | 0.235901 | 0.18012 | 0.360096 | -0.317282 | -0.0694499 | -0.363567 | -0.116735 | 0.340759 | -0.673291 | 0.884106 | 0.606648 | 0.294978 | 0.175188 | -0.245768 | 0.269212 | -0.0200029 | 0.124079 | 0.0252647 | 0.21792 | 0.409602 | -0.589638 | -0.327337 | -0.0520886 | 0.411777 | 0.09315 | -0.143922 | 0.38183 | 0.0916742 | 0.201024 | -0.10852 | 0.320168 | -0.259112 | 0.39255 | -0.172737 | 0.371132 | 0.460941 | -0.0133471 | -0.238938 | -0.226956 | 0.297199 | -0.314315 | 0.165405 | 0.0842257 | -0.400583 | 0.151181 | 0.346786 | 0.275771 | -0.433518 | -0.234866 | -0.367062 | 0.214556 | -0.620324 | -0.284036 | 0.230501 | 0.0543145 | 0.110878 | -0.602834 | 0.455412 | 0.325825 | -0.0291731 | 0.4177 | -0.0487769 | 0.719916 | 0.091659 | -0.0373595 | 0.0773591 | -0.135434 | 0.0181273 | 0.0261117 | 0.14644 | -0.0933808 | 0.105142 | 0.24001 | 0.0931343 | 0.0627232 | 0.101432 | -0.11545 | 0.102735 | -0.0011381 | 0.520417 | -0.0511215 | 0.347643 | 0.156714 | -0.248581 | -0.213454 | -0.277386 | 0.193475 | 0.0239697 | 0.345145 | -0.284584 | -0.189322 | -0.287148 | -0.207969 | -0.202163 | -0.0796535 | -0.105895 | -0.229858 | -0.236454 | -0.246952 | 0.103366 | -0.0597777 | -0.110702 | 0.254327 | 0.00290837 | 0.111981 | -0.240961 | 0.0804205 | -0.203052 | 0.291348 | 0.380352 | 0.339571 | -0.166293 | -0.205874 | -0.10269 | -0.173863 | -0.411589 | 0.0428641 | -0.0847032 | 0.371689 | -0.238893 | 0.530464 | 0.244679 | 0.389905 | 0.34426 |
train_frame_pca_df = train_frame_pca.as_data_frame()
train_frame_pca_df.head()
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | ... | PC291 | PC292 | PC293 | PC294 | PC295 | PC296 | PC297 | PC298 | PC299 | PC300 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | -7.215279 | 5.487787 | -0.045743 | -3.295824 | -8.025171 | -2.949743 | -2.967593 | -2.266287 | -0.652408 | 0.578522 | ... | 0.012587 | 0.371804 | -0.071848 | -0.341443 | 0.465335 | -0.433011 | -0.265740 | -0.491029 | -0.128080 | 0.655469 |
1 | -11.599985 | 5.534724 | -0.067638 | 0.442869 | 6.543390 | 0.485848 | -2.291297 | -1.485078 | -1.267895 | 2.487861 | ... | 0.054867 | 0.137572 | 0.059569 | 0.114289 | -0.194232 | 0.028769 | 0.060136 | 0.102203 | 0.070037 | -0.115447 |
2 | -9.149900 | -4.451211 | -0.000561 | -0.211492 | 0.891811 | -1.619368 | -0.031481 | -1.116217 | -0.521429 | 0.226712 | ... | -0.161497 | 0.041387 | 0.080233 | -0.031551 | 0.088953 | 0.104130 | 0.031573 | -0.036647 | 0.139434 | 0.224164 |
3 | -4.590492 | 5.312944 | -0.043539 | -1.586112 | -3.702485 | -0.156249 | 2.930343 | -4.974554 | -0.930162 | -0.817911 | ... | -0.465097 | 0.220127 | 0.127802 | 0.044233 | 0.098754 | 0.005934 | -0.151121 | 0.346246 | 0.041682 | -0.487852 |
4 | -8.682463 | -4.772522 | 0.003525 | 0.094409 | 0.517031 | -3.716390 | 0.988545 | 0.652860 | -0.217747 | 0.573477 | ... | -0.182978 | -0.093368 | 0.121302 | 0.067732 | -0.121732 | 0.079970 | -0.121168 | 0.044018 | -0.070295 | 0.017215 |
5 rows × 300 columns
test_frame_pca_df = test_frame_pca.as_data_frame()
test_frame_pca_df.head()
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | ... | PC291 | PC292 | PC293 | PC294 | PC295 | PC296 | PC297 | PC298 | PC299 | PC300 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | -9.629457 | 3.427494 | -0.054488 | -1.997283 | -0.501536 | 5.336753 | 1.883176 | 2.342219 | 0.550157 | 2.244874 | ... | 0.127281 | 0.080378 | 0.342437 | -0.283436 | -0.272764 | -0.157943 | -0.103696 | -0.056571 | -0.413420 | -0.201708 |
1 | -6.500589 | 5.032125 | 9.899641 | -1.751147 | -1.998420 | 5.184365 | 5.728812 | 22.975901 | -72.911270 | -19.434493 | ... | -0.005212 | -0.002507 | -0.001169 | 0.001140 | -0.000947 | 0.004027 | 0.005030 | -0.003485 | 0.002891 | -0.003535 |
2 | -12.947850 | 4.520129 | -0.072757 | 0.795501 | 5.604925 | -3.833929 | -0.123111 | 0.276374 | -0.394928 | 1.513401 | ... | -0.052364 | -0.218587 | 0.404883 | 0.508618 | 0.063992 | 0.420349 | -0.243656 | -0.125900 | -0.114601 | 0.135860 |
3 | -8.945284 | -5.015450 | 0.002182 | 0.197580 | 0.776913 | -3.340270 | 0.435418 | -0.418539 | -0.392206 | 0.062804 | ... | 0.033338 | -0.027150 | 0.042037 | -0.027205 | -0.192404 | -0.003779 | -0.075270 | -0.038884 | 0.059448 | 0.089166 |
4 | -8.616033 | -5.402211 | 0.008112 | -0.470638 | -0.436735 | 2.802968 | -0.717564 | 0.032025 | 0.384208 | -0.915967 | ... | 0.317406 | -0.058061 | 0.173129 | 0.315004 | 0.085500 | 0.000209 | 0.275298 | 0.104563 | -0.004634 | 0.090837 |
5 rows × 300 columns
response_col_df = train_frame[response_col].as_data_frame()
index_col_df = train_frame[index_col].as_data_frame()
train_pca_df = (train_frame_pca_df.join(response_col_df)).join(index_col_df).set_index('SampleID')
train_pca_df.head()
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | ... | PC292 | PC293 | PC294 | PC295 | PC296 | PC297 | PC298 | PC299 | PC300 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
SRR10525336 | -7.215279 | 5.487787 | -0.045743 | -3.295824 | -8.025171 | -2.949743 | -2.967593 | -2.266287 | -0.652408 | 0.578522 | ... | 0.371804 | -0.071848 | -0.341443 | 0.465335 | -0.433011 | -0.265740 | -0.491029 | -0.128080 | 0.655469 | 1 |
SRR10380004 | -11.599985 | 5.534724 | -0.067638 | 0.442869 | 6.543390 | 0.485848 | -2.291297 | -1.485078 | -1.267895 | 2.487861 | ... | 0.137572 | 0.059569 | 0.114289 | -0.194232 | 0.028769 | 0.060136 | 0.102203 | 0.070037 | -0.115447 | 1 |
SRR6807701 | -9.149900 | -4.451211 | -0.000561 | -0.211492 | 0.891811 | -1.619368 | -0.031481 | -1.116217 | -0.521429 | 0.226712 | ... | 0.041387 | 0.080233 | -0.031551 | 0.088953 | 0.104130 | 0.031573 | -0.036647 | 0.139434 | 0.224164 | 1 |
SRR11033700 | -4.590492 | 5.312944 | -0.043539 | -1.586112 | -3.702485 | -0.156249 | 2.930343 | -4.974554 | -0.930162 | -0.817911 | ... | 0.220127 | 0.127802 | 0.044233 | 0.098754 | 0.005934 | -0.151121 | 0.346246 | 0.041682 | -0.487852 | 1 |
SRR1163101 | -8.682463 | -4.772522 | 0.003525 | 0.094409 | 0.517031 | -3.716390 | 0.988545 | 0.652860 | -0.217747 | 0.573477 | ... | -0.093368 | 0.121302 | 0.067732 | -0.121732 | 0.079970 | -0.121168 | 0.044018 | -0.070295 | 0.017215 | 1 |
5 rows × 301 columns
train_pca_df.to_csv(DATA_LOCATION + "processed/train_pca_df.tsv", "\t")
train_pca_df.head()
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | ... | PC292 | PC293 | PC294 | PC295 | PC296 | PC297 | PC298 | PC299 | PC300 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
SRR10525336 | -7.215279 | 5.487787 | -0.045743 | -3.295824 | -8.025171 | -2.949743 | -2.967593 | -2.266287 | -0.652408 | 0.578522 | ... | 0.371804 | -0.071848 | -0.341443 | 0.465335 | -0.433011 | -0.265740 | -0.491029 | -0.128080 | 0.655469 | 1 |
SRR10380004 | -11.599985 | 5.534724 | -0.067638 | 0.442869 | 6.543390 | 0.485848 | -2.291297 | -1.485078 | -1.267895 | 2.487861 | ... | 0.137572 | 0.059569 | 0.114289 | -0.194232 | 0.028769 | 0.060136 | 0.102203 | 0.070037 | -0.115447 | 1 |
SRR6807701 | -9.149900 | -4.451211 | -0.000561 | -0.211492 | 0.891811 | -1.619368 | -0.031481 | -1.116217 | -0.521429 | 0.226712 | ... | 0.041387 | 0.080233 | -0.031551 | 0.088953 | 0.104130 | 0.031573 | -0.036647 | 0.139434 | 0.224164 | 1 |
SRR11033700 | -4.590492 | 5.312944 | -0.043539 | -1.586112 | -3.702485 | -0.156249 | 2.930343 | -4.974554 | -0.930162 | -0.817911 | ... | 0.220127 | 0.127802 | 0.044233 | 0.098754 | 0.005934 | -0.151121 | 0.346246 | 0.041682 | -0.487852 | 1 |
SRR1163101 | -8.682463 | -4.772522 | 0.003525 | 0.094409 | 0.517031 | -3.716390 | 0.988545 | 0.652860 | -0.217747 | 0.573477 | ... | -0.093368 | 0.121302 | 0.067732 | -0.121732 | 0.079970 | -0.121168 | 0.044018 | -0.070295 | 0.017215 | 1 |
5 rows × 301 columns
response_col_df = test_frame[response_col].as_data_frame()
index_col_df = test_frame[index_col].as_data_frame()
test_pca_df = (test_frame_pca_df.join(response_col_df)).join(index_col_df).set_index('SampleID')
test_pca_df.head()
PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | ... | PC292 | PC293 | PC294 | PC295 | PC296 | PC297 | PC298 | PC299 | PC300 | Resistance_Status | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SampleID | |||||||||||||||||||||
ERR3335735 | -9.629457 | 3.427494 | -0.054488 | -1.997283 | -0.501536 | 5.336753 | 1.883176 | 2.342219 | 0.550157 | 2.244874 | ... | 0.080378 | 0.342437 | -0.283436 | -0.272764 | -0.157943 | -0.103696 | -0.056571 | -0.413420 | -0.201708 | 1 |
SRR8552929 | -6.500589 | 5.032125 | 9.899641 | -1.751147 | -1.998420 | 5.184365 | 5.728812 | 22.975901 | -72.911270 | -19.434493 | ... | -0.002507 | -0.001169 | 0.001140 | -0.000947 | 0.004027 | 0.005030 | -0.003485 | 0.002891 | -0.003535 | 1 |
ERR067629 | -12.947850 | 4.520129 | -0.072757 | 0.795501 | 5.604925 | -3.833929 | -0.123111 | 0.276374 | -0.394928 | 1.513401 | ... | -0.218587 | 0.404883 | 0.508618 | 0.063992 | 0.420349 | -0.243656 | -0.125900 | -0.114601 | 0.135860 | 1 |
ERR067714 | -8.945284 | -5.015450 | 0.002182 | 0.197580 | 0.776913 | -3.340270 | 0.435418 | -0.418539 | -0.392206 | 0.062804 | ... | -0.027150 | 0.042037 | -0.027205 | -0.192404 | -0.003779 | -0.075270 | -0.038884 | 0.059448 | 0.089166 | 1 |
SRR5065314 | -8.616033 | -5.402211 | 0.008112 | -0.470638 | -0.436735 | 2.802968 | -0.717564 | 0.032025 | 0.384208 | -0.915967 | ... | -0.058061 | 0.173129 | 0.315004 | 0.085500 | 0.000209 | 0.275298 | 0.104563 | -0.004634 | 0.090837 | 1 |
5 rows × 301 columns
test_pca_df.to_csv(DATA_LOCATION + "processed/test_pca_df.tsv", "\t")
test_pca_df.head()
--------------------------------------------------------------------------- NameError Traceback (most recent call last) <ipython-input-41-9c1ff35e6473> in <module> ----> 1 test_pca_df.to_csv(DATA_LOCATION + "processed/test_pca_df.tsv", "\t") 2 3 test_pca_df.head() NameError: name 'test_pca_df' is not defined
# train_pca_df_frame = h2o.H2OFrame(train_pca_df)
train_pca_df_frame = h2o.import_file(DATA_LOCATION + "processed/train_pca_df.tsv")
train_pca_df_frame.head()
Parse progress: |█████████████████████████████████████████████████████████| 100%
SampleID | PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | PC11 | PC12 | PC13 | PC14 | PC15 | PC16 | PC17 | PC18 | PC19 | PC20 | PC21 | PC22 | PC23 | PC24 | PC25 | PC26 | PC27 | PC28 | PC29 | PC30 | PC31 | PC32 | PC33 | PC34 | PC35 | PC36 | PC37 | PC38 | PC39 | PC40 | PC41 | PC42 | PC43 | PC44 | PC45 | PC46 | PC47 | PC48 | PC49 | PC50 | PC51 | PC52 | PC53 | PC54 | PC55 | PC56 | PC57 | PC58 | PC59 | PC60 | PC61 | PC62 | PC63 | PC64 | PC65 | PC66 | PC67 | PC68 | PC69 | PC70 | PC71 | PC72 | PC73 | PC74 | PC75 | PC76 | PC77 | PC78 | PC79 | PC80 | PC81 | PC82 | PC83 | PC84 | PC85 | PC86 | PC87 | PC88 | PC89 | PC90 | PC91 | PC92 | PC93 | PC94 | PC95 | PC96 | PC97 | PC98 | PC99 | PC100 | PC101 | PC102 | PC103 | PC104 | PC105 | PC106 | PC107 | PC108 | PC109 | PC110 | PC111 | PC112 | PC113 | PC114 | PC115 | PC116 | PC117 | PC118 | PC119 | PC120 | PC121 | PC122 | PC123 | PC124 | PC125 | PC126 | PC127 | PC128 | PC129 | PC130 | PC131 | PC132 | PC133 | PC134 | PC135 | PC136 | PC137 | PC138 | PC139 | PC140 | PC141 | PC142 | PC143 | PC144 | PC145 | PC146 | PC147 | PC148 | PC149 | PC150 | PC151 | PC152 | PC153 | PC154 | PC155 | PC156 | PC157 | PC158 | PC159 | PC160 | PC161 | PC162 | PC163 | PC164 | PC165 | PC166 | PC167 | PC168 | PC169 | PC170 | PC171 | PC172 | PC173 | PC174 | PC175 | PC176 | PC177 | PC178 | PC179 | PC180 | PC181 | PC182 | PC183 | PC184 | PC185 | PC186 | PC187 | PC188 | PC189 | PC190 | PC191 | PC192 | PC193 | PC194 | PC195 | PC196 | PC197 | PC198 | PC199 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SRR10525336 | -7.21528 | 5.48779 | -0.0457426 | -3.29582 | -8.02517 | -2.94974 | -2.96759 | -2.26629 | -0.652408 | 0.578522 | 0.182181 | 0.434753 | 2.51645 | -2.40717 | -0.0528002 | -0.867347 | -0.77548 | 0.779273 | -0.362249 | -0.189216 | -1.43005 | 0.0339925 | 0.0361673 | -0.59373 | 0.642088 | -0.0192343 | 0.0159929 | 0.10032 | -2.14885 | 0.72847 | -0.426612 | -2.17743 | 0.564177 | -0.419728 | -0.040311 | 0.174175 | 0.0958375 | -0.840905 | -0.412918 | 0.0362403 | -1.12543 | 1.47642 | -0.288826 | 0.204485 | 0.970888 | 0.830999 | 0.392813 | -0.160212 | 0.045166 | -0.775327 | 0.854433 | 3.10933 | 1.62966 | -0.403796 | 2.37824 | -1.07053 | 1.22014 | -0.0348898 | 0.709709 | -1.60722 | -0.537093 | -0.519959 | -0.607373 | 1.96028 | -1.37502 | 0.788434 | 0.623542 | 0.117146 | -0.662954 | -0.788601 | 0.0349831 | -0.104036 | 0.64312 | 0.498023 | 1.10188 | 1.07592 | 0.471287 | -0.870997 | 0.134068 | 0.192699 | 0.590267 | 1.93532 | 1.70993 | 0.0663423 | -0.0086952 | -0.131918 | 0.4172 | -1.12597 | 0.123066 | -2.76761 | -0.0105532 | -0.186149 | -0.528908 | -0.59734 | -0.125254 | 0.853391 | -0.353671 | 0.527961 | -1.19337 | 0.320649 | -0.910347 | 0.726797 | -1.19437 | 0.643785 | 2.2666 | 1.23807 | -1.71336 | 1.6379 | -1.35046 | -0.0621283 | -2.1299 | 0.338774 | -0.294789 | 0.635849 | 0.393347 | 0.461294 | 0.799493 | 0.182817 | -0.0629657 | -0.0312119 | 0.38403 | -0.29482 | 0.102779 | -0.0105114 | -0.613126 | -0.635172 | 0.318172 | -0.604303 | -1.23884 | -0.367584 | 0.13739 | 0.403578 | 1.11971 | -1.58696 | 0.0275307 | 1.58684 | -0.519128 | 0.250662 | -0.731469 | 1.03236 | -0.272874 | -0.146155 | -1.12871 | 0.518941 | -0.731375 | -0.186096 | 0.206038 | -0.129464 | 0.20192 | 0.0572525 | 0.337063 | 1.8732 | 0.718144 | 0.609294 | -0.0976525 | 1.02692 | 1.16342 | -0.027039 | -0.366797 | -0.126558 | 0.145244 | 0.0541146 | -0.293231 | -0.430163 | -0.623036 | 0.119761 | 0.0857521 | 0.654185 | -0.597948 | 0.906505 | 0.00763198 | 0.760529 | -0.196652 | 1.37364 | 0.38687 | 1.06562 | -0.592595 | 0.096302 | -0.982776 | 0.205194 | 0.795516 | 1.4415 | 0.103181 | 0.958078 | -0.024321 | 0.423626 | 0.416048 | -0.422432 | -0.822004 | 0.286042 | -0.334727 | 0.236006 | 0.430699 | -1.99712 | 0.0612397 | -0.281902 | 0.561714 | -0.545934 | 0.920071 |
SRR10380004 | -11.6 | 5.53472 | -0.0676378 | 0.442869 | 6.54339 | 0.485848 | -2.2913 | -1.48508 | -1.26789 | 2.48786 | 1.61519 | -1.82951 | -1.14724 | -0.686728 | 0.0791433 | 0.244093 | -0.673544 | -0.298431 | 0.569891 | 1.3156 | 0.936164 | -1.74636 | -1.05101 | 0.351799 | -0.744067 | 0.26847 | -0.322997 | -0.0033458 | 0.139044 | 0.83802 | 0.0462784 | 0.18821 | 0.0188327 | 0.311519 | -0.103977 | 0.924853 | 1.06325 | -0.617407 | 0.416026 | 0.152573 | -0.00922459 | -0.540769 | -0.42493 | 0.224336 | 0.842236 | -0.0829223 | 0.104743 | -0.249455 | -0.237306 | 0.123351 | 0.373262 | 0.402359 | 0.0419783 | -1.21117 | -0.482892 | -0.974701 | -0.132585 | 0.422715 | -0.532571 | -0.512553 | -0.417771 | 0.55964 | -0.123657 | -0.481367 | -0.395624 | 0.235399 | -0.338215 | -0.311371 | 0.25003 | -0.187722 | -0.145724 | 0.0526789 | 0.49318 | 0.0865632 | -0.12011 | -0.482305 | 0.176727 | -0.126995 | -0.1996 | -0.169428 | 0.0459824 | -0.10309 | -0.100268 | -0.066558 | 0.290223 | 0.0640084 | 0.192294 | 0.367173 | -0.726469 | -0.255324 | 0.376527 | 0.0864552 | 0.429294 | 0.361994 | -0.0955574 | 0.10195 | 0.101228 | -0.164574 | 0.105739 | 0.0161596 | -0.309447 | -0.148715 | 0.0122466 | 0.408371 | -0.140452 | 0.34785 | 0.134036 | 0.312078 | 0.0964443 | 0.262582 | 0.0372175 | 0.103305 | 0.0706207 | 0.0719518 | 0.171051 | -0.0878448 | 0.0998239 | -0.0338992 | 0.00544983 | 0.186707 | 0.281369 | -0.021923 | 0.384559 | -0.145023 | 0.107315 | -0.314057 | 0.0957007 | -0.178865 | -0.00989666 | -0.151766 | 0.141986 | -0.228017 | -0.237458 | -0.12697 | -0.318449 | 0.113567 | 0.30737 | -0.20337 | 0.202596 | 0.386656 | -0.266906 | 0.164085 | 0.318025 | 0.0820759 | 0.14793 | 0.01882 | 0.495149 | -0.260415 | -0.0617778 | 0.362951 | 0.0325297 | 0.117637 | 0.113324 | 0.429079 | -0.334004 | 0.0182072 | -0.187317 | 0.081209 | 0.0555776 | -0.100039 | 0.183181 | -0.027631 | 0.00739474 | 0.274455 | -0.186653 | 0.177429 | -0.178171 | 0.108237 | 0.214357 | 0.279921 | -0.100227 | 0.434997 | 0.0841473 | 0.0511457 | -0.231324 | -0.0408152 | 0.0517595 | -0.00591222 | -0.212198 | -0.0753098 | -0.0714339 | 0.0261387 | 0.463119 | -0.0376576 | -0.0828916 | 0.152708 | -0.111939 | -0.132567 | 0.0222411 | -0.0039838 | -0.211777 | -0.19423 | -0.156346 | -0.166492 | 0.121824 | -0.110317 | 0.217815 | -0.0654254 | -0.119042 |
SRR6807701 | -9.1499 | -4.45121 | -0.000560915 | -0.211492 | 0.891811 | -1.61937 | -0.0314806 | -1.11622 | -0.521429 | 0.226712 | -0.650277 | -0.479117 | -0.996814 | -1.1133 | -1.26154 | -0.974177 | -0.00247332 | -0.0530825 | -0.201434 | -1.98052 | -1.29959 | -0.260899 | 0.78139 | -0.048447 | 0.238562 | -0.334514 | -0.853045 | 0.0713396 | -0.484966 | -0.619925 | -0.21595 | 0.653184 | -1.5664 | 0.0428643 | -1.3497 | 0.0193528 | -0.51782 | 0.820135 | 0.293265 | -0.509604 | 0.134869 | 0.00260967 | -0.452535 | -0.293624 | -0.00177784 | -0.149006 | -0.594837 | 0.165374 | 0.351211 | -0.462701 | -1.30318 | 0.00425985 | -1.19819 | 0.371879 | 0.325116 | -0.123847 | 0.937828 | 0.263567 | 0.0863833 | 0.268786 | 0.402629 | -0.26627 | 0.384837 | 0.60637 | -0.152096 | -0.0725101 | 0.792331 | -0.0321351 | -0.481089 | -0.42079 | -0.0660262 | -0.148211 | 0.378529 | 0.02314 | -0.0201441 | 0.487322 | -0.194526 | -0.0200701 | -0.29859 | 0.0686552 | -0.199198 | -0.241327 | -0.263722 | 0.519523 | -0.0661203 | -0.386223 | 0.337415 | -0.0933436 | -0.738899 | 0.41998 | -0.180534 | 0.162631 | 0.0589995 | -0.343279 | -0.141084 | -0.00846396 | -0.494676 | 0.062485 | 0.143639 | -0.154256 | 0.100058 | 0.0459747 | -0.10124 | 0.0749152 | 0.0433454 | 0.407651 | -0.00085629 | 0.272083 | -0.36515 | 0.186306 | -0.106947 | -0.179909 | -0.154551 | -0.239001 | 0.390033 | 0.103301 | -0.179483 | 0.22951 | -0.0668002 | -0.0825495 | 0.0340617 | 0.203809 | -0.275612 | 0.310813 | -0.0216203 | 0.0308512 | 0.295299 | 0.0617808 | 0.233424 | -0.602807 | -0.264453 | -0.0983916 | -0.367157 | 0.33488 | -0.248688 | -0.0103886 | 0.0212966 | -0.139436 | 0.126407 | 0.163799 | -0.0999936 | 0.159078 | 0.326816 | -0.422006 | 0.328108 | -0.12589 | -0.224009 | 0.165427 | 0.00736128 | 0.273949 | -0.432772 | 0.261663 | -0.032972 | -0.417354 | -0.222135 | -0.277632 | -0.151629 | 0.199935 | -0.109284 | 0.0932435 | 0.435215 | -0.0667091 | -0.0196309 | 0.346601 | -0.0825501 | 0.154359 | -0.164206 | 0.37597 | -0.136508 | 0.229612 | 0.213105 | 0.086485 | -0.0631953 | 0.159335 | -0.214413 | -0.114718 | 0.0446415 | -0.0986768 | 0.0589636 | -0.27537 | -0.470475 | -0.071911 | 0.185972 | -0.316124 | 0.204503 | -0.435719 | 0.31322 | 0.379372 | -0.0453729 | -0.167095 | -0.0395213 | 0.064882 | 0.348529 | 0.41005 | 0.0878616 | -0.0791032 | 0.187943 | 0.105175 | 0.19989 |
SRR11033700 | -4.59049 | 5.31294 | -0.043539 | -1.58611 | -3.70249 | -0.156249 | 2.93034 | -4.97455 | -0.930162 | -0.817911 | 1.69132 | 0.357042 | -1.68802 | 1.82346 | 1.65873 | 0.993338 | -0.769028 | 0.648757 | 0.739181 | 0.40869 | 1.46154 | -1.07547 | -0.412326 | -1.15372 | 0.033482 | -0.399165 | -1.04086 | 0.0623232 | 0.0584557 | 0.287642 | 0.441088 | 1.40573 | 0.373167 | 0.595857 | 0.777845 | -0.284434 | 0.893216 | 0.0325202 | -0.253651 | -0.256632 | 0.216368 | -1.11769 | 0.182434 | -0.300572 | -0.090939 | -0.220814 | 0.592161 | 0.422401 | 0.615093 | -0.910159 | -0.441763 | 0.315778 | 0.165484 | 0.419825 | -0.294703 | 0.0210309 | 0.213716 | -0.211021 | 0.879258 | 0.0419514 | -0.500143 | -0.0916183 | 0.199057 | -0.275862 | -0.313245 | 0.239273 | 0.113842 | -0.159077 | 0.669248 | -0.49075 | -0.165403 | 0.175773 | 0.49225 | -0.407117 | -0.818282 | -0.758563 | -0.0963912 | -0.253328 | -0.544874 | 0.221636 | 0.406422 | -0.219667 | 0.195245 | -0.149426 | -0.317279 | 0.582046 | -0.210104 | 0.849998 | -0.506772 | 0.455948 | 0.468586 | -0.264578 | -0.197681 | 0.321523 | -0.0873612 | 0.234735 | -0.205255 | -0.356656 | 0.246365 | -0.374521 | 0.216978 | -0.184585 | -0.550619 | -0.202771 | -0.722441 | 0.21047 | -0.227439 | 0.408528 | 0.615943 | 0.0445044 | -0.0414433 | 0.340925 | 0.294431 | 0.648748 | -0.191099 | 0.322158 | 0.419815 | 0.598406 | 0.141637 | -0.274665 | 0.482582 | -0.0160315 | 0.0962388 | -0.450854 | -0.0831487 | 0.363272 | 0.0283987 | -0.304109 | 0.0881775 | -0.281148 | -0.347671 | 0.48956 | -0.679409 | -0.0465728 | -0.0229669 | 0.305086 | 0.630215 | -0.247286 | 0.0045951 | -0.607346 | -0.00771802 | 0.229427 | -0.398598 | -0.666365 | -0.153768 | -0.323856 | -0.209572 | -0.241635 | -0.302749 | 0.194522 | 0.685216 | 0.00430719 | 0.027653 | 0.318633 | 0.318989 | 0.333135 | 0.345507 | -0.145466 | 0.0686151 | 0.115055 | -0.362267 | -0.616801 | 0.104639 | -0.34185 | -0.354017 | -0.435519 | -0.169556 | 0.060568 | 0.530617 | 0.252677 | -0.0308713 | -0.401517 | 0.370231 | 0.193731 | -0.212494 | 0.212407 | 0.0962742 | -0.0251926 | 0.013189 | 0.237966 | -0.0909133 | -0.31605 | -0.045298 | 0.43653 | 0.0797025 | -0.598752 | 0.219091 | -0.246436 | 0.355176 | -0.615051 | 0.214979 | -0.228767 | 0.174032 | -0.347543 | 0.355885 | -0.970259 | 0.529508 | 0.348943 | -0.0221957 |
SRR1163101 | -8.68246 | -4.77252 | 0.00352481 | 0.0944094 | 0.517031 | -3.71639 | 0.988545 | 0.65286 | -0.217747 | 0.573477 | 0.52632 | -0.683847 | -0.328461 | -0.396951 | -0.832451 | 0.354952 | -2.34578 | 1.25273 | -0.0812596 | -0.894451 | 1.79601 | -0.755556 | -1.18765 | -0.329411 | 0.130982 | 0.0222099 | -0.690187 | 0.0358821 | 0.24405 | -0.157876 | 0.157296 | -0.45587 | -0.32256 | 0.496656 | -0.321544 | -0.447171 | 0.0159054 | -0.071811 | -0.527262 | 0.294327 | 0.0221319 | -0.44001 | -0.17165 | -0.0971737 | 0.0824659 | -0.32426 | 0.175003 | -0.121623 | -0.332931 | -0.109857 | 0.113921 | 0.185016 | -0.172949 | -0.146797 | 0.0518847 | -0.241559 | -0.0679523 | 0.0335394 | -0.397274 | -0.122382 | -1.07938 | 0.804987 | -0.784403 | 0.049347 | 0.0892695 | -0.234216 | -0.393779 | 0.12618 | 0.110403 | -0.293747 | -0.196784 | -0.247168 | 0.097565 | 0.275938 | -0.0729131 | 0.12785 | 0.167029 | -0.0804026 | 0.13433 | -0.384247 | 0.0972462 | -0.068248 | -0.183705 | 0.00138043 | 0.345901 | 0.314085 | 0.432695 | 0.0817047 | -0.247884 | -0.405813 | 0.264043 | -0.181348 | -0.0680196 | 0.263482 | -0.070708 | 0.145009 | -0.180823 | 0.155849 | -0.31145 | -0.0989632 | -0.0866583 | 0.464757 | 0.0708443 | 0.177191 | 0.00976185 | 0.113518 | -0.0383682 | 0.0381381 | 0.0265574 | -0.12861 | 0.16697 | -0.331246 | 0.162963 | 0.3131 | 0.0116855 | -0.170562 | 0.0675353 | -0.135805 | 0.1076 | -0.367674 | -0.00944606 | 0.664511 | -0.0524581 | 0.149948 | -0.37418 | -0.173271 | 0.374806 | 0.322866 | 0.0653631 | 0.117941 | 0.0171137 | -0.196438 | 0.183118 | -0.184732 | -0.196132 | 0.0925266 | -0.0897482 | 0.0666219 | -0.00172925 | 0.00750581 | 0.0064723 | 0.157167 | -0.30515 | 0.0055818 | -0.0963982 | 0.110583 | -0.139017 | -0.0481604 | -0.232714 | -0.160162 | 0.173199 | -0.0826625 | -0.241485 | -0.0495134 | 0.151465 | 0.0346363 | -0.148535 | -0.144367 | 0.0784351 | 0.09193 | 0.0801042 | 0.103298 | -0.0168575 | -0.121607 | 0.137488 | -0.080562 | -0.0122179 | 0.278007 | 0.300971 | 0.0471241 | -0.0783548 | 0.0483359 | 0.26833 | -0.148815 | 0.0062242 | 0.41095 | 0.1374 | -0.0122015 | -0.0344289 | -0.261423 | -0.131396 | -0.211338 | 0.00387303 | 0.082486 | -0.130322 | -0.137823 | 0.0903963 | 0.00290438 | 0.0638734 | 0.117863 | 0.00904495 | -0.0510632 | -0.0925759 | -0.00737436 | -0.108323 | -0.00531824 | 0.00543457 | 0.276971 | 0.245328 |
SRR7592336 | -9.19672 | 7.94682 | -0.0615294 | -1.82745 | -4.61263 | -2.20144 | -6.78272 | 0.342489 | 0.726244 | -2.52807 | 2.35922 | -0.920174 | 1.58982 | 1.77681 | -1.02456 | -0.135104 | -1.06266 | -1.23535 | -1.06946 | 0.256949 | -0.135148 | 0.0709823 | 0.120553 | -0.212403 | 0.314243 | -0.718003 | -0.0869338 | 0.124004 | -2.44493 | 0.276341 | 0.149156 | -0.887986 | 0.74151 | -0.488781 | -0.0879999 | -0.646071 | 0.247737 | 2.36842 | -0.191677 | -0.843649 | 0.932515 | -0.412667 | -1.76671 | 1.40751 | 0.31721 | 0.412233 | 0.636046 | 0.482982 | -1.7244 | -1.14457 | -1.8538 | -0.382721 | -0.100829 | 1.13878 | -0.671918 | -1.06497 | -1.17288 | -0.097851 | -0.69384 | 1.24439 | -0.048193 | -0.645799 | -0.132279 | -2.03033 | 2.31706 | 0.017334 | 0.431449 | -1.51772 | 0.162575 | 0.758915 | -0.138466 | 0.136531 | -0.49254 | -0.298467 | -1.42526 | -0.740595 | -1.18069 | 0.513582 | -0.586936 | -0.203759 | 0.627928 | 1.36234 | -0.866153 | -1.29616 | 0.535693 | 0.415754 | 0.570849 | -1.48843 | 0.270096 | 0.543689 | -0.908162 | -0.105914 | 0.339703 | 0.496366 | 0.925362 | -0.933789 | -1.00079 | 0.00877185 | 0.322465 | 0.91807 | -1.99269 | 0.165965 | 0.353154 | 0.306088 | 0.326838 | -0.952772 | -0.146353 | 0.434984 | -0.340664 | 2.29767 | 0.0678048 | 0.420068 | -1.27611 | 0.259335 | 0.302944 | 0.911172 | -0.762877 | 0.00954014 | 1.78079 | -0.326688 | -0.603852 | 1.44774 | 0.267919 | -0.226292 | 1.30767 | 0.233281 | 0.24383 | 0.0630102 | 0.122896 | 1.05555 | 0.280146 | -0.134538 | -0.731806 | -0.285732 | -1.32877 | -0.335229 | -0.519341 | -0.643283 | 0.897955 | 0.672274 | 0.294411 | 0.143189 | -0.0573502 | 0.451826 | 0.42029 | -0.324798 | -1.14813 | 1.55177 | 0.302485 | 0.0641582 | -0.128799 | -1.17716 | -0.648077 | -0.761746 | 0.782809 | -1.34186 | -0.948957 | 0.617957 | 0.691935 | -0.00794323 | -0.36627 | 0.5934 | 0.669587 | 0.0575043 | -0.668937 | -0.208462 | -0.475375 | -0.114637 | -0.712252 | 0.706196 | 0.393449 | -0.0882379 | -0.215291 | 0.000254881 | -1.08491 | 0.26807 | -1.35235 | 0.83783 | 0.559586 | -0.905636 | 0.771805 | -0.450792 | -0.428496 | 0.0861287 | 0.379909 | -0.448908 | -0.729855 | -1.16339 | 0.153952 | 0.492471 | 0.122041 | 0.834458 | 0.341664 | -0.329075 | -1.22 | 0.723765 | -0.649107 | -0.778855 | 2.10345 |
SRR1163415 | -8.97007 | -5.43213 | 0.00272524 | 0.28841 | 0.0794467 | -3.89085 | 0.632721 | 0.5904 | -0.127595 | 0.102558 | 0.71127 | -0.632055 | -0.726413 | -0.124563 | -0.851183 | -0.054087 | -1.16743 | 0.376756 | -0.485514 | 1.74656 | 1.82665 | -0.158678 | -0.241553 | -0.364044 | -0.217666 | 0.325344 | -0.32731 | -0.00430132 | 0.631429 | 0.602307 | 0.00693307 | -0.100303 | -0.522723 | 0.60247 | 0.181705 | -0.255738 | 0.049287 | -0.0754982 | -0.0537969 | 0.434123 | 0.0349033 | 0.0485308 | -0.263522 | -0.0376923 | 0.143516 | -0.22031 | 0.29255 | 0.0904726 | -0.0917416 | -0.0518825 | -0.134846 | -0.0404059 | 0.205374 | 0.4644 | 0.010876 | 0.265961 | -0.48591 | -0.116062 | 0.246857 | 0.0471285 | -0.153093 | -0.000917792 | 0.0952652 | -0.0410535 | 0.107979 | 0.0804973 | -0.144514 | 0.118716 | -0.216696 | 0.210607 | 0.135711 | 0.125965 | 0.0628714 | 0.127415 | 0.469845 | -0.0667844 | 0.299821 | -0.12846 | -0.310889 | -0.0219621 | -0.0634152 | 0.280179 | -0.190406 | 0.080822 | 0.505054 | -0.274689 | 0.0995224 | 0.129501 | -0.0746645 | -0.280162 | -0.00093445 | 0.325553 | 0.298584 | 0.290192 | -0.221259 | -0.316362 | -0.0866782 | 0.50856 | 0.115006 | 0.386605 | -0.0275449 | 0.325659 | 0.125141 | 0.1233 | 0.118446 | 0.213108 | -0.21447 | 0.103515 | -0.162711 | -0.146634 | 0.207015 | -0.172975 | 0.369363 | -0.117679 | 0.127677 | -0.0634523 | -0.0536918 | 0.192478 | 0.198908 | 0.342845 | 0.0431692 | -0.328894 | 0.326333 | -0.0311168 | -0.245055 | 0.268527 | 0.193657 | -0.103903 | -0.0323027 | 0.321355 | -0.0616184 | -0.0753923 | -0.0921688 | -0.204716 | -0.410808 | 0.132522 | 0.0881262 | -0.0974992 | -0.0268259 | 0.118561 | 0.39624 | -0.422308 | -0.047406 | 0.0247631 | -0.0875903 | 0.0627485 | -0.287498 | -0.0175366 | -0.152858 | -0.0592951 | 0.206058 | 0.0673219 | 0.0939456 | 0.0170619 | -0.254741 | -0.0368757 | 0.161321 | -0.00412753 | -0.240887 | 0.0474343 | 0.199414 | -0.133641 | 0.165681 | 0.0410559 | -0.242758 | 0.0618847 | 0.129121 | -0.0017245 | -0.135786 | -0.104665 | -0.0768873 | 0.155628 | -0.226643 | -0.311717 | -0.00275112 | -0.265139 | -0.243158 | 0.0752308 | -0.0870046 | -0.183222 | -0.145014 | 0.0244057 | 0.0655492 | -0.153869 | -0.140731 | -0.0511595 | 0.305929 | 0.215741 | 0.0643249 | -0.111242 | 0.0574274 | 0.0537022 | -0.31474 | -0.21632 | 0.0157848 | 0.109514 | 0.0300488 | -0.104866 | -0.133928 |
SRR6458388 | -6.99841 | -2.98309 | -0.00022671 | -1.11203 | -1.20356 | 2.99938 | 0.792167 | 1.05258 | 0.65212 | -0.31234 | -0.192416 | 0.710371 | 1.59316 | 0.206608 | -0.346359 | 0.485749 | 0.635867 | -0.896472 | 0.680551 | -2.08688 | 0.475259 | -1.7706 | -0.62088 | 0.612203 | -0.14104 | -0.699463 | 0.650789 | -0.0262048 | -0.877455 | -1.0542 | 0.856707 | 0.541396 | 0.349956 | 0.331304 | -0.213139 | 0.774679 | -0.139329 | -0.975618 | 0.463806 | 0.715431 | -0.113045 | 0.272788 | 0.319152 | -0.40954 | 0.27471 | 0.268401 | -0.259543 | 0.272648 | -0.40678 | 0.375968 | -0.188106 | -0.108689 | -0.192379 | 0.104581 | 0.262699 | -0.559073 | 0.27288 | 0.414692 | 0.290314 | -0.357249 | 0.0937383 | -0.141974 | 0.278577 | 0.301905 | -0.266512 | 0.455196 | 0.227363 | 0.135629 | 0.354646 | 0.354206 | -0.110135 | 0.046093 | -0.536456 | 0.411382 | -0.566792 | 0.125481 | 0.255462 | 0.0793334 | -0.157157 | 0.179331 | -0.243474 | 0.172762 | -0.341583 | 0.134515 | 0.140128 | -0.0330968 | -0.587655 | 0.0485561 | 0.235821 | -0.0395163 | -0.205601 | 0.0350589 | 0.101773 | -0.0747391 | 0.271811 | -0.0368525 | 0.215494 | 0.00417177 | 0.11549 | 0.249065 | -0.0919896 | 0.147014 | 0.454241 | 0.0631964 | -0.0799047 | -0.206424 | 0.0626648 | 0.254552 | -0.126758 | -0.0135385 | 0.103113 | -0.0470452 | -0.0234869 | 0.0569321 | 0.302449 | 0.107023 | 0.197454 | 0.105974 | -0.0316742 | -0.0724548 | -0.143969 | 0.0551029 | -0.152243 | -0.124432 | -0.1107 | -0.0454275 | 0.375159 | -0.13424 | 0.113136 | 0.0845437 | -0.0824407 | -0.0427799 | 0.0288591 | 0.0546468 | 0.0112691 | 0.254756 | -0.0664561 | -0.0944385 | -0.0845776 | -0.348813 | -0.388426 | 0.331286 | 0.214688 | 0.12623 | 0.078729 | 0.133513 | -0.055878 | 0.361878 | 0.0198201 | 0.129158 | -0.133021 | -0.0430224 | -0.104172 | -0.0844451 | 0.123224 | 0.0786226 | -0.154249 | -0.234724 | 0.214356 | -0.176343 | -0.04811 | -0.278694 | 0.0631813 | -0.00826134 | -0.0339437 | 0.147426 | 0.21716 | 0.0806935 | 0.0963404 | -0.123161 | 0.206812 | -0.384298 | 0.0548116 | 0.0746361 | 0.0921111 | 0.371321 | 0.292604 | 0.190858 | 0.205624 | -0.305565 | 0.0741434 | 0.0436073 | -0.0483075 | 0.129479 | 0.0881774 | 0.144502 | -0.156171 | 0.154395 | -0.0339808 | 0.0232897 | 0.070536 | 0.143951 | -0.136796 | 0.311865 | -0.0452586 | -0.127641 | -0.00310456 | -0.0674689 | -0.220191 |
SRR5153333 | -11.4408 | 3.91069 | -0.0533963 | 1.10893 | 5.12126 | -4.0803 | -0.0529325 | -0.577976 | -0.522176 | 1.24176 | 2.51208 | -0.801427 | 1.1297 | 0.173791 | 1.67921 | 1.44797 | -2.08321 | -0.945879 | 0.125994 | 1.41064 | 0.325474 | -1.19619 | 1.39569 | -0.668194 | 0.101959 | -0.806764 | -1.06909 | 0.0805773 | -0.168554 | -0.207682 | -0.179091 | 0.891167 | 1.12312 | -1.44565 | -0.22525 | -0.781858 | 0.780147 | 1.30059 | 0.0663721 | 0.0359448 | -0.750649 | 0.958028 | 1.12601 | -1.40816 | 0.400875 | -0.107926 | 0.268149 | 0.303018 | -0.481072 | -0.102791 | -0.0510634 | -0.824892 | 0.922151 | -0.337871 | -1.3525 | -0.644757 | 1.3427 | 0.283754 | -0.57398 | -0.602533 | 0.881829 | -0.876745 | -0.584974 | 0.0359255 | -0.32868 | -0.391202 | -0.447582 | 0.274852 | 0.142741 | -0.667909 | -0.863052 | 0.150856 | -0.438702 | 0.750841 | -0.385989 | -0.310674 | -0.0790464 | -0.0680184 | 0.222167 | 0.557807 | -0.11575 | 0.387843 | 0.725434 | -0.402882 | -0.535717 | -0.0202945 | 0.117413 | 0.429501 | 0.153339 | 0.107547 | 0.427923 | -0.50234 | 0.129575 | -0.141354 | 0.0388434 | -0.0238002 | -0.290518 | 0.0415737 | 0.249019 | -0.536361 | 0.304088 | 0.0245802 | 0.135671 | 0.179917 | 0.45321 | 0.63413 | 0.424292 | -0.215174 | 0.247985 | 0.175937 | -0.139369 | -0.00493264 | 0.377265 | 0.0013446 | -0.144286 | -0.400853 | 0.245314 | -0.0452821 | -0.565764 | -0.306721 | 0.324002 | 0.370195 | -0.194664 | -0.0298646 | 0.376266 | 0.237367 | 0.290039 | 0.000584293 | -0.080829 | -0.379429 | -0.182291 | 0.984333 | 0.0874452 | 0.135156 | 0.139681 | 0.240714 | -0.0559758 | -0.148529 | 0.0806939 | -0.633445 | 0.123141 | -0.271885 | 0.196269 | 0.205204 | -0.336892 | 0.410195 | -0.165723 | 0.561479 | -0.59274 | -0.224254 | -0.325978 | -0.140057 | -0.193693 | -0.0940802 | -0.162493 | 0.140356 | 0.183163 | -0.381249 | 0.251974 | -0.334173 | 0.0931959 | -0.000737978 | 0.117114 | -0.206884 | 0.101043 | -0.132863 | 0.152506 | -0.134385 | 0.452986 | 0.152312 | 0.0582496 | 0.0839865 | -0.260468 | 0.478922 | -0.232389 | -0.137869 | 0.0222461 | 0.0882454 | 0.173291 | -0.206527 | 0.0762306 | 0.114507 | 0.165444 | -0.0534536 | -0.0920498 | -0.0482851 | 0.156824 | 0.278767 | -0.235759 | -0.103127 | 0.351468 | 0.0567588 | -0.0251241 | 0.47271 | -0.35859 | -0.0731565 | -0.128044 | 0.148674 | 0.234844 |
SRR5152963 | -9.28681 | -4.90312 | -0.00260397 | -0.0484381 | 0.264835 | -4.63516 | 1.50224 | 0.357337 | -0.17422 | 0.359103 | -0.99246 | 0.0470872 | 0.236459 | -0.685021 | -0.497964 | 0.286454 | -1.0784 | 0.287785 | 0.142118 | -1.95973 | 0.474228 | -0.131709 | -0.65227 | -0.0330496 | -0.160879 | 0.0376077 | -0.284 | -0.00654314 | 0.860162 | 0.59502 | -0.0143426 | -0.310572 | 1.18587 | -0.76121 | 0.469566 | -0.461658 | 0.66815 | 0.376559 | 0.294312 | -0.52857 | -0.0855447 | 0.393372 | -0.0614584 | 0.466387 | 0.167627 | -0.166838 | -0.0566179 | 0.261778 | 0.23537 | -0.023874 | -0.269284 | -0.301234 | 0.514908 | 0.0554866 | 0.213697 | 0.17933 | 0.155894 | 0.168836 | -0.581615 | 0.782444 | -0.508643 | 0.309706 | -0.0866412 | 0.319645 | -0.255015 | 0.373621 | 0.13159 | 0.355665 | -0.0152177 | 0.0343728 | -0.226289 | -0.0396509 | 0.0890247 | -0.314686 | 0.254015 | -0.00557643 | -0.073443 | 0.0256341 | -0.0160978 | -0.194006 | -0.0268144 | 0.115604 | 0.246627 | -0.255683 | 0.108665 | 0.26341 | 0.057678 | 0.14296 | 0.111766 | -0.331197 | -0.0193557 | -0.00387406 | -0.124914 | 0.0608201 | -0.222559 | -0.225016 | 0.0165621 | -0.0301462 | -0.088343 | 0.0176888 | -0.133887 | 0.13669 | 0.00392239 | -0.0276523 | -0.343728 | -0.10763 | -0.286567 | -0.199684 | 0.0126868 | -0.17505 | 0.224408 | -0.00865879 | 0.20032 | 0.0144414 | -0.162134 | 0.0565026 | -0.0137815 | 0.0879913 | 0.214719 | 0.086483 | 0.241405 | 0.307029 | -0.188092 | 0.130884 | -0.160446 | 0.00855652 | -0.345006 | 0.060206 | 0.0967177 | 0.109908 | -0.0354725 | 0.0919997 | -0.151296 | -0.127584 | -0.195341 | 0.168563 | 0.0190496 | 0.0890706 | 0.115683 | 0.112105 | -0.115679 | -0.0499728 | -0.0841381 | -0.15374 | 0.0492803 | -0.0540748 | 0.111392 | 0.137551 | -0.27198 | 0.0150838 | -0.259813 | -0.148247 | -0.00539514 | 0.0489178 | -0.063976 | 0.202161 | -0.171876 | 0.12256 | -0.0702188 | 0.254428 | -0.19253 | 0.200451 | 0.010829 | -0.0996432 | 0.112846 | 0.0234955 | 0.0498658 | 0.138928 | -0.0556585 | -0.0764542 | -0.341671 | -0.111084 | 0.141304 | -0.0660777 | 0.0418051 | -0.0573906 | 0.148952 | 0.108492 | -0.282072 | 0.164999 | 0.156052 | -0.0552209 | -0.149022 | 0.0272333 | -0.00249091 | -0.195615 | 0.248751 | -0.0022166 | -0.204083 | 0.100609 | 0.150012 | -0.12504 | 0.176794 | -0.0911637 | -0.0638807 | 0.209557 | -0.0724328 | -0.186826 | 0.0963438 |
# test_pca_df_frame = h2o.H2OFrame(test_pca_df)
test_pca_df_frame = h2o.import_file(DATA_LOCATION + "processed/test_pca_df.tsv")
test_pca_df_frame.head()
Parse progress: |█████████████████████████████████████████████████████████| 100%
SampleID | PC1 | PC2 | PC3 | PC4 | PC5 | PC6 | PC7 | PC8 | PC9 | PC10 | PC11 | PC12 | PC13 | PC14 | PC15 | PC16 | PC17 | PC18 | PC19 | PC20 | PC21 | PC22 | PC23 | PC24 | PC25 | PC26 | PC27 | PC28 | PC29 | PC30 | PC31 | PC32 | PC33 | PC34 | PC35 | PC36 | PC37 | PC38 | PC39 | PC40 | PC41 | PC42 | PC43 | PC44 | PC45 | PC46 | PC47 | PC48 | PC49 | PC50 | PC51 | PC52 | PC53 | PC54 | PC55 | PC56 | PC57 | PC58 | PC59 | PC60 | PC61 | PC62 | PC63 | PC64 | PC65 | PC66 | PC67 | PC68 | PC69 | PC70 | PC71 | PC72 | PC73 | PC74 | PC75 | PC76 | PC77 | PC78 | PC79 | PC80 | PC81 | PC82 | PC83 | PC84 | PC85 | PC86 | PC87 | PC88 | PC89 | PC90 | PC91 | PC92 | PC93 | PC94 | PC95 | PC96 | PC97 | PC98 | PC99 | PC100 | PC101 | PC102 | PC103 | PC104 | PC105 | PC106 | PC107 | PC108 | PC109 | PC110 | PC111 | PC112 | PC113 | PC114 | PC115 | PC116 | PC117 | PC118 | PC119 | PC120 | PC121 | PC122 | PC123 | PC124 | PC125 | PC126 | PC127 | PC128 | PC129 | PC130 | PC131 | PC132 | PC133 | PC134 | PC135 | PC136 | PC137 | PC138 | PC139 | PC140 | PC141 | PC142 | PC143 | PC144 | PC145 | PC146 | PC147 | PC148 | PC149 | PC150 | PC151 | PC152 | PC153 | PC154 | PC155 | PC156 | PC157 | PC158 | PC159 | PC160 | PC161 | PC162 | PC163 | PC164 | PC165 | PC166 | PC167 | PC168 | PC169 | PC170 | PC171 | PC172 | PC173 | PC174 | PC175 | PC176 | PC177 | PC178 | PC179 | PC180 | PC181 | PC182 | PC183 | PC184 | PC185 | PC186 | PC187 | PC188 | PC189 | PC190 | PC191 | PC192 | PC193 | PC194 | PC195 | PC196 | PC197 | PC198 | PC199 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ERR3335735 | -9.62946 | 3.42749 | -0.0544876 | -1.99728 | -0.501536 | 5.33675 | 1.88318 | 2.34222 | 0.550157 | 2.24487 | 1.01714 | -0.274509 | 0.473391 | -1.15809 | 0.0800588 | -1.07554 | 1.76168 | 2.19104 | -0.0812096 | -1.188 | 0.480369 | 1.51523 | -0.73458 | 0.856701 | -0.463986 | 1.1826 | -0.756524 | 0.0237812 | 0.516223 | 1.13772 | -0.564756 | 0.633247 | -0.349465 | -0.067741 | 0.234908 | -0.444675 | 0.17611 | -0.532194 | 0.0915564 | -0.113063 | 1.13146 | -0.302093 | 0.490816 | -0.493271 | -0.585398 | 0.8064 | -0.424099 | -0.672412 | 0.236234 | 0.621226 | 0.421086 | -0.957542 | 0.609662 | -0.625019 | 0.188252 | 0.878188 | -0.0257143 | -0.138875 | -0.0223257 | 1.23374 | -0.363303 | -0.19214 | 0.637254 | 0.567913 | 0.199097 | -0.825055 | 0.482516 | 0.0236314 | -0.274883 | -0.26622 | 0.389476 | -0.254482 | 0.476774 | 0.806681 | -0.515323 | -0.268944 | -0.521861 | -0.0541904 | 0.0623078 | -0.427573 | 0.209428 | 0.675307 | -0.156747 | -0.488074 | 0.266841 | 0.216901 | -0.365613 | -0.483448 | -0.16199 | -0.311047 | -0.877527 | -0.30912 | -0.48697 | 0.149168 | -0.372397 | -0.163269 | -0.117403 | 0.138337 | -0.19628 | 0.201152 | -0.0601995 | 0.192374 | -0.52172 | -0.127364 | -0.232277 | -0.0896376 | -0.125402 | 0.187321 | -0.271664 | -0.2616 | 0.0108175 | 0.43486 | -0.319592 | 0.198224 | -0.258672 | -0.383842 | -0.435208 | 0.323674 | -0.708164 | -0.422046 | -0.207349 | -0.780153 | 0.00302298 | 0.213339 | 0.0179504 | 0.450774 | -0.478498 | -0.0366665 | 0.0296298 | 0.283827 | -0.472738 | 0.0141913 | 0.275673 | 0.052553 | 0.255064 | 0.240547 | 0.15366 | -0.170729 | 0.243725 | 0.588446 | 0.528715 | -0.147671 | -0.216204 | 0.56448 | -0.525028 | 0.0715956 | 0.332453 | -0.223248 | 0.61728 | 0.123985 | -0.0749367 | 0.0996517 | -0.257484 | -0.405051 | 0.293621 | -0.227607 | -0.427547 | -0.384105 | 0.20133 | -0.0139542 | -0.396255 | 0.0760807 | 0.15238 | 0.0874545 | 0.195867 | 0.241876 | 0.124269 | -0.272356 | 0.188318 | 0.0350412 | 0.100087 | 0.0796334 | -0.349118 | 0.14185 | -0.00669717 | 0.19513 | 0.223768 | -0.268808 | -0.19858 | -0.134069 | 0.213021 | -0.0708481 | -0.370438 | -0.42775 | -0.0108664 | -0.189859 | -0.370499 | -0.286406 | 0.192455 | 0.252574 | -0.241866 | -0.0577385 | 0.207005 | -0.373174 | -0.254423 | 0.370247 | 0.0748705 | 0.00531612 | 0.150201 |
SRR8552929 | -6.50059 | 5.03212 | 9.89964 | -1.75115 | -1.99842 | 5.18436 | 5.72881 | 22.9759 | -72.9113 | -19.4345 | 3.5075 | 0.688388 | 1.69246 | -0.351719 | 0.807579 | 0.162097 | 0.751626 | -0.18388 | 0.114748 | -0.708287 | -0.431597 | 0.0908924 | 0.351024 | -0.106659 | -0.333741 | -0.275902 | -0.0169099 | 0.738175 | 0.298389 | 0.173786 | -0.232006 | -0.157514 | -0.0104423 | -0.0416099 | 0.00259742 | 0.153628 | -0.130673 | -0.0629438 | 0.103533 | 0.00953883 | -0.0284005 | 0.101688 | -0.15913 | 0.126722 | -0.0756605 | -0.0757435 | 0.0441156 | 0.0158992 | 0.0966239 | -0.0160974 | -0.00503431 | 0.0116024 | 0.0095455 | -0.0067565 | -0.026261 | -0.0215083 | 0.0502305 | -0.0297334 | 0.00990971 | -0.0598099 | 0.0232784 | -0.0248749 | -0.0285802 | 0.00209873 | 0.0368059 | 0.0434571 | -0.0579956 | -0.000134279 | 0.0298716 | -0.0178984 | 0.0093227 | -0.0204604 | -0.0540928 | 0.0371086 | 0.00754352 | -0.0336085 | -0.0019139 | 0.00628899 | -0.0455008 | 0.052359 | 0.0163493 | 0.00218547 | 0.0132377 | 0.00211587 | -0.0146862 | -0.00559338 | -0.000155938 | 0.00755395 | 0.0033325 | 0.00209277 | 0.00105389 | -0.0748952 | 0.0101986 | -0.0145325 | -0.00125014 | -0.0258381 | -0.0540903 | -0.0410478 | 0.0387674 | 0.00351536 | 0.0128107 | 0.00557929 | -0.0619911 | 0.0247265 | 0.0154274 | -0.0321825 | -0.00951977 | 0.00769412 | -0.0357834 | -0.0591719 | -0.00457642 | -0.00606525 | 0.00840811 | 0.0210038 | 0.004185 | -0.014654 | 0.0225778 | -0.00183399 | 0.00217674 | 0.0351158 | -0.00135192 | -0.0150031 | 0.0036849 | -0.00310188 | 0.000879287 | 0.00355384 | -0.0084746 | -0.00534059 | -0.0105895 | 0.00742139 | 0.011533 | -0.00614121 | -0.0129047 | 0.020875 | -0.0049962 | -0.00231064 | 0.00582987 | -0.00690987 | -0.00203907 | 0.00527454 | 0.00045267 | 0.00388553 | -0.0197361 | 0.00423608 | 0.00979886 | 0.000483858 | -0.00017943 | -0.00964616 | 0.0194447 | 0.0148543 | 0.00513786 | -0.0106696 | -0.00341618 | 0.00174641 | 0.0118982 | 0.00116556 | 0.0209835 | 0.00243423 | -0.000339955 | 0.00521808 | -0.00359017 | -0.0172559 | -0.00280436 | -0.00727958 | 0.026531 | 0.00720347 | 0.00123806 | 0.0154357 | 0.00556288 | 0.00342277 | 0.0102327 | -0.0109282 | -0.00307871 | -0.00308189 | -0.00206439 | 0.0103463 | -0.00746865 | -0.00659294 | 0.0021469 | 0.00023555 | 0.0107691 | -0.00834449 | 0.0171208 | 0.00355487 | 0.0104005 | 0.00500246 | 0.000461584 | 0.000601585 | 0.00443169 | 0.016988 | -0.00255609 | 0.0107808 | 0.00364382 | -0.00654571 | -0.0063882 | -0.00536978 | 0.000630954 | 0.0107065 | 0.0136769 |
ERR067629 | -12.9479 | 4.52013 | -0.0727567 | 0.795501 | 5.60493 | -3.83393 | -0.123111 | 0.276374 | -0.394928 | 1.5134 | 0.0998441 | -0.160441 | 0.875783 | 0.144141 | 1.50295 | 0.662061 | -0.152918 | -1.32294 | 0.494843 | 0.120914 | 0.409421 | 1.27984 | 0.89714 | -0.4064 | 0.436947 | -0.264961 | -0.504652 | 0.0964939 | -0.857363 | 0.640224 | 0.00723726 | -0.427967 | 0.128956 | -0.386457 | -0.294656 | -0.138751 | -0.556036 | -0.0155012 | -0.478571 | 0.665948 | -0.00757544 | 0.0321201 | -0.430406 | -0.53032 | 1.22734 | 0.12203 | 1.33503 | 0.968721 | -0.417973 | 0.607955 | -0.330774 | 0.561572 | 0.352208 | 1.5755 | -0.707895 | -0.909152 | 0.28725 | 0.0648046 | -0.0253563 | -0.217064 | 0.413599 | 0.61586 | 0.537453 | 0.0908139 | -0.675122 | -0.489732 | 0.581519 | 0.330403 | -0.240445 | 0.167285 | -0.323837 | -0.203957 | 0.662979 | -0.2441 | 0.212523 | -0.801479 | -0.320418 | -0.0492246 | 0.0482084 | -0.143322 | 0.540529 | 0.84252 | 0.304992 | 0.255836 | 0.296174 | -0.203431 | 0.15144 | 0.0989564 | 0.231816 | -0.0948375 | 0.383431 | -0.130254 | 0.368513 | 0.10371 | 0.252825 | -0.265766 | 0.268541 | 0.4523 | -0.0431464 | -0.282415 | 0.455213 | -0.159996 | 0.361028 | -0.260988 | 0.186677 | 0.0308555 | 0.137222 | -0.0186495 | 0.273489 | -0.342984 | 0.101656 | -0.162863 | -0.0422177 | 0.0131981 | 0.0687778 | -0.845328 | -0.289969 | 0.162009 | -0.372335 | 0.472539 | 0.335047 | -0.259656 | -0.0743039 | 0.104449 | -0.44302 | -0.00990119 | -0.361591 | 0.0910314 | 0.184432 | -0.366909 | 0.100612 | -0.201271 | -0.0203719 | 0.0346376 | -0.0766412 | 0.771028 | -0.373069 | -0.510017 | -0.192733 | 0.511328 | -0.358742 | 0.781616 | -0.0907365 | -0.162883 | 0.418575 | 0.385409 | 0.392492 | 0.235851 | 0.408559 | 0.663412 | -0.288445 | -0.388877 | -0.377931 | 0.790468 | -0.21487 | 0.369718 | 0.249138 | -0.0841726 | 0.257572 | 0.43072 | -0.0510586 | -0.0270357 | 0.427252 | 0.108473 | -0.256147 | -0.425715 | -0.244946 | -0.0475409 | 0.134611 | -0.35111 | -0.00822583 | -0.169693 | -0.156576 | 0.370779 | -0.390898 | 0.140082 | -0.15994 | -0.218447 | -0.174837 | -0.127382 | 0.27608 | 0.102577 | 0.085631 | -0.51676 | 0.410059 | 0.401514 | -0.0918516 | -0.368146 | 0.445533 | 0.517653 | 0.124488 | 0.10141 | 0.1146 | 0.217356 | 0.631302 | -0.333418 | 0.342894 | -0.226901 | -0.293725 |
ERR067714 | -8.94528 | -5.01545 | 0.00218169 | 0.19758 | 0.776913 | -3.34027 | 0.435418 | -0.418539 | -0.392206 | 0.0628038 | 0.194703 | -0.470089 | -0.505175 | -0.666116 | -1.32472 | -1.18856 | -0.0948413 | 0.846526 | -0.351893 | 0.994438 | 0.709866 | 0.0946708 | 0.730704 | -0.415959 | 0.20027 | -0.0269342 | -0.0357076 | 0.00894854 | -0.396809 | -0.561537 | 0.0696797 | 1.07964 | -1.27838 | -0.177258 | -0.92883 | -0.129073 | -0.399533 | 0.0544567 | -0.503208 | 0.225213 | -0.125742 | -0.401784 | 0.0836486 | -0.0663367 | -0.339606 | -0.0227511 | 0.314145 | -0.698153 | -0.384385 | -0.482622 | 0.123586 | 0.035008 | 0.0553435 | 0.375374 | -0.165647 | 0.576548 | -0.148979 | -0.522299 | 0.35583 | -0.475503 | -0.117024 | -0.0363074 | 0.171169 | -0.0971223 | 0.175799 | -0.0940921 | -0.145786 | -0.0449375 | -0.0327391 | 0.266942 | 0.371082 | 0.148319 | -0.192359 | 0.114621 | 0.0116713 | -0.0226767 | -0.0395446 | 0.123841 | 0.0915411 | -0.368156 | 0.142615 | 0.0449073 | -0.0961354 | -0.285895 | -0.399253 | 0.336092 | 0.151977 | 0.227483 | 0.1069 | -0.141486 | -0.397814 | -0.352355 | -0.152311 | -0.125061 | -0.030034 | 0.219326 | 0.22168 | -0.274953 | 0.037017 | -0.214727 | -0.0662301 | 0.107729 | 0.27112 | 0.0018463 | 0.0442201 | -0.279706 | -0.0151437 | -0.0484053 | 0.0693774 | -0.150624 | -0.0293918 | 0.0167988 | -0.0950179 | -0.343762 | -0.0134441 | -0.0923724 | 0.0734659 | -0.1104 | -0.0647773 | -0.27454 | 0.16298 | 0.160289 | -0.337939 | 0.134666 | 0.0826234 | -0.0991061 | 0.00194032 | -0.0835894 | 0.0239177 | 0.1042 | 0.0224501 | 0.264522 | -0.0986982 | 0.0640312 | -0.155391 | 0.038349 | -0.0327791 | 0.052411 | 0.0375473 | 0.042954 | -0.334741 | 0.101777 | -0.00269391 | -0.0725712 | 0.142811 | -0.197656 | 0.226308 | 0.21958 | 0.104074 | 0.0606405 | 0.151589 | -0.0177989 | -0.0394543 | -0.060618 | 0.034742 | 0.117939 | -0.0518007 | -0.0837149 | -0.0975527 | -0.203868 | -0.169478 | -0.268492 | -0.051744 | 0.0340075 | -0.114194 | -0.0014794 | 0.184438 | -0.115449 | 0.0871521 | 0.125626 | -0.0201496 | -0.211015 | 0.370505 | 0.161568 | -0.0331975 | 0.115279 | -0.0729038 | 0.167561 | 0.0427467 | -0.238144 | 0.0151419 | -0.158566 | -0.0342529 | -0.140659 | 0.0779365 | 0.0792503 | -0.208821 | -0.0337909 | 0.168655 | -0.0670168 | -0.0351762 | 0.178609 | -0.0471835 | 0.136935 | -0.0638909 | -0.146832 | 0.177575 | 0.0438678 | 0.0781435 |
SRR5065314 | -8.61603 | -5.40221 | 0.00811241 | -0.470638 | -0.436735 | 2.80297 | -0.717564 | 0.0320249 | 0.384208 | -0.915967 | 0.109527 | 0.47088 | 0.56927 | 0.160269 | 1.68617 | 1.00034 | -0.268822 | 0.0977931 | 0.296411 | 0.619891 | -0.622163 | 0.976312 | -0.49164 | 0.403487 | -0.389032 | 0.472982 | 1.40307 | -0.0736759 | -0.46472 | -0.184554 | 0.0479997 | -0.334994 | 0.160773 | -0.313563 | -0.234564 | 0.0904426 | 0.187123 | -0.1894 | -0.382194 | -0.201534 | -0.192287 | -0.369397 | 0.24313 | 0.378067 | -0.0988708 | 0.0338374 | 0.457246 | -0.188525 | 0.658951 | -0.130829 | 0.298092 | 0.200871 | -0.00588034 | -0.0506975 | 0.202035 | 0.0840065 | -0.336172 | -0.217707 | 0.159621 | -0.113108 | -0.260194 | 0.210903 | -0.297812 | 0.191484 | 0.329767 | 0.134989 | -0.0103842 | 0.0685854 | -0.00680479 | 0.266239 | 0.0298477 | -0.0748851 | -0.226567 | 0.255102 | -0.46267 | -0.0558517 | 0.335046 | -0.145945 | 0.20236 | 0.304878 | -0.078967 | 0.0183667 | 0.273161 | -0.335248 | -0.254011 | 0.118854 | 0.307712 | -0.262988 | 0.00616952 | 0.29753 | -0.202918 | 0.468733 | -0.188677 | -0.11437 | 0.11525 | 0.48977 | 0.386582 | -0.0465705 | -0.213999 | -0.186912 | -0.0642073 | 0.258249 | 0.0956704 | -0.0400266 | 0.295486 | -0.194503 | 0.270661 | -0.132432 | -0.00319387 | -0.0266163 | -0.135375 | -0.1325 | -0.198468 | -0.130475 | -0.0800707 | -0.0386215 | 0.249876 | -0.126518 | 0.219047 | 0.0443893 | 0.224987 | 0.300631 | -0.0520516 | -0.21036 | 0.354681 | 0.0235207 | 0.0676734 | -0.0435437 | 0.000305147 | 0.11257 | 0.0879637 | -0.238431 | -0.137048 | 0.119859 | 0.538576 | -0.0492506 | 0.132892 | 0.171543 | -0.207903 | -0.220583 | -0.0663057 | -0.249994 | -0.106164 | -0.0968478 | -0.0368319 | -0.0663302 | 0.0632253 | 0.437415 | -0.104386 | 0.335587 | -0.24875 | -0.0855293 | 0.066421 | 0.119544 | 0.0120892 | 0.0322334 | -0.112484 | 0.199125 | -0.284355 | -0.180984 | 0.00111741 | -0.28127 | 0.0789765 | 0.0622286 | 0.100738 | -0.213872 | 0.0294017 | -0.0373952 | -0.237339 | 0.034477 | 0.103067 | 0.11292 | -0.182185 | -0.161504 | 0.0491328 | 0.532505 | 0.175996 | 0.078395 | -0.0769586 | -0.0977332 | 0.0300075 | 0.148379 | -0.277488 | -0.140362 | 0.0533468 | -0.216524 | -0.224543 | 0.13969 | 0.0212791 | 0.189716 | 0.263188 | -0.333152 | 0.490811 | -0.00826002 | 0.250755 | -0.0532916 | 0.420241 | -0.003078 | 0.00691849 |
ERR067659 | -9.48605 | -4.62876 | -0.0113746 | 0.00264897 | 0.775464 | -3.74757 | 0.77578 | -0.347808 | -0.456373 | 0.557025 | -0.34515 | -0.525534 | -0.770694 | -0.893606 | -1.36622 | -0.886175 | -0.660253 | 0.680601 | 0.087117 | -1.99732 | 0.109212 | -0.287926 | 0.0916569 | -0.337078 | 0.529247 | -0.370455 | -0.353317 | 0.0351915 | -0.315187 | -1.04475 | 0.0678574 | 0.129865 | -0.294966 | -0.138945 | -1.23803 | -0.174998 | -1.22771 | -0.148812 | -0.438866 | 0.67779 | 0.609984 | -0.491248 | -0.811174 | -0.267217 | -0.687741 | -0.44685 | -0.208941 | 0.598894 | -0.0131963 | -0.506304 | 0.214687 | -0.442467 | -0.0567995 | 0.638434 | -0.290937 | 0.225813 | -0.770266 | -0.177163 | 0.494052 | -0.00251475 | -0.551776 | 0.555569 | -0.672519 | 0.0681414 | 0.143526 | -0.141077 | -0.12622 | -1.1825 | -0.890815 | 0.809135 | -0.0734005 | -0.352972 | -0.23503 | 0.146524 | 0.391508 | 0.223599 | 0.208097 | -0.505177 | 0.0281984 | -0.184417 | 0.462344 | -0.3132 | 0.0922791 | -0.260115 | -0.502435 | 0.635807 | -0.18061 | -0.559209 | 0.172449 | -0.236082 | 0.294326 | -0.0327853 | -0.110448 | 0.316669 | -0.50329 | -0.467994 | -0.386507 | 0.128248 | -0.195392 | 0.214672 | -0.433561 | -0.17302 | -0.418322 | -0.225325 | -0.198205 | -0.409893 | 0.0723651 | 0.0195491 | -0.119501 | 0.53044 | -0.208966 | -0.0434626 | 0.335261 | -0.0186331 | -0.197542 | 0.542854 | 0.431388 | -0.0885179 | -0.0761147 | 0.34833 | -0.286945 | 0.121582 | 0.163274 | 0.202084 | 0.0408521 | -0.0559559 | -0.00372374 | -0.405219 | 0.0149087 | 0.191357 | -0.0619767 | -0.0499176 | 0.163253 | -0.177005 | -0.693782 | -0.0374278 | -0.000758044 | 0.0458899 | 0.0892009 | -0.0336944 | 0.027149 | -0.236796 | 0.165388 | 0.328765 | -0.420372 | -0.0441485 | -0.541111 | 0.364678 | -0.200678 | -0.325924 | 0.434868 | -0.0713203 | -0.308079 | 0.546199 | 0.208701 | -0.428515 | 0.3897 | -0.268265 | 0.0722884 | -0.242711 | -0.154381 | -0.478868 | 0.111516 | 0.110804 | 0.013939 | -0.561829 | 0.421027 | 0.396893 | -0.509855 | 0.0646768 | -0.29089 | 0.16559 | -0.521093 | 0.611326 | 0.237163 | 0.185881 | 0.254386 | 0.363215 | -0.119303 | 0.496844 | 0.139088 | 0.331454 | 0.210057 | -0.419926 | 0.236703 | -0.185421 | 0.14139 | -0.0706251 | -0.118829 | 0.00907507 | 0.220119 | 0.233469 | -0.210597 | -0.422977 | 0.278417 | -0.125613 | -0.117672 | 0.204266 | 0.100809 |
ERR067590 | -9.76658 | -5.5994 | -3.89829e-05 | 0.128426 | 0.275775 | -3.69459 | 0.934526 | -0.210841 | -0.167749 | 0.01654 | -0.435993 | -0.0865435 | -0.0988782 | -0.916727 | -1.00726 | -0.965776 | 0.394868 | 0.0572899 | -0.25157 | 0.346353 | 0.402495 | 0.564993 | 1.01356 | -0.282266 | -0.191537 | 0.143237 | 0.192089 | -0.0401013 | 0.592642 | 0.307771 | -0.210301 | 0.885181 | 0.623763 | -1.24509 | 0.308801 | -0.390058 | 0.0322479 | -0.378667 | -0.171962 | -0.388523 | -0.203368 | 0.150018 | -0.311775 | 0.716699 | -0.34096 | -0.123057 | 0.343106 | 0.0780912 | 0.0999492 | -0.21739 | -0.439137 | -0.641553 | 0.63747 | 0.212651 | 0.00023834 | 0.752072 | -0.35732 | -0.0844205 | -0.05655 | 0.486645 | -0.144824 | 0.00930026 | 0.509781 | 0.955677 | 0.156868 | 0.338637 | 0.235263 | 0.409853 | -0.0224862 | 0.414458 | -0.0496435 | 0.25 | 0.0278119 | 0.09181 | 0.325807 | 0.113944 | -0.512569 | 0.211964 | -0.40525 | -0.00559174 | -0.335272 | -0.0507388 | -0.271236 | 0.506507 | -0.0271158 | 0.0993435 | -0.264506 | 0.13633 | 0.0295806 | -0.029975 | -0.20447 | -0.357801 | -0.234231 | 0.271066 | 0.0340541 | 0.0197665 | -0.0858676 | -0.0685943 | -0.223353 | -0.140029 | -0.0177669 | 0.13616 | -0.0288363 | -0.144437 | -0.216546 | -0.481661 | -0.241355 | 0.57967 | 0.381273 | 0.199381 | 0.0247126 | -0.293661 | 0.0366443 | -0.0894075 | 0.284502 | 0.0516168 | 0.392418 | 0.277646 | -0.290867 | 0.181913 | -0.253747 | -0.172934 | 0.115745 | -0.169049 | -0.168836 | -0.108469 | 0.060913 | 0.0477332 | 0.153886 | 0.17978 | -0.390308 | -0.000594149 | -0.0922742 | 0.0948177 | 0.1513 | 0.0629856 | -0.0766572 | 0.0214414 | -0.0950004 | 0.0877746 | 0.141019 | 0.0743689 | 0.0662412 | 0.520284 | -0.303057 | 0.183541 | 0.166094 | 0.421861 | 0.136801 | -0.11681 | -0.163334 | -0.0581083 | -0.158864 | 0.0991802 | -0.157009 | 0.299469 | -0.0443993 | -0.0668477 | -0.0397008 | 0.0152228 | 0.0125098 | -0.229027 | -0.0256575 | -0.152536 | 0.0809117 | -0.182133 | 0.0761649 | -0.106114 | 0.112669 | 0.0769044 | 0.290035 | 0.082249 | -0.161454 | -0.23842 | 0.0490028 | 0.227777 | 0.0811296 | -0.172135 | 0.198609 | -0.048791 | 0.39733 | -0.0440375 | -0.302422 | 0.121435 | -0.0814581 | -0.457707 | -0.111481 | 0.157116 | -0.261661 | -0.0290202 | -0.0832653 | -0.15217 | 0.346027 | -0.12647 | 0.101427 | -0.0278872 | 0.0469565 | -0.0606447 | 0.0924889 |
ERR688027 | -6.8708 | 2.68057 | -0.0355698 | -0.699036 | 0.736729 | 0.257921 | 3.02569 | 1.1828 | 0.413017 | 1.53433 | 5.12066 | -1.7532 | -0.738115 | -2.14663 | -0.683129 | -0.654376 | -0.61325 | 0.185093 | 0.415841 | -0.534862 | -0.220786 | 1.42245 | 0.176689 | 0.0192469 | 0.396607 | -0.005357 | 1.40927 | -0.0209309 | -1.71154 | -0.270967 | 0.503112 | -0.453672 | -0.834217 | 1.10271 | 0.392462 | 1.47327 | 0.559773 | -1.06503 | -0.155041 | -0.281089 | 0.336117 | 0.527712 | -0.547592 | 0.625531 | -0.584138 | -0.408617 | 0.212724 | -1.05129 | 0.307422 | 0.597414 | 0.308627 | 0.0839721 | 1.0917 | -0.797267 | 0.0857386 | 0.0500546 | -0.187399 | 0.159411 | -0.0430745 | 0.0136178 | 0.29476 | -0.168814 | -0.2206 | 0.0783109 | -0.132235 | 0.220012 | -0.188318 | 0.24743 | 0.464853 | 0.0383091 | -0.686787 | 0.111268 | 0.0162829 | 0.325926 | -0.0904145 | 0.465747 | -0.016556 | -0.15027 | 0.207866 | 0.572747 | -0.0418297 | -0.545091 | -0.173507 | 0.15963 | 0.1852 | 0.314861 | -0.299225 | 0.0272655 | -0.134234 | 0.0170405 | 0.336794 | 0.288353 | -0.139473 | 0.166308 | -0.121751 | -0.161998 | 0.0468824 | -0.132319 | 0.138868 | 0.0860348 | 0.200801 | 0.107458 | -0.21358 | -0.106988 | -0.633656 | 0.121946 | -0.123863 | -0.320828 | -0.344134 | 0.251929 | 0.0805143 | -0.221949 | -0.180121 | -0.120502 | -0.22436 | 0.204527 | 0.521209 | -0.0929853 | -0.116271 | 0.0938814 | -0.0186209 | -0.122752 | -0.0490904 | 0.221927 | 0.0744466 | 0.122014 | -0.073049 | -0.115816 | 0.0574372 | 0.277756 | -0.00358919 | 0.0481752 | -0.341583 | 0.250432 | 0.0920894 | 0.10257 | -0.113817 | 0.10745 | 0.176046 | -0.149467 | -0.0509981 | 0.024196 | 0.00076316 | -0.0449122 | 0.091909 | -0.0479243 | 0.214462 | 0.13844 | -0.240763 | 0.269624 | -0.194052 | -0.209013 | 0.113906 | -0.194578 | 0.140454 | -0.1064 | -0.581816 | -0.131183 | -0.349921 | -0.168237 | -0.0816458 | -0.226236 | 0.150529 | 0.274294 | -0.165284 | 0.00747436 | -0.0591628 | 0.0272055 | -0.0140462 | 0.0427684 | -0.16886 | -0.0207045 | 0.186032 | -0.264496 | 0.177216 | -0.00905544 | 0.0825891 | 0.246186 | 0.111854 | 0.448187 | 0.0607458 | -0.189043 | 0.0269027 | 0.299077 | -0.141073 | -0.0316477 | 0.048967 | 0.270196 | -0.204264 | -0.0493952 | -0.116593 | 0.0616901 | 0.229456 | 0.0879137 | -0.0471718 | -0.0450974 | -0.34514 | -0.115519 | 0.108102 |
ERR3335727 | -9.7002 | 2.01993 | -0.0419022 | -1.78693 | -0.868938 | 4.90576 | 3.07665 | 1.46937 | 0.497968 | 2.8248 | 4.23813 | -0.6334 | 1.22995 | -1.28486 | 1.02514 | -0.576321 | 1.38022 | 1.20001 | 0.389443 | -1.77273 | -1.24207 | 1.16477 | 0.697286 | -0.368327 | -0.00249318 | -0.127154 | -0.250148 | 0.0167133 | 0.617982 | 0.592714 | -0.570079 | -0.0316759 | 0.315347 | -0.637864 | 0.943744 | -0.95563 | 0.0187535 | 0.840864 | 0.614452 | 0.703567 | 0.732973 | -0.135743 | 0.614975 | -0.575716 | -0.0218175 | 0.879477 | -0.0555101 | 0.987613 | 0.5341 | 0.544382 | 0.144836 | -0.530193 | 0.55032 | 0.189941 | 0.568939 | 0.555888 | -1.45468 | 0.100443 | 0.243123 | -0.106879 | -0.545287 | 0.300738 | 0.213071 | 0.418881 | 0.230577 | -0.797578 | 0.00839976 | -0.514347 | -0.397928 | 0.251805 | 0.0655922 | -0.284184 | -0.244452 | 0.0890336 | -0.235954 | 0.0687547 | 0.59685 | -0.381562 | 0.217461 | -0.115784 | -0.220976 | 0.135589 | 0.380991 | -0.376626 | 0.153256 | 0.124564 | -0.0237586 | 0.156169 | -0.0594366 | 0.0874143 | -0.296594 | -0.0797775 | 0.115377 | -0.17258 | -0.20333 | -0.390256 | 0.61364 | 0.208968 | 0.196587 | 0.462276 | -0.519164 | 0.158059 | 0.155647 | -0.12425 | 0.0731028 | 0.142651 | -0.130596 | 0.217428 | 0.325612 | 0.215072 | -0.101754 | -0.514854 | 0.0425049 | 0.430603 | -0.568491 | -0.265812 | -0.560729 | 0.140233 | -0.331596 | 0.399495 | 0.0114895 | -0.380821 | 0.0857853 | 0.476789 | 0.117023 | 0.0347636 | -0.321351 | 0.0941885 | -0.13162 | -0.303511 | -0.215142 | -0.122692 | 0.898417 | -0.0212619 | -0.231751 | 0.00636333 | -0.107066 | -0.302672 | 0.21904 | -0.264316 | -0.114049 | -0.359548 | 0.043984 | -0.417547 | -0.0733333 | 0.219099 | 0.00445267 | -0.24492 | -0.00254248 | 0.270459 | 0.258728 | 0.0124197 | 0.0574718 | 0.118086 | 0.100874 | -0.287752 | 0.216107 | -0.524942 | -0.188604 | 0.222052 | -0.288676 | 0.0389674 | -0.039381 | -0.0241603 | 0.131161 | 0.149168 | -0.50884 | 0.314479 | 0.325975 | -0.0304763 | 0.597556 | -0.0751168 | 0.285042 | 0.404374 | 0.340443 | -0.246579 | 0.248091 | 0.225155 | -0.158595 | -0.219442 | -0.00982387 | -0.0913876 | 0.116182 | 0.0220935 | -0.179899 | 0.118903 | 0.164548 | -0.103457 | -0.324 | -0.194148 | 0.205753 | 0.277896 | -0.429106 | 0.325799 | -0.452503 | -0.35914 | 0.0457975 | -0.103766 | -0.226946 |
ERR3335759 | -8.54219 | 1.20221 | -0.0337894 | -1.70933 | -1.31788 | 4.43432 | 2.78561 | 1.62459 | 0.844757 | 1.30749 | 3.03594 | -0.389582 | 1.38847 | -0.790943 | 0.411406 | -0.215496 | 0.0373483 | 0.888375 | 0.217075 | -1.25865 | -0.840179 | 0.762913 | 0.464845 | -0.653663 | -0.140936 | -0.0993573 | 0.698259 | -0.0461487 | 0.244734 | -0.219995 | 0.0686529 | -0.408289 | -0.0627849 | -0.532491 | 1.05035 | -0.830271 | -0.37178 | 0.551295 | -0.0337151 | 0.0254299 | -0.739716 | -0.237236 | -0.268804 | 0.0528469 | 0.253406 | -0.314882 | 0.63836 | 0.479703 | -0.512762 | 0.00980382 | 0.0365693 | 0.283264 | 0.385486 | 0.844663 | -0.722482 | 0.389155 | 0.518976 | 0.140026 | 0.367951 | 0.0578155 | -0.237808 | 0.726078 | 0.0794338 | -0.396036 | 0.223692 | 0.564151 | 0.0105188 | -0.751705 | -0.127846 | 0.0994481 | -0.601196 | -0.17901 | -0.440456 | -0.424434 | -0.0342483 | -0.281859 | 0.235901 | 0.18012 | 0.360096 | -0.317282 | -0.0694499 | -0.363567 | -0.116735 | 0.340759 | -0.673291 | 0.884106 | 0.606648 | 0.294978 | 0.175188 | -0.245768 | 0.269212 | -0.0200029 | 0.124079 | 0.0252647 | 0.21792 | 0.409602 | -0.589638 | -0.327337 | -0.0520886 | 0.411777 | 0.09315 | -0.143922 | 0.38183 | 0.0916742 | 0.201024 | -0.10852 | 0.320168 | -0.259112 | 0.39255 | -0.172737 | 0.371132 | 0.460941 | -0.0133471 | -0.238938 | -0.226956 | 0.297199 | -0.314315 | 0.165405 | 0.0842257 | -0.400583 | 0.151181 | 0.346786 | 0.275771 | -0.433518 | -0.234866 | -0.367062 | 0.214556 | -0.620324 | -0.284036 | 0.230501 | 0.0543145 | 0.110878 | -0.602834 | 0.455412 | 0.325825 | -0.0291731 | 0.4177 | -0.0487769 | 0.719916 | 0.091659 | -0.0373595 | 0.0773591 | -0.135434 | 0.0181273 | 0.0261117 | 0.14644 | -0.0933808 | 0.105142 | 0.24001 | 0.0931343 | 0.0627232 | 0.101432 | -0.11545 | 0.102735 | -0.0011381 | 0.520417 | -0.0511215 | 0.347643 | 0.156714 | -0.248581 | -0.213454 | -0.277386 | 0.193475 | 0.0239697 | 0.345145 | -0.284584 | -0.189322 | -0.287148 | -0.207969 | -0.202163 | -0.0796535 | -0.105895 | -0.229858 | -0.236454 | -0.246952 | 0.103366 | -0.0597777 | -0.110702 | 0.254327 | 0.00290837 | 0.111981 | -0.240961 | 0.0804205 | -0.203052 | 0.291348 | 0.380352 | 0.339571 | -0.166293 | -0.205874 | -0.10269 | -0.173863 | -0.411589 | 0.0428641 | -0.0847032 | 0.371689 | -0.238893 | 0.530464 | 0.244679 | 0.389905 |
index_col = 'SampleID'
nfolds = 5
# Identify predictors and response columns
predictor_cols = train_pca_df_frame.columns
response_col = "Resistance_Status"
predictor_cols.remove(response_col)
# For binary classification, response should be a factor
train_pca_df_frame[response_col] = train_pca_df_frame[response_col].asfactor()
test_pca_df_frame[response_col] = test_pca_df_frame[response_col].asfactor()
x = predictor_cols
y = response_col
from h2o.automl import H2OAutoML
# Run AutoML for 20 base models (limited to 1 hour max runtime by default)
aml = H2OAutoML(max_models=20, seed=1234, stopping_metric= 'AUTO')
aml.train(x=x, y=y, training_frame=train_pca_df_frame)
# View the AutoML Leaderboard
lb = aml.leaderboard
lb.head(rows=lb.nrows)
AutoML progress: |████████████████████████████████████████████████████████| 100%
model_id | auc | logloss | aucpr | mean_per_class_error | rmse | mse |
---|---|---|---|---|---|---|
StackedEnsemble_BestOfFamily_AutoML_20201108_044243 | 0.898379 | 0.385515 | 0.939439 | 0.201463 | 0.345492 | 0.119365 |
StackedEnsemble_AllModels_AutoML_20201108_044243 | 0.897125 | 0.389261 | 0.93964 | 0.194425 | 0.347953 | 0.121071 |
GBM_4_AutoML_20201108_044243 | 0.884563 | 0.412288 | 0.930272 | 0.205892 | 0.360915 | 0.13026 |
GBM_grid__1_AutoML_20201108_044243_model_2 | 0.883757 | 0.412247 | 0.929666 | 0.212998 | 0.358975 | 0.128863 |
GBM_2_AutoML_20201108_044243 | 0.882101 | 0.408096 | 0.924653 | 0.190866 | 0.356368 | 0.126998 |
GBM_grid__1_AutoML_20201108_044243_model_1 | 0.879994 | 0.411873 | 0.926902 | 0.219601 | 0.360577 | 0.130016 |
GBM_3_AutoML_20201108_044243 | 0.876952 | 0.418408 | 0.923052 | 0.212156 | 0.363543 | 0.132164 |
GBM_1_AutoML_20201108_044243 | 0.876497 | 0.422203 | 0.925008 | 0.222101 | 0.365536 | 0.133617 |
GLM_1_AutoML_20201108_044243 | 0.875757 | 0.426938 | 0.921075 | 0.228976 | 0.368016 | 0.135436 |
XGBoost_grid__1_AutoML_20201108_044243_model_3 | 0.872385 | 0.513561 | 0.917598 | 0.220728 | 0.371594 | 0.138082 |
GBM_5_AutoML_20201108_044243 | 0.869842 | 0.428889 | 0.919382 | 0.206164 | 0.368263 | 0.135618 |
XGBoost_grid__1_AutoML_20201108_044243_model_4 | 0.859046 | 0.454019 | 0.913158 | 0.264396 | 0.377553 | 0.142546 |
XGBoost_grid__1_AutoML_20201108_044243_model_1 | 0.856996 | 0.443175 | 0.908054 | 0.249709 | 0.375767 | 0.141201 |
XGBoost_3_AutoML_20201108_044243 | 0.856359 | 0.459651 | 0.907647 | 0.229669 | 0.379338 | 0.143897 |
DeepLearning_grid__2_AutoML_20201108_044243_model_1 | 0.856299 | 1.25953 | 0.899245 | 0.237114 | 0.419033 | 0.175589 |
XGBoost_1_AutoML_20201108_044243 | 0.855931 | 0.454767 | 0.910027 | 0.239397 | 0.380238 | 0.144581 |
DRF_1_AutoML_20201108_044243 | 0.8528 | 0.474152 | 0.907583 | 0.245266 | 0.390851 | 0.152765 |
XRT_1_AutoML_20201108_044243 | 0.845461 | 0.484405 | 0.899942 | 0.2829 | 0.395608 | 0.156505 |
XGBoost_grid__1_AutoML_20201108_044243_model_2 | 0.845414 | 0.46337 | 0.892877 | 0.235226 | 0.381605 | 0.145623 |
XGBoost_2_AutoML_20201108_044243 | 0.844431 | 0.465161 | 0.902156 | 0.226884 | 0.383919 | 0.147394 |
DeepLearning_grid__1_AutoML_20201108_044243_model_1 | 0.836792 | 1.71017 | 0.880211 | 0.230702 | 0.432594 | 0.187138 |
DeepLearning_1_AutoML_20201108_044243 | 0.80954 | 0.684416 | 0.871226 | 0.318824 | 0.429181 | 0.184196 |
all_automl_model_ids = aml.leaderboard['model_id'].as_data_frame()['model_id'].tolist()
for mdl_id in all_automl_model_ids:
print(mdl_id)
h2o.save_model(model= h2o.get_model(mdl_id), path= MODELS_LOCATION + "pca300/aml_models", force=True)
StackedEnsemble_BestOfFamily_AutoML_20201108_044243 StackedEnsemble_AllModels_AutoML_20201108_044243 GBM_4_AutoML_20201108_044243 GBM_grid__1_AutoML_20201108_044243_model_2 GBM_2_AutoML_20201108_044243 GBM_grid__1_AutoML_20201108_044243_model_1 GBM_3_AutoML_20201108_044243 GBM_1_AutoML_20201108_044243 GLM_1_AutoML_20201108_044243 XGBoost_grid__1_AutoML_20201108_044243_model_3 GBM_5_AutoML_20201108_044243 XGBoost_grid__1_AutoML_20201108_044243_model_4 XGBoost_grid__1_AutoML_20201108_044243_model_1 XGBoost_3_AutoML_20201108_044243 DeepLearning_grid__2_AutoML_20201108_044243_model_1 XGBoost_1_AutoML_20201108_044243 DRF_1_AutoML_20201108_044243 XRT_1_AutoML_20201108_044243 XGBoost_grid__1_AutoML_20201108_044243_model_2 XGBoost_2_AutoML_20201108_044243 DeepLearning_grid__1_AutoML_20201108_044243_model_1 DeepLearning_1_AutoML_20201108_044243
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2ONaiveBayesEstimator
hyper_params = {
"laplace": [0.1, 0.3, 0.6, 0.9, 1.0],
"min_sdev":[0.1, 0.3, 0.6, 0.9, 1.0],
"eps_sdev":[0.1, 0.3, 0.6, 0.9, 1.0],
"min_prob":[0.1, 0.3, 0.6, 0.9, 1.0],
"eps_prob":[0.1, 0.3, 0.6, 0.9, 1.0],
# "compute_metrics": [True, False]
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
base_model = H2ONaiveBayesEstimator(
nfolds=nfolds,
fold_assignment = "random",
keep_cross_validation_predictions = True,
seed=1234)
nb_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria)
nb_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
naivebayes Grid Build progress: |█████████████████████████████████████████| 100%
h2o.save_grid(MODELS_LOCATION + "pca300/nb_grid", nb_grid.grid_id)
'../../models/pca300/nb_grid/Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178'
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2OGeneralizedLinearEstimator
hyper_params = {
# lambda //use self.lambda_
# "missing_values_handling" : ["mean_imputation", "skip", "plug_values"],
# 'standardize'
"alpha" : [0, 0.3, 0.6, 0.9, 1],
"theta" : [0, 0.3, 0.6, 0.9, 1],
"tweedie_link_power" : [0, 0.3, 0.6, 0.9, 1, 3, 6, 9],
"tweedie_variance_power" : [0, 0.3, 0.6, 0.9, 1, 3, 6, 9],
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
# Train and cross-validate a NB
base_model = H2OGeneralizedLinearEstimator(
family= "binomial",
nfolds=nfolds,
fold_assignment = "random",
keep_cross_validation_predictions = True,
seed=1234)
# Train the grid
glm_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria)
glm_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
glm Grid Build progress: |████████████████████████████████████████████████| 100%
h2o.save_grid(MODELS_LOCATION + "pca300/glm_grid", glm_grid.grid_id)
'../../models/pca300/glm_grid/Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504'
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2OGradientBoostingEstimator
hyper_params = {
'learn_rate': [0.1, 0.3, 0.6, 0.9],
'learn_rate_annealing': [0.1, 0.3, 0.6, 0.9, 1],
'distribution': ['bernoulli', 'multinomial'],
'quantile_alpha':[0.1, 0.3, 0.5, 0.8, 1],
'tweedie_power': [1.1, 1.5,1.9],
'col_sample_rate': [0.1, 0.3, 0.7, 0.9],
'balance_classes': [True, False],
'ntrees': [10, 20, 50, 100, 150],
'max_depth': [5, 10, 15, 20], # defaults to 20
'sample_rate': [ 0.1, 0.3, 0.6, 0.9],
'col_sample_rate_per_tree': [ 0.1, 0.3, 0.6, 0.8, 1],
'col_sample_rate_change_per_level': [ 0.1, 0.3, 0.6, 0.8, 1, 1.3, 1.5, 1.7, 1.9],
'histogram_type': ["AUTO", "UniformAdaptive", "Random", "QuantilesGlobal", "RoundRobin"]
#'max_abs_leafnode_pred' # use default value
#'class_sampling_factors',
#'max_after_balance_size',
#'min_rows', # defaults to 1
#'nbins', # default is 20
#'nbins_top_level', # requires too much tuning
#'nbins_cats', # requires too much tuning
#'r2_stopping',
#'seed',
#'build_tree_one_node',
#'sample_rate_per_class':[ 0.1, 0.3, 0.6, 0.9],
#'score_tree_interval',
#'min_split_improvement',
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
base_model = H2OGradientBoostingEstimator(
nfolds=nfolds,
fold_assignment = "random",
keep_cross_validation_predictions = True,
seed=1234
)
# Train the grid
gbm_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria,
parallelism= 1)
gbm_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
gbm Grid Build progress: |████████████████████████████████████████████████| 100%
h2o.save_grid(MODELS_LOCATION + "pca300/gbm_grid", gbm_grid.grid_id)
'../../models/pca300/gbm_grid/Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444'
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2ORandomForestEstimator
hyper_params = {
'mtries': [-1, 30, 60, 90, 150, 200],
'balance_classes': [True, False],
'ntrees': [10, 20, 50, 100, 150],
'max_depth': [5, 10, 15, 20], # defaults to 20
'sample_rate': [ 0.1, 0.3, 0.6, 0.9],
'col_sample_rate_per_tree': [ 0.1, 0.3, 0.6, 0.8, 1],
'col_sample_rate_change_per_level': [ 0.1, 0.3, 0.6, 0.8, 1, 1.3, 1.5, 1.7, 1.9],
'histogram_type': ["AUTO", "UniformAdaptive", "Random", "QuantilesGlobal", "RoundRobin"]
#'score_tree_interval',
#'min_split_improvement',
#'class_sampling_factors',
#'max_after_balance_size',
#'min_rows', # defaults to 1
#'nbins', # default is 20
#'nbins_top_level', # requires too much tuning
#'nbins_cats', # requires too much tuning
#'r2_stopping',
#'seed',
#'build_tree_one_node',
#'sample_rate_per_class':[ 0.1, 0.9],
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
base_model = H2ORandomForestEstimator(
nfolds=nfolds,
fold_assignment = "random",
keep_cross_validation_predictions = True,
seed=1234)
# Train the grid
drf_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria,
parallelism= 1)
drf_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
drf Grid Build progress: |████████████████████████████████████████████████| 100%
h2o.save_grid(MODELS_LOCATION + "pca300/drf_grid", drf_grid.grid_id)
'../../models/pca300/drf_grid/Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677'
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2ODeepLearningEstimator
hyper_params = {
# 'adaptive_rate',
# 'categorical_encoding',
# 'classification_stop',
# 'class_sampling_factors',
# 'col_major',
# 'elastic_averaging_moving_rate',
# 'elastic_averaging_regularization',
# 'elastic_averaging',
# 'epsilon',
# 'fast_mode',
# 'force_load_balance',
# 'initial_biases',
# 'initial_weights',
# 'initial_weight_distribution',
# 'initial_weight_scale',
# 'max_after_balance_size',
# 'max_categorical_features',
# 'max_w2',
# 'missing_values_handling',
# 'momentum_ramp',
# 'momentum_stable',
# 'momentum_start',
# 'nesterov_accelerated_gradient',
# 'overwrite_with_best_model',
# 'quantile_alpha',
# 'quiet_mode',
# 'rate_annealing',
# 'rate_decay',
# 'rate',
# 'regression_stop',
# 'replicate_training_data',
# 'reproducible',
# 'score_duty_cycle',
# 'score_interval',
# 'score_training_samples',
# 'score_validation_samples',
# 'score_validation_sampling',
# 'seed',
# 'shuffle_training_data',
# 'single_node_mode',
# 'sparsity_beta',
# 'target_ratio_comm_to_comp',
# 'train_samples_per_iteration',
# 'tweedie_power',
# 'use_all_factor_levels',
# 'variable_importances ',
# "hidden_dropout_ratios": [0, 0.1, 0.2, [0.5, 0.5], [0.5, 0.5]] ,
'l1': [0, 1e-5, 1e-2],
'l2': [0, 1e-5, 1e-2],
'sparse': [ True, False],
'balance_classes': [ True, False],
'average_activation': [0, 0.5, 1, 3, 5, 7, 10],
'epochs': [10, 20, 30],
"activation" : ['Rectifier', 'RectifierWithDropout', 'TanHWithDropout', 'TanH', 'Maxout', 'MaxoutWithDropout'] ,
'distribution': ['bernoulli', 'multinomial'],
"hidden": [[10, 10, 10], [50], [500, 500], [500, 500, 500]] ,
"input_dropout_ratio":[0, 0.10, 0.15, 0.20] ,
"rho" : [0.95, 0.90] ,
"standardize" : [True, False] ,
'loss': ['Automatic', 'Quadratic', 'CrossEntropy'],
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
base_model = H2ODeepLearningEstimator(
keep_cross_validation_predictions = True,
nfolds= nfolds,
fold_assignment = "random",
seed=1234)
# Train the grid
dl_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria)
dl_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
deeplearning Grid Build progress: |███████████████████████████████████████| 100%
h2o.save_grid(MODELS_LOCATION + "PCA300/dl_grid", dl_grid.grid_id)
'../../models/PCA300/dl_grid_LATEST/Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758'
from h2o.grid.grid_search import H2OGridSearch
from h2o.estimators import H2OXGBoostEstimator
hyper_params = {
'distribution': ['bernoulli', 'multinomial'],
'categorical_encoding': ['auto', 'binary', 'label_encoder'],
'ntrees': [10, 50, 70, 100],
'booster': ['gbtree', 'gblinear', 'dart'],
'col_sample_rate': [0.1, 0.3, 0.6, 0.8, 1],
'colsample_bylevel': [0.1, 0.3, 0.6, 0.8, 1],
'colsample_bytree': [0.1, 0.3, 0.6, 0.8, 1],
'learn_rate': [0.1, 0.3, 0.6, 0.8, 1],
# 'grow_policy': ['lossguide'],
'max_depth': [0, 3, 6],
'normalize_type': ['tree', 'forest'],
'sample_type': ['uniform', 'weighted'],
'sample_rate': [0.1, 0.3, 0.6, 0.8, 1],
# 'tree_method': ['auto', 'exact', 'approx', 'hist'],
'tweedie_power': [1.2, 1.5, 1.8],
# 'max_abs_leafnode_pred'
# 'min_split_improvement',
# 'max_bins',
# 'max_delta_step',
# 'max_leaves',
# 'min_rows':
# 'one_drop',
# 'rate_drop',
# 'reg_alpha',
# 'reg_lambda',
# 'skip_drop',
# 'num_leaves'
}
search_criteria = {"strategy": "RandomDiscrete",
"max_models": MAX_MODELS}
base_model = H2OXGBoostEstimator(grow_policy= 'lossguide',
tree_method='hist',
keep_cross_validation_predictions = True,
nfolds= nfolds,
fold_assignment = "random",
seed=1234)
# Train the grid
xgb_grid = H2OGridSearch(model=base_model,
hyper_params=hyper_params,
search_criteria=search_criteria)
xgb_grid.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
xgboost Grid Build progress: |████████████████████████████████████████████| 100% Errors/Warnings building gridsearch model Hyper-parameter: booster, dart Hyper-parameter: categorical_encoding, Binary Hyper-parameter: col_sample_rate, 1.0 Hyper-parameter: colsample_bylevel, 0.3 Hyper-parameter: colsample_bytree, 0.1 Hyper-parameter: distribution, multinomial Hyper-parameter: learn_rate, 1.0 Hyper-parameter: max_depth, 0 Hyper-parameter: normalize_type, forest Hyper-parameter: ntrees, 100 Hyper-parameter: sample_rate, 0.3 Hyper-parameter: sample_type, weighted Hyper-parameter: tweedie_power, 1.5 failure_details: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 failure_stack_traces: java.lang.IllegalStateException: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 at ml.dmlc.xgboost4j.java.XGBoostUpdater.invoke(XGBoostUpdater.java:108) at ml.dmlc.xgboost4j.java.XGBoostUpdater.doUpdate(XGBoostUpdater.java:178) at ml.dmlc.xgboost4j.java.XGBoostUpdateTask.execute(XGBoostUpdateTask.java:19) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.setupLocal(AbstractXGBoostTask.java:35) at water.MRTask.setupLocal0(MRTask.java:566) at water.MRTask.dfork(MRTask.java:416) at water.MRTask.doAll(MRTask.java:408) at water.MRTask.doAllNodes(MRTask.java:421) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.run(AbstractXGBoostTask.java:46) at hex.tree.xgboost.XGBoost$XGBoostDriver.scoreAndBuildTrees(XGBoost.java:466) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModelImpl(XGBoost.java:390) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModel(XGBoost.java:337) at hex.tree.xgboost.XGBoost$XGBoostDriver.computeImpl(XGBoost.java:327) at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:248) at water.H2O$H2OCountedCompleter.compute(H2O.java:1557) at jsr166y.CountedCompleter.exec(CountedCompleter.java:468) at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263) at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974) at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477) at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104) Hyper-parameter: booster, dart Hyper-parameter: categorical_encoding, LabelEncoder Hyper-parameter: col_sample_rate, 0.6 Hyper-parameter: colsample_bylevel, 0.6 Hyper-parameter: colsample_bytree, 0.6 Hyper-parameter: distribution, bernoulli Hyper-parameter: learn_rate, 0.8 Hyper-parameter: max_depth, 0 Hyper-parameter: normalize_type, tree Hyper-parameter: ntrees, 50 Hyper-parameter: sample_rate, 0.6 Hyper-parameter: sample_type, weighted Hyper-parameter: tweedie_power, 1.8 failure_details: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 failure_stack_traces: java.lang.IllegalStateException: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 at ml.dmlc.xgboost4j.java.XGBoostUpdater.invoke(XGBoostUpdater.java:108) at ml.dmlc.xgboost4j.java.XGBoostUpdater.doUpdate(XGBoostUpdater.java:178) at ml.dmlc.xgboost4j.java.XGBoostUpdateTask.execute(XGBoostUpdateTask.java:19) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.setupLocal(AbstractXGBoostTask.java:35) at water.MRTask.setupLocal0(MRTask.java:566) at water.MRTask.dfork(MRTask.java:416) at water.MRTask.doAll(MRTask.java:408) at water.MRTask.doAllNodes(MRTask.java:421) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.run(AbstractXGBoostTask.java:46) at hex.tree.xgboost.XGBoost$XGBoostDriver.scoreAndBuildTrees(XGBoost.java:466) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModelImpl(XGBoost.java:390) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModel(XGBoost.java:337) at hex.tree.xgboost.XGBoost$XGBoostDriver.computeImpl(XGBoost.java:327) at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:248) at water.H2O$H2OCountedCompleter.compute(H2O.java:1557) at jsr166y.CountedCompleter.exec(CountedCompleter.java:468) at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263) at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974) at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477) at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104) Hyper-parameter: booster, gbtree Hyper-parameter: categorical_encoding, AUTO Hyper-parameter: col_sample_rate, 1.0 Hyper-parameter: colsample_bylevel, 0.6 Hyper-parameter: colsample_bytree, 0.3 Hyper-parameter: distribution, bernoulli Hyper-parameter: learn_rate, 0.3 Hyper-parameter: max_depth, 0 Hyper-parameter: normalize_type, tree Hyper-parameter: ntrees, 100 Hyper-parameter: sample_rate, 0.1 Hyper-parameter: sample_type, uniform Hyper-parameter: tweedie_power, 1.2 failure_details: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 failure_stack_traces: java.lang.IllegalStateException: Cannot perform booster operation: updater is inactive on node /127.0.0.1:54321 at ml.dmlc.xgboost4j.java.XGBoostUpdater.invoke(XGBoostUpdater.java:108) at ml.dmlc.xgboost4j.java.XGBoostUpdater.doUpdate(XGBoostUpdater.java:178) at ml.dmlc.xgboost4j.java.XGBoostUpdateTask.execute(XGBoostUpdateTask.java:19) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.setupLocal(AbstractXGBoostTask.java:35) at water.MRTask.setupLocal0(MRTask.java:566) at water.MRTask.dfork(MRTask.java:416) at water.MRTask.doAll(MRTask.java:408) at water.MRTask.doAllNodes(MRTask.java:421) at ml.dmlc.xgboost4j.java.AbstractXGBoostTask.run(AbstractXGBoostTask.java:46) at hex.tree.xgboost.XGBoost$XGBoostDriver.scoreAndBuildTrees(XGBoost.java:466) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModelImpl(XGBoost.java:390) at hex.tree.xgboost.XGBoost$XGBoostDriver.buildModel(XGBoost.java:337) at hex.tree.xgboost.XGBoost$XGBoostDriver.computeImpl(XGBoost.java:327) at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:248) at water.H2O$H2OCountedCompleter.compute(H2O.java:1557) at jsr166y.CountedCompleter.exec(CountedCompleter.java:468) at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263) at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974) at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477) at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104)
h2o.save_grid(MODELS_LOCATION + "pca300/xgb_grid", xgb_grid.grid_id)
'../../models/pca300/xgb_grid/Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1'
nb_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/nb_grid/Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178")
glm_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/glm_grid/Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504")
gbm_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/gbm_grid/Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444")
xgb_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/xgb_grid/Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1")
dl_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/dl_grid/Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758")
drf_grid = h2o.load_grid(MODELS_LOCATION + "PCA300/drf_grid/Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677")
# Select best models from the grids based on performance on the test data
def best_model_from_grid (model_grid):
sorted_grid = model_grid.get_grid(sort_by='auc', decreasing=True)
for mdl in sorted_grid:
print("Modeld ID: ", mdl.model_id)
# print('Train data AUC: ', mdl.model_performance(train=True).auc()) # same result with model_performance()
print('Default Test data AUC: ', mdl.model_performance(valid=True).auc())
print('Default Test data AUCPR: ', mdl.model_performance(valid=True).aucpr())
print('Default Cross-validation AUC: ', mdl.model_performance(xval=True).auc())
print('Default Cross-validation AUCPR: ', mdl.model_performance(xval=True).aucpr())
print("\n--------------------\n")
print("\n@@@@@@@@@@@@@@@@@@@@@@@\n")
return sorted_grid[0]
best_nb_model = best_model_from_grid(nb_grid)
best_glm_model = best_model_from_grid(glm_grid)
best_gbm_model = best_model_from_grid(gbm_grid)
best_xgb_model= best_model_from_grid(xgb_grid)
best_dl_model= best_model_from_grid(dl_grid)
best_drf_model= best_model_from_grid(drf_grid)
Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_3 Default Test data AUC: 0.5736287073002505 Default Test data AUCPR: 0.722796224545721 Default Cross-validation AUC: 0.62177304964539 Default Cross-validation AUCPR: 0.7463032863986705 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_10 Default Test data AUC: 0.5484717029077576 Default Test data AUCPR: 0.7123235647071509 Default Cross-validation AUC: 0.5759293735224587 Default Cross-validation AUCPR: 0.6842246540548909 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_9 Default Test data AUC: 0.5590354666569862 Default Test data AUCPR: 0.7002563536407302 Default Cross-validation AUC: 0.5701713947990544 Default Cross-validation AUCPR: 0.7105505892531342 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_7 Default Test data AUC: 0.5320361563872654 Default Test data AUCPR: 0.707325077533424 Default Cross-validation AUC: 0.5394060283687943 Default Cross-validation AUCPR: 0.6829883264851554 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_4 Default Test data AUC: 0.5149381057828438 Default Test data AUCPR: 0.674797115684899 Default Cross-validation AUC: 0.5199423758865248 Default Cross-validation AUCPR: 0.6718191012843986 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_5 Default Test data AUC: 0.5180237412422406 Default Test data AUCPR: 0.6906664433624456 Default Cross-validation AUC: 0.4947104018912529 Default Cross-validation AUCPR: 0.6374350512034186 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_6 Default Test data AUC: 0.4901168911315207 Default Test data AUCPR: 0.68834210257479 Default Cross-validation AUC: 0.4929255319148936 Default Cross-validation AUCPR: 0.6363421060102182 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_1 Default Test data AUC: 0.5 Default Test data AUCPR: 0.6746506986027944 Default Cross-validation AUC: 0.4831131796690307 Default Cross-validation AUCPR: 0.641963388575653 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_2 Default Test data AUC: 0.5 Default Test data AUCPR: 0.6746506986027944 Default Cross-validation AUC: 0.4831131796690307 Default Cross-validation AUCPR: 0.641963388575653 -------------------- Modeld ID: Grid_NaiveBayes_py_30_sid_bdfe_model_python_1604806499448_2178_model_8 Default Test data AUC: 0.5 Default Test data AUCPR: 0.6746506986027944 Default Cross-validation AUC: 0.4831131796690307 Default Cross-validation AUCPR: 0.641963388575653 -------------------- @@@@@@@@@@@@@@@@@@@@@@@ Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_2 Default Test data AUC: 0.6266381094130032 Default Test data AUCPR: 0.7515512182825628 Default Cross-validation AUC: 0.8693484042553191 Default Cross-validation AUCPR: 0.9206885107574454 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_6 Default Test data AUC: 0.6266381094130032 Default Test data AUCPR: 0.7515512182825628 Default Cross-validation AUC: 0.8693484042553191 Default Cross-validation AUCPR: 0.9206885107574454 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_3 Default Test data AUC: 0.5863251896758268 Default Test data AUCPR: 0.7123711533205923 Default Cross-validation AUC: 0.8570907210401891 Default Cross-validation AUCPR: 0.8962271232275381 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_7 Default Test data AUC: 0.5863251896758268 Default Test data AUCPR: 0.7123711533205923 Default Cross-validation AUC: 0.8570907210401891 Default Cross-validation AUCPR: 0.8962271232275381 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_1 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_10 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_4 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_5 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_8 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- Modeld ID: Grid_GLM_py_30_sid_bdfe_model_python_1604806499448_2504_model_9 Default Test data AUC: 0.591788579518641 Default Test data AUCPR: 0.7168702488556923 Default Cross-validation AUC: 0.8549231678486997 Default Cross-validation AUCPR: 0.893730528947243 -------------------- @@@@@@@@@@@@@@@@@@@@@@@ Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_5 Default Test data AUC: 0.5621574037100229 Default Test data AUCPR: 0.7342422655997748 Default Cross-validation AUC: 0.8782254728132387 Default Cross-validation AUCPR: 0.9117333177488975 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_7 Default Test data AUC: 0.5911714524267615 Default Test data AUCPR: 0.7543769573104404 Default Cross-validation AUC: 0.8044193262411348 Default Cross-validation AUCPR: 0.8828104770819434 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_3 Default Test data AUC: 0.5650524558028097 Default Test data AUCPR: 0.7059262799195561 Default Cross-validation AUC: 0.7986805555555556 Default Cross-validation AUCPR: 0.867315768349834 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_1 Default Test data AUC: 0.5493520165535267 Default Test data AUCPR: 0.7040377715788042 Default Cross-validation AUC: 0.797191193853428 Default Cross-validation AUCPR: 0.8726856025971447 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_10 Default Test data AUC: 0.5104820851635387 Default Test data AUCPR: 0.6999949148168211 Default Cross-validation AUC: 0.7670227541371158 Default Cross-validation AUCPR: 0.8346180931988019 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_6 Default Test data AUC: 0.6056830144843358 Default Test data AUCPR: 0.7618816164994612 Default Cross-validation AUC: 0.7251226359338062 Default Cross-validation AUCPR: 0.8019681140716669 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_9 Default Test data AUC: 0.5600791374741352 Default Test data AUCPR: 0.7417224976322403 Default Cross-validation AUC: 0.6983333333333333 Default Cross-validation AUCPR: 0.7898803717471761 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_4 Default Test data AUC: 0.4968780629469634 Default Test data AUCPR: 0.6840605335031601 Default Cross-validation AUC: 0.6692996453900709 Default Cross-validation AUCPR: 0.7800891842461939 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_2 Default Test data AUC: 0.5485624568918576 Default Test data AUCPR: 0.6953869210230089 Default Cross-validation AUC: 0.6555067966903073 Default Cross-validation AUCPR: 0.7521405906346205 -------------------- Modeld ID: Grid_GBM_py_30_sid_bdfe_model_python_1604806499448_4444_model_8 Default Test data AUC: 0.5015972701201582 Default Test data AUCPR: 0.6641705612072644 Default Cross-validation AUC: 0.5941193853427896 Default Cross-validation AUCPR: 0.7078480055102175 -------------------- @@@@@@@@@@@@@@@@@@@@@@@ Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_1 Default Test data AUC: 0.6006189421715613 Default Test data AUCPR: 0.757982161501983 Default Cross-validation AUC: 0.8880614657210402 Default Cross-validation AUCPR: 0.9298853306000129 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_5 Default Test data AUC: 0.6373833811304316 Default Test data AUCPR: 0.7748548483987819 Default Cross-validation AUC: 0.870196513002364 Default Cross-validation AUCPR: 0.9182560753525744 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_10 Default Test data AUC: 0.5815696809089919 Default Test data AUCPR: 0.7375729038675836 Default Cross-validation AUC: 0.8111790780141844 Default Cross-validation AUCPR: 0.875342293499504 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_3 Default Test data AUC: 0.6144952263404363 Default Test data AUCPR: 0.7634580813387875 Default Cross-validation AUC: 0.8105023640661938 Default Cross-validation AUCPR: 0.8743426454795941 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_4 Default Test data AUC: 0.6177714451664428 Default Test data AUCPR: 0.764129489835918 Default Cross-validation AUC: 0.8090750591016548 Default Cross-validation AUCPR: 0.8741350674711706 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_6 Default Test data AUC: 0.6000744182669618 Default Test data AUCPR: 0.736903633999404 Default Cross-validation AUC: 0.7280053191489362 Default Cross-validation AUCPR: 0.8211763724670733 -------------------- Modeld ID: Grid_XGBoost_py_173_sid_9c98_model_python_1604825008375_1_model_2 Default Test data AUC: 0.532371946128435 Default Test data AUCPR: 0.6897493739316475 Default Cross-validation AUC: 0.7035800827423168 Default Cross-validation AUCPR: 0.7991183385997647 -------------------- @@@@@@@@@@@@@@@@@@@@@@@ Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_5 Default Test data AUC: 0.6312847133989182 Default Test data AUCPR: 0.7804867860351187 Default Cross-validation AUC: 0.8736111111111111 Default Cross-validation AUCPR: 0.9222555417769538 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_9 Default Test data AUC: 0.6440901005554144 Default Test data AUCPR: 0.7702323387778022 Default Cross-validation AUC: 0.8547916666666666 Default Cross-validation AUCPR: 0.9060445923140601 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_3 Default Test data AUC: 0.6306948125022689 Default Test data AUCPR: 0.7542601978583798 Default Cross-validation AUC: 0.8536052009456264 Default Cross-validation AUCPR: 0.905387474639246 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_2 Default Test data AUC: 0.5976694376883145 Default Test data AUCPR: 0.7620697914279121 Default Cross-validation AUC: 0.8387174940898344 Default Cross-validation AUCPR: 0.8934394867894748 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_8 Default Test data AUC: 0.6135513849057973 Default Test data AUCPR: 0.7562079654636168 Default Cross-validation AUC: 0.8291829196217494 Default Cross-validation AUCPR: 0.8897291806733669 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_7 Default Test data AUC: 0.5948560641812176 Default Test data AUCPR: 0.717706114608065 Default Cross-validation AUC: 0.8281043144208038 Default Cross-validation AUCPR: 0.8814089855031274 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_4 Default Test data AUC: 0.6513231930881767 Default Test data AUCPR: 0.771860804472994 Default Cross-validation AUC: 0.7714568557919622 Default Cross-validation AUCPR: 0.8638169616902509 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_1 Default Test data AUC: 0.6269829745525829 Default Test data AUCPR: 0.7623296430172621 Default Cross-validation AUC: 0.6530422576832151 Default Cross-validation AUCPR: 0.7725882631259251 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_10 Default Test data AUC: 0.5 Default Test data AUCPR: 0.6746506986027944 Default Cross-validation AUC: 0.5872960992907802 Default Cross-validation AUCPR: 0.7482558648957338 -------------------- Modeld ID: Grid_DeepLearning_py_3_sid_b60c_model_python_1605362597414_758_model_6 Default Test data AUC: 0.5 Default Test data AUCPR: 0.6746506986027944 Default Cross-validation AUC: 0.4935328014184397 Default Cross-validation AUCPR: 0.6517516457626242 -------------------- @@@@@@@@@@@@@@@@@@@@@@@ Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_5 Default Test data AUC: 0.5821051294151813 Default Test data AUCPR: 0.7520371662557974 Default Cross-validation AUC: 0.8844089834515367 Default Cross-validation AUCPR: 0.9292240110585137 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_7 Default Test data AUC: 0.5827857842959306 Default Test data AUCPR: 0.7503998063297266 Default Cross-validation AUC: 0.8731914893617022 Default Cross-validation AUCPR: 0.9252970368944919 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_6 Default Test data AUC: 0.5775674302101862 Default Test data AUCPR: 0.7441007584662777 Default Cross-validation AUC: 0.8658348108747045 Default Cross-validation AUCPR: 0.9146143851385142 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_2 Default Test data AUC: 0.5770955094928668 Default Test data AUCPR: 0.748800319841249 Default Cross-validation AUC: 0.8519119385342789 Default Cross-validation AUCPR: 0.9069872633627765 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_8 Default Test data AUC: 0.5849820307111482 Default Test data AUCPR: 0.7594751443978316 Default Cross-validation AUC: 0.8505673758865249 Default Cross-validation AUCPR: 0.9011700452611322 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_10 Default Test data AUC: 0.5915435437615711 Default Test data AUCPR: 0.7494350743502506 Default Cross-validation AUC: 0.8329373522458628 Default Cross-validation AUCPR: 0.8953810623184211 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_4 Default Test data AUC: 0.5773677714451665 Default Test data AUCPR: 0.746395521499641 Default Cross-validation AUC: 0.8284293735224587 Default Cross-validation AUCPR: 0.888035602758361 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_1 Default Test data AUC: 0.5668040076959379 Default Test data AUCPR: 0.7307154403277908 Default Cross-validation AUC: 0.7938371749408983 Default Cross-validation AUCPR: 0.8683331042352752 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_9 Default Test data AUC: 0.5979053980469743 Default Test data AUCPR: 0.7634623112748247 Default Cross-validation AUC: 0.786846926713948 Default Cross-validation AUCPR: 0.8613930267125789 -------------------- Modeld ID: Grid_DRF_py_173_sid_9c98_model_python_1604825008375_8677_model_3 Default Test data AUC: 0.6031509783279486 Default Test data AUCPR: 0.742750777213124 Default Cross-validation AUC: 0.7450723995271867 Default Cross-validation AUCPR: 0.8329935230794867 -------------------- @@@@@@@@@@@@@@@@@@@@@@@
def extract_params_from_model(actual_params_dict, extra_params = [], additional_keys = {}):
final_params = actual_params_dict
columns_to_be_removed = [
'model_id',
'validation_frame',
'response_column',
'ignored_columns',
'training_frame',
*extra_params
]
for col_name in columns_to_be_removed:
del final_params[col_name]
return {**final_params, **additional_keys}
from h2o.estimators import H2ONaiveBayesEstimator
top_nb = H2ONaiveBayesEstimator(**extract_params_from_model(best_nb_model.actual_params))
top_nb.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_nb, MODELS_LOCATION + "PCA300/top_nb")
print('AUC on test_pca_df_frame data: ', top_nb.model_performance(valid=True).auc(), "\n\n============================")
top_nb.model_performance
naivebayes Model Build progress: |████████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5736650088938905 ============================ Model Details ============= H2ONaiveBayesEstimator : Naive Bayes Model Key: NaiveBayes_model_python_1605504255659_1 Model Summary: ModelMetricsBinomial: naivebayes ** Reported on train data. ** MSE: 0.23176875895186294 RMSE: 0.4814236792596132 LogLoss: 0.8090609556633163 Mean Per-Class Error: 0.3141134751773049 AUC: 0.7467124704491725 AUCPR: 0.8338461959696989 Gini: 0.4934249408983451 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.06978097423895066: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 57.53 % ModelMetricsBinomial: naivebayes ** Reported on validation data. ** MSE: 0.35348622076185887 RMSE: 0.5945470719479315 LogLoss: 1.2712951498433689 Mean Per-Class Error: 0.43942171561331544 AUC: 0.5736650088938905 AUCPR: 0.7243829622084862 Gini: 0.147330017787781 Confusion Matrix (Act/Pred) for max f1 @ threshold = 1.882199883640578e-05: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 48.41 % ModelMetricsBinomial: naivebayes ** Reported on cross-validation data. ** MSE: 0.3187324803753368 RMSE: 0.5645639736782155 LogLoss: 1.2753938215212923 Mean Per-Class Error: 0.41355348699763594 AUC: 0.62177304964539 AUCPR: 0.7463032863986705 Gini: 0.24354609929078008 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.00026154732736230425: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 58.42 % Cross-Validation Metrics Summary:
number_of_response_levels | min_apriori_probability | max_apriori_probability | ||
---|---|---|---|---|
0 | 2.0 | 0.346022 | 0.653978 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 148.0 | 275.0 | 0.6501 | (275.0/423.0) |
1 | 1 | 62.0 | 738.0 | 0.0775 | (62.0/800.0) |
2 | Total | 210.0 | 1013.0 | 0.2756 | (337.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.069781 | 0.814120 | 354.0 |
1 | max f2 | 0.000378 | 0.904364 | 399.0 |
2 | max f0point5 | 0.320159 | 0.779862 | 264.0 |
3 | max accuracy | 0.135834 | 0.730989 | 326.0 |
4 | max precision | 0.999263 | 0.960000 | 1.0 |
5 | max recall | 0.000378 | 1.000000 | 399.0 |
6 | max specificity | 0.999880 | 0.997636 | 0.0 |
7 | max absolute_mcc | 0.179494 | 0.371467 | 311.0 |
8 | max min_per_class_accuracy | 0.563942 | 0.683215 | 189.0 |
9 | max mean_per_class_accuracy | 0.699184 | 0.685887 | 145.0 |
10 | max tns | 0.999880 | 422.000000 | 0.0 |
11 | max fns | 0.999880 | 779.000000 | 0.0 |
12 | max fps | 0.000378 | 423.000000 | 399.0 |
13 | max tps | 0.000378 | 800.000000 | 399.0 |
14 | max tnr | 0.999880 | 0.997636 | 0.0 |
15 | max fnr | 0.999880 | 0.973750 | 0.0 |
16 | max fpr | 0.000378 | 1.000000 | 399.0 |
17 | max tpr | 0.000378 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.999884 | 1.411154 | 1.411154 | 0.923077 | 0.999963 | 0.923077 | 0.999963 | 0.01500 | 0.01500 | 41.115385 | 41.115385 | |
1 | 2 | 0.020442 | 0.999515 | 1.401354 | 1.406450 | 0.916667 | 0.999722 | 0.920000 | 0.999847 | 0.01375 | 0.02875 | 40.135417 | 40.645000 | |
2 | 3 | 0.030253 | 0.999176 | 1.528750 | 1.446115 | 1.000000 | 0.999405 | 0.945946 | 0.999704 | 0.01500 | 0.04375 | 52.875000 | 44.611486 | |
3 | 4 | 0.040065 | 0.998847 | 1.528750 | 1.466352 | 1.000000 | 0.999075 | 0.959184 | 0.999550 | 0.01500 | 0.05875 | 52.875000 | 46.635204 | |
4 | 5 | 0.050695 | 0.998293 | 1.411154 | 1.454778 | 0.923077 | 0.998601 | 0.951613 | 0.999351 | 0.01500 | 0.07375 | 41.115385 | 45.477823 | |
5 | 6 | 0.100572 | 0.994998 | 1.328258 | 1.392033 | 0.868852 | 0.996639 | 0.910569 | 0.998006 | 0.06625 | 0.14000 | 32.825820 | 39.203252 | |
6 | 7 | 0.150450 | 0.986820 | 1.328258 | 1.370890 | 0.868852 | 0.991332 | 0.896739 | 0.995793 | 0.06625 | 0.20625 | 32.825820 | 37.088995 | |
7 | 8 | 0.200327 | 0.972453 | 1.228012 | 1.335316 | 0.803279 | 0.981436 | 0.873469 | 0.992219 | 0.06125 | 0.26750 | 22.801230 | 33.531633 | |
8 | 9 | 0.300082 | 0.926313 | 1.265605 | 1.312142 | 0.827869 | 0.952795 | 0.858311 | 0.979113 | 0.12625 | 0.39375 | 26.560451 | 31.214237 | |
9 | 10 | 0.399836 | 0.844079 | 1.140297 | 1.269269 | 0.745902 | 0.889900 | 0.830266 | 0.956855 | 0.11375 | 0.50750 | 14.029713 | 26.926892 | |
10 | 11 | 0.500409 | 0.680641 | 1.168313 | 1.248979 | 0.764228 | 0.765484 | 0.816993 | 0.918393 | 0.11750 | 0.62500 | 16.831301 | 24.897876 | |
11 | 12 | 0.600164 | 0.468491 | 0.977398 | 1.203839 | 0.639344 | 0.572908 | 0.787466 | 0.860969 | 0.09750 | 0.72250 | -2.260246 | 20.383856 | |
12 | 13 | 0.699918 | 0.255103 | 0.927275 | 1.164422 | 0.606557 | 0.358007 | 0.761682 | 0.789285 | 0.09250 | 0.81500 | -7.272541 | 16.442173 | |
13 | 14 | 0.799673 | 0.094874 | 0.839559 | 1.123897 | 0.549180 | 0.168650 | 0.735174 | 0.711865 | 0.08375 | 0.89875 | -16.044057 | 12.389698 | |
14 | 15 | 0.899428 | 0.021975 | 0.651598 | 1.071515 | 0.426230 | 0.053418 | 0.700909 | 0.638837 | 0.06500 | 0.96375 | -34.840164 | 7.151477 | |
15 | 16 | 1.000000 | 0.000068 | 0.360437 | 1.000000 | 0.235772 | 0.007576 | 0.654129 | 0.575350 | 0.03625 | 1.00000 | -63.956301 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 163.0 | 1.0 | (163.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 0.0 | 501.0 | 0.3253 | (163.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.000019 | 0.805721 | 399.0 |
1 | max f2 | 0.000019 | 0.912035 | 399.0 |
2 | max f0point5 | 0.033002 | 0.731707 | 358.0 |
3 | max accuracy | 0.004415 | 0.678643 | 389.0 |
4 | max precision | 0.999972 | 1.000000 | 0.0 |
5 | max recall | 0.000019 | 1.000000 | 399.0 |
6 | max specificity | 0.999972 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.072467 | 0.137092 | 329.0 |
8 | max min_per_class_accuracy | 0.435723 | 0.553254 | 214.0 |
9 | max mean_per_class_accuracy | 0.630219 | 0.560578 | 168.0 |
10 | max tns | 0.999972 | 163.000000 | 0.0 |
11 | max fns | 0.999972 | 337.000000 | 0.0 |
12 | max fps | 0.000019 | 163.000000 | 399.0 |
13 | max tps | 0.000019 | 338.000000 | 399.0 |
14 | max tnr | 0.999972 | 1.000000 | 0.0 |
15 | max fnr | 0.999972 | 0.997041 | 0.0 |
16 | max fpr | 0.000019 | 1.000000 | 399.0 |
17 | max tpr | 0.000019 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.011976 | 0.999151 | 0.988166 | 0.988166 | 0.666667 | 0.999484 | 0.666667 | 0.999484 | 0.011834 | 0.011834 | -1.183432 | -1.183432 | |
1 | 2 | 0.021956 | 0.997826 | 1.185799 | 1.077999 | 0.800000 | 0.998375 | 0.727273 | 0.998980 | 0.011834 | 0.023669 | 18.579882 | 7.799892 | |
2 | 3 | 0.031936 | 0.996729 | 1.185799 | 1.111686 | 0.800000 | 0.997253 | 0.750000 | 0.998440 | 0.011834 | 0.035503 | 18.579882 | 11.168639 | |
3 | 4 | 0.041916 | 0.995198 | 1.482249 | 1.199915 | 1.000000 | 0.995839 | 0.809524 | 0.997821 | 0.014793 | 0.050296 | 48.224852 | 19.991547 | |
4 | 5 | 0.053892 | 0.992816 | 0.988166 | 1.152860 | 0.666667 | 0.993714 | 0.777778 | 0.996908 | 0.011834 | 0.062130 | -1.183432 | 15.285996 | |
5 | 6 | 0.101796 | 0.982072 | 1.049926 | 1.104420 | 0.708333 | 0.987526 | 0.745098 | 0.992493 | 0.050296 | 0.112426 | 4.992604 | 10.442047 | |
6 | 7 | 0.151697 | 0.960561 | 1.067219 | 1.092183 | 0.720000 | 0.972885 | 0.736842 | 0.986043 | 0.053254 | 0.165680 | 6.721893 | 9.218312 | |
7 | 8 | 0.201597 | 0.915961 | 1.126509 | 1.100680 | 0.760000 | 0.940022 | 0.742574 | 0.974652 | 0.056213 | 0.221893 | 12.650888 | 10.067959 | |
8 | 9 | 0.301397 | 0.793827 | 1.096864 | 1.099416 | 0.740000 | 0.858133 | 0.741722 | 0.936069 | 0.109467 | 0.331361 | 9.686391 | 9.941612 | |
9 | 10 | 0.401198 | 0.645576 | 1.037574 | 1.084033 | 0.700000 | 0.724299 | 0.731343 | 0.883390 | 0.103550 | 0.434911 | 3.757396 | 8.403250 | |
10 | 11 | 0.500998 | 0.455959 | 1.037574 | 1.074778 | 0.700000 | 0.562622 | 0.725100 | 0.819492 | 0.103550 | 0.538462 | 3.757396 | 7.477781 | |
11 | 12 | 0.600798 | 0.305265 | 0.889349 | 1.043976 | 0.600000 | 0.379646 | 0.704319 | 0.746428 | 0.088757 | 0.627219 | -11.065089 | 4.397570 | |
12 | 13 | 0.700599 | 0.145351 | 1.067219 | 1.047287 | 0.720000 | 0.214842 | 0.706553 | 0.670703 | 0.106509 | 0.733728 | 6.721893 | 4.728670 | |
13 | 14 | 0.800399 | 0.061849 | 1.007929 | 1.042379 | 0.680000 | 0.100026 | 0.703242 | 0.599547 | 0.100592 | 0.834320 | 0.792899 | 4.237926 | |
14 | 15 | 0.900200 | 0.014352 | 0.889349 | 1.025414 | 0.600000 | 0.035928 | 0.691796 | 0.537061 | 0.088757 | 0.923077 | -11.065089 | 2.541361 | |
15 | 16 | 1.000000 | 0.000018 | 0.770769 | 1.000000 | 0.520000 | 0.006091 | 0.674651 | 0.484070 | 0.076923 | 1.000000 | -22.923077 | 0.000000 |
See the whole table with table.as_data_frame()
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 423.0 | 1.0 | (423.0/423.0) |
1 | 1 | 0.0 | 800.0 | 0.0 | (0.0/800.0) |
2 | Total | 0.0 | 1223.0 | 0.3459 | (423.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.000262 | 0.790905 | 399.0 |
1 | max f2 | 0.000262 | 0.904364 | 399.0 |
2 | max f0point5 | 0.069536 | 0.726111 | 351.0 |
3 | max accuracy | 0.028679 | 0.674571 | 371.0 |
4 | max precision | 0.999896 | 0.868421 | 0.0 |
5 | max recall | 0.000262 | 1.000000 | 399.0 |
6 | max specificity | 0.999896 | 0.988180 | 0.0 |
7 | max absolute_mcc | 0.028679 | 0.191441 | 371.0 |
8 | max min_per_class_accuracy | 0.677169 | 0.572500 | 155.0 |
9 | max mean_per_class_accuracy | 0.545321 | 0.586447 | 197.0 |
10 | max tns | 0.999896 | 418.000000 | 0.0 |
11 | max fns | 0.999896 | 767.000000 | 0.0 |
12 | max fps | 0.000262 | 423.000000 | 399.0 |
13 | max tps | 0.000262 | 800.000000 | 399.0 |
14 | max tnr | 0.999896 | 0.988180 | 0.0 |
15 | max fnr | 0.999896 | 0.958750 | 0.0 |
16 | max fpr | 0.000262 | 1.000000 | 399.0 |
17 | max tpr | 0.000262 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.999964 | 1.175962 | 1.175962 | 0.769231 | 0.999988 | 0.769231 | 0.999988 | 0.01250 | 0.01250 | 17.596154 | 17.596154 | |
1 | 2 | 0.020442 | 0.999885 | 1.528750 | 1.345300 | 1.000000 | 0.999930 | 0.880000 | 0.999960 | 0.01500 | 0.02750 | 52.875000 | 34.530000 | |
2 | 3 | 0.030253 | 0.999742 | 1.401354 | 1.363480 | 0.916667 | 0.999825 | 0.891892 | 0.999916 | 0.01375 | 0.04125 | 40.135417 | 36.347973 | |
3 | 4 | 0.040065 | 0.999622 | 1.146562 | 1.310357 | 0.750000 | 0.999685 | 0.857143 | 0.999860 | 0.01125 | 0.05250 | 14.656250 | 31.035714 | |
4 | 5 | 0.050695 | 0.999470 | 1.411154 | 1.331492 | 0.923077 | 0.999541 | 0.870968 | 0.999793 | 0.01500 | 0.06750 | 41.115385 | 33.149194 | |
5 | 6 | 0.100572 | 0.997892 | 1.202951 | 1.267744 | 0.786885 | 0.998813 | 0.829268 | 0.999307 | 0.06000 | 0.12750 | 20.295082 | 26.774390 | |
6 | 7 | 0.150450 | 0.995142 | 1.077643 | 1.204721 | 0.704918 | 0.996485 | 0.788043 | 0.998371 | 0.05375 | 0.18125 | 7.764344 | 20.472147 | |
7 | 8 | 0.200327 | 0.988102 | 1.177889 | 1.198041 | 0.770492 | 0.991979 | 0.783673 | 0.996780 | 0.05875 | 0.24000 | 17.788934 | 19.804082 | |
8 | 9 | 0.300082 | 0.955576 | 1.127766 | 1.174680 | 0.737705 | 0.976113 | 0.768392 | 0.989910 | 0.11250 | 0.35250 | 12.776639 | 17.467984 | |
9 | 10 | 0.399836 | 0.872114 | 0.964867 | 1.122334 | 0.631148 | 0.919737 | 0.734151 | 0.972402 | 0.09625 | 0.44875 | -3.513320 | 12.233384 | |
10 | 11 | 0.500409 | 0.724054 | 1.068882 | 1.111591 | 0.699187 | 0.809394 | 0.727124 | 0.939641 | 0.10750 | 0.55625 | 6.888211 | 11.159109 | |
11 | 12 | 0.600164 | 0.493700 | 1.014990 | 1.095535 | 0.663934 | 0.607225 | 0.716621 | 0.884389 | 0.10125 | 0.65750 | 1.498975 | 9.553474 | |
12 | 13 | 0.699918 | 0.220413 | 0.939805 | 1.073340 | 0.614754 | 0.354122 | 0.702103 | 0.808814 | 0.09375 | 0.75125 | -6.019467 | 7.333966 | |
13 | 14 | 0.799673 | 0.078218 | 1.014990 | 1.066061 | 0.663934 | 0.138178 | 0.697342 | 0.725156 | 0.10125 | 0.85250 | 1.498975 | 6.606084 | |
14 | 15 | 0.899428 | 0.012923 | 0.801967 | 1.036770 | 0.524590 | 0.039012 | 0.678182 | 0.649056 | 0.08000 | 0.93250 | -19.803279 | 3.677045 | |
15 | 16 | 1.000000 | 0.000009 | 0.671159 | 1.000000 | 0.439024 | 0.004251 | 0.654129 | 0.584206 | 0.06750 | 1.00000 | -32.884146 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.6813875 | 0.032319296 | 0.7108434 | 0.63095236 | 0.6987448 | 0.6680498 | 0.6983471 |
1 | auc | 0.6512176 | 0.020242797 | 0.6659452 | 0.64347064 | 0.6209906 | 0.67228264 | 0.65339893 |
2 | aucpr | 0.7582092 | 0.026206708 | 0.7725955 | 0.7343244 | 0.73981434 | 0.797079 | 0.74723285 |
3 | err | 0.31861252 | 0.032319296 | 0.28915662 | 0.3690476 | 0.30125523 | 0.33195022 | 0.30165288 |
4 | err_count | 78.0 | 9.027735 | 72.0 | 93.0 | 72.0 | 80.0 | 73.0 |
5 | f0point5 | 0.7236188 | 0.027202625 | 0.7522124 | 0.68123394 | 0.73913044 | 0.71555555 | 0.7299618 |
6 | f1 | 0.8002306 | 0.015225069 | 0.8095238 | 0.77372265 | 0.8095238 | 0.80099505 | 0.8073879 |
7 | f2 | 0.8958176 | 0.012522429 | 0.87628865 | 0.8952703 | 0.8947368 | 0.90960455 | 0.9031877 |
8 | lift_top_group | 1.4234031 | 0.20615338 | 1.5090909 | 1.0566038 | 1.5031446 | 1.4968944 | 1.551282 |
9 | logloss | 1.2761745 | 0.1843319 | 1.1700575 | 1.3332363 | 1.5758824 | 1.1597352 | 1.1419615 |
10 | max_per_class_error | 0.87064785 | 0.12570904 | 0.71428573 | 1.0 | 0.825 | 1.0 | 0.81395346 |
11 | mcc | 0.27236786 | 0.033709124 | 0.2863477 | NaN | 0.233918 | NaN | 0.2968379 |
12 | mean_per_class_accuracy | 0.5517067 | 0.04909224 | 0.60649353 | 0.5 | 0.56863207 | 0.5 | 0.5834079 |
13 | mean_per_class_error | 0.4482933 | 0.04909224 | 0.3935065 | 0.5 | 0.43136793 | 0.5 | 0.41659212 |
14 | mse | 0.31911555 | 0.054569524 | 0.30913097 | 0.30073154 | 0.4096822 | 0.2621607 | 0.31387228 |
15 | pr_auc | 0.7582092 | 0.026206708 | 0.7725955 | 0.7343244 | 0.73981434 | 0.797079 | 0.74723285 |
16 | precision | 0.6804082 | 0.033164605 | 0.7183099 | 0.63095236 | 0.69863015 | 0.6680498 | 0.68609864 |
17 | r2 | -0.41328508 | 0.251438 | -0.38285926 | -0.2915165 | -0.83973724 | -0.182186 | -0.3701264 |
18 | recall | 0.97406125 | 0.030491687 | 0.92727274 | 1.0 | 0.9622642 | 1.0 | 0.9807692 |
19 | rmse | 0.5633418 | 0.046924848 | 0.55599546 | 0.5483899 | 0.64006424 | 0.5120163 | 0.56024307 |
<bound method ModelBase.model_performance of >
from h2o.estimators import H2OGeneralizedLinearEstimator
top_glm = H2OGeneralizedLinearEstimator(**extract_params_from_model(best_glm_model.actual_params, ['lambda']))
top_glm.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_glm, MODELS_LOCATION + "PCA300/top_glm")
print('AUC on test_pca_df_frame data: ', top_glm.model_performance(valid=True).auc(), "\n\n============================")
top_glm.model_performance
glm Model Build progress: |███████████████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6266381094130032 ============================ Model Details ============= H2OGeneralizedLinearEstimator : Generalized Linear Modeling Model Key: GLM_model_python_1605504255659_20 GLM Model: summary ModelMetricsBinomialGLM: glm ** Reported on train data. ** MSE: 0.06737869858143082 RMSE: 0.2595740714736948 LogLoss: 0.23465203622551015 Null degrees of freedom: 1222 Residual degrees of freedom: 922 Null deviance: 1577.310356148988 Residual deviance: 573.958880607598 AIC: 1175.958880607598 AUC: 0.9708421985815603 AUCPR: 0.9839626762765715 Gini: 0.9416843971631206 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.5308632131207871: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 65.41 % ModelMetricsBinomialGLM: glm ** Reported on validation data. ** MSE: 0.25607792452539224 RMSE: 0.5060414257008928 LogLoss: 0.9472698917241775 Null degrees of freedom: 500 Residual degrees of freedom: 200 Null deviance: 633.0394016859412 Residual deviance: 2383.229676671357 AIC: 2985.229676671357 AUC: 0.6266381094130032 AUCPR: 0.7515512182825628 Gini: 0.2532762188260065 Confusion Matrix (Act/Pred) for max f1 @ threshold = 1.7755963216651885e-34: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 64.06 % ModelMetricsBinomialGLM: glm ** Reported on cross-validation data. ** MSE: 0.1395447128968992 RMSE: 0.3735568402491102 LogLoss: 0.4527805055290165 Null degrees of freedom: 1222 Residual degrees of freedom: 922 Null deviance: 1577.9471491067366 Residual deviance: 1107.5011165239741 AIC: 1709.5011165239741 AUC: 0.8693484042553191 AUCPR: 0.9206885107574454
family | link | regularization | number_of_predictors_total | number_of_active_predictors | number_of_iterations | training_frame | ||
---|---|---|---|---|---|---|---|---|
0 | binomial | logit | Ridge ( lambda = 0.01677 ) | 300 | 300 | 5 | py_3_sid_81ee |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 366.0 | 57.0 | 0.1348 | (57.0/423.0) |
1 | 1 | 45.0 | 755.0 | 0.0563 | (45.0/800.0) |
2 | Total | 411.0 | 812.0 | 0.0834 | (102.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.530863 | 0.936725 | 219.0 |
1 | max f2 | 0.350370 | 0.953659 | 270.0 |
2 | max f0point5 | 0.708890 | 0.953228 | 167.0 |
3 | max accuracy | 0.642200 | 0.916599 | 188.0 |
4 | max precision | 0.999739 | 1.000000 | 0.0 |
5 | max recall | 0.113270 | 1.000000 | 347.0 |
6 | max specificity | 0.999739 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.642200 | 0.822160 | 188.0 |
8 | max min_per_class_accuracy | 0.627963 | 0.912530 | 193.0 |
9 | max mean_per_class_accuracy | 0.642200 | 0.919539 | 188.0 |
10 | max tns | 0.999739 | 423.000000 | 0.0 |
11 | max fns | 0.999739 | 784.000000 | 0.0 |
12 | max fps | 0.000207 | 423.000000 | 399.0 |
13 | max tps | 0.113270 | 800.000000 | 347.0 |
14 | max tnr | 0.999739 | 1.000000 | 0.0 |
15 | max fnr | 0.999739 | 0.980000 | 0.0 |
16 | max fpr | 0.000207 | 1.000000 | 399.0 |
17 | max tpr | 0.113270 | 1.000000 | 347.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.999616 | 1.528750 | 1.528750 | 1.000000 | 0.999787 | 1.000000 | 0.999787 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 0.998603 | 1.528750 | 1.528750 | 1.000000 | 0.999156 | 1.000000 | 0.999484 | 0.01500 | 0.03125 | 52.875000 | 52.875000 | |
2 | 3 | 0.030253 | 0.997103 | 1.528750 | 1.528750 | 1.000000 | 0.997897 | 1.000000 | 0.998970 | 0.01500 | 0.04625 | 52.875000 | 52.875000 | |
3 | 4 | 0.040065 | 0.995161 | 1.528750 | 1.528750 | 1.000000 | 0.996197 | 1.000000 | 0.998291 | 0.01500 | 0.06125 | 52.875000 | 52.875000 | |
4 | 5 | 0.050695 | 0.993913 | 1.528750 | 1.528750 | 1.000000 | 0.994620 | 1.000000 | 0.997521 | 0.01625 | 0.07750 | 52.875000 | 52.875000 | |
5 | 6 | 0.100572 | 0.987903 | 1.528750 | 1.528750 | 1.000000 | 0.991093 | 1.000000 | 0.994333 | 0.07625 | 0.15375 | 52.875000 | 52.875000 | |
6 | 7 | 0.150450 | 0.979469 | 1.528750 | 1.528750 | 1.000000 | 0.983049 | 1.000000 | 0.990592 | 0.07625 | 0.23000 | 52.875000 | 52.875000 | |
7 | 8 | 0.200327 | 0.969746 | 1.528750 | 1.528750 | 1.000000 | 0.975220 | 1.000000 | 0.986765 | 0.07625 | 0.30625 | 52.875000 | 52.875000 | |
8 | 9 | 0.300082 | 0.945710 | 1.503689 | 1.520419 | 0.983607 | 0.957797 | 0.994550 | 0.977135 | 0.15000 | 0.45625 | 50.368852 | 52.041894 | |
9 | 10 | 0.399836 | 0.898344 | 1.491158 | 1.513119 | 0.975410 | 0.922858 | 0.989775 | 0.963594 | 0.14875 | 0.60500 | 49.115779 | 51.311861 | |
10 | 11 | 0.500409 | 0.823264 | 1.479035 | 1.506268 | 0.967480 | 0.863465 | 0.985294 | 0.943470 | 0.14875 | 0.75375 | 47.903455 | 50.626838 | |
11 | 12 | 0.600164 | 0.678715 | 1.353320 | 1.480846 | 0.885246 | 0.758413 | 0.968665 | 0.912711 | 0.13500 | 0.88875 | 35.331967 | 48.084639 | |
12 | 13 | 0.699918 | 0.423889 | 0.726783 | 1.373375 | 0.475410 | 0.562245 | 0.898364 | 0.862761 | 0.07250 | 0.96125 | -27.321721 | 37.337471 | |
13 | 14 | 0.799673 | 0.229252 | 0.288207 | 1.238006 | 0.188525 | 0.324006 | 0.809816 | 0.795555 | 0.02875 | 0.99000 | -71.179303 | 23.800613 | |
14 | 15 | 0.899428 | 0.077290 | 0.100246 | 1.111818 | 0.065574 | 0.140127 | 0.727273 | 0.722862 | 0.01000 | 1.00000 | -89.975410 | 11.181818 | |
15 | 16 | 1.000000 | 0.000207 | 0.000000 | 1.000000 | 0.000000 | 0.039440 | 0.654129 | 0.654128 | 0.00000 | 1.00000 | -100.000000 | 0.000000 |
Gini: 0.7386968085106382 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.5371233996347867: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 66.03 % Cross-Validation Metrics Summary: See the whole table with table.as_data_frame() Scoring History:
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 163.0 | 1.0 | (163.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 0.0 | 501.0 | 0.3253 | (163.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 1.775596e-34 | 0.805721 | 399.0 |
1 | max f2 | 1.775596e-34 | 0.912035 | 399.0 |
2 | max f0point5 | 7.193462e-01 | 0.744361 | 180.0 |
3 | max accuracy | 5.300331e-02 | 0.678643 | 384.0 |
4 | max precision | 8.944720e-01 | 0.832117 | 89.0 |
5 | max recall | 1.775596e-34 | 1.000000 | 399.0 |
6 | max specificity | 9.999816e-01 | 0.987730 | 0.0 |
7 | max absolute_mcc | 7.274565e-01 | 0.262032 | 176.0 |
8 | max min_per_class_accuracy | 6.789091e-01 | 0.612426 | 199.0 |
9 | max mean_per_class_accuracy | 7.274565e-01 | 0.639743 | 176.0 |
10 | max tns | 9.999816e-01 | 161.000000 | 0.0 |
11 | max fns | 9.999816e-01 | 337.000000 | 0.0 |
12 | max fps | 8.439892e-03 | 163.000000 | 395.0 |
13 | max tps | 1.775596e-34 | 338.000000 | 399.0 |
14 | max tnr | 9.999816e-01 | 0.987730 | 0.0 |
15 | max fnr | 9.999816e-01 | 0.997041 | 0.0 |
16 | max fpr | 8.439892e-03 | 1.000000 | 395.0 |
17 | max tpr | 1.775596e-34 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.011976 | 9.993451e-01 | 0.741124 | 0.741124 | 0.500000 | 0.999707 | 0.500000 | 0.999707 | 0.008876 | 0.008876 | -25.887574 | -25.887574 | |
1 | 2 | 0.021956 | 9.942697e-01 | 1.482249 | 1.077999 | 1.000000 | 0.995651 | 0.727273 | 0.997863 | 0.014793 | 0.023669 | 48.224852 | 7.799892 | |
2 | 3 | 0.031936 | 9.906410e-01 | 0.889349 | 1.019046 | 0.600000 | 0.992628 | 0.687500 | 0.996227 | 0.008876 | 0.032544 | -11.065089 | 1.904586 | |
3 | 4 | 0.041916 | 9.865676e-01 | 1.185799 | 1.058749 | 0.800000 | 0.988036 | 0.714286 | 0.994277 | 0.011834 | 0.044379 | 18.579882 | 5.874894 | |
4 | 5 | 0.051896 | 9.830744e-01 | 1.482249 | 1.140191 | 1.000000 | 0.984516 | 0.769231 | 0.992400 | 0.014793 | 0.059172 | 48.224852 | 14.019117 | |
5 | 6 | 0.101796 | 9.663331e-01 | 1.126509 | 1.133484 | 0.760000 | 0.974368 | 0.764706 | 0.983561 | 0.056213 | 0.115385 | 12.650888 | 13.348416 | |
6 | 7 | 0.151697 | 9.474713e-01 | 1.363669 | 1.209203 | 0.920000 | 0.956715 | 0.815789 | 0.974730 | 0.068047 | 0.183432 | 36.366864 | 20.920274 | |
7 | 8 | 0.201597 | 9.352137e-01 | 1.185799 | 1.203410 | 0.800000 | 0.940910 | 0.811881 | 0.966359 | 0.059172 | 0.242604 | 18.579882 | 20.340969 | |
8 | 9 | 0.301397 | 8.765075e-01 | 1.245089 | 1.217211 | 0.840000 | 0.905349 | 0.821192 | 0.946157 | 0.124260 | 0.366864 | 24.508876 | 21.721071 | |
9 | 10 | 0.401198 | 8.087037e-01 | 1.037574 | 1.172525 | 0.700000 | 0.848144 | 0.791045 | 0.921775 | 0.103550 | 0.470414 | 3.757396 | 17.252495 | |
10 | 11 | 0.500998 | 7.178550e-01 | 1.185799 | 1.175169 | 0.800000 | 0.756387 | 0.792829 | 0.888830 | 0.118343 | 0.588757 | 18.579882 | 17.516915 | |
11 | 12 | 0.602794 | 6.154637e-01 | 0.697529 | 1.094508 | 0.470588 | 0.661910 | 0.738411 | 0.850509 | 0.071006 | 0.659763 | -30.247128 | 9.450801 | |
12 | 13 | 0.700599 | 4.934618e-01 | 0.756249 | 1.047287 | 0.510204 | 0.557423 | 0.706553 | 0.809594 | 0.073964 | 0.733728 | -24.375075 | 4.728670 | |
13 | 14 | 0.800399 | 3.358252e-01 | 0.978284 | 1.038683 | 0.660000 | 0.426580 | 0.700748 | 0.761836 | 0.097633 | 0.831361 | -2.171598 | 3.868288 | |
14 | 15 | 0.900200 | 1.369725e-01 | 0.889349 | 1.022127 | 0.600000 | 0.237362 | 0.689579 | 0.703690 | 0.088757 | 0.920118 | -11.065089 | 2.212703 | |
15 | 16 | 1.000000 | 1.775596e-34 | 0.800414 | 1.000000 | 0.540000 | 0.071469 | 0.674651 | 0.640595 | 0.079882 | 1.000000 | -19.958580 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 290.0 | 133.0 | 0.3144 | (133.0/423.0) |
1 | 1 | 102.0 | 698.0 | 0.1275 | (102.0/800.0) |
2 | Total | 392.0 | 831.0 | 0.1922 | (235.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.537123 | 0.855917 | 218.0 |
1 | max f2 | 0.119758 | 0.910047 | 344.0 |
2 | max f0point5 | 0.735585 | 0.868885 | 152.0 |
3 | max accuracy | 0.550566 | 0.808667 | 213.0 |
4 | max precision | 0.999730 | 1.000000 | 0.0 |
5 | max recall | 0.000151 | 1.000000 | 399.0 |
6 | max specificity | 0.999730 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.694445 | 0.583450 | 170.0 |
8 | max min_per_class_accuracy | 0.702083 | 0.798750 | 167.0 |
9 | max mean_per_class_accuracy | 0.735585 | 0.801497 | 152.0 |
10 | max tns | 0.999730 | 423.000000 | 0.0 |
11 | max fns | 0.999730 | 790.000000 | 0.0 |
12 | max fps | 0.000151 | 423.000000 | 399.0 |
13 | max tps | 0.000151 | 800.000000 | 399.0 |
14 | max tnr | 0.999730 | 1.000000 | 0.0 |
15 | max fnr | 0.999730 | 0.987500 | 0.0 |
16 | max fpr | 0.000151 | 1.000000 | 399.0 |
17 | max tpr | 0.000151 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.998523 | 1.411154 | 1.411154 | 0.923077 | 0.999516 | 0.923077 | 0.999516 | 0.01500 | 0.01500 | 41.115385 | 41.115385 | |
1 | 2 | 0.020442 | 0.997224 | 1.401354 | 1.406450 | 0.916667 | 0.998027 | 0.920000 | 0.998801 | 0.01375 | 0.02875 | 40.135417 | 40.645000 | |
2 | 3 | 0.030253 | 0.996328 | 1.528750 | 1.446115 | 1.000000 | 0.996829 | 0.945946 | 0.998162 | 0.01500 | 0.04375 | 52.875000 | 44.611486 | |
3 | 4 | 0.040065 | 0.994908 | 1.528750 | 1.466352 | 1.000000 | 0.995508 | 0.959184 | 0.997512 | 0.01500 | 0.05875 | 52.875000 | 46.635204 | |
4 | 5 | 0.050695 | 0.993039 | 1.411154 | 1.454778 | 0.923077 | 0.993942 | 0.951613 | 0.996763 | 0.01500 | 0.07375 | 41.115385 | 45.477823 | |
5 | 6 | 0.100572 | 0.984540 | 1.528750 | 1.491463 | 1.000000 | 0.988600 | 0.975610 | 0.992715 | 0.07625 | 0.15000 | 52.875000 | 49.146341 | |
6 | 7 | 0.150450 | 0.975300 | 1.478627 | 1.487208 | 0.967213 | 0.980045 | 0.972826 | 0.988515 | 0.07375 | 0.22375 | 47.862705 | 48.720788 | |
7 | 8 | 0.200327 | 0.963804 | 1.478627 | 1.485071 | 0.967213 | 0.969176 | 0.971429 | 0.983700 | 0.07375 | 0.29750 | 47.862705 | 48.507143 | |
8 | 9 | 0.300082 | 0.929459 | 1.453566 | 1.474598 | 0.950820 | 0.948175 | 0.964578 | 0.971890 | 0.14500 | 0.44250 | 45.356557 | 47.459809 | |
9 | 10 | 0.399836 | 0.872848 | 1.303197 | 1.431835 | 0.852459 | 0.903500 | 0.936605 | 0.954828 | 0.13000 | 0.57250 | 30.319672 | 43.183538 | |
10 | 11 | 0.500409 | 0.792277 | 1.280173 | 1.401354 | 0.837398 | 0.837360 | 0.916667 | 0.931219 | 0.12875 | 0.70125 | 28.017276 | 40.135417 | |
11 | 12 | 0.600164 | 0.686784 | 1.065113 | 1.345467 | 0.696721 | 0.739974 | 0.880109 | 0.899432 | 0.10625 | 0.80750 | 6.511270 | 34.546662 | |
12 | 13 | 0.699918 | 0.494666 | 0.739314 | 1.259076 | 0.483607 | 0.593596 | 0.823598 | 0.855843 | 0.07375 | 0.88125 | -26.068648 | 25.907564 | |
13 | 14 | 0.799673 | 0.281606 | 0.588945 | 1.175481 | 0.385246 | 0.387120 | 0.768916 | 0.797372 | 0.05875 | 0.94000 | -41.105533 | 17.548057 | |
14 | 15 | 0.899428 | 0.094618 | 0.350861 | 1.084023 | 0.229508 | 0.180079 | 0.709091 | 0.728909 | 0.03500 | 0.97500 | -64.913934 | 8.402273 | |
15 | 16 | 1.000000 | 0.000060 | 0.248577 | 1.000000 | 0.162602 | 0.046484 | 0.654129 | 0.660276 | 0.02500 | 1.00000 | -75.142276 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.8160008 | 0.021070773 | 0.7871486 | 0.8373016 | 0.8033473 | 0.8340249 | 0.8181818 |
1 | auc | 0.8698101 | 0.015944941 | 0.84415585 | 0.8861838 | 0.8792453 | 0.8706522 | 0.86881334 |
2 | aucpr | 0.92141294 | 0.018122284 | 0.8909563 | 0.9269646 | 0.93958586 | 0.92370063 | 0.92585725 |
3 | err | 0.18399917 | 0.021070773 | 0.2128514 | 0.16269842 | 0.19665273 | 0.16597511 | 0.18181819 |
4 | err_count | 45.0 | 5.2440443 | 53.0 | 41.0 | 47.0 | 40.0 | 44.0 |
5 | f0point5 | 0.8489646 | 0.028703708 | 0.8145766 | 0.8882907 | 0.8304892 | 0.8639053 | 0.847561 |
6 | f1 | 0.86426866 | 0.01006933 | 0.8515406 | 0.86557376 | 0.8613569 | 0.8795181 | 0.863354 |
7 | f2 | 0.8812137 | 0.021759702 | 0.8920188 | 0.8439898 | 0.89460784 | 0.8957055 | 0.87974685 |
8 | lift_top_group | 1.4284575 | 0.23887382 | 1.0060606 | 1.5849056 | 1.5031446 | 1.4968944 | 1.551282 |
9 | logloss | 0.45273125 | 0.03007873 | 0.49771476 | 0.4211145 | 0.43569115 | 0.44234762 | 0.4667883 |
10 | max_per_class_error | 0.33949107 | 0.118501484 | 0.47619048 | 0.16981132 | 0.425 | 0.3125 | 0.3139535 |
11 | mcc | 0.5833133 | 0.06423936 | 0.500812 | 0.66434956 | 0.53980726 | 0.6165101 | 0.59508747 |
12 | mean_per_class_accuracy | 0.7789316 | 0.04571704 | 0.7225108 | 0.8398255 | 0.7466195 | 0.79716617 | 0.7885361 |
13 | mean_per_class_error | 0.22106838 | 0.04571704 | 0.2774892 | 0.16017447 | 0.2533805 | 0.20283385 | 0.21146393 |
14 | mse | 0.1395134 | 0.008161301 | 0.15205601 | 0.13344538 | 0.13846648 | 0.13148622 | 0.14211294 |
15 | null_deviance | 315.58942 | 11.1641865 | 318.47858 | 332.80194 | 304.91693 | 306.6569 | 315.0928 |
16 | pr_auc | 0.92141294 | 0.018122284 | 0.8909563 | 0.9269646 | 0.93958586 | 0.92370063 | 0.92585725 |
17 | precision | 0.8396076 | 0.043236114 | 0.7916667 | 0.9041096 | 0.8111111 | 0.8538012 | 0.8373494 |
18 | r2 | 0.3823241 | 0.040417697 | 0.31979617 | 0.42690775 | 0.37819624 | 0.40707675 | 0.37964353 |
19 | recall | 0.89349955 | 0.0373235 | 0.92121214 | 0.8301887 | 0.918239 | 0.9068323 | 0.89102566 |
timestamp | duration | iterations | negative_log_likelihood | objective | ||
---|---|---|---|---|---|---|
0 | 2020-11-16 05:26:52 | 0.000 sec | 0 | 788.655178 | 0.644853 | |
1 | 2020-11-16 05:26:53 | 0.117 sec | 1 | 378.294602 | 0.328072 | |
2 | 2020-11-16 05:26:53 | 0.147 sec | 2 | 312.852395 | 0.292164 | |
3 | 2020-11-16 05:26:53 | 0.177 sec | 3 | 291.179150 | 0.286272 | |
4 | 2020-11-16 05:26:53 | 0.205 sec | 4 | 287.185359 | 0.285953 | |
5 | 2020-11-16 05:26:53 | 0.235 sec | 5 | 286.979440 | 0.285951 |
<bound method ModelBase.model_performance of >
from h2o.estimators import H2OGradientBoostingEstimator
top_gbm = H2OGradientBoostingEstimator(**extract_params_from_model(best_gbm_model.actual_params))
top_gbm.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_gbm, MODELS_LOCATION + "PCA300/top_gbm")
print('AUC on test_pca_df_frame data: ', top_gbm.model_performance(valid=True).auc(), "\n\n============================")
top_gbm.model_performance
gbm Model Build progress: |███████████████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5569935020147384 ============================ Model Details ============= H2OGradientBoostingEstimator : Gradient Boosting Machine Model Key: GBM_model_python_1605504255659_39 Model Summary: ModelMetricsBinomial: gbm ** Reported on train data. **
number_of_trees | number_of_internal_trees | model_size_in_bytes | min_depth | max_depth | mean_depth | min_leaves | max_leaves | mean_leaves | ||
---|---|---|---|---|---|---|---|---|---|---|
0 | 150.0 | 150.0 | 80456.0 | 1.0 | 10.0 | 7.686667 | 2.0 | 87.0 | 37.97333 |
MSE: 2.015691192817385e-33 RMSE: 4.4896449668290976e-17 LogLoss: 9.622538071158348e-18 Mean Per-Class Error: 0.0 AUC: 1.0 AUCPR: 1.0 Gini: 1.0 Confusion Matrix (Act/Pred) for max f1 @ threshold = 1.0: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 65.41 % ModelMetricsBinomial: gbm ** Reported on validation data. ** MSE: 0.386094728377163 RMSE: 0.621365213362611 LogLoss: 4.44770804705716 Mean Per-Class Error: 0.4255000544523905 AUC: 0.5569935020147384 AUCPR: 0.7182021038974806 Gini: 0.11398700402947681 Confusion Matrix (Act/Pred) for max f1 @ threshold = 5.997054880112864e-11: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 75.33 % ModelMetricsBinomial: gbm ** Reported on cross-validation data. ** MSE: 0.16866504419297862 RMSE: 0.4106885001956819 LogLoss: 1.9557627576485224 Mean Per-Class Error: 0.18732121749408992 AUC: 0.8782254728132387 AUCPR: 0.9117333177488975 Gini: 0.7564509456264774 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.32318228841095886: Maximum Metrics: Maximum metrics at their respective thresholds
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 423.0 | 0.0 | 0.0 | (0.0/423.0) |
1 | 1 | 0.0 | 800.0 | 0.0 | (0.0/800.0) |
2 | Total | 423.0 | 800.0 | 0.0 | (0.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 1.000000e+00 | 1.0 | 0.0 |
1 | max f2 | 1.000000e+00 | 1.0 | 0.0 |
2 | max f0point5 | 1.000000e+00 | 1.0 | 0.0 |
3 | max accuracy | 1.000000e+00 | 1.0 | 0.0 |
4 | max precision | 1.000000e+00 | 1.0 | 0.0 |
5 | max recall | 1.000000e+00 | 1.0 | 0.0 |
6 | max specificity | 1.000000e+00 | 1.0 | 0.0 |
7 | max absolute_mcc | 1.000000e+00 | 1.0 | 0.0 |
8 | max min_per_class_accuracy | 1.000000e+00 | 1.0 | 0.0 |
9 | max mean_per_class_accuracy | 1.000000e+00 | 1.0 | 0.0 |
10 | max tns | 1.000000e+00 | 423.0 | 0.0 |
11 | max fns | 1.000000e+00 | 0.0 | 0.0 |
12 | max fps | 1.000000e-19 | 423.0 | 368.0 |
13 | max tps | 1.000000e+00 | 800.0 | 0.0 |
14 | max tnr | 1.000000e+00 | 1.0 | 0.0 |
15 | max fnr | 1.000000e+00 | 0.0 | 0.0 |
16 | max fpr | 1.000000e-19 | 1.0 | 368.0 |
17 | max tpr | 1.000000e+00 | 1.0 | 0.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.616517 | 1.000000e+00 | 1.528750 | 1.528750 | 1.00000 | 1.000000e+00 | 1.000000 | 1.000000 | 0.9425 | 0.9425 | 52.875000 | 52.875000 | |
1 | 2 | 0.699918 | 2.087403e-17 | 0.689436 | 1.428738 | 0.45098 | 4.509804e-01 | 0.934579 | 0.934579 | 0.0575 | 1.0000 | -31.056373 | 42.873832 | |
2 | 3 | 0.799673 | 3.586533e-18 | 0.000000 | 1.250511 | 0.00000 | 9.679615e-18 | 0.817996 | 0.817996 | 0.0000 | 1.0000 | -100.000000 | 25.051125 | |
3 | 4 | 0.899428 | 5.047307e-19 | 0.000000 | 1.111818 | 0.00000 | 1.630406e-18 | 0.727273 | 0.727273 | 0.0000 | 1.0000 | -100.000000 | 11.181818 | |
4 | 5 | 1.000000 | 1.000000e-19 | 0.000000 | 1.000000 | 0.00000 | 1.859889e-19 | 0.654129 | 0.654129 | 0.0000 | 1.0000 | -100.000000 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 4.0 | 159.0 | 0.9755 | (159.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 4.0 | 497.0 | 0.3174 | (159.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 5.997055e-11 | 0.809581 | 311.0 |
1 | max f2 | 5.997055e-11 | 0.914008 | 311.0 |
2 | max f0point5 | 6.125291e-08 | 0.727432 | 300.0 |
3 | max accuracy | 1.197387e-09 | 0.682635 | 309.0 |
4 | max precision | 9.999999e-01 | 0.750000 | 2.0 |
5 | max recall | 5.997055e-11 | 1.000000 | 311.0 |
6 | max specificity | 1.000000e+00 | 0.773006 | 0.0 |
7 | max absolute_mcc | 9.999592e-01 | 0.139661 | 58.0 |
8 | max min_per_class_accuracy | 9.998663e-01 | 0.564417 | 76.0 |
9 | max mean_per_class_accuracy | 9.999592e-01 | 0.574500 | 58.0 |
10 | max tns | 1.000000e+00 | 126.000000 | 0.0 |
11 | max fns | 1.000000e+00 | 229.000000 | 0.0 |
12 | max fps | 2.832764e-14 | 163.000000 | 315.0 |
13 | max tps | 5.997055e-11 | 338.000000 | 311.0 |
14 | max tnr | 1.000000e+00 | 0.773006 | 0.0 |
15 | max fnr | 1.000000e+00 | 0.677515 | 0.0 |
16 | max fpr | 2.832764e-14 | 1.000000 | 315.0 |
17 | max tpr | 5.997055e-11 | 1.000000 | 311.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.033932 | 1.000000e+00 | 1.220675 | 1.220675 | 0.823529 | 1.000000 | 0.823529 | 1.000000 | 0.041420 | 0.041420 | 22.067525 | 22.067525 | |
1 | 2 | 0.041916 | 1.000000e+00 | 1.111686 | 1.199915 | 0.750000 | 1.000000 | 0.809524 | 1.000000 | 0.008876 | 0.050296 | 11.168639 | 19.991547 | |
2 | 3 | 0.051896 | 1.000000e+00 | 1.482249 | 1.254210 | 1.000000 | 1.000000 | 0.846154 | 1.000000 | 0.014793 | 0.065089 | 48.224852 | 25.421029 | |
3 | 4 | 0.101796 | 1.000000e+00 | 1.185799 | 1.220675 | 0.800000 | 1.000000 | 0.823529 | 1.000000 | 0.059172 | 0.124260 | 18.579882 | 22.067525 | |
4 | 5 | 0.151697 | 1.000000e+00 | 0.948639 | 1.131190 | 0.640000 | 1.000000 | 0.763158 | 1.000000 | 0.047337 | 0.171598 | -5.136095 | 13.118966 | |
5 | 6 | 0.201597 | 1.000000e+00 | 1.126509 | 1.130031 | 0.760000 | 1.000000 | 0.762376 | 1.000000 | 0.056213 | 0.227811 | 12.650888 | 13.003105 | |
6 | 7 | 0.301397 | 1.000000e+00 | 1.096864 | 1.119049 | 0.740000 | 1.000000 | 0.754967 | 1.000000 | 0.109467 | 0.337278 | 9.686391 | 11.904855 | |
7 | 8 | 0.401198 | 9.999982e-01 | 1.007929 | 1.091407 | 0.680000 | 1.000000 | 0.736318 | 1.000000 | 0.100592 | 0.437870 | 0.792899 | 9.140687 | |
8 | 9 | 0.500998 | 9.999435e-01 | 1.067219 | 1.086589 | 0.720000 | 0.999980 | 0.733068 | 0.999996 | 0.106509 | 0.544379 | 6.721893 | 8.658856 | |
9 | 10 | 0.600798 | 9.961731e-01 | 0.830059 | 1.043976 | 0.560000 | 0.998915 | 0.704319 | 0.999816 | 0.082840 | 0.627219 | -16.994083 | 4.397570 | |
10 | 11 | 0.700599 | 9.074671e-01 | 0.800414 | 1.009280 | 0.540000 | 0.970440 | 0.680912 | 0.995632 | 0.079882 | 0.707101 | -19.958580 | 0.928033 | |
11 | 12 | 0.800399 | 1.208526e-01 | 0.830059 | 0.986934 | 0.560000 | 0.534798 | 0.665835 | 0.938171 | 0.082840 | 0.789941 | -16.994083 | -1.306645 | |
12 | 13 | 0.900200 | 2.483908e-04 | 1.126509 | 1.002408 | 0.760000 | 0.024323 | 0.676275 | 0.836858 | 0.112426 | 0.902367 | 12.650888 | 0.240754 | |
13 | 14 | 1.000000 | 2.832764e-14 | 0.978284 | 1.000000 | 0.660000 | 0.000018 | 0.674651 | 0.753341 | 0.097633 | 1.000000 | -2.171598 | 0.000000 |
Gains/Lift Table: Avg response rate: 65.41 %, avg score: 71.99 % Cross-Validation Metrics Summary: See the whole table with table.as_data_frame() Scoring History: See the whole table with table.as_data_frame() Variable Importances: See the whole table with table.as_data_frame()
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 268.0 | 155.0 | 0.3664 | (155.0/423.0) |
1 | 1 | 65.0 | 735.0 | 0.0813 | (65.0/800.0) |
2 | Total | 333.0 | 890.0 | 0.1799 | (220.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 3.231823e-01 | 0.869822 | 238.0 |
1 | max f2 | 9.540450e-05 | 0.924430 | 356.0 |
2 | max f0point5 | 9.999822e-01 | 0.876678 | 45.0 |
3 | max accuracy | 9.800485e-01 | 0.827473 | 167.0 |
4 | max precision | 1.000000e+00 | 0.937615 | 0.0 |
5 | max recall | 2.398012e-09 | 1.000000 | 399.0 |
6 | max specificity | 1.000000e+00 | 0.919622 | 0.0 |
7 | max absolute_mcc | 9.800485e-01 | 0.615008 | 167.0 |
8 | max min_per_class_accuracy | 9.998924e-01 | 0.807500 | 76.0 |
9 | max mean_per_class_accuracy | 9.999822e-01 | 0.812679 | 45.0 |
10 | max tns | 1.000000e+00 | 389.000000 | 0.0 |
11 | max fns | 1.000000e+00 | 289.000000 | 0.0 |
12 | max fps | 2.398012e-09 | 423.000000 | 399.0 |
13 | max tps | 2.398012e-09 | 800.000000 | 399.0 |
14 | max tnr | 1.000000e+00 | 0.919622 | 0.0 |
15 | max fnr | 1.000000e+00 | 0.361250 | 0.0 |
16 | max fpr | 2.398012e-09 | 1.000000 | 399.0 |
17 | max tpr | 2.398012e-09 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.065413 | 1.000000e+00 | 1.490531 | 1.490531 | 0.975000 | 1.000000e+00 | 0.975000 | 1.000000 | 0.09750 | 0.09750 | 49.053125 | 49.053125 | |
1 | 2 | 0.103025 | 1.000000e+00 | 1.495516 | 1.492351 | 0.978261 | 1.000000e+00 | 0.976190 | 1.000000 | 0.05625 | 0.15375 | 49.551630 | 49.235119 | |
2 | 3 | 0.150450 | 1.000000e+00 | 1.476034 | 1.487208 | 0.965517 | 1.000000e+00 | 0.972826 | 1.000000 | 0.07000 | 0.22375 | 47.603448 | 48.720788 | |
3 | 4 | 0.200327 | 1.000000e+00 | 1.478627 | 1.485071 | 0.967213 | 1.000000e+00 | 0.971429 | 1.000000 | 0.07375 | 0.29750 | 47.862705 | 48.507143 | |
4 | 5 | 0.300082 | 1.000000e+00 | 1.403443 | 1.457936 | 0.918033 | 1.000000e+00 | 0.953678 | 1.000000 | 0.14000 | 0.43750 | 40.344262 | 45.793597 | |
5 | 6 | 0.399836 | 1.000000e+00 | 1.441035 | 1.453719 | 0.942623 | 1.000000e+00 | 0.950920 | 1.000000 | 0.14375 | 0.58125 | 44.103484 | 45.371933 | |
6 | 7 | 0.500409 | 9.999993e-01 | 1.242886 | 1.411346 | 0.813008 | 9.999999e-01 | 0.923203 | 1.000000 | 0.12500 | 0.70625 | 24.288618 | 41.134600 | |
7 | 8 | 0.600164 | 9.998290e-01 | 1.065113 | 1.353798 | 0.696721 | 9.999755e-01 | 0.885559 | 0.999996 | 0.10625 | 0.81250 | 6.511270 | 35.379768 | |
8 | 9 | 0.699918 | 8.250288e-01 | 0.852090 | 1.282293 | 0.557377 | 9.734470e-01 | 0.838785 | 0.996212 | 0.08500 | 0.89750 | -14.790984 | 28.229264 | |
9 | 10 | 0.799673 | 5.303647e-04 | 0.651598 | 1.203617 | 0.426230 | 2.269344e-01 | 0.787321 | 0.900249 | 0.06500 | 0.96250 | -34.840164 | 20.361708 | |
10 | 11 | 0.899428 | 1.270028e-08 | 0.263145 | 1.099310 | 0.172131 | 6.356409e-05 | 0.719091 | 0.800410 | 0.02625 | 0.98875 | -73.685451 | 9.931023 | |
11 | 12 | 1.000000 | 1.632584e-18 | 0.111860 | 1.000000 | 0.073171 | 1.140950e-09 | 0.654129 | 0.719911 | 0.01125 | 1.00000 | -88.814024 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.831843 | 0.01859163 | 0.82329315 | 0.8055556 | 0.83682007 | 0.8381743 | 0.8553719 |
1 | auc | 0.8775816 | 0.011729488 | 0.87460315 | 0.8894299 | 0.8612421 | 0.8740295 | 0.88860315 |
2 | aucpr | 0.9119413 | 0.011119945 | 0.9171611 | 0.92475086 | 0.89485925 | 0.9091185 | 0.9138167 |
3 | err | 0.168157 | 0.01859163 | 0.17670682 | 0.19444445 | 0.16317992 | 0.16182573 | 0.1446281 |
4 | err_count | 41.2 | 5.4037023 | 44.0 | 49.0 | 39.0 | 39.0 | 35.0 |
5 | f0point5 | 0.8503556 | 0.027037434 | 0.8513053 | 0.81124073 | 0.86412394 | 0.84126985 | 0.88383836 |
6 | f1 | 0.8790338 | 0.012038547 | 0.872093 | 0.86197186 | 0.88145894 | 0.8907563 | 0.8888889 |
7 | f2 | 0.91066444 | 0.022579378 | 0.8939213 | 0.91947114 | 0.8995037 | 0.9464286 | 0.89399743 |
8 | lift_top_group | 1.4909613 | 0.0676803 | 1.5090909 | 1.5849056 | 1.5031446 | 1.4033386 | 1.4543269 |
9 | logloss | 1.9550341 | 0.08839667 | 1.9753071 | 2.0436678 | 2.0313797 | 1.8631929 | 1.8616235 |
10 | max_per_class_error | 0.36070678 | 0.103437215 | 0.3452381 | 0.4623656 | 0.3125 | 0.4625 | 0.22093023 |
11 | mcc | 0.62282103 | 0.039857086 | 0.5930234 | 0.5802296 | 0.6242338 | 0.6345227 | 0.68209577 |
12 | mean_per_class_accuracy | 0.78647846 | 0.034584176 | 0.7819264 | 0.7499493 | 0.7997248 | 0.7625388 | 0.83825284 |
13 | mean_per_class_error | 0.21352157 | 0.034584176 | 0.21807359 | 0.25005072 | 0.20027515 | 0.23746118 | 0.16174717 |
14 | mse | 0.16851825 | 0.008485014 | 0.17579463 | 0.1789323 | 0.16356316 | 0.15891518 | 0.16538592 |
15 | pr_auc | 0.9119413 | 0.011119945 | 0.9171611 | 0.92475086 | 0.89485925 | 0.9091185 | 0.9138167 |
16 | precision | 0.832654 | 0.038396414 | 0.83798885 | 0.78061223 | 0.85294116 | 0.81122446 | 0.8805031 |
17 | r2 | 0.2544202 | 0.03044994 | 0.21360438 | 0.23156036 | 0.26549596 | 0.28338882 | 0.2780515 |
18 | recall | 0.93366367 | 0.03909115 | 0.90909094 | 0.9622642 | 0.9119497 | 0.9875776 | 0.8974359 |
19 | rmse | 0.41040608 | 0.010313331 | 0.4192787 | 0.4230039 | 0.40442944 | 0.39864165 | 0.40667668 |
timestamp | duration | number_of_trees | training_rmse | training_logloss | training_auc | training_pr_auc | training_lift | training_classification_error | validation_rmse | validation_logloss | validation_auc | validation_pr_auc | validation_lift | validation_classification_error | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 2020-11-16 05:28:15 | 1 min 21.886 sec | 0.0 | 4.756513e-01 | 6.448530e-01 | 0.500000 | 0.654129 | 1.000000 | 0.345871 | 0.468954 | 0.631776 | 0.500000 | 0.674651 | 1.000000 | 0.325349 | |
1 | 2020-11-16 05:28:17 | 1 min 23.694 sec | 1.0 | 3.162353e-01 | 3.413688e-01 | 0.936668 | 0.963593 | 1.519784 | 0.138185 | 0.503058 | 0.728740 | 0.601735 | 0.740769 | 1.160629 | 0.325349 | |
2 | 2020-11-16 05:28:17 | 1 min 23.911 sec | 2.0 | 2.189493e-01 | 1.935571e-01 | 0.987368 | 0.993094 | 1.528750 | 0.045789 | 0.536939 | 0.882639 | 0.565343 | 0.734887 | 1.482249 | 0.323353 | |
3 | 2020-11-16 05:28:18 | 1 min 24.180 sec | 3.0 | 1.457040e-01 | 1.069637e-01 | 0.997986 | 0.998838 | 1.528750 | 0.018806 | 0.537076 | 0.923506 | 0.580816 | 0.742031 | 1.482249 | 0.325349 | |
4 | 2020-11-16 05:28:18 | 1 min 24.402 sec | 4.0 | 1.078160e-01 | 6.884595e-02 | 0.999622 | 0.999798 | 1.528750 | 0.007359 | 0.528007 | 0.936873 | 0.605138 | 0.745152 | 0.988166 | 0.325349 | |
5 | 2020-11-16 05:28:18 | 1 min 24.579 sec | 5.0 | 7.338120e-02 | 4.307819e-02 | 0.999713 | 0.999847 | 1.528750 | 0.001635 | 0.535525 | 0.984352 | 0.602144 | 0.741490 | 0.741124 | 0.325349 | |
6 | 2020-11-16 05:28:18 | 1 min 24.828 sec | 6.0 | 4.622081e-02 | 2.621180e-02 | 0.999997 | 0.999998 | 1.528750 | 0.000818 | 0.546897 | 1.056714 | 0.587305 | 0.744102 | 1.235207 | 0.325349 | |
7 | 2020-11-16 05:28:19 | 1 min 25.092 sec | 7.0 | 2.640568e-02 | 1.501857e-02 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.556110 | 1.126048 | 0.581352 | 0.742909 | 1.235207 | 0.325349 | |
8 | 2020-11-16 05:28:19 | 1 min 25.295 sec | 8.0 | 1.873358e-02 | 9.755299e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.566971 | 1.183291 | 0.572767 | 0.743397 | 1.235207 | 0.325349 | |
9 | 2020-11-16 05:28:19 | 1 min 25.489 sec | 9.0 | 1.189123e-02 | 6.746149e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.568130 | 1.203292 | 0.572730 | 0.749955 | 1.235207 | 0.325349 | |
10 | 2020-11-16 05:28:19 | 1 min 25.743 sec | 10.0 | 8.161421e-03 | 4.397734e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.566834 | 1.226132 | 0.575725 | 0.751956 | 1.482249 | 0.325349 | |
11 | 2020-11-16 05:28:19 | 1 min 25.960 sec | 11.0 | 7.865222e-03 | 3.003800e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.572155 | 1.263443 | 0.570588 | 0.752325 | 1.482249 | 0.325349 | |
12 | 2020-11-16 05:28:20 | 1 min 26.150 sec | 12.0 | 3.982023e-03 | 1.813033e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.571731 | 1.263830 | 0.574736 | 0.752917 | 1.482249 | 0.323353 | |
13 | 2020-11-16 05:28:20 | 1 min 26.404 sec | 13.0 | 2.922944e-03 | 1.219933e-03 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.571873 | 1.288086 | 0.576342 | 0.755963 | 1.482249 | 0.325349 | |
14 | 2020-11-16 05:28:20 | 1 min 26.622 sec | 14.0 | 3.384075e-03 | 8.764708e-04 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.573586 | 1.298539 | 0.578094 | 0.754107 | 1.482249 | 0.323353 | |
15 | 2020-11-16 05:28:20 | 1 min 26.849 sec | 15.0 | 1.559586e-03 | 5.884929e-04 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.564780 | 1.307047 | 0.587196 | 0.758601 | 1.482249 | 0.323353 | |
16 | 2020-11-16 05:28:21 | 1 min 27.108 sec | 16.0 | 7.879267e-04 | 3.734047e-04 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.562631 | 1.348081 | 0.586253 | 0.754426 | 1.482249 | 0.325349 | |
17 | 2020-11-16 05:28:21 | 1 min 27.342 sec | 17.0 | 4.568924e-04 | 2.260202e-04 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.567673 | 1.418261 | 0.582468 | 0.747905 | 1.482249 | 0.325349 | |
18 | 2020-11-16 05:28:25 | 1 min 31.524 sec | 37.0 | 1.983039e-07 | 8.510897e-08 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.577637 | 2.308046 | 0.552456 | 0.723682 | 1.482249 | 0.323353 | |
19 | 2020-11-16 05:28:29 | 1 min 35.571 sec | 56.0 | 7.196953e-11 | 4.249348e-11 | 1.000000 | 1.000000 | 1.528750 | 0.000000 | 0.601356 | 3.145119 | 0.541429 | 0.713703 | 1.235207 | 0.319361 |
variable | relative_importance | scaled_importance | percentage | |
---|---|---|---|---|
0 | PC14 | 35.467583 | 1.000000 | 0.135559 |
1 | PC11 | 16.497795 | 0.465151 | 0.063055 |
2 | PC8 | 9.303946 | 0.262323 | 0.035560 |
3 | PC69 | 8.890472 | 0.250665 | 0.033980 |
4 | PC20 | 7.806957 | 0.220115 | 0.029839 |
5 | PC2 | 7.707667 | 0.217316 | 0.029459 |
6 | PC5 | 7.509401 | 0.211726 | 0.028701 |
7 | PC3 | 7.465839 | 0.210498 | 0.028535 |
8 | PC111 | 6.293296 | 0.177438 | 0.024053 |
9 | PC128 | 6.280142 | 0.177067 | 0.024003 |
10 | PC4 | 5.694570 | 0.160557 | 0.021765 |
11 | PC218 | 4.972324 | 0.140193 | 0.019005 |
12 | PC7 | 4.649944 | 0.131104 | 0.017772 |
13 | PC97 | 4.283659 | 0.120777 | 0.016372 |
14 | PC27 | 3.937489 | 0.111017 | 0.015049 |
15 | PC13 | 3.929464 | 0.110790 | 0.015019 |
16 | PC44 | 3.922213 | 0.110586 | 0.014991 |
17 | PC55 | 3.897375 | 0.109886 | 0.014896 |
18 | PC129 | 3.311144 | 0.093357 | 0.012655 |
19 | PC94 | 2.901412 | 0.081805 | 0.011089 |
<bound method ModelBase.model_performance of >
from h2o.estimators import H2OXGBoostEstimator
top_xgb = H2OXGBoostEstimator(**extract_params_from_model(best_xgb_model.actual_params))
top_xgb.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_xgb, MODELS_LOCATION + "PCA300/top_xgb")
print('AUC on test_pca_df_frame data: ', top_xgb.model_performance(valid= True).auc(), "\n\n============================")
top_xgb.model_performance
xgboost Model Build progress: |███████████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6006189421715613 ============================ Model Details ============= H2OXGBoostEstimator : XGBoost Model Key: XGBoost_model_python_1605504255659_286 Model Summary: ModelMetricsBinomial: xgboost ** Reported on train data. ** MSE: 0.0033808608330304197 RMSE: 0.05814517033280081 LogLoss: 0.04830052729085686 Mean Per-Class Error: 0.0 AUC: 1.0 AUCPR: 1.0 Gini: 1.0 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.8332616090774536: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 65.33 % ModelMetricsBinomial: xgboost ** Reported on validation data. ** MSE: 0.24513856243186335 RMSE: 0.4951146962390264
number_of_trees | ||
---|---|---|
0 | 70.0 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 423.0 | 0.0 | 0.0 | (0.0/423.0) |
1 | 1 | 0.0 | 800.0 | 0.0 | (0.0/800.0) |
2 | Total | 423.0 | 800.0 | 0.0 | (0.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.833262 | 1.00000 | 211.0 |
1 | max f2 | 0.833262 | 1.00000 | 211.0 |
2 | max f0point5 | 0.833262 | 1.00000 | 211.0 |
3 | max accuracy | 0.833262 | 1.00000 | 211.0 |
4 | max precision | 0.996885 | 1.00000 | 0.0 |
5 | max recall | 0.833262 | 1.00000 | 211.0 |
6 | max specificity | 0.996885 | 1.00000 | 0.0 |
7 | max absolute_mcc | 0.833262 | 1.00000 | 211.0 |
8 | max min_per_class_accuracy | 0.833262 | 1.00000 | 211.0 |
9 | max mean_per_class_accuracy | 0.833262 | 1.00000 | 211.0 |
10 | max tns | 0.996885 | 423.00000 | 0.0 |
11 | max fns | 0.996885 | 799.00000 | 0.0 |
12 | max fps | 0.014052 | 423.00000 | 399.0 |
13 | max tps | 0.833262 | 800.00000 | 211.0 |
14 | max tnr | 0.996885 | 1.00000 | 0.0 |
15 | max fnr | 0.996885 | 0.99875 | 0.0 |
16 | max fpr | 0.014052 | 1.00000 | 399.0 |
17 | max tpr | 0.833262 | 1.00000 | 211.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.993755 | 1.528750 | 1.528750 | 1.000000 | 0.994982 | 1.000000 | 0.994982 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 0.992838 | 1.528750 | 1.528750 | 1.000000 | 0.993361 | 1.000000 | 0.994204 | 0.01500 | 0.03125 | 52.875000 | 52.875000 | |
2 | 3 | 0.030253 | 0.991498 | 1.528750 | 1.528750 | 1.000000 | 0.992257 | 1.000000 | 0.993572 | 0.01500 | 0.04625 | 52.875000 | 52.875000 | |
3 | 4 | 0.040065 | 0.990777 | 1.528750 | 1.528750 | 1.000000 | 0.991211 | 1.000000 | 0.992994 | 0.01500 | 0.06125 | 52.875000 | 52.875000 | |
4 | 5 | 0.050695 | 0.990105 | 1.528750 | 1.528750 | 1.000000 | 0.990415 | 1.000000 | 0.992453 | 0.01625 | 0.07750 | 52.875000 | 52.875000 | |
5 | 6 | 0.100572 | 0.986664 | 1.528750 | 1.528750 | 1.000000 | 0.988356 | 1.000000 | 0.990421 | 0.07625 | 0.15375 | 52.875000 | 52.875000 | |
6 | 7 | 0.150450 | 0.984156 | 1.528750 | 1.528750 | 1.000000 | 0.985409 | 1.000000 | 0.988760 | 0.07625 | 0.23000 | 52.875000 | 52.875000 | |
7 | 8 | 0.200327 | 0.980479 | 1.528750 | 1.528750 | 1.000000 | 0.982317 | 1.000000 | 0.987155 | 0.07625 | 0.30625 | 52.875000 | 52.875000 | |
8 | 9 | 0.300082 | 0.973543 | 1.528750 | 1.528750 | 1.000000 | 0.977050 | 1.000000 | 0.983796 | 0.15250 | 0.45875 | 52.875000 | 52.875000 | |
9 | 10 | 0.399836 | 0.963129 | 1.528750 | 1.528750 | 1.000000 | 0.968153 | 1.000000 | 0.979893 | 0.15250 | 0.61125 | 52.875000 | 52.875000 | |
10 | 11 | 0.500409 | 0.949958 | 1.528750 | 1.528750 | 1.000000 | 0.957031 | 1.000000 | 0.975298 | 0.15375 | 0.76500 | 52.875000 | 52.875000 | |
11 | 12 | 0.600164 | 0.925196 | 1.528750 | 1.528750 | 1.000000 | 0.939748 | 1.000000 | 0.969389 | 0.15250 | 0.91750 | 52.875000 | 52.875000 | |
12 | 13 | 0.699918 | 0.116726 | 0.827029 | 1.428738 | 0.540984 | 0.556255 | 0.934579 | 0.910508 | 0.08250 | 1.00000 | -17.297131 | 42.873832 | |
13 | 14 | 0.799673 | 0.059845 | 0.000000 | 1.250511 | 0.000000 | 0.083720 | 0.817996 | 0.807371 | 0.00000 | 1.00000 | -100.000000 | 25.051125 | |
14 | 15 | 0.899428 | 0.037587 | 0.000000 | 1.111818 | 0.000000 | 0.048611 | 0.727273 | 0.723218 | 0.00000 | 1.00000 | -100.000000 | 11.181818 | |
15 | 16 | 1.000000 | 0.014052 | 0.000000 | 1.000000 | 0.000000 | 0.027621 | 0.654129 | 0.653260 | 0.00000 | 1.00000 | -100.000000 | 0.000000 |
LogLoss: 0.7253855637689238 Mean Per-Class Error: 0.4032199513558645 AUC: 0.6006189421715613 AUCPR: 0.757982161501983 Gini: 0.20123788434312262 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.06184113025665283: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 70.81 % ModelMetricsBinomial: xgboost ** Reported on cross-validation data. ** MSE: 0.126513604609309 RMSE: 0.35568750977411195 LogLoss: 0.4026131330710863 Mean Per-Class Error: 0.18774083924349871 AUC: 0.8880614657210402 AUCPR: 0.9298853306000129 Gini: 0.7761229314420803 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.6205197870731354: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 69.56 % Cross-Validation Metrics Summary: See the whole table with table.as_data_frame() Scoring History: See the whole table with table.as_data_frame() Variable Importances: See the whole table with table.as_data_frame()
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 163.0 | 1.0 | (163.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 0.0 | 501.0 | 0.3253 | (163.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.061841 | 0.805721 | 399.0 |
1 | max f2 | 0.061841 | 0.912035 | 399.0 |
2 | max f0point5 | 0.349946 | 0.730842 | 343.0 |
3 | max accuracy | 0.061841 | 0.674651 | 399.0 |
4 | max precision | 0.995495 | 1.000000 | 0.0 |
5 | max recall | 0.061841 | 1.000000 | 399.0 |
6 | max specificity | 0.995495 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.866196 | 0.190725 | 118.0 |
8 | max min_per_class_accuracy | 0.759645 | 0.568047 | 186.0 |
9 | max mean_per_class_accuracy | 0.866196 | 0.596780 | 118.0 |
10 | max tns | 0.995495 | 163.000000 | 0.0 |
11 | max fns | 0.995495 | 337.000000 | 0.0 |
12 | max fps | 0.096281 | 163.000000 | 396.0 |
13 | max tps | 0.061841 | 338.000000 | 399.0 |
14 | max tnr | 0.995495 | 1.000000 | 0.0 |
15 | max fnr | 0.995495 | 0.997041 | 0.0 |
16 | max fpr | 0.096281 | 1.000000 | 396.0 |
17 | max tpr | 0.061841 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.011976 | 0.988995 | 1.482249 | 1.482249 | 1.00 | 0.991787 | 1.000000 | 0.991787 | 0.017751 | 0.017751 | 48.224852 | 48.224852 | |
1 | 2 | 0.021956 | 0.985476 | 0.889349 | 1.212749 | 0.60 | 0.987282 | 0.818182 | 0.989739 | 0.008876 | 0.026627 | -11.065089 | 21.274879 | |
2 | 3 | 0.031936 | 0.980057 | 1.482249 | 1.296967 | 1.00 | 0.982329 | 0.875000 | 0.987424 | 0.014793 | 0.041420 | 48.224852 | 29.696746 | |
3 | 4 | 0.041916 | 0.977705 | 0.889349 | 1.199915 | 0.60 | 0.978471 | 0.809524 | 0.985292 | 0.008876 | 0.050296 | -11.065089 | 19.991547 | |
4 | 5 | 0.051896 | 0.974306 | 1.482249 | 1.254210 | 1.00 | 0.975998 | 0.846154 | 0.983505 | 0.014793 | 0.065089 | 48.224852 | 25.421029 | |
5 | 6 | 0.101796 | 0.956100 | 1.126509 | 1.191612 | 0.76 | 0.964057 | 0.803922 | 0.973972 | 0.056213 | 0.121302 | 12.650888 | 19.161156 | |
6 | 7 | 0.151697 | 0.941595 | 1.245089 | 1.209203 | 0.84 | 0.948843 | 0.815789 | 0.965706 | 0.062130 | 0.183432 | 24.508876 | 20.920274 | |
7 | 8 | 0.201597 | 0.919802 | 1.185799 | 1.203410 | 0.80 | 0.930159 | 0.811881 | 0.956907 | 0.059172 | 0.242604 | 18.579882 | 20.340969 | |
8 | 9 | 0.301397 | 0.882816 | 1.096864 | 1.168130 | 0.74 | 0.901427 | 0.788079 | 0.938536 | 0.109467 | 0.352071 | 9.686391 | 16.812963 | |
9 | 10 | 0.401198 | 0.838573 | 1.007929 | 1.128279 | 0.68 | 0.861915 | 0.761194 | 0.919476 | 0.100592 | 0.452663 | 0.792899 | 12.827872 | |
10 | 11 | 0.500998 | 0.771878 | 1.037574 | 1.110210 | 0.70 | 0.806606 | 0.749004 | 0.896992 | 0.103550 | 0.556213 | 3.757396 | 11.021005 | |
11 | 12 | 0.600798 | 0.709230 | 0.800414 | 1.058749 | 0.54 | 0.740312 | 0.714286 | 0.870966 | 0.079882 | 0.636095 | -19.958580 | 5.874894 | |
12 | 13 | 0.700599 | 0.617023 | 0.770769 | 1.017726 | 0.52 | 0.660737 | 0.686610 | 0.841018 | 0.076923 | 0.713018 | -22.923077 | 1.772619 | |
13 | 14 | 0.800399 | 0.509008 | 1.185799 | 1.038683 | 0.80 | 0.560820 | 0.700748 | 0.806081 | 0.118343 | 0.831361 | 18.579882 | 3.868288 | |
14 | 15 | 0.900200 | 0.307938 | 0.889349 | 1.022127 | 0.60 | 0.430207 | 0.689579 | 0.764410 | 0.088757 | 0.920118 | -11.065089 | 2.212703 | |
15 | 16 | 1.000000 | 0.061841 | 0.800414 | 1.000000 | 0.54 | 0.200451 | 0.674651 | 0.708126 | 0.079882 | 1.000000 | -19.958580 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 307.0 | 116.0 | 0.2742 | (116.0/423.0) |
1 | 1 | 81.0 | 719.0 | 0.1013 | (81.0/800.0) |
2 | Total | 388.0 | 835.0 | 0.1611 | (197.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.620520 | 0.879511 | 205.0 |
1 | max f2 | 0.241455 | 0.922605 | 318.0 |
2 | max f0point5 | 0.780233 | 0.872881 | 141.0 |
3 | max accuracy | 0.620520 | 0.838921 | 205.0 |
4 | max precision | 0.995584 | 1.000000 | 0.0 |
5 | max recall | 0.022781 | 1.000000 | 398.0 |
6 | max specificity | 0.995584 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.620520 | 0.638265 | 205.0 |
8 | max min_per_class_accuracy | 0.743228 | 0.806147 | 157.0 |
9 | max mean_per_class_accuracy | 0.620520 | 0.812259 | 205.0 |
10 | max tns | 0.995584 | 423.000000 | 0.0 |
11 | max fns | 0.995584 | 798.000000 | 0.0 |
12 | max fps | 0.021227 | 423.000000 | 399.0 |
13 | max tps | 0.022781 | 800.000000 | 398.0 |
14 | max tnr | 0.995584 | 1.000000 | 0.0 |
15 | max fnr | 0.995584 | 0.997500 | 0.0 |
16 | max fpr | 0.021227 | 1.000000 | 399.0 |
17 | max tpr | 0.022781 | 1.000000 | 398.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.992334 | 1.528750 | 1.528750 | 1.000000 | 0.993334 | 1.000000 | 0.993334 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 0.990809 | 1.401354 | 1.467600 | 0.916667 | 0.991453 | 0.960000 | 0.992431 | 0.01375 | 0.03000 | 40.135417 | 46.760000 | |
2 | 3 | 0.030253 | 0.989421 | 1.528750 | 1.487432 | 1.000000 | 0.990086 | 0.972973 | 0.991671 | 0.01500 | 0.04500 | 52.875000 | 48.743243 | |
3 | 4 | 0.040065 | 0.987439 | 1.528750 | 1.497551 | 1.000000 | 0.988567 | 0.979592 | 0.990911 | 0.01500 | 0.06000 | 52.875000 | 49.755102 | |
4 | 5 | 0.050695 | 0.986476 | 1.528750 | 1.504093 | 1.000000 | 0.986994 | 0.983871 | 0.990089 | 0.01625 | 0.07625 | 52.875000 | 50.409274 | |
5 | 6 | 0.100572 | 0.978343 | 1.503689 | 1.503892 | 0.983607 | 0.982372 | 0.983740 | 0.986262 | 0.07500 | 0.15125 | 50.368852 | 50.389228 | |
6 | 7 | 0.150450 | 0.970047 | 1.478627 | 1.495516 | 0.967213 | 0.974051 | 0.978261 | 0.982214 | 0.07375 | 0.22500 | 47.862705 | 49.551630 | |
7 | 8 | 0.200327 | 0.960739 | 1.503689 | 1.497551 | 0.983607 | 0.965573 | 0.979592 | 0.978071 | 0.07500 | 0.30000 | 50.368852 | 49.755102 | |
8 | 9 | 0.300082 | 0.937027 | 1.428504 | 1.474598 | 0.934426 | 0.948186 | 0.964578 | 0.968136 | 0.14250 | 0.44250 | 42.850410 | 47.459809 | |
9 | 10 | 0.399836 | 0.897359 | 1.328258 | 1.438088 | 0.868852 | 0.919391 | 0.940695 | 0.955975 | 0.13250 | 0.57500 | 32.825820 | 43.808793 | |
10 | 11 | 0.500409 | 0.835142 | 1.242886 | 1.398856 | 0.813008 | 0.866688 | 0.915033 | 0.938030 | 0.12500 | 0.70000 | 24.288618 | 39.885621 | |
11 | 12 | 0.600164 | 0.737403 | 1.127766 | 1.353798 | 0.737705 | 0.789530 | 0.885559 | 0.913347 | 0.11250 | 0.81250 | 12.776639 | 35.379768 | |
12 | 13 | 0.699918 | 0.585166 | 0.964867 | 1.298366 | 0.631148 | 0.668575 | 0.849299 | 0.878462 | 0.09625 | 0.90875 | -3.513320 | 29.836595 | |
13 | 14 | 0.799673 | 0.347572 | 0.513760 | 1.200491 | 0.336066 | 0.477624 | 0.785276 | 0.828459 | 0.05125 | 0.96000 | -48.623975 | 20.049080 | |
14 | 15 | 0.899428 | 0.151209 | 0.288207 | 1.099310 | 0.188525 | 0.244151 | 0.719091 | 0.763654 | 0.02875 | 0.98875 | -71.179303 | 9.931023 | |
15 | 16 | 1.000000 | 0.021227 | 0.111860 | 1.000000 | 0.073171 | 0.087266 | 0.654129 | 0.695628 | 0.01125 | 1.00000 | -88.814024 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.8439114 | 0.009800501 | 0.8514056 | 0.8293651 | 0.8493724 | 0.8381743 | 0.8512397 |
1 | auc | 0.8873135 | 0.010410762 | 0.891342 | 0.897207 | 0.8889151 | 0.86964285 | 0.8894603 |
2 | aucpr | 0.93073946 | 0.012864572 | 0.94105965 | 0.9394219 | 0.9393698 | 0.91347164 | 0.9203742 |
3 | err | 0.15608859 | 0.009800501 | 0.14859438 | 0.17063493 | 0.15062761 | 0.16182573 | 0.14876033 |
4 | err_count | 38.2 | 2.9495761 | 37.0 | 43.0 | 36.0 | 39.0 | 36.0 |
5 | f0point5 | 0.86003184 | 0.0130484775 | 0.87456846 | 0.85005903 | 0.85858583 | 0.8449946 | 0.8719512 |
6 | f1 | 0.88680804 | 0.0096642515 | 0.8914956 | 0.87009066 | 0.8947368 | 0.88951844 | 0.88819873 |
7 | f2 | 0.9156609 | 0.020263776 | 0.90909094 | 0.8910891 | 0.93406594 | 0.93899524 | 0.9050633 |
8 | lift_top_group | 1.5290636 | 0.03780725 | 1.5090909 | 1.5849056 | 1.5031446 | 1.4968944 | 1.551282 |
9 | logloss | 0.40265596 | 0.009278146 | 0.39286137 | 0.40253487 | 0.3960655 | 0.4050471 | 0.41677105 |
10 | max_per_class_error | 0.33334628 | 0.07112779 | 0.2857143 | 0.30107528 | 0.375 | 0.4375 | 0.26744187 |
11 | mcc | 0.6479294 | 0.019078607 | 0.66005164 | 0.62674123 | 0.6542707 | 0.6290906 | 0.6694926 |
12 | mean_per_class_accuracy | 0.8014227 | 0.021955615 | 0.8177489 | 0.8022925 | 0.7936321 | 0.7688276 | 0.8246124 |
13 | mean_per_class_error | 0.19857728 | 0.021955615 | 0.18225108 | 0.19770744 | 0.20636792 | 0.23117235 | 0.17538759 |
14 | mse | 0.1264941 | 0.0029697428 | 0.12417467 | 0.12958266 | 0.123956524 | 0.124892786 | 0.12986383 |
15 | pr_auc | 0.93073946 | 0.012864572 | 0.94105965 | 0.9394219 | 0.9393698 | 0.91347164 | 0.9203742 |
16 | precision | 0.8432131 | 0.019281898 | 0.8636364 | 0.8372093 | 0.8360656 | 0.8177083 | 0.8614458 |
17 | r2 | 0.44025895 | 0.005029392 | 0.44451994 | 0.44349653 | 0.4433553 | 0.43680918 | 0.4331138 |
18 | recall | 0.93619174 | 0.030560225 | 0.92121214 | 0.9056604 | 0.9622642 | 0.9751553 | 0.9166667 |
19 | rmse | 0.35564056 | 0.0041671083 | 0.35238427 | 0.3599759 | 0.3520746 | 0.35340172 | 0.36036623 |
timestamp | duration | number_of_trees | training_rmse | training_logloss | training_auc | training_pr_auc | training_lift | training_classification_error | validation_rmse | validation_logloss | validation_auc | validation_pr_auc | validation_lift | validation_classification_error | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 2020-11-16 05:28:54 | 15.570 sec | 0.0 | 0.500000 | 0.693147 | 0.500000 | 0.654129 | 1.000000 | 0.345871 | 0.500000 | 0.693147 | 0.500000 | 0.674651 | 1.000000 | 0.325349 | |
1 | 2020-11-16 05:28:54 | 15.738 sec | 1.0 | 0.475108 | 0.644499 | 0.893283 | 0.934619 | 1.520209 | 0.147997 | 0.494108 | 0.681405 | 0.569636 | 0.739420 | 1.283141 | 0.325349 | |
2 | 2020-11-16 05:28:55 | 15.787 sec | 2.0 | 0.453779 | 0.604356 | 0.934603 | 0.961879 | 1.528750 | 0.117743 | 0.491526 | 0.676212 | 0.524122 | 0.718283 | 1.338805 | 0.321357 | |
3 | 2020-11-16 05:28:55 | 15.845 sec | 3.0 | 0.430273 | 0.561689 | 0.965932 | 0.981046 | 1.528750 | 0.083401 | 0.491490 | 0.676070 | 0.516436 | 0.702038 | 1.296967 | 0.321357 | |
4 | 2020-11-16 05:28:55 | 15.949 sec | 4.0 | 0.405544 | 0.518412 | 0.981142 | 0.990292 | 1.528750 | 0.062142 | 0.493391 | 0.679803 | 0.488529 | 0.676933 | 1.164624 | 0.319361 | |
5 | 2020-11-16 05:28:55 | 15.995 sec | 5.0 | 0.387562 | 0.487536 | 0.982431 | 0.990796 | 1.528750 | 0.060507 | 0.491797 | 0.676621 | 0.493085 | 0.678748 | 1.212749 | 0.321357 | |
6 | 2020-11-16 05:28:55 | 16.060 sec | 6.0 | 0.370697 | 0.459064 | 0.984969 | 0.991893 | 1.528750 | 0.052330 | 0.491912 | 0.676842 | 0.487467 | 0.676611 | 1.212749 | 0.315369 | |
7 | 2020-11-16 05:28:55 | 16.115 sec | 7.0 | 0.355001 | 0.433188 | 0.987351 | 0.993140 | 1.528750 | 0.044154 | 0.490928 | 0.674643 | 0.498167 | 0.688697 | 1.212749 | 0.317365 | |
8 | 2020-11-16 05:28:55 | 16.173 sec | 8.0 | 0.341396 | 0.410832 | 0.988654 | 0.993790 | 1.528750 | 0.044154 | 0.491934 | 0.677117 | 0.496288 | 0.681667 | 1.235207 | 0.323353 | |
9 | 2020-11-16 05:28:55 | 16.228 sec | 9.0 | 0.328628 | 0.390355 | 0.991099 | 0.995128 | 1.528750 | 0.039248 | 0.493176 | 0.679863 | 0.497640 | 0.681109 | 1.058749 | 0.323353 | |
10 | 2020-11-16 05:28:55 | 16.283 sec | 10.0 | 0.317421 | 0.372369 | 0.992686 | 0.996057 | 1.528750 | 0.036795 | 0.488912 | 0.671263 | 0.515864 | 0.695958 | 0.988166 | 0.325349 | |
11 | 2020-11-16 05:28:55 | 16.330 sec | 11.0 | 0.309168 | 0.358571 | 0.993168 | 0.996369 | 1.528750 | 0.036795 | 0.488986 | 0.671631 | 0.519621 | 0.698344 | 0.988166 | 0.323353 | |
12 | 2020-11-16 05:28:55 | 16.387 sec | 12.0 | 0.298017 | 0.341027 | 0.994218 | 0.996979 | 1.528750 | 0.032706 | 0.487721 | 0.669002 | 0.532327 | 0.707309 | 0.988166 | 0.323353 | |
13 | 2020-11-16 05:28:55 | 16.444 sec | 13.0 | 0.287860 | 0.325120 | 0.995066 | 0.997361 | 1.528750 | 0.028618 | 0.489893 | 0.673915 | 0.530058 | 0.705822 | 0.988166 | 0.321357 | |
14 | 2020-11-16 05:28:55 | 16.504 sec | 14.0 | 0.278006 | 0.310059 | 0.996288 | 0.998014 | 1.528750 | 0.024530 | 0.489704 | 0.673841 | 0.531410 | 0.705833 | 0.988166 | 0.323353 | |
15 | 2020-11-16 05:28:55 | 16.567 sec | 15.0 | 0.268490 | 0.295897 | 0.997320 | 0.998585 | 1.528750 | 0.024530 | 0.488970 | 0.672491 | 0.537409 | 0.709221 | 0.988166 | 0.323353 | |
16 | 2020-11-16 05:28:55 | 16.625 sec | 16.0 | 0.262262 | 0.286050 | 0.997364 | 0.998603 | 1.528750 | 0.022077 | 0.487714 | 0.670187 | 0.544170 | 0.712653 | 0.988166 | 0.323353 | |
17 | 2020-11-16 05:28:55 | 16.695 sec | 17.0 | 0.250550 | 0.269401 | 0.998329 | 0.999120 | 1.528750 | 0.017989 | 0.488228 | 0.671728 | 0.543471 | 0.711558 | 0.988166 | 0.321357 | |
18 | 2020-11-16 05:28:55 | 16.755 sec | 18.0 | 0.243133 | 0.258780 | 0.998843 | 0.999392 | 1.528750 | 0.015536 | 0.485485 | 0.665859 | 0.551666 | 0.717244 | 1.235207 | 0.323353 | |
19 | 2020-11-16 05:28:56 | 16.820 sec | 19.0 | 0.237383 | 0.249938 | 0.999085 | 0.999517 | 1.528750 | 0.014718 | 0.485455 | 0.666119 | 0.552674 | 0.718537 | 0.988166 | 0.321357 |
variable | relative_importance | scaled_importance | percentage | |
---|---|---|---|---|
0 | PC14 | 688.135315 | 1.000000 | 0.091193 |
1 | PC4 | 246.798950 | 0.358649 | 0.032706 |
2 | PC20 | 236.119598 | 0.343130 | 0.031291 |
3 | PC7 | 228.511597 | 0.332074 | 0.030283 |
4 | PC2 | 203.115204 | 0.295168 | 0.026917 |
5 | PC27 | 202.068222 | 0.293646 | 0.026778 |
6 | PC13 | 189.076080 | 0.274766 | 0.025057 |
7 | PC3 | 168.413849 | 0.244739 | 0.022319 |
8 | PC11 | 167.146347 | 0.242897 | 0.022151 |
9 | PC24 | 159.061966 | 0.231149 | 0.021079 |
10 | PC19 | 120.138481 | 0.174586 | 0.015921 |
11 | PC97 | 108.921036 | 0.158284 | 0.014434 |
12 | PC10 | 106.459511 | 0.154707 | 0.014108 |
13 | PC15 | 104.881935 | 0.152415 | 0.013899 |
14 | PC1 | 101.662224 | 0.147736 | 0.013472 |
15 | PC182 | 85.187820 | 0.123795 | 0.011289 |
16 | PC205 | 83.684479 | 0.121610 | 0.011090 |
17 | PC111 | 83.373093 | 0.121158 | 0.011049 |
18 | PC5 | 82.712181 | 0.120198 | 0.010961 |
19 | PC45 | 71.626793 | 0.104088 | 0.009492 |
<bound method ModelBase.model_performance of >
from h2o.estimators import H2ORandomForestEstimator
top_drf = H2ORandomForestEstimator(**extract_params_from_model(best_drf_model.actual_params,
extra_params=['weights_column'],
additional_keys= {'nfolds':5,
'fold_assignment':'random'}))
top_drf.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_drf, MODELS_LOCATION + "PCA300/top_drf")
print('AUC on test_pca_df_frame data: ', top_drf.model_performance(valid=True).auc(), "\n\n============================")
top_drf.model_performance
drf Model Build progress: |███████████████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5821051294151813 ============================ Model Details ============= H2ORandomForestEstimator : Distributed Random Forest Model Key: DRF_model_python_1605504255659_889 Model Summary:
number_of_trees | number_of_internal_trees | model_size_in_bytes | min_depth | max_depth | mean_depth | min_leaves | max_leaves | mean_leaves | ||
---|---|---|---|---|---|---|---|---|---|---|
0 | 100.0 | 100.0 | 115558.0 | 10.0 | 10.0 | 10.0 | 63.0 | 113.0 | 87.42 |
ModelMetricsBinomial: drf ** Reported on train data. ** MSE: 0.09378924212244653 RMSE: 0.3062502932609968 LogLoss: 0.3338295215374348 Mean Per-Class Error: 0.056559405940594054 AUC: 0.977375464108911 AUCPR: 0.980135446032191 Gini: 0.9547509282178219 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.5673465723395894: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 49.75 %, avg score: 56.38 %
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 757.0 | 51.0 | 0.0631 | (51.0/808.0) |
1 | 1 | 40.0 | 760.0 | 0.05 | (40.0/800.0) |
2 | Total | 797.0 | 811.0 | 0.0566 | (91.0/1608.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.567347 | 0.943513 | 185.0 |
1 | max f2 | 0.554408 | 0.947826 | 190.0 |
2 | max f0point5 | 0.648927 | 0.955490 | 161.0 |
3 | max accuracy | 0.567347 | 0.943408 | 185.0 |
4 | max precision | 0.995143 | 1.000000 | 0.0 |
5 | max recall | 0.119408 | 1.000000 | 376.0 |
6 | max specificity | 0.995143 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.567347 | 0.886904 | 185.0 |
8 | max min_per_class_accuracy | 0.582987 | 0.941250 | 180.0 |
9 | max mean_per_class_accuracy | 0.567347 | 0.943441 | 185.0 |
10 | max tns | 0.995143 | 808.000000 | 0.0 |
11 | max fns | 0.995143 | 798.000000 | 0.0 |
12 | max fps | 0.018249 | 808.000000 | 399.0 |
13 | max tps | 0.119408 | 800.000000 | 376.0 |
14 | max tnr | 0.995143 | 1.000000 | 0.0 |
15 | max fnr | 0.995143 | 0.997500 | 0.0 |
16 | max fpr | 0.018249 | 1.000000 | 399.0 |
17 | max tpr | 0.119408 | 1.000000 | 376.0 |
ModelMetricsBinomial: drf ** Reported on validation data. ** MSE: 0.21987748973068402 RMSE: 0.468910961410249 LogLoss: 0.6322992883445343 Mean Per-Class Error: 0.4282135985769775 AUC: 0.5821051294151813 AUCPR: 0.7520371662557974 Gini: 0.16421025883036267 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.28797825975519664: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 69.08 % ModelMetricsBinomial: drf ** Reported on cross-validation data. ** MSE: 0.1480384722901824 RMSE: 0.3847576799625739 LogLoss: 0.45660318420183876 Mean Per-Class Error: 0.18654550827423177 AUC: 0.8844089834515367 AUCPR: 0.9292240110585137 Gini: 0.7688179669030735 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.623777872790557: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 71.56 % Cross-Validation Metrics Summary: See the whole table with table.as_data_frame() Scoring History:
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010572 | 0.979453 | 2.010000 | 2.010000 | 1.000000 | 0.986354 | 1.000000 | 0.986354 | 0.02125 | 0.02125 | 101.000000 | 101.000000 | |
1 | 2 | 0.020522 | 0.968347 | 2.010000 | 2.010000 | 1.000000 | 0.973256 | 1.000000 | 0.980003 | 0.02000 | 0.04125 | 101.000000 | 101.000000 | |
2 | 3 | 0.030473 | 0.961837 | 2.010000 | 2.010000 | 1.000000 | 0.965600 | 1.000000 | 0.975300 | 0.02000 | 0.06125 | 101.000000 | 101.000000 | |
3 | 4 | 0.040423 | 0.953626 | 2.010000 | 2.010000 | 1.000000 | 0.957496 | 1.000000 | 0.970918 | 0.02000 | 0.08125 | 101.000000 | 101.000000 | |
4 | 5 | 0.050373 | 0.947936 | 2.010000 | 2.010000 | 1.000000 | 0.951225 | 1.000000 | 0.967028 | 0.02000 | 0.10125 | 101.000000 | 101.000000 | |
5 | 6 | 0.100124 | 0.913712 | 2.010000 | 2.010000 | 1.000000 | 0.931750 | 1.000000 | 0.949499 | 0.10000 | 0.20125 | 101.000000 | 101.000000 | |
6 | 7 | 0.150498 | 0.877486 | 1.985185 | 2.001694 | 0.987654 | 0.894401 | 0.995868 | 0.931057 | 0.10000 | 0.30125 | 98.518519 | 100.169421 | |
7 | 8 | 0.200249 | 0.850112 | 1.984875 | 1.997516 | 0.987500 | 0.863214 | 0.993789 | 0.914201 | 0.09875 | 0.40000 | 98.487500 | 99.751553 | |
8 | 9 | 0.300373 | 0.796541 | 1.997516 | 1.997516 | 0.993789 | 0.823710 | 0.993789 | 0.884037 | 0.20000 | 0.60000 | 99.751553 | 99.751553 | |
9 | 10 | 0.399876 | 0.730431 | 1.922063 | 1.978740 | 0.956250 | 0.764863 | 0.984448 | 0.854383 | 0.19125 | 0.79125 | 92.206250 | 97.874028 | |
10 | 11 | 0.500000 | 0.576023 | 1.523106 | 1.887500 | 0.757764 | 0.660187 | 0.939055 | 0.815496 | 0.15250 | 0.94375 | 52.310559 | 88.750000 | |
11 | 12 | 0.600124 | 0.445800 | 0.299627 | 1.622580 | 0.149068 | 0.505380 | 0.807254 | 0.763756 | 0.03000 | 0.97375 | -70.037267 | 62.258031 | |
12 | 13 | 0.699627 | 0.340139 | 0.150750 | 1.413253 | 0.075000 | 0.394661 | 0.703111 | 0.711263 | 0.01500 | 0.98875 | -84.925000 | 41.325333 | |
13 | 14 | 0.799751 | 0.262819 | 0.012484 | 1.237885 | 0.006211 | 0.299262 | 0.615863 | 0.659682 | 0.00125 | 0.99000 | -98.751553 | 23.788491 | |
14 | 15 | 0.899876 | 0.188404 | 0.062422 | 1.107097 | 0.031056 | 0.225883 | 0.550795 | 0.611416 | 0.00625 | 0.99625 | -93.757764 | 10.709744 | |
15 | 16 | 1.000000 | 0.018249 | 0.037453 | 1.000000 | 0.018634 | 0.135817 | 0.497512 | 0.563797 | 0.00375 | 1.00000 | -96.254658 | 0.000000 |
See the whole table with table.as_data_frame() Variable Importances: See the whole table with table.as_data_frame()
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 163.0 | 1.0 | (163.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 0.0 | 501.0 | 0.3253 | (163.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.287978 | 0.805721 | 399.0 |
1 | max f2 | 0.287978 | 0.912035 | 399.0 |
2 | max f0point5 | 0.501896 | 0.735430 | 358.0 |
3 | max accuracy | 0.490848 | 0.686627 | 364.0 |
4 | max precision | 0.976633 | 1.000000 | 0.0 |
5 | max recall | 0.287978 | 1.000000 | 399.0 |
6 | max specificity | 0.976633 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.834430 | 0.169249 | 68.0 |
8 | max min_per_class_accuracy | 0.689065 | 0.550296 | 202.0 |
9 | max mean_per_class_accuracy | 0.808645 | 0.571786 | 86.0 |
10 | max tns | 0.976633 | 163.000000 | 0.0 |
11 | max fns | 0.976633 | 337.000000 | 0.0 |
12 | max fps | 0.317697 | 163.000000 | 397.0 |
13 | max tps | 0.287978 | 338.000000 | 399.0 |
14 | max tnr | 0.976633 | 1.000000 | 0.0 |
15 | max fnr | 0.976633 | 0.997041 | 0.0 |
16 | max fpr | 0.317697 | 1.000000 | 397.0 |
17 | max tpr | 0.287978 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.011976 | 0.945625 | 1.235207 | 1.235207 | 0.833333 | 0.958670 | 0.833333 | 0.958670 | 0.014793 | 0.014793 | 23.520710 | 23.520710 | |
1 | 2 | 0.021956 | 0.932828 | 1.185799 | 1.212749 | 0.800000 | 0.936473 | 0.818182 | 0.948581 | 0.011834 | 0.026627 | 18.579882 | 21.274879 | |
2 | 3 | 0.031936 | 0.919073 | 1.482249 | 1.296967 | 1.000000 | 0.925097 | 0.875000 | 0.941242 | 0.014793 | 0.041420 | 48.224852 | 29.696746 | |
3 | 4 | 0.041916 | 0.900995 | 1.482249 | 1.341082 | 1.000000 | 0.912775 | 0.904762 | 0.934464 | 0.014793 | 0.056213 | 48.224852 | 34.108199 | |
4 | 5 | 0.051896 | 0.888879 | 1.482249 | 1.368229 | 1.000000 | 0.894768 | 0.923077 | 0.926830 | 0.014793 | 0.071006 | 48.224852 | 36.822940 | |
5 | 6 | 0.101796 | 0.856645 | 1.185799 | 1.278803 | 0.800000 | 0.867869 | 0.862745 | 0.897927 | 0.059172 | 0.130178 | 18.579882 | 27.880265 | |
6 | 7 | 0.151697 | 0.838139 | 1.185799 | 1.248209 | 0.800000 | 0.846720 | 0.842105 | 0.881083 | 0.059172 | 0.189349 | 18.579882 | 24.820928 | |
7 | 8 | 0.201597 | 0.817721 | 1.067219 | 1.203410 | 0.720000 | 0.829072 | 0.811881 | 0.868209 | 0.053254 | 0.242604 | 6.721893 | 20.340969 | |
8 | 9 | 0.301397 | 0.773934 | 0.948639 | 1.119049 | 0.640000 | 0.796048 | 0.754967 | 0.844314 | 0.094675 | 0.337278 | -5.136095 | 11.904855 | |
9 | 10 | 0.401198 | 0.726800 | 0.859704 | 1.054535 | 0.580000 | 0.751998 | 0.711443 | 0.821350 | 0.085799 | 0.423077 | -14.029586 | 5.453502 | |
10 | 11 | 0.500998 | 0.694774 | 1.037574 | 1.051156 | 0.700000 | 0.710728 | 0.709163 | 0.799314 | 0.103550 | 0.526627 | 3.757396 | 5.115632 | |
11 | 12 | 0.600798 | 0.658020 | 1.007929 | 1.043976 | 0.680000 | 0.675168 | 0.704319 | 0.778692 | 0.100592 | 0.627219 | 0.792899 | 4.397570 | |
12 | 13 | 0.700599 | 0.618438 | 1.067219 | 1.047287 | 0.720000 | 0.639085 | 0.706553 | 0.758805 | 0.106509 | 0.733728 | 6.721893 | 4.728670 | |
13 | 14 | 0.800399 | 0.577367 | 0.948639 | 1.034986 | 0.640000 | 0.599407 | 0.698254 | 0.738930 | 0.094675 | 0.828402 | -5.136095 | 3.498650 | |
14 | 15 | 0.900200 | 0.511389 | 1.007929 | 1.031987 | 0.680000 | 0.545050 | 0.696231 | 0.717435 | 0.100592 | 0.928994 | 0.792899 | 3.198677 | |
15 | 16 | 1.000000 | 0.287978 | 0.711479 | 1.000000 | 0.480000 | 0.450133 | 0.674651 | 0.690758 | 0.071006 | 1.000000 | -28.852071 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 272.0 | 151.0 | 0.357 | (151.0/423.0) |
1 | 1 | 54.0 | 746.0 | 0.0675 | (54.0/800.0) |
2 | Total | 326.0 | 897.0 | 0.1676 | (205.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.623778 | 0.879199 | 235.0 |
1 | max f2 | 0.525139 | 0.925000 | 280.0 |
2 | max f0point5 | 0.698162 | 0.870536 | 201.0 |
3 | max accuracy | 0.682321 | 0.834832 | 210.0 |
4 | max precision | 0.985729 | 1.000000 | 0.0 |
5 | max recall | 0.139715 | 1.000000 | 399.0 |
6 | max specificity | 0.985729 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.698162 | 0.629782 | 201.0 |
8 | max min_per_class_accuracy | 0.730109 | 0.803783 | 180.0 |
9 | max mean_per_class_accuracy | 0.698162 | 0.813454 | 201.0 |
10 | max tns | 0.985729 | 423.000000 | 0.0 |
11 | max fns | 0.985729 | 799.000000 | 0.0 |
12 | max fps | 0.139715 | 423.000000 | 399.0 |
13 | max tps | 0.139715 | 800.000000 | 399.0 |
14 | max tnr | 0.985729 | 1.000000 | 0.0 |
15 | max fnr | 0.985729 | 0.998750 | 0.0 |
16 | max fpr | 0.139715 | 1.000000 | 399.0 |
17 | max tpr | 0.139715 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 0.973447 | 1.528750 | 1.528750 | 1.000000 | 0.976624 | 1.000000 | 0.976624 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 0.966153 | 1.401354 | 1.467600 | 0.916667 | 0.968725 | 0.960000 | 0.972832 | 0.01375 | 0.03000 | 40.135417 | 46.760000 | |
2 | 3 | 0.030253 | 0.956775 | 1.528750 | 1.487432 | 1.000000 | 0.961230 | 0.972973 | 0.969069 | 0.01500 | 0.04500 | 52.875000 | 48.743243 | |
3 | 4 | 0.040065 | 0.951030 | 1.528750 | 1.497551 | 1.000000 | 0.953947 | 0.979592 | 0.965366 | 0.01500 | 0.06000 | 52.875000 | 49.755102 | |
4 | 5 | 0.050695 | 0.945337 | 1.528750 | 1.504093 | 1.000000 | 0.948086 | 0.983871 | 0.961743 | 0.01625 | 0.07625 | 52.875000 | 50.409274 | |
5 | 6 | 0.100572 | 0.922875 | 1.528750 | 1.516321 | 1.000000 | 0.933242 | 0.991870 | 0.947608 | 0.07625 | 0.15250 | 52.875000 | 51.632114 | |
6 | 7 | 0.150450 | 0.903162 | 1.478627 | 1.503825 | 0.967213 | 0.912983 | 0.983696 | 0.936129 | 0.07375 | 0.22625 | 47.862705 | 50.382473 | |
7 | 8 | 0.200327 | 0.878481 | 1.403443 | 1.478832 | 0.918033 | 0.890297 | 0.967347 | 0.924718 | 0.07000 | 0.29625 | 40.344262 | 47.883163 | |
8 | 9 | 0.300082 | 0.841677 | 1.428504 | 1.462101 | 0.934426 | 0.860057 | 0.956403 | 0.903223 | 0.14250 | 0.43875 | 42.850410 | 46.210150 | |
9 | 10 | 0.399836 | 0.806635 | 1.378381 | 1.441214 | 0.901639 | 0.824239 | 0.942740 | 0.883517 | 0.13750 | 0.57625 | 37.838115 | 44.121421 | |
10 | 11 | 0.500409 | 0.766653 | 1.143455 | 1.381371 | 0.747967 | 0.786644 | 0.903595 | 0.864048 | 0.11500 | 0.69125 | 14.345528 | 38.137051 | |
11 | 12 | 0.600164 | 0.727136 | 1.190420 | 1.349632 | 0.778689 | 0.747643 | 0.882834 | 0.844700 | 0.11875 | 0.81000 | 19.042008 | 34.963215 | |
12 | 13 | 0.699918 | 0.663034 | 0.977398 | 1.296580 | 0.639344 | 0.701658 | 0.848131 | 0.824313 | 0.09750 | 0.90750 | -2.260246 | 29.658002 | |
13 | 14 | 0.799673 | 0.546061 | 0.538822 | 1.202054 | 0.352459 | 0.608000 | 0.786299 | 0.797329 | 0.05375 | 0.96125 | -46.117828 | 20.205394 | |
14 | 15 | 0.899428 | 0.403196 | 0.250615 | 1.096531 | 0.163934 | 0.475731 | 0.717273 | 0.761661 | 0.02500 | 0.98625 | -74.938525 | 9.653068 | |
15 | 16 | 1.000000 | 0.139141 | 0.136717 | 1.000000 | 0.089431 | 0.303825 | 0.654129 | 0.715615 | 0.01375 | 1.00000 | -86.328252 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.85056084 | 0.012191841 | 0.8514056 | 0.8293651 | 0.8577406 | 0.8589212 | 0.8553719 |
1 | auc | 0.8847304 | 0.005531013 | 0.88795096 | 0.8817204 | 0.89064467 | 0.8767081 | 0.8866279 |
2 | aucpr | 0.9298648 | 0.011238017 | 0.9416512 | 0.92589223 | 0.9382394 | 0.91313046 | 0.93041086 |
3 | err | 0.14943913 | 0.012191841 | 0.14859438 | 0.17063493 | 0.14225942 | 0.14107884 | 0.1446281 |
4 | err_count | 36.6 | 3.7815342 | 37.0 | 43.0 | 34.0 | 34.0 | 35.0 |
5 | f0point5 | 0.873479 | 0.012376249 | 0.8841099 | 0.86845464 | 0.86206895 | 0.86358637 | 0.88917524 |
6 | f1 | 0.8886605 | 0.015630547 | 0.8888889 | 0.8634921 | 0.9011628 | 0.90229887 | 0.8874598 |
7 | f2 | 0.9053345 | 0.037887756 | 0.8937198 | 0.85858583 | 0.94397074 | 0.944645 | 0.88575095 |
8 | lift_top_group | 1.5290636 | 0.03780725 | 1.5090909 | 1.5849056 | 1.5031446 | 1.4968944 | 1.551282 |
9 | logloss | 0.45639262 | 0.014040419 | 0.4562537 | 0.4768668 | 0.44247666 | 0.44437772 | 0.46198812 |
10 | max_per_class_error | 0.2801647 | 0.08775162 | 0.23809524 | 0.21505377 | 0.375 | 0.375 | 0.19767442 |
11 | mcc | 0.66820604 | 0.019285075 | 0.66494715 | 0.636239 | 0.676859 | 0.67780364 | 0.68518126 |
12 | mean_per_class_accuracy | 0.81861055 | 0.01890995 | 0.82943726 | 0.8201461 | 0.7999214 | 0.8000776 | 0.84347045 |
13 | mean_per_class_error | 0.18138944 | 0.01890995 | 0.17056277 | 0.17985393 | 0.20007862 | 0.19992235 | 0.15652952 |
14 | mse | 0.14792621 | 0.007462843 | 0.14901493 | 0.15820105 | 0.14169522 | 0.13970213 | 0.15101774 |
15 | pr_auc | 0.9298648 | 0.011238017 | 0.9416512 | 0.92589223 | 0.9382394 | 0.91313046 | 0.93041086 |
16 | precision | 0.864096 | 0.024094356 | 0.88095236 | 0.8717949 | 0.8378378 | 0.8395722 | 0.89032257 |
17 | r2 | 0.3456979 | 0.020746762 | 0.33340004 | 0.3205924 | 0.3636971 | 0.370028 | 0.340772 |
18 | recall | 0.9173858 | 0.054722667 | 0.8969697 | 0.8553459 | 0.9748428 | 0.9751553 | 0.88461536 |
19 | rmse | 0.38451424 | 0.009683092 | 0.38602453 | 0.39774495 | 0.37642425 | 0.37376747 | 0.38861 |
timestamp | duration | number_of_trees | training_rmse | training_logloss | training_auc | training_pr_auc | training_lift | training_classification_error | validation_rmse | validation_logloss | validation_auc | validation_pr_auc | validation_lift | validation_classification_error | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 2020-11-16 05:29:25 | 25.636 sec | 0.0 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | |
1 | 2020-11-16 05:29:25 | 25.798 sec | 1.0 | 0.484766 | 6.422745 | 0.732803 | 0.724162 | 1.584808 | 0.241379 | 0.676686 | 11.573860 | 0.503685 | 0.678196 | 1.012267 | 0.325349 | |
2 | 2020-11-16 05:29:26 | 25.849 sec | 2.0 | 0.436246 | 4.268980 | 0.783656 | 0.777626 | 1.687577 | 0.207305 | 0.574286 | 3.098114 | 0.524195 | 0.697968 | 1.101099 | 0.325349 | |
3 | 2020-11-16 05:29:26 | 25.905 sec | 3.0 | 0.435541 | 4.044009 | 0.785518 | 0.764063 | 1.619364 | 0.214739 | 0.533667 | 1.845286 | 0.533525 | 0.698375 | 1.004104 | 0.325349 | |
4 | 2020-11-16 05:29:26 | 25.951 sec | 4.0 | 0.417959 | 3.142821 | 0.811935 | 0.796946 | 1.692268 | 0.208034 | 0.512782 | 1.195344 | 0.532317 | 0.692950 | 0.846999 | 0.323353 | |
5 | 2020-11-16 05:29:26 | 25.997 sec | 5.0 | 0.407482 | 2.776868 | 0.825337 | 0.807112 | 1.695458 | 0.205285 | 0.501664 | 0.912134 | 0.551476 | 0.707181 | 0.988166 | 0.325349 | |
6 | 2020-11-16 05:29:26 | 26.045 sec | 6.0 | 0.392713 | 1.956826 | 0.852800 | 0.835116 | 1.758750 | 0.205497 | 0.486623 | 0.766033 | 0.573320 | 0.728366 | 1.376374 | 0.319361 | |
7 | 2020-11-16 05:29:26 | 26.095 sec | 7.0 | 0.377544 | 1.405504 | 0.873801 | 0.864890 | 1.842500 | 0.189622 | 0.479296 | 0.735066 | 0.585826 | 0.737493 | 1.347499 | 0.323353 | |
8 | 2020-11-16 05:29:26 | 26.142 sec | 8.0 | 0.364893 | 1.089499 | 0.889264 | 0.883474 | 1.879350 | 0.171628 | 0.477982 | 0.733914 | 0.588068 | 0.732852 | 1.347499 | 0.309381 | |
9 | 2020-11-16 05:29:26 | 26.189 sec | 9.0 | 0.368507 | 1.016379 | 0.887268 | 0.883542 | 1.871813 | 0.177136 | 0.477006 | 0.659835 | 0.578965 | 0.739755 | 1.482249 | 0.313373 | |
10 | 2020-11-16 05:29:26 | 26.245 sec | 10.0 | 0.365489 | 0.908864 | 0.893159 | 0.894497 | 1.892628 | 0.167500 | 0.470488 | 0.643114 | 0.591997 | 0.748925 | 1.482249 | 0.307385 | |
11 | 2020-11-16 05:29:26 | 26.299 sec | 11.0 | 0.357199 | 0.813296 | 0.903258 | 0.901770 | 1.899213 | 0.170200 | 0.466840 | 0.630077 | 0.601182 | 0.752480 | 1.482249 | 0.313373 | |
12 | 2020-11-16 05:29:26 | 26.355 sec | 12.0 | 0.352161 | 0.684402 | 0.910875 | 0.911987 | 1.921842 | 0.145262 | 0.466412 | 0.628228 | 0.604222 | 0.758303 | 1.482249 | 0.307385 | |
13 | 2020-11-16 05:29:26 | 26.409 sec | 13.0 | 0.349300 | 0.621431 | 0.915466 | 0.913482 | 1.900761 | 0.143746 | 0.472169 | 0.640399 | 0.581951 | 0.746363 | 1.482249 | 0.311377 | |
14 | 2020-11-16 05:29:26 | 26.461 sec | 14.0 | 0.347158 | 0.541071 | 0.920144 | 0.916861 | 1.890000 | 0.147388 | 0.473240 | 0.643043 | 0.575380 | 0.742316 | 1.482249 | 0.313373 | |
15 | 2020-11-16 05:29:26 | 26.511 sec | 15.0 | 0.345296 | 0.500078 | 0.924577 | 0.921434 | 1.902321 | 0.134328 | 0.470595 | 0.637670 | 0.582459 | 0.745816 | 1.482249 | 0.309381 | |
16 | 2020-11-16 05:29:26 | 26.562 sec | 16.0 | 0.342888 | 0.476831 | 0.927257 | 0.927957 | 1.929600 | 0.126866 | 0.471933 | 0.640382 | 0.573511 | 0.742373 | 1.482249 | 0.309381 | |
17 | 2020-11-16 05:29:26 | 26.614 sec | 17.0 | 0.341277 | 0.414201 | 0.931873 | 0.937108 | 2.010000 | 0.129975 | 0.473804 | 0.644666 | 0.561341 | 0.735158 | 1.482249 | 0.313373 | |
18 | 2020-11-16 05:29:26 | 26.671 sec | 18.0 | 0.337992 | 0.409313 | 0.935721 | 0.939918 | 2.010000 | 0.125000 | 0.473775 | 0.644610 | 0.557828 | 0.733086 | 1.235207 | 0.321357 | |
19 | 2020-11-16 05:29:26 | 26.734 sec | 19.0 | 0.337185 | 0.408306 | 0.936905 | 0.941563 | 2.010000 | 0.124378 | 0.474806 | 0.647191 | 0.556068 | 0.731769 | 1.235207 | 0.319361 |
variable | relative_importance | scaled_importance | percentage | |
---|---|---|---|---|
0 | PC14 | 1724.483154 | 1.000000 | 0.076722 |
1 | PC2 | 952.419678 | 0.552293 | 0.042373 |
2 | PC11 | 858.823853 | 0.498018 | 0.038209 |
3 | PC3 | 700.542847 | 0.406234 | 0.031167 |
4 | PC4 | 621.191162 | 0.360219 | 0.027637 |
5 | PC5 | 580.841248 | 0.336820 | 0.025842 |
6 | PC20 | 493.652649 | 0.286261 | 0.021963 |
7 | PC13 | 466.062317 | 0.270262 | 0.020735 |
8 | PC1 | 417.042847 | 0.241836 | 0.018554 |
9 | PC7 | 364.417877 | 0.211320 | 0.016213 |
10 | PC10 | 350.441589 | 0.203215 | 0.015591 |
11 | PC27 | 270.892731 | 0.157086 | 0.012052 |
12 | PC19 | 245.425873 | 0.142319 | 0.010919 |
13 | PC22 | 219.490494 | 0.127279 | 0.009765 |
14 | PC6 | 206.910248 | 0.119984 | 0.009205 |
15 | PC24 | 198.131271 | 0.114893 | 0.008815 |
16 | PC37 | 159.309555 | 0.092381 | 0.007088 |
17 | PC111 | 155.600647 | 0.090230 | 0.006923 |
18 | PC9 | 154.789062 | 0.089760 | 0.006887 |
19 | PC8 | 153.105988 | 0.088784 | 0.006812 |
<bound method ModelBase.model_performance of >
from h2o.estimators import H2ODeepLearningEstimator
top_dl = H2ODeepLearningEstimator(**extract_params_from_model(best_dl_model.actual_params))
top_dl.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
# h2o.save_model(top_dl, MODELS_LOCATION + "PCA300/top_dl")
print('AUC on test_pca_df_frame data: ', top_dl.model_performance(valid=True).auc(), "\n\n============================")
top_dl.model_performance
deeplearning Model Build progress: |██████████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6136421388898973 ============================ Model Details ============= H2ODeepLearningEstimator : Deep Learning Model Key: DeepLearning_model_python_1605504255659_1778 Status of Neuron Layers: predicting Resistance_Status, 2-class classification, bernoulli distribution, CrossEntropy loss, 652,502 weights/biases, 7.6 MB, 25,087 training samples, mini-batch size 1 ModelMetricsBinomial: deeplearning ** Reported on train data. ** MSE: 0.020155790752860954 RMSE: 0.1419710912575548 LogLoss: 0.06882824483799292 Mean Per-Class Error: 0.02592346335697404 AUC: 0.9969148936170212 AUCPR: 0.998326749051774 Gini: 0.9938297872340425 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.21897911559292374: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 64.49 % ModelMetricsBinomial: deeplearning ** Reported on validation data. ** MSE: 0.37933064592517834 RMSE: 0.6158982431580547 LogLoss: 2.1628654205523583 Mean Per-Class Error: 0.41544451301412133 AUC: 0.6136421388898973 AUCPR: 0.7680173323631072 Gini: 0.22728427777979454 Confusion Matrix (Act/Pred) for max f1 @ threshold = 1.8105741125690687e-06: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 67.47 %, avg score: 49.69 % ModelMetricsBinomial: deeplearning ** Reported on cross-validation data. ** MSE: 0.18024669868105994 RMSE: 0.42455470634661435 LogLoss: 1.037612270655366 Mean Per-Class Error: 0.2159884751773049 AUC: 0.8590898345153664 AUCPR: 0.9121296853687093 Gini: 0.7181796690307327 Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.05130588535206401: Maximum Metrics: Maximum metrics at their respective thresholds Gains/Lift Table: Avg response rate: 65.41 %, avg score: 65.89 % Cross-Validation Metrics Summary: See the whole table with table.as_data_frame() Scoring History: Variable Importances: See the whole table with table.as_data_frame()
layer | units | type | dropout | l1 | l2 | mean_rate | rate_rms | momentum | mean_weight | weight_rms | mean_bias | bias_rms | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 300 | Input | 20 | ||||||||||
1 | 2 | 500 | Tanh | 0 | 1e-05 | 0 | 0.0216942 | 0.0182189 | 0 | -8.84944e-05 | 0.0509939 | 0.00420635 | 0.047057 | |
2 | 3 | 500 | Tanh | 0 | 1e-05 | 0 | 0.0307862 | 0.0212547 | 0 | -5.02267e-05 | 0.0432497 | -0.00430718 | 0.0965656 | |
3 | 4 | 500 | Tanh | 0 | 1e-05 | 0 | 0.302142 | 0.409598 | 0 | -5.0987e-05 | 0.0346254 | 0.00325625 | 0.0452591 | |
4 | 5 | 2 | Softmax | 1e-05 | 0 | 0.0674489 | 0.144285 | 0 | -0.00470909 | 0.221872 | -0.000674079 | 0.0187405 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 402.0 | 21.0 | 0.0496 | (21.0/423.0) |
1 | 1 | 7.0 | 793.0 | 0.0088 | (7.0/800.0) |
2 | Total | 409.0 | 814.0 | 0.0229 | (28.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.218979 | 0.982652 | 250.0 |
1 | max f2 | 0.168367 | 0.988054 | 254.0 |
2 | max f0point5 | 0.782785 | 0.983161 | 202.0 |
3 | max accuracy | 0.347010 | 0.977105 | 240.0 |
4 | max precision | 1.000000 | 1.000000 | 0.0 |
5 | max recall | 0.024409 | 1.000000 | 294.0 |
6 | max specificity | 1.000000 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.347010 | 0.949315 | 240.0 |
8 | max min_per_class_accuracy | 0.602942 | 0.971250 | 225.0 |
9 | max mean_per_class_accuracy | 0.381008 | 0.974077 | 235.0 |
10 | max tns | 1.000000 | 423.000000 | 0.0 |
11 | max fns | 1.000000 | 666.000000 | 0.0 |
12 | max fps | 0.000001 | 423.000000 | 399.0 |
13 | max tps | 0.024409 | 800.000000 | 294.0 |
14 | max tnr | 1.000000 | 1.000000 | 0.0 |
15 | max fnr | 1.000000 | 0.832500 | 0.0 |
16 | max fpr | 0.000001 | 1.000000 | 399.0 |
17 | max tpr | 0.024409 | 1.000000 | 294.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 1.000000e+00 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 1.000000e+00 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01500 | 0.03125 | 52.875000 | 52.875000 | |
2 | 3 | 0.030253 | 9.999999e-01 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01500 | 0.04625 | 52.875000 | 52.875000 | |
3 | 4 | 0.040065 | 9.999999e-01 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01500 | 0.06125 | 52.875000 | 52.875000 | |
4 | 5 | 0.050695 | 9.999998e-01 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01625 | 0.07750 | 52.875000 | 52.875000 | |
5 | 6 | 0.100572 | 9.999988e-01 | 1.528750 | 1.528750 | 1.000000 | 0.999999 | 1.000000 | 1.000000 | 0.07625 | 0.15375 | 52.875000 | 52.875000 | |
6 | 7 | 0.150450 | 9.999966e-01 | 1.528750 | 1.528750 | 1.000000 | 0.999998 | 1.000000 | 0.999999 | 0.07625 | 0.23000 | 52.875000 | 52.875000 | |
7 | 8 | 0.200327 | 9.999913e-01 | 1.528750 | 1.528750 | 1.000000 | 0.999995 | 1.000000 | 0.999998 | 0.07625 | 0.30625 | 52.875000 | 52.875000 | |
8 | 9 | 0.300082 | 9.999429e-01 | 1.528750 | 1.528750 | 1.000000 | 0.999973 | 1.000000 | 0.999990 | 0.15250 | 0.45875 | 52.875000 | 52.875000 | |
9 | 10 | 0.399836 | 9.995840e-01 | 1.528750 | 1.528750 | 1.000000 | 0.999817 | 1.000000 | 0.999947 | 0.15250 | 0.61125 | 52.875000 | 52.875000 | |
10 | 11 | 0.500409 | 9.974741e-01 | 1.528750 | 1.528750 | 1.000000 | 0.998780 | 1.000000 | 0.999712 | 0.15375 | 0.76500 | 52.875000 | 52.875000 | |
11 | 12 | 0.600164 | 9.282836e-01 | 1.478627 | 1.520419 | 0.967213 | 0.978166 | 0.994550 | 0.996131 | 0.14750 | 0.91250 | 47.862705 | 52.041894 | |
12 | 13 | 0.699918 | 2.879595e-02 | 0.864621 | 1.426952 | 0.565574 | 0.465629 | 0.933411 | 0.920522 | 0.08625 | 0.99875 | -13.537910 | 42.695239 | |
13 | 14 | 0.799673 | 2.889778e-04 | 0.012531 | 1.250511 | 0.008197 | 0.006025 | 0.817996 | 0.806444 | 0.00125 | 1.00000 | -98.746926 | 25.051125 | |
14 | 15 | 0.899428 | 1.054270e-05 | 0.000000 | 1.111818 | 0.000000 | 0.000097 | 0.727273 | 0.717012 | 0.00000 | 1.00000 | -100.000000 | 11.181818 | |
15 | 16 | 1.000000 | 2.046165e-09 | 0.000000 | 1.000000 | 0.000000 | 0.000003 | 0.654129 | 0.644901 | 0.00000 | 1.00000 | -100.000000 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 0.0 | 163.0 | 1.0 | (163.0/163.0) |
1 | 1 | 0.0 | 338.0 | 0.0 | (0.0/338.0) |
2 | Total | 0.0 | 501.0 | 0.3253 | (163.0/501.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.000002 | 0.805721 | 399.0 |
1 | max f2 | 0.000002 | 0.912035 | 399.0 |
2 | max f0point5 | 0.002498 | 0.743175 | 353.0 |
3 | max accuracy | 0.002498 | 0.680639 | 353.0 |
4 | max precision | 0.999999 | 1.000000 | 0.0 |
5 | max recall | 0.000002 | 1.000000 | 399.0 |
6 | max specificity | 0.999999 | 1.000000 | 0.0 |
7 | max absolute_mcc | 0.002498 | 0.192200 | 353.0 |
8 | max min_per_class_accuracy | 0.428011 | 0.571006 | 205.0 |
9 | max mean_per_class_accuracy | 0.980645 | 0.584555 | 81.0 |
10 | max tns | 0.999999 | 163.000000 | 0.0 |
11 | max fns | 0.999999 | 329.000000 | 0.0 |
12 | max fps | 0.000002 | 163.000000 | 399.0 |
13 | max tps | 0.000002 | 338.000000 | 399.0 |
14 | max tnr | 0.999999 | 1.000000 | 0.0 |
15 | max fnr | 0.999999 | 0.973373 | 0.0 |
16 | max fpr | 0.000002 | 1.000000 | 399.0 |
17 | max tpr | 0.000002 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.011976 | 9.999993e-01 | 1.482249 | 1.482249 | 1.00 | 1.000000 | 1.000000 | 1.000000 | 0.017751 | 0.017751 | 48.224852 | 48.224852 | |
1 | 2 | 0.021956 | 9.999947e-01 | 1.482249 | 1.482249 | 1.00 | 0.999997 | 1.000000 | 0.999999 | 0.014793 | 0.032544 | 48.224852 | 48.224852 | |
2 | 3 | 0.031936 | 9.999908e-01 | 0.592899 | 1.204327 | 0.40 | 0.999992 | 0.812500 | 0.999997 | 0.005917 | 0.038462 | -40.710059 | 20.432692 | |
3 | 4 | 0.041916 | 9.999859e-01 | 1.482249 | 1.270499 | 1.00 | 0.999987 | 0.857143 | 0.999994 | 0.014793 | 0.053254 | 48.224852 | 27.049873 | |
4 | 5 | 0.051896 | 9.999759e-01 | 1.482249 | 1.311220 | 1.00 | 0.999981 | 0.884615 | 0.999992 | 0.014793 | 0.068047 | 48.224852 | 31.121985 | |
5 | 6 | 0.101796 | 9.998206e-01 | 1.304379 | 1.307866 | 0.88 | 0.999929 | 0.882353 | 0.999961 | 0.065089 | 0.133136 | 30.437870 | 30.786634 | |
6 | 7 | 0.151697 | 9.992971e-01 | 0.948639 | 1.189699 | 0.64 | 0.999625 | 0.802632 | 0.999850 | 0.047337 | 0.180473 | -5.136095 | 18.969947 | |
7 | 8 | 0.201597 | 9.973996e-01 | 1.304379 | 1.218085 | 0.88 | 0.998505 | 0.821782 | 0.999517 | 0.065089 | 0.245562 | 30.437870 | 21.808542 | |
8 | 9 | 0.301397 | 9.714250e-01 | 1.067219 | 1.168130 | 0.72 | 0.986028 | 0.788079 | 0.995051 | 0.106509 | 0.352071 | 6.721893 | 16.812963 | |
9 | 10 | 0.401198 | 8.175460e-01 | 1.007929 | 1.128279 | 0.68 | 0.917855 | 0.761194 | 0.975848 | 0.100592 | 0.452663 | 0.792899 | 12.827872 | |
10 | 11 | 0.500998 | 5.173307e-01 | 0.978284 | 1.098399 | 0.66 | 0.658899 | 0.741036 | 0.912710 | 0.097633 | 0.550296 | -2.171598 | 9.839930 | |
11 | 12 | 0.600798 | 1.592683e-01 | 0.948639 | 1.073522 | 0.64 | 0.301410 | 0.724252 | 0.811166 | 0.094675 | 0.644970 | -5.136095 | 7.352218 | |
12 | 13 | 0.700599 | 3.228655e-02 | 0.978284 | 1.059955 | 0.66 | 0.081231 | 0.715100 | 0.707186 | 0.097633 | 0.742604 | -2.171598 | 5.995549 | |
13 | 14 | 0.800399 | 4.302530e-03 | 1.037574 | 1.057165 | 0.70 | 0.013558 | 0.713217 | 0.620699 | 0.103550 | 0.846154 | 3.757396 | 5.716478 | |
14 | 15 | 0.900200 | 2.744685e-04 | 0.741124 | 1.022127 | 0.50 | 0.001322 | 0.689579 | 0.552032 | 0.073964 | 0.920118 | -25.887574 | 2.212703 | |
15 | 16 | 1.000000 | 1.874009e-08 | 0.800414 | 1.000000 | 0.54 | 0.000040 | 0.674651 | 0.496943 | 0.079882 | 1.000000 | -19.958580 | 0.000000 |
0 | 1 | Error | Rate | ||
---|---|---|---|---|---|
0 | 0 | 240.0 | 183.0 | 0.4326 | (183.0/423.0) |
1 | 1 | 71.0 | 729.0 | 0.0887 | (71.0/800.0) |
2 | Total | 311.0 | 912.0 | 0.2077 | (254.0/1223.0) |
metric | threshold | value | idx | |
---|---|---|---|---|
0 | max f1 | 0.051306 | 0.851636 | 320.0 |
1 | max f2 | 0.000417 | 0.912392 | 394.0 |
2 | max f0point5 | 0.983591 | 0.856370 | 65.0 |
3 | max accuracy | 0.162647 | 0.798038 | 278.0 |
4 | max precision | 0.999997 | 0.962199 | 0.0 |
5 | max recall | 0.000010 | 1.000000 | 399.0 |
6 | max specificity | 0.999997 | 0.973995 | 0.0 |
7 | max absolute_mcc | 0.800537 | 0.556570 | 175.0 |
8 | max min_per_class_accuracy | 0.901671 | 0.781250 | 134.0 |
9 | max mean_per_class_accuracy | 0.800537 | 0.784012 | 175.0 |
10 | max tns | 0.999997 | 412.000000 | 0.0 |
11 | max fns | 0.999997 | 520.000000 | 0.0 |
12 | max fps | 0.000010 | 423.000000 | 399.0 |
13 | max tps | 0.000010 | 800.000000 | 399.0 |
14 | max tnr | 0.999997 | 0.973995 | 0.0 |
15 | max fnr | 0.999997 | 0.650000 | 0.0 |
16 | max fpr | 0.000010 | 1.000000 | 399.0 |
17 | max tpr | 0.000010 | 1.000000 | 399.0 |
group | cumulative_data_fraction | lower_threshold | lift | cumulative_lift | response_rate | score | cumulative_response_rate | cumulative_score | capture_rate | cumulative_capture_rate | gain | cumulative_gain | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0.010630 | 1.000000e+00 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01625 | 0.01625 | 52.875000 | 52.875000 | |
1 | 2 | 0.020442 | 1.000000e+00 | 1.528750 | 1.528750 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 0.01500 | 0.03125 | 52.875000 | 52.875000 | |
2 | 3 | 0.030253 | 1.000000e+00 | 1.401354 | 1.487432 | 0.916667 | 1.000000 | 0.972973 | 1.000000 | 0.01375 | 0.04500 | 40.135417 | 48.743243 | |
3 | 4 | 0.040065 | 9.999999e-01 | 1.528750 | 1.497551 | 1.000000 | 1.000000 | 0.979592 | 1.000000 | 0.01500 | 0.06000 | 52.875000 | 49.755102 | |
4 | 5 | 0.050695 | 9.999999e-01 | 1.528750 | 1.504093 | 1.000000 | 1.000000 | 0.983871 | 1.000000 | 0.01625 | 0.07625 | 52.875000 | 50.409274 | |
5 | 6 | 0.100572 | 9.999994e-01 | 1.478627 | 1.491463 | 0.967213 | 1.000000 | 0.975610 | 1.000000 | 0.07375 | 0.15000 | 47.862705 | 49.146341 | |
6 | 7 | 0.150450 | 9.999973e-01 | 1.528750 | 1.503825 | 1.000000 | 0.999999 | 0.983696 | 0.999999 | 0.07625 | 0.22625 | 52.875000 | 50.382473 | |
7 | 8 | 0.200327 | 9.999921e-01 | 1.428504 | 1.485071 | 0.934426 | 0.999995 | 0.971429 | 0.999998 | 0.07125 | 0.29750 | 42.850410 | 48.507143 | |
8 | 9 | 0.300082 | 9.999145e-01 | 1.378381 | 1.449605 | 0.901639 | 0.999964 | 0.948229 | 0.999987 | 0.13750 | 0.43500 | 37.838115 | 44.960490 | |
9 | 10 | 0.399836 | 9.992415e-01 | 1.403443 | 1.438088 | 0.918033 | 0.999683 | 0.940695 | 0.999911 | 0.14000 | 0.57500 | 40.344262 | 43.808793 | |
10 | 11 | 0.500409 | 9.898016e-01 | 1.155884 | 1.381371 | 0.756098 | 0.996464 | 0.903595 | 0.999218 | 0.11625 | 0.69125 | 15.588415 | 38.137051 | |
11 | 12 | 0.600164 | 8.758568e-01 | 1.040051 | 1.324639 | 0.680328 | 0.951790 | 0.866485 | 0.991335 | 0.10375 | 0.79500 | 4.005123 | 32.463896 | |
12 | 13 | 0.699918 | 2.138102e-01 | 0.839559 | 1.255504 | 0.549180 | 0.578096 | 0.821262 | 0.932439 | 0.08375 | 0.87875 | -16.044057 | 25.550380 | |
13 | 14 | 0.799673 | 7.470877e-03 | 0.601475 | 1.173917 | 0.393443 | 0.061741 | 0.767894 | 0.823824 | 0.06000 | 0.93875 | -39.852459 | 17.391743 | |
14 | 15 | 0.899428 | 1.191290e-04 | 0.388453 | 1.086802 | 0.254098 | 0.001580 | 0.710909 | 0.732630 | 0.03875 | 0.97750 | -61.154713 | 8.680227 | |
15 | 16 | 1.000000 | 8.492341e-09 | 0.223720 | 1.000000 | 0.146341 | 0.000023 | 0.654129 | 0.658950 | 0.02250 | 1.00000 | -77.628049 | 0.000000 |
mean | sd | cv_1_valid | cv_2_valid | cv_3_valid | cv_4_valid | cv_5_valid | ||
---|---|---|---|---|---|---|---|---|
0 | accuracy | 0.8090388 | 0.053631157 | 0.7269076 | 0.8214286 | 0.79079497 | 0.8672199 | 0.838843 |
1 | auc | 0.86538297 | 0.041840862 | 0.797583 | 0.90254956 | 0.8538129 | 0.8864907 | 0.88647884 |
2 | aucpr | 0.9198272 | 0.01798225 | 0.8965769 | 0.94207394 | 0.9070567 | 0.9266913 | 0.92673725 |
3 | err | 0.19096118 | 0.053631157 | 0.27309236 | 0.17857143 | 0.20920502 | 0.13278009 | 0.16115703 |
4 | err_count | 46.8 | 13.627179 | 68.0 | 45.0 | 50.0 | 32.0 | 39.0 |
5 | f0point5 | 0.83169746 | 0.04773542 | 0.7609756 | 0.8342728 | 0.8142077 | 0.88269454 | 0.86633664 |
6 | f1 | 0.8655829 | 0.03064958 | 0.8210526 | 0.8680352 | 0.8563218 | 0.9047619 | 0.87774295 |
7 | f2 | 0.9033038 | 0.0153516885 | 0.8914286 | 0.9046455 | 0.9030303 | 0.92796093 | 0.88945365 |
8 | lift_top_group | 1.5290636 | 0.03780725 | 1.5090909 | 1.5849056 | 1.5031446 | 1.4968944 | 1.551282 |
9 | logloss | 1.0353905 | 0.34899655 | 1.6494354 | 0.82408893 | 0.9315049 | 0.81509316 | 0.95682997 |
10 | max_per_class_error | 0.42458284 | 0.18015584 | 0.70238096 | 0.3655914 | 0.5 | 0.2875 | 0.26744187 |
11 | mcc | 0.55743825 | 0.14195217 | 0.33470386 | 0.60894436 | 0.5071254 | 0.69337374 | 0.6430439 |
12 | mean_per_class_accuracy | 0.7532 | 0.08494049 | 0.6215368 | 0.7826131 | 0.7185535 | 0.8282997 | 0.814997 |
13 | mean_per_class_error | 0.24679999 | 0.08494049 | 0.3784632 | 0.21738689 | 0.28144655 | 0.17170031 | 0.18500298 |
14 | mse | 0.17999338 | 0.04357984 | 0.25307897 | 0.15617277 | 0.18107317 | 0.14033964 | 0.16930236 |
15 | pr_auc | 0.9198272 | 0.01798225 | 0.8965769 | 0.94207394 | 0.9070567 | 0.9266913 | 0.92673725 |
16 | precision | 0.81091905 | 0.057926968 | 0.7255814 | 0.8131868 | 0.78835976 | 0.8685714 | 0.8588957 |
17 | r2 | 0.20243177 | 0.19926119 | -0.13211757 | 0.3293031 | 0.18686473 | 0.36715323 | 0.26095533 |
18 | recall | 0.9309829 | 0.019649446 | 0.94545454 | 0.9308176 | 0.9371069 | 0.94409937 | 0.8974359 |
19 | rmse | 0.4219733 | 0.0491416 | 0.5030696 | 0.395187 | 0.42552695 | 0.37461933 | 0.41146368 |
timestamp | duration | training_speed | epochs | iterations | samples | training_rmse | training_logloss | training_r2 | ... | training_pr_auc | training_lift | training_classification_error | validation_rmse | validation_logloss | validation_r2 | validation_auc | validation_pr_auc | validation_lift | validation_classification_error | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 2020-11-16 05:35:12 | 0.000 sec | None | 0.000000 | 0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | |
1 | 2020-11-16 05:35:15 | 5 min 43.116 sec | 358 obs/sec | 0.932952 | 1 | 1141.0 | 0.546002 | 1.458851 | -0.317683 | ... | 0.925707 | 1.528750 | 0.183156 | 0.644808 | 1.814105 | -0.894228 | 0.668376 | 0.780854 | 1.482249 | 0.285429 | |
2 | 2020-11-16 05:35:22 | 5 min 49.959 sec | 359 obs/sec | 2.790679 | 3 | 3413.0 | 0.331168 | 0.463371 | 0.515249 | ... | 0.952972 | 1.411154 | 0.135732 | 0.538314 | 1.421737 | -0.320206 | 0.607516 | 0.734735 | 1.235207 | 0.311377 | |
3 | 2020-11-16 05:35:29 | 5 min 56.706 sec | 361 obs/sec | 4.644317 | 5 | 5680.0 | 0.456968 | 1.229500 | 0.077014 | ... | 0.965297 | 1.528750 | 0.129191 | 0.569215 | 2.296494 | -0.476130 | 0.574654 | 0.733309 | 1.235207 | 0.323353 | |
4 | 2020-11-16 05:35:35 | 6 min 3.212 sec | 367 obs/sec | 6.516762 | 7 | 7970.0 | 0.378438 | 0.633780 | 0.366987 | ... | 0.979618 | 1.528750 | 0.083401 | 0.570356 | 1.817939 | -0.482053 | 0.566132 | 0.734262 | 1.482249 | 0.321357 | |
5 | 2020-11-16 05:35:42 | 6 min 10.134 sec | 365 obs/sec | 8.380213 | 9 | 10249.0 | 0.484391 | 1.068571 | -0.037086 | ... | 0.955239 | 1.528750 | 0.111202 | 0.519076 | 1.305403 | -0.227533 | 0.613225 | 0.740176 | 1.235207 | 0.299401 | |
6 | 2020-11-16 05:35:49 | 6 min 16.874 sec | 365 obs/sec | 10.240392 | 11 | 12524.0 | 0.340978 | 0.441854 | 0.486103 | ... | 0.989278 | 1.528750 | 0.062142 | 0.632557 | 2.041221 | -0.822935 | 0.592388 | 0.750380 | 0.988166 | 0.325349 | |
7 | 2020-11-16 05:35:56 | 6 min 24.651 sec | 357 obs/sec | 12.117743 | 13 | 14820.0 | 0.379015 | 0.601574 | 0.365055 | ... | 0.986602 | 1.528750 | 0.064595 | 0.534864 | 1.882528 | -0.303339 | 0.619305 | 0.738101 | 1.235207 | 0.309381 | |
8 | 2020-11-16 05:36:03 | 6 min 31.436 sec | 359 obs/sec | 13.989370 | 15 | 17109.0 | 0.223263 | 0.199249 | 0.779679 | ... | 0.993577 | 1.528750 | 0.042518 | 0.564276 | 1.780475 | -0.450623 | 0.595419 | 0.742705 | 0.988166 | 0.325349 | |
9 | 2020-11-16 05:36:10 | 6 min 38.373 sec | 358 obs/sec | 15.849550 | 17 | 19384.0 | 0.193699 | 0.153616 | 0.834165 | ... | 0.995050 | 1.528750 | 0.040065 | 0.665435 | 2.512549 | -1.017354 | 0.582368 | 0.744666 | 0.988166 | 0.317365 | |
10 | 2020-11-16 05:36:17 | 6 min 44.990 sec | 360 obs/sec | 17.712183 | 19 | 21662.0 | 0.153558 | 0.086104 | 0.895776 | ... | 0.998085 | 1.528750 | 0.023712 | 0.626591 | 2.016020 | -0.788706 | 0.601100 | 0.753073 | 1.235207 | 0.315369 | |
11 | 2020-11-16 05:36:23 | 6 min 51.587 sec | 362 obs/sec | 19.582993 | 21 | 23950.0 | 0.175417 | 0.104663 | 0.863992 | ... | 0.998438 | 1.528750 | 0.021259 | 0.557972 | 1.648858 | -0.418393 | 0.626493 | 0.791866 | 1.482249 | 0.325349 | |
12 | 2020-11-16 05:36:27 | 6 min 55.209 sec | 362 obs/sec | 20.512674 | 22 | 25087.0 | 0.141971 | 0.068828 | 0.910911 | ... | 0.998327 | 1.528750 | 0.022895 | 0.615898 | 2.162865 | -0.728180 | 0.613642 | 0.768017 | 1.482249 | 0.325349 |
13 rows × 21 columns
variable | relative_importance | scaled_importance | percentage | |
---|---|---|---|---|
0 | PC169 | 1.000000 | 1.000000 | 0.004035 |
1 | PC182 | 0.976314 | 0.976314 | 0.003939 |
2 | PC14 | 0.963786 | 0.963786 | 0.003889 |
3 | PC218 | 0.948938 | 0.948938 | 0.003829 |
4 | PC122 | 0.943232 | 0.943232 | 0.003806 |
5 | PC206 | 0.941399 | 0.941399 | 0.003798 |
6 | PC20 | 0.936940 | 0.936940 | 0.003780 |
7 | PC82 | 0.933824 | 0.933824 | 0.003768 |
8 | PC217 | 0.926745 | 0.926745 | 0.003739 |
9 | PC94 | 0.924351 | 0.924351 | 0.003730 |
10 | PC246 | 0.918917 | 0.918917 | 0.003708 |
11 | PC154 | 0.918534 | 0.918534 | 0.003706 |
12 | PC297 | 0.917722 | 0.917722 | 0.003703 |
13 | PC250 | 0.915394 | 0.915394 | 0.003694 |
14 | PC57 | 0.906814 | 0.906814 | 0.003659 |
15 | PC189 | 0.904806 | 0.904806 | 0.003651 |
16 | PC175 | 0.904475 | 0.904475 | 0.003649 |
17 | PC252 | 0.901748 | 0.901748 | 0.003638 |
18 | PC66 | 0.899770 | 0.899770 | 0.003630 |
19 | PC124 | 0.899018 | 0.899018 | 0.003627 |
<bound method ModelBase.model_performance of >
all_model_hyperparams = {
'naivebayes' : {
'pca': {
'laplace': 0.6,
'min_sdev': 0.1,
'min_prob': 0.1,
'eps_sdev': 0.1,
'eps_prob': 0.3,
},
'non_pca': {
'laplace': 0.3,
'min_sdev': 0.9,
'min_prob': 0.1,
'eps_sdev': 1,
'eps_prob': 0.1,
}
},
'glm' : {
'pca': {
'alpha': [
0.0
],
'theta': 1,
'tweedie_link_power': 0,
'tweedie_variance_power': 3,
},
'non_pca': {
'alpha': [
1.0
],
'theta': 0.3,
'tweedie_link_power': 0,
'tweedie_variance_power': 9,
}
},
'gbm' : {
'pca': {
'learn_rate': 0.9,
'learn_rate_annealing': 1,
'distribution': 'bernoulli',
'quantile_alpha': 0.3,
'tweedie_power': 1.5,
'balance_classes': False,
'ntrees': 150,
'max_depth': 10,
'sample_rate': 0.9,
'col_sample_rate': 0.3,
'col_sample_rate_per_tree': 1,
'col_sample_rate_change_per_level': 1.3,
'histogram_type': 'RoundRobin',
},
'non_pca': {
'learn_rate': 0.1,
'learn_rate_annealing': 0.9,
'distribution': 'bernoulli',
'quantile_alpha': 1,
'tweedie_power': 1.9,
'balance_classes': False,
'ntrees': 50,
'max_depth': 5,
'sample_rate': 0.9,
'col_sample_rate': 0.3,
'col_sample_rate_per_tree': 0.6,
'col_sample_rate_change_per_level': 0.8,
'histogram_type': 'Random',
}
},
'drf' : {
'pca': {
# 'mtries': 150, # doesn't work for some reason
'balance_classes': True,
'ntrees': 100,
'max_depth': 10,
'sample_rate': 0.6,
'col_sample_rate_per_tree': 0.3,
'col_sample_rate_change_per_level': 0.8,
'histogram_type': 'Auto',
},
'non_pca': {
'mtries': -1,
'balance_classes': True,
'ntrees': 50,
'max_depth': 10,
'sample_rate': 0.3,
'col_sample_rate_per_tree': 0.6,
'col_sample_rate_change_per_level': 1.7,
'histogram_type': 'RoundRobin',
}
},
'xgboost' : {
'pca': {
'distribution': 'multinomial',
'categorical_encoding': 'auto',
'ntrees': 70,
'booster': 'gbtree',
'col_sample_rate': 0.6,
'col_sample_rate_bylevel': 0.6,
'col_sample_rate_bytree': 0.6,
'learn_rate': 0.1,
'grow_policy': 'lossguide',
'max_depth': 6,
'normalize_type': 'forest',
'sample_type': 'uniform',
'sample_rate': 1,
'tree_method': 'hist',
'tweedie_power': 1.5,
},
'non_pca': {
'distribution': 'bernoulli',
'categorical_encoding': 'label_encoder',
'ntrees': 50,
'booster': 'dart',
'col_sample_rate': 0.8,
'col_sample_rate_bylevel': 0.8,
'col_sample_rate_bytree': 0.3,
'learn_rate': 0.1,
'grow_policy': 'depthwise',
'max_depth': 6,
'normalize_type': 'forest',
'sample_type': 'weighted',
'sample_rate': 1,
'tree_method': 'hist',
'tweedie_power': 1.5,
}
},
'deeplearning' : {
'pca': {
'distribution': 'bernoulli',
'epochs': 20.399,
'loss': 'CrossEntropy',
'l1': 1e-5,
'l2': 0,
'sparse': False,
'balance_classes': False,
'average_activation': 10,
'activation': 'TanH',
'hidden': [
500,
500,
500
],
'input_dropout_ratio': 0.2,
'rho': 0.95,
'standardize': False,
},
'non_pca': {
'distribution': 'bernoulli',
'epochs': 31.1822,
'loss': 'Automatic',
'l1': 0,
'l2': 0,
'sparse': False,
'balance_classes': False,
'average_activation': 0,
'activation': 'RectifierWithDropout',
'hidden': [
500,
500,
500
],
'input_dropout_ratio': 0,
'rho': 0.9,
'standardize': True,
}
},
}
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
collection_of_models = [
top_nb,
top_glm,
# checkpoint-enabled models
top_gbm,
top_xgb,
top_dl,
top_drf
]
meta_algos = ["xgboost", "drf", "gbm", "glm", "naivebayes", "deeplearning"]
all_models_ensembles_list = []
for metalearner in meta_algos:
print("\n\n>>>>> ", metalearner, " <<<<<<")
if metalearner == 'xgboost' or metalearner == 'naivebayes':
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_ALL_MODELS_metalearner_" + metalearner,
#metalearner_params
metalearner_algorithm= metalearner,
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
else:
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_ALL_MODELS_metalearner_" + metalearner,
metalearner_algorithm= metalearner,
metalearner_params = all_model_hyperparams[metalearner]['pca'],
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
ensemble.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
h2o.save_model(ensemble, MODELS_LOCATION + "PCA300/top_ensemble_ALL_MODELS_METALEARNER_" + metalearner)
print("AUC on test_pca_df_frame data: ", ensemble.model_performance(valid=True).auc())
all_models_ensembles_list.append(ensemble)
>>>>> xgboost <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5999473626892221 >>>>> drf <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5751079972410789 >>>>> gbm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5934584528260791 >>>>> glm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6213834537336189 >>>>> naivebayes <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6091044396849021 >>>>> deeplearning <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6143227937706466
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
collection_of_models = [
# checkpoint-enabled models
top_gbm,
top_xgb,
top_dl,
top_drf
]
meta_algos = ["xgboost",
"drf",
"gbm",
"glm",
"naivebayes",
"deeplearning"]
ensemble_list = []
for metalearner in meta_algos:
print("\n\n>>>>> ", metalearner, " <<<<<<")
if metalearner == 'xgboost' or metalearner == 'naivebayes':
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_CHECKPOINT_MODELS_metalearner_" + metalearner,
metalearner_algorithm= metalearner,
# metalearner_params = all_model_hyperparams[metalearner]['pca'],
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
else:
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_CHECKPOINT_MODELS_metalearner_" + metalearner,
metalearner_algorithm= metalearner,
metalearner_params = all_model_hyperparams[metalearner]['pca'],
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
ensemble.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
h2o.save_model(ensemble, MODELS_LOCATION + "PCA300/top_ensemble_CHECKPOINT_MODELS_METALEARNER_" + metalearner)
print("AUC on test_pca_df_frame data: ", ensemble.model_performance(valid=True).auc())
ensemble_list.append(ensemble)
>>>>> xgboost <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5822231095945112 >>>>> drf <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5761970450502777 >>>>> gbm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5840744908701492 >>>>> glm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6081696736486731 >>>>> naivebayes <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5926507423675899 >>>>> deeplearning <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5992485570116528
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
collection_of_models = [
top_xgb,
top_dl,
top_drf
]
meta_algos = ["xgboost",
"drf",
"gbm",
"glm",
"naivebayes",
"deeplearning"]
no_gbm_meta_ensemble_list = []
for metalearner in meta_algos:
print("\n\n>>>>> ", metalearner, " <<<<<<")
if metalearner == 'xgboost' or metalearner == 'naivebayes':
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_" + metalearner,
metalearner_algorithm= metalearner,
# metalearner_params = all_model_hyperparams[metalearner]['pca'],
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
else:
ensemble = H2OStackedEnsembleEstimator(
base_models= collection_of_models,
model_id= "stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_" + metalearner,
metalearner_algorithm= metalearner,
metalearner_params = all_model_hyperparams[metalearner]['pca'],
metalearner_nfolds = 5,
metalearner_fold_assignment = 'random',
seed=1234
)
ensemble.train(x=x, y=y, training_frame=train_pca_df_frame, validation_frame=test_pca_df_frame)
h2o.save_model(ensemble, MODELS_LOCATION + "PCA300/top_ensemble_CHECKPOINT_nogbm_MODELS_METALEARNER_" + metalearner)
print("AUC on test_pca_df_frame data: ", ensemble.model_performance(valid=True).auc())
no_gbm_meta_ensemble_list.append(ensemble)
>>>>> xgboost <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5808164228409627 >>>>> drf <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.577776164373616 >>>>> gbm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.5681834682542564 >>>>> glm <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6095309834101716 >>>>> naivebayes <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6125530910806984 >>>>> deeplearning <<<<<< stackedensemble Model Build progress: |███████████████████████████████████| 100% AUC on test_pca_df_frame data: 0.6149943732529858
for a_mdl in no_gbm_meta_ensemble_list:
xval_perf = a_mdl.model_performance(xval=True)
valid_perf = a_mdl.model_performance(valid=True)
print('Model ID: ', a_mdl.model_id)
print('Training time (ms): ', a_mdl.run_time)
print('XVal AUC: ', xval_perf.auc())
print('XVal Accuracy: ', xval_perf.accuracy()[0][1])
print('Validation data AUC: ', valid_perf.auc())
print('Validation data Accuracy: ', valid_perf.accuracy()[0][1])
print("-----------------------------")
Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_xgboost Training time (ms): 6247 XVal AUC: 0.8744400118203309 XVal Accuracy: 0.8143908421913328 Validation data AUC: 0.5808164228409627 Validation data Accuracy: 0.6746506986027944 ----------------------------- Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_drf Training time (ms): 6518 XVal AUC: 0.8663593380614658 XVal Accuracy: 0.8160261651676206 Validation data AUC: 0.577776164373616 Validation data Accuracy: 0.6746506986027944 ----------------------------- Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_gbm Training time (ms): 11571 XVal AUC: 0.8412086288416076 XVal Accuracy: 0.7923139820114473 Validation data AUC: 0.5681834682542564 Validation data Accuracy: 0.6786427145708582 ----------------------------- Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_glm Training time (ms): 589 XVal AUC: 0.8967715721040189 XVal Accuracy: 0.8413736713000818 Validation data AUC: 0.6095309834101716 Validation data Accuracy: 0.6746506986027944 ----------------------------- Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_naivebayes Training time (ms): 468 XVal AUC: 0.8972680260047281 XVal Accuracy: 0.83892068683565 Validation data AUC: 0.6125530910806984 Validation data Accuracy: 0.6746506986027944 ----------------------------- Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_deeplearning Training time (ms): 338640 XVal AUC: 0.6323758865248227 XVal Accuracy: 0.7031888798037612 Validation data AUC: 0.6149943732529858 Validation data Accuracy: 0.6746506986027944 -----------------------------
mdl = no_gbm_meta_ensemble_list[5]
print('Model ID: ', mdl.model_id)
mdl.model_performance(xval=True).plot()
mdl.model_performance(valid=True).plot()
Model ID: stacked_ensemble_PCA300_FEATURES_CHECKPOINT_nogbm_MODELS_metalearner_deeplearning
ensemble_list[0].metalearner().actual_params
{'model_id': 'metalearner_naivebayes_stacked_ensemble_PCA300_FEATURES_ALL_MODELS_metalearner_naivebayes', 'nfolds': 5, 'seed': 1234, 'fold_assignment': 'Random', 'fold_column': None, 'keep_cross_validation_models': True, 'keep_cross_validation_predictions': False, 'keep_cross_validation_fold_assignment': False, 'training_frame': None, 'validation_frame': None, 'response_column': 'Resistance_Status', 'ignored_columns': None, 'ignore_const_cols': True, 'score_each_iteration': False, 'balance_classes': False, 'class_sampling_factors': None, 'max_after_balance_size': 5.0, 'max_confusion_matrix_size': 20, 'max_hit_ratio_k': 0, 'laplace': 0.0, 'min_sdev': 0.001, 'eps_sdev': 0.0, 'min_prob': 0.001, 'eps_prob': 0.0, 'compute_metrics': True, 'max_runtime_secs': 0.0, 'export_checkpoints_dir': None}
ensemble_list[0].metalearner().varimp_plot()
Warning: This model doesn't have variable importances
--------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-85-661a7a4c2a3e> in <module> ----> 1 ensemble_list[0].metalearner().varimp_plot() /anaconda/envs/azureml_py36/lib/python3.6/site-packages/h2o/model/model_base.py in varimp_plot(self, num_of_features, server) 1441 importances = self.varimp(use_pandas=False) 1442 # features labels correspond to the first value of each tuple in the importances list -> 1443 feature_labels = [tup[0] for tup in importances] 1444 # relative importances correspond to the first value of each tuple in the importances list 1445 scaled_importances = [tup[2] for tup in importances] TypeError: 'NoneType' object is not iterable