3343208
doi
10.5281/zenodo.3343208
oai:zenodo.org:3343208
James Bourbeau
@Quansight
Reiichiro Nakano
@infostellarinc
Zach Griffith
@WIPACrepo
Kota Mori
Will McGinnis
Predikto Inc.
JJLWHarrison
Guillaume Poirier-Morency
IRIC @major-lab
Daniel
Qiang Gu
Floris Hoogenboom
Colin
Vahid Mirjalili
Michigan State University
selay01
Christos Aridas
Steve Harenberg
Pablo Fernandez
FANSI Motorsport
Oliver Tomic
Norwegian University of Life Sciences
Laurens Geffert
Janpreet Singh
Alejandro Correa Bahnsen
Easy Solutions
Benjamin Lee
@Lab41
Batuhan Bardak
STM
Arfon Smith
@spacetelescope
Anton Loss
Anebi
Ajinkya Kale
Adam Erickson
Adam Cooper
Tribal
Ackerley Tng
Centre for Strategic Infocomm Technologies
rasbt/mlxtend: Version 0.17.0
Sebastian Raschka
UW-Madison
url:https://github.com/rasbt/mlxtend/tree/v0.17.0
info:eu-repo/semantics/openAccess
Other (Open)
New Features
<ul>
<li>Added an enhancement to the existing <code>iris_data()</code> such that both the UCI Repository version of the Iris dataset as well as the corrected, original
version of the dataset can be loaded, which has a slight difference in two data points (consistent with Fisher's paper; this is also the same as in R). (via <a href="https://github.com/rasbt/mlxtend/pull/532">#539</a> via <a href="https://github.com/janismdhanbad">janismdhanbad</a>)</li>
<li>Added optional <code>groups</code> parameter to <code>SequentialFeatureSelector</code> and <code>ExhaustiveFeatureSelector</code> <code>fit()</code> methods for forwarding to sklearn CV (<a href="https://github.com/rasbt/mlxtend/pull/537">#537</a> via <a href="https://github.com/qiaguhttps://github.com/arc12">arc12</a>)</li>
<li>Added a new <code>plot_pca_correlation_graph</code> function to the <code>mlxtend.plotting</code> submodule for plotting a PCA correlation graph. (<a href="https://github.com/rasbt/mlxtend/pull/544">#544</a> via <a href="https://github.com/qiaguhttps://github.com/Gabriel-Azevedo-Ferreira">Gabriel-Azevedo-Ferreira</a>)</li>
<li>Added a <code>zoom_factor</code> parameter to the <code>mlxten.plotting.plot_decision_region</code> function that allows users to zoom in and out of the decision region plots. (<a href="https://github.com/rasbt/mlxtend/pull/545">#545</a>)</li>
<li>Added a function <code>fpgrowth</code> that implements the FP-Growth algorithm for mining frequent itemsets as a drop-in replacement for the existing <code>apriori</code> algorithm. (<a href="https://github.com/rasbt/mlxtend/pull/550">#550</a> via <a href="https://github.com/harenbergsd">Steve Harenberg</a>)</li>
<li>New <code>heatmap</code> function in <code>mlxtend.plotting</code>. (<a href="https://github.com/rasbt/mlxtend/pull/552">#552</a>)</li>
<li>Added a function <code>fpmax</code> that implements the FP-Max algorithm for mining maximal itemsets as a drop-in replacement for the <code>fpgrowth</code> algorithm. (<a href="https://github.com/rasbt/mlxtend/pull/553">#553</a> via <a href="https://github.com/harenbergsd">Steve Harenberg</a>)</li>
<li>New <code>figsize</code> parameter for the <code>plot_decision_regions</code> function in <code>mlxtend.plotting</code>. (<a href="https://github.com/rasbt/mlxtend/pull/555">#555</a> via <a href="https://github.com/kazyka">Mirza Hasanbasic</a>)</li>
<li>New <code>low_memory</code> option for the <code>apriori</code> frequent itemset generating function. Setting <code>low_memory=False</code> (default) uses a substantially optimized version of the algorithm that is 3-6x faster than the original implementation (<code>low_memory=True</code>). (<a href="https://github.com/rasbt/mlxtend/pull/567">#567</a> via <a href="https://github.com/jmayse">jmayse</a>)</li>
</ul>
Changes
<ul>
<li>Now uses the latest joblib library under the hood for multiprocessing instead of <code>sklearn.externals.joblib</code>. (<a href="https://github.com/rasbt/mlxtend/pull/547">#547</a>)</li>
<li>Changes to <code>StackingCVClassifier</code> and <code>StackingCVRegressor</code> such that first-level models are allowed to generate output of non-numeric type. (<a href="https://github.com/rasbt/mlxtend/pull/562">#562</a>)</li>
</ul>
Bug Fixes
<ul>
<li>Fixed documentation of <code>iris_data()</code> under <code>iris.py</code> by adding a note about differences in the iris data in R and UCI machine learning repo.</li>
<li>Make sure that if the <code>'svd'</code> mode is used in PCA, the number of eigenvalues is the same as when using <code>'eigen'</code> (append 0's zeros in that case) (<a href="https://github.com/rasbt/mlxtend/pull/565">#565</a>)</li>
</ul>
Zenodo
2019-07-19
info:eu-repo/semantics/other
594432
v0.17.0
1630626857.631658
15939191
md5:c52871bd06c2fe4e422ff2195a1f44e4
https://zenodo.org/records/3343208/files/rasbt/mlxtend-v0.17.0.zip
public
https://github.com/rasbt/mlxtend/tree/v0.17.0
Is supplement to
url
10.5281/zenodo.594432
isVersionOf
doi