{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e4c8a783-200a-4762-8b66-cf13cf8b3aa9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "\n",
    "prop_cycle = plt.rcParams['axes.prop_cycle']\n",
    "colors = prop_cycle.by_key()['color']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "06ba2568-f53e-44c9-9cba-4b99bad53ded",
   "metadata": {},
   "source": [
    "#### Read field_296_100rows.csv (downsampled from field_296.csv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e8a073fd-3f33-4671-97d5-48f670b97433",
   "metadata": {},
   "outputs": [],
   "source": [
    "field_296_100rows = pd.read_csv(f'field_296_100rows.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e137ddf7-bff4-4afb-a00e-4ec2e1581cc4",
   "metadata": {},
   "source": [
    "#### Display dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1386d78d-745c-4483-8a53-5dddffee1842",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>_id</th>\n",
       "      <th>Gaia_EDR3___id</th>\n",
       "      <th>AllWISE___id</th>\n",
       "      <th>PS1_DR1___id</th>\n",
       "      <th>ra</th>\n",
       "      <th>dec</th>\n",
       "      <th>period</th>\n",
       "      <th>field</th>\n",
       "      <th>ccd</th>\n",
       "      <th>quad</th>\n",
       "      <th>...</th>\n",
       "      <th>hp_xgb</th>\n",
       "      <th>i_xgb</th>\n",
       "      <th>blyr_xgb</th>\n",
       "      <th>yso_xgb</th>\n",
       "      <th>saw_xgb</th>\n",
       "      <th>ceph2_xgb</th>\n",
       "      <th>rrab_xgb</th>\n",
       "      <th>sin_xgb</th>\n",
       "      <th>osarg_xgb</th>\n",
       "      <th>rrblz_xgb</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10296582009946</td>\n",
       "      <td>0</td>\n",
       "      <td>140015201351056624</td>\n",
       "      <td>90610143756592496</td>\n",
       "      <td>14.375673</td>\n",
       "      <td>-14.489669</td>\n",
       "      <td>5.751999</td>\n",
       "      <td>296</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10296531000371</td>\n",
       "      <td>2468292420539961088</td>\n",
       "      <td>170013701351041248</td>\n",
       "      <td>91920166559039984</td>\n",
       "      <td>16.655579</td>\n",
       "      <td>-13.392433</td>\n",
       "      <td>0.253672</td>\n",
       "      <td>296</td>\n",
       "      <td>14</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10296332007046</td>\n",
       "      <td>2358756082883576832</td>\n",
       "      <td>188016701351063040</td>\n",
       "      <td>88900182352849744</td>\n",
       "      <td>18.235299</td>\n",
       "      <td>-15.908833</td>\n",
       "      <td>0.025950</td>\n",
       "      <td>296</td>\n",
       "      <td>9</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10296352004611</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>88150190046276512</td>\n",
       "      <td>19.004638</td>\n",
       "      <td>-16.536509</td>\n",
       "      <td>0.033279</td>\n",
       "      <td>296</td>\n",
       "      <td>9</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10296193002860</td>\n",
       "      <td>2355129515577873280</td>\n",
       "      <td>190018201351021696</td>\n",
       "      <td>85910189467390912</td>\n",
       "      <td>18.946842</td>\n",
       "      <td>-18.407839</td>\n",
       "      <td>0.025762</td>\n",
       "      <td>296</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>10296311002011</td>\n",
       "      <td>0</td>\n",
       "      <td>142018201351013568</td>\n",
       "      <td>85930135304772064</td>\n",
       "      <td>13.530474</td>\n",
       "      <td>-18.390206</td>\n",
       "      <td>0.099423</td>\n",
       "      <td>296</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>10296162004575</td>\n",
       "      <td>2355334535841260160</td>\n",
       "      <td>190018201351060032</td>\n",
       "      <td>86850190585978048</td>\n",
       "      <td>19.058643</td>\n",
       "      <td>-17.618552</td>\n",
       "      <td>637.168335</td>\n",
       "      <td>296</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>10296332000029</td>\n",
       "      <td>0</td>\n",
       "      <td>172015201351026912</td>\n",
       "      <td>89710179705849520</td>\n",
       "      <td>17.970427</td>\n",
       "      <td>-15.234044</td>\n",
       "      <td>0.079058</td>\n",
       "      <td>296</td>\n",
       "      <td>9</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>10296561018331</td>\n",
       "      <td>2373028431006093312</td>\n",
       "      <td>155013701351040992</td>\n",
       "      <td>92000149780744640</td>\n",
       "      <td>14.978093</td>\n",
       "      <td>-13.329795</td>\n",
       "      <td>0.034946</td>\n",
       "      <td>296</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>10296392037084</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>88190168016806816</td>\n",
       "      <td>16.801518</td>\n",
       "      <td>-16.503011</td>\n",
       "      <td>0.366488</td>\n",
       "      <td>296</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 99 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               _id       Gaia_EDR3___id        AllWISE___id  \\\n",
       "0   10296582009946                    0  140015201351056624   \n",
       "1   10296531000371  2468292420539961088  170013701351041248   \n",
       "2   10296332007046  2358756082883576832  188016701351063040   \n",
       "3   10296352004611                    0                   0   \n",
       "4   10296193002860  2355129515577873280  190018201351021696   \n",
       "..             ...                  ...                 ...   \n",
       "95  10296311002011                    0  142018201351013568   \n",
       "96  10296162004575  2355334535841260160  190018201351060032   \n",
       "97  10296332000029                    0  172015201351026912   \n",
       "98  10296561018331  2373028431006093312  155013701351040992   \n",
       "99  10296392037084                    0                   0   \n",
       "\n",
       "         PS1_DR1___id         ra        dec      period  field  ccd  quad  \\\n",
       "0   90610143756592496  14.375673 -14.489669    5.751999    296   15     3   \n",
       "1   91920166559039984  16.655579 -13.392433    0.253672    296   14     2   \n",
       "2   88900182352849744  18.235299 -15.908833    0.025950    296    9     2   \n",
       "3   88150190046276512  19.004638 -16.536509    0.033279    296    9     4   \n",
       "4   85910189467390912  18.946842 -18.407839    0.025762    296    5     4   \n",
       "..                ...        ...        ...         ...    ...  ...   ...   \n",
       "95  85930135304772064  13.530474 -18.390206    0.099423    296    8     4   \n",
       "96  86850190585978048  19.058643 -17.618552  637.168335    296    5     1   \n",
       "97  89710179705849520  17.970427 -15.234044    0.079058    296    9     2   \n",
       "98  92000149780744640  14.978093 -13.329795    0.034946    296   15     1   \n",
       "99  88190168016806816  16.801518 -16.503011    0.366488    296   10     4   \n",
       "\n",
       "    ...  hp_xgb  i_xgb  blyr_xgb  yso_xgb  saw_xgb  ceph2_xgb  rrab_xgb  \\\n",
       "0   ...    0.00   0.00       0.0      0.0     0.00       0.23       0.0   \n",
       "1   ...    0.00   0.00       0.0      0.0     0.00       0.23       0.0   \n",
       "2   ...    0.00   0.00       0.0      0.0     0.00       0.23       0.0   \n",
       "3   ...    0.01   0.01       0.0      0.0     0.00       0.23       0.0   \n",
       "4   ...    0.00   0.00       0.0      0.0     0.00       0.23       0.0   \n",
       "..  ...     ...    ...       ...      ...      ...        ...       ...   \n",
       "95  ...    0.01   0.01       0.0      0.0     0.00       0.23       0.0   \n",
       "96  ...    0.01   0.03       0.0      0.0     0.00       0.23       0.0   \n",
       "97  ...    0.00   0.13       0.0      0.0     0.02       0.23       0.0   \n",
       "98  ...    0.00   0.01       0.0      0.0     0.02       0.23       0.0   \n",
       "99  ...    0.00   0.00       0.0      0.0     0.00       0.23       0.0   \n",
       "\n",
       "    sin_xgb  osarg_xgb  rrblz_xgb  \n",
       "0      0.00        0.0       0.33  \n",
       "1      0.01        0.0       0.33  \n",
       "2      0.00        0.0       0.33  \n",
       "3      0.00        0.0       0.33  \n",
       "4      0.00        0.0       0.33  \n",
       "..      ...        ...        ...  \n",
       "95     0.00        0.0       0.33  \n",
       "96     0.01        0.0       0.33  \n",
       "97     0.00        0.0       0.33  \n",
       "98     0.00        0.0       0.33  \n",
       "99     0.00        0.0       0.33  \n",
       "\n",
       "[100 rows x 99 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "field_296_100rows"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4e42f2fc-2818-40bf-804c-16c1caac3a9b",
   "metadata": {},
   "source": [
    "#### Describe dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f4b3f66b-3f64-43f4-b376-46768be7d164",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>_id</th>\n",
       "      <th>Gaia_EDR3___id</th>\n",
       "      <th>AllWISE___id</th>\n",
       "      <th>PS1_DR1___id</th>\n",
       "      <th>ra</th>\n",
       "      <th>dec</th>\n",
       "      <th>period</th>\n",
       "      <th>field</th>\n",
       "      <th>ccd</th>\n",
       "      <th>quad</th>\n",
       "      <th>...</th>\n",
       "      <th>hp_xgb</th>\n",
       "      <th>i_xgb</th>\n",
       "      <th>blyr_xgb</th>\n",
       "      <th>yso_xgb</th>\n",
       "      <th>saw_xgb</th>\n",
       "      <th>ceph2_xgb</th>\n",
       "      <th>rrab_xgb</th>\n",
       "      <th>sin_xgb</th>\n",
       "      <th>osarg_xgb</th>\n",
       "      <th>rrblz_xgb</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1.000000e+02</td>\n",
       "      <td>1.000000e+02</td>\n",
       "      <td>1.000000e+02</td>\n",
       "      <td>1.000000e+02</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.0</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.0</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.00000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.0000</td>\n",
       "      <td>100.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.029634e+13</td>\n",
       "      <td>1.757088e+18</td>\n",
       "      <td>1.259936e+17</td>\n",
       "      <td>8.795916e+16</td>\n",
       "      <td>15.559047</td>\n",
       "      <td>-16.696696</td>\n",
       "      <td>20.546433</td>\n",
       "      <td>296.0</td>\n",
       "      <td>9.160000</td>\n",
       "      <td>2.550000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.001100</td>\n",
       "      <td>0.009100</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000400</td>\n",
       "      <td>0.00060</td>\n",
       "      <td>0.230300</td>\n",
       "      <td>0.001000</td>\n",
       "      <td>0.001700</td>\n",
       "      <td>0.0002</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.774576e+08</td>\n",
       "      <td>1.047139e+18</td>\n",
       "      <td>6.459028e+16</td>\n",
       "      <td>2.553461e+15</td>\n",
       "      <td>2.168615</td>\n",
       "      <td>2.128283</td>\n",
       "      <td>104.364753</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.416955</td>\n",
       "      <td>1.085953</td>\n",
       "      <td>...</td>\n",
       "      <td>0.003145</td>\n",
       "      <td>0.036628</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.003153</td>\n",
       "      <td>0.00312</td>\n",
       "      <td>0.001714</td>\n",
       "      <td>0.007177</td>\n",
       "      <td>0.004507</td>\n",
       "      <td>0.0020</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.029601e+13</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>8.321013e+16</td>\n",
       "      <td>12.136068</td>\n",
       "      <td>-20.651207</td>\n",
       "      <td>0.021168</td>\n",
       "      <td>296.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.230000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.029620e+13</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>1.250167e+17</td>\n",
       "      <td>8.600515e+16</td>\n",
       "      <td>13.763547</td>\n",
       "      <td>-18.323814</td>\n",
       "      <td>0.026841</td>\n",
       "      <td>296.0</td>\n",
       "      <td>5.750000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.230000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.029636e+13</td>\n",
       "      <td>2.357130e+18</td>\n",
       "      <td>1.415175e+17</td>\n",
       "      <td>8.844513e+16</td>\n",
       "      <td>15.020253</td>\n",
       "      <td>-16.293143</td>\n",
       "      <td>0.039651</td>\n",
       "      <td>296.0</td>\n",
       "      <td>9.500000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.230000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.029647e+13</td>\n",
       "      <td>2.371505e+18</td>\n",
       "      <td>1.720156e+17</td>\n",
       "      <td>8.981017e+16</td>\n",
       "      <td>17.482961</td>\n",
       "      <td>-15.151479</td>\n",
       "      <td>0.096073</td>\n",
       "      <td>296.0</td>\n",
       "      <td>12.250000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.230000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.029663e+13</td>\n",
       "      <td>2.468292e+18</td>\n",
       "      <td>1.930213e+17</td>\n",
       "      <td>9.200015e+16</td>\n",
       "      <td>19.534744</td>\n",
       "      <td>-13.329795</td>\n",
       "      <td>637.168335</td>\n",
       "      <td>296.0</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.330000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.030000</td>\n",
       "      <td>0.02000</td>\n",
       "      <td>0.240000</td>\n",
       "      <td>0.070000</td>\n",
       "      <td>0.020000</td>\n",
       "      <td>0.0200</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 99 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                _id  Gaia_EDR3___id  AllWISE___id  PS1_DR1___id          ra  \\\n",
       "count  1.000000e+02    1.000000e+02  1.000000e+02  1.000000e+02  100.000000   \n",
       "mean   1.029634e+13    1.757088e+18  1.259936e+17  8.795916e+16   15.559047   \n",
       "std    1.774576e+08    1.047139e+18  6.459028e+16  2.553461e+15    2.168615   \n",
       "min    1.029601e+13    0.000000e+00  0.000000e+00  8.321013e+16   12.136068   \n",
       "25%    1.029620e+13    0.000000e+00  1.250167e+17  8.600515e+16   13.763547   \n",
       "50%    1.029636e+13    2.357130e+18  1.415175e+17  8.844513e+16   15.020253   \n",
       "75%    1.029647e+13    2.371505e+18  1.720156e+17  8.981017e+16   17.482961   \n",
       "max    1.029663e+13    2.468292e+18  1.930213e+17  9.200015e+16   19.534744   \n",
       "\n",
       "              dec      period  field         ccd        quad  ...      hp_xgb  \\\n",
       "count  100.000000  100.000000  100.0  100.000000  100.000000  ...  100.000000   \n",
       "mean   -16.696696   20.546433  296.0    9.160000    2.550000  ...    0.001100   \n",
       "std      2.128283  104.364753    0.0    4.416955    1.085953  ...    0.003145   \n",
       "min    -20.651207    0.021168  296.0    1.000000    1.000000  ...    0.000000   \n",
       "25%    -18.323814    0.026841  296.0    5.750000    2.000000  ...    0.000000   \n",
       "50%    -16.293143    0.039651  296.0    9.500000    2.000000  ...    0.000000   \n",
       "75%    -15.151479    0.096073  296.0   12.250000    4.000000  ...    0.000000   \n",
       "max    -13.329795  637.168335  296.0   16.000000    4.000000  ...    0.010000   \n",
       "\n",
       "            i_xgb  blyr_xgb     yso_xgb    saw_xgb   ceph2_xgb    rrab_xgb  \\\n",
       "count  100.000000     100.0  100.000000  100.00000  100.000000  100.000000   \n",
       "mean     0.009100       0.0    0.000400    0.00060    0.230300    0.001000   \n",
       "std      0.036628       0.0    0.003153    0.00312    0.001714    0.007177   \n",
       "min      0.000000       0.0    0.000000    0.00000    0.230000    0.000000   \n",
       "25%      0.000000       0.0    0.000000    0.00000    0.230000    0.000000   \n",
       "50%      0.000000       0.0    0.000000    0.00000    0.230000    0.000000   \n",
       "75%      0.010000       0.0    0.000000    0.00000    0.230000    0.000000   \n",
       "max      0.330000       0.0    0.030000    0.02000    0.240000    0.070000   \n",
       "\n",
       "          sin_xgb  osarg_xgb  rrblz_xgb  \n",
       "count  100.000000   100.0000     100.00  \n",
       "mean     0.001700     0.0002       0.33  \n",
       "std      0.004507     0.0020       0.00  \n",
       "min      0.000000     0.0000       0.33  \n",
       "25%      0.000000     0.0000       0.33  \n",
       "50%      0.000000     0.0000       0.33  \n",
       "75%      0.000000     0.0000       0.33  \n",
       "max      0.020000     0.0200       0.33  \n",
       "\n",
       "[8 rows x 99 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "field_296_100rows.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "32116af4-c2c9-418e-899d-f66292966588",
   "metadata": {},
   "source": [
    "#### List all columns found in prediction files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "5e9b6e37-a30a-44cb-9c88-4c989ad8e2b4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['_id',\n",
       " 'Gaia_EDR3___id',\n",
       " 'AllWISE___id',\n",
       " 'PS1_DR1___id',\n",
       " 'ra',\n",
       " 'dec',\n",
       " 'period',\n",
       " 'field',\n",
       " 'ccd',\n",
       " 'quad',\n",
       " 'filter',\n",
       " 'sin_dnn',\n",
       " 'rscvn_dnn',\n",
       " 'emsms_dnn',\n",
       " 'ea_dnn',\n",
       " 'rrlyr_dnn',\n",
       " 'el_dnn',\n",
       " 'saw_dnn',\n",
       " 'bogus_dnn',\n",
       " 'wuma_dnn',\n",
       " 'e_dnn',\n",
       " 'yso_dnn',\n",
       " 'ceph_dnn',\n",
       " 'cv_dnn',\n",
       " 'srv_dnn',\n",
       " 'fla_dnn',\n",
       " 'blyr_dnn',\n",
       " 'wp_dnn',\n",
       " 'eb_dnn',\n",
       " 'blher_dnn',\n",
       " 'hp_dnn',\n",
       " 'ext_dnn',\n",
       " 'dip_dnn',\n",
       " 'rrab_dnn',\n",
       " 'vnv_dnn',\n",
       " 'pnp_dnn',\n",
       " 'wvir_dnn',\n",
       " 'dp_dnn',\n",
       " 'bright_dnn',\n",
       " 'ceph2_dnn',\n",
       " 'dscu_dnn',\n",
       " 'bis_dnn',\n",
       " 'osarg_dnn',\n",
       " 'rrblz_dnn',\n",
       " 'i_dnn',\n",
       " 'puls_dnn',\n",
       " 'mp_dnn',\n",
       " 'rrc_dnn',\n",
       " 'mir_dnn',\n",
       " 'agn_dnn',\n",
       " 'longt_dnn',\n",
       " 'blend_dnn',\n",
       " 'ew_dnn',\n",
       " 'lpv_dnn',\n",
       " 'rrd_dnn',\n",
       " 'rrd_xgb',\n",
       " 'wvir_xgb',\n",
       " 'dp_xgb',\n",
       " 'blher_xgb',\n",
       " 'lpv_xgb',\n",
       " 'agn_xgb',\n",
       " 'dscu_xgb',\n",
       " 'puls_xgb',\n",
       " 'rrc_xgb',\n",
       " 'mir_xgb',\n",
       " 'e_xgb',\n",
       " 'rscvn_xgb',\n",
       " 'rrlyr_xgb',\n",
       " 'bis_xgb',\n",
       " 'emsms_xgb',\n",
       " 'mp_xgb',\n",
       " 'ew_xgb',\n",
       " 'bogus_xgb',\n",
       " 'ea_xgb',\n",
       " 'vnv_xgb',\n",
       " 'pnp_xgb',\n",
       " 'longt_xgb',\n",
       " 'dip_xgb',\n",
       " 'cv_xgb',\n",
       " 'blend_xgb',\n",
       " 'ext_xgb',\n",
       " 'wuma_xgb',\n",
       " 'srv_xgb',\n",
       " 'fla_xgb',\n",
       " 'bright_xgb',\n",
       " 'el_xgb',\n",
       " 'ceph_xgb',\n",
       " 'eb_xgb',\n",
       " 'wp_xgb',\n",
       " 'hp_xgb',\n",
       " 'i_xgb',\n",
       " 'blyr_xgb',\n",
       " 'yso_xgb',\n",
       " 'saw_xgb',\n",
       " 'ceph2_xgb',\n",
       " 'rrab_xgb',\n",
       " 'sin_xgb',\n",
       " 'osarg_xgb',\n",
       " 'rrblz_xgb']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_columns = [x for x in field_296_100rows.columns]\n",
    "df_columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c69df69-f902-4a35-b1f3-1427c8d885ab",
   "metadata": {},
   "source": [
    "#### 99 total columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "43383b84-6b46-4e6b-98c9-2ba9b5384403",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "99"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df_columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b6bd50f-4b4a-4f4b-a139-5293574c8309",
   "metadata": {},
   "source": [
    "#### Dataframe columns begin with ZTF ID and Gaia/AllWISE/Pan-STARRS IDs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "05c0d38b-7cc0-4887-b06b-e0e1b5f78567",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['_id', 'Gaia_EDR3___id', 'AllWISE___id', 'PS1_DR1___id']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_columns[0:4]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ac65805-769e-4183-abb7-5bb10bdf9dfd",
   "metadata": {},
   "source": [
    "#### Next columns include ra/dec, computed period, ZTF field/CCD/quadrant/filter of observations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4056636d-032e-44e4-ab08-d7d31e9b76c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['ra', 'dec', 'period', 'field', 'ccd', 'quad', 'filter']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_columns[4:11]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18906ea8-0be4-45a8-ab9d-442bcf728d73",
   "metadata": {},
   "source": [
    "#### Next are DNN classification columns, one per class, each containing probabilities from 0-1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e789cfc0-a7a4-4950-9c4e-976db80c2bd5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['sin_dnn',\n",
       " 'rscvn_dnn',\n",
       " 'emsms_dnn',\n",
       " 'ea_dnn',\n",
       " 'rrlyr_dnn',\n",
       " 'el_dnn',\n",
       " 'saw_dnn',\n",
       " 'bogus_dnn',\n",
       " 'wuma_dnn',\n",
       " 'e_dnn',\n",
       " 'yso_dnn',\n",
       " 'ceph_dnn',\n",
       " 'cv_dnn',\n",
       " 'srv_dnn',\n",
       " 'fla_dnn',\n",
       " 'blyr_dnn',\n",
       " 'wp_dnn',\n",
       " 'eb_dnn',\n",
       " 'blher_dnn',\n",
       " 'hp_dnn',\n",
       " 'ext_dnn',\n",
       " 'dip_dnn',\n",
       " 'rrab_dnn',\n",
       " 'vnv_dnn',\n",
       " 'pnp_dnn',\n",
       " 'wvir_dnn',\n",
       " 'dp_dnn',\n",
       " 'bright_dnn',\n",
       " 'ceph2_dnn',\n",
       " 'dscu_dnn',\n",
       " 'bis_dnn',\n",
       " 'osarg_dnn',\n",
       " 'rrblz_dnn',\n",
       " 'i_dnn',\n",
       " 'puls_dnn',\n",
       " 'mp_dnn',\n",
       " 'rrc_dnn',\n",
       " 'mir_dnn',\n",
       " 'agn_dnn',\n",
       " 'longt_dnn',\n",
       " 'blend_dnn',\n",
       " 'ew_dnn',\n",
       " 'lpv_dnn',\n",
       " 'rrd_dnn']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_columns[11:55]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9586adb7-c7e0-451e-85bf-cdf2a1118771",
   "metadata": {},
   "source": [
    "#### Columns conclude with XGB classifications "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f4738d54-032e-43e4-89a8-6b77c593a23d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['rrd_xgb',\n",
       " 'wvir_xgb',\n",
       " 'dp_xgb',\n",
       " 'blher_xgb',\n",
       " 'lpv_xgb',\n",
       " 'agn_xgb',\n",
       " 'dscu_xgb',\n",
       " 'puls_xgb',\n",
       " 'rrc_xgb',\n",
       " 'mir_xgb',\n",
       " 'e_xgb',\n",
       " 'rscvn_xgb',\n",
       " 'rrlyr_xgb',\n",
       " 'bis_xgb',\n",
       " 'emsms_xgb',\n",
       " 'mp_xgb',\n",
       " 'ew_xgb',\n",
       " 'bogus_xgb',\n",
       " 'ea_xgb',\n",
       " 'vnv_xgb',\n",
       " 'pnp_xgb',\n",
       " 'longt_xgb',\n",
       " 'dip_xgb',\n",
       " 'cv_xgb',\n",
       " 'blend_xgb',\n",
       " 'ext_xgb',\n",
       " 'wuma_xgb',\n",
       " 'srv_xgb',\n",
       " 'fla_xgb',\n",
       " 'bright_xgb',\n",
       " 'el_xgb',\n",
       " 'ceph_xgb',\n",
       " 'eb_xgb',\n",
       " 'wp_xgb',\n",
       " 'hp_xgb',\n",
       " 'i_xgb',\n",
       " 'blyr_xgb',\n",
       " 'yso_xgb',\n",
       " 'saw_xgb',\n",
       " 'ceph2_xgb',\n",
       " 'rrab_xgb',\n",
       " 'sin_xgb',\n",
       " 'osarg_xgb',\n",
       " 'rrblz_xgb']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_columns[55:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24440618-baa8-473a-bbb6-17d16d39436f",
   "metadata": {},
   "source": [
    "#### This code down-sampled the full field_296.csv data from 380,571 rows to 100 rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "8271f4d7-e726-4f35-a874-ff4aa8d5ff75",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\nfield_296 = pd.read_csv(\"preds_dnn_xgb/field_296.csv\")\\nrandom = field_296.sample(n=100, frac=None, replace=False, weights=None, random_state=1, axis=None, ignore_index=False)\\nrandom.to_csv(\\'field_296_100rows.csv\\', index=False)\\n'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"\n",
    "field_296 = pd.read_csv(\"preds_dnn_xgb/field_296.csv\")\n",
    "random = field_296.sample(n=100, frac=None, replace=False, weights=None, random_state=1, axis=None, ignore_index=False)\n",
    "random.to_csv('field_296_100rows.csv', index=False)\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba978685-59ba-4550-95bf-c67002910d70",
   "metadata": {},
   "source": [
    "#### Scatter plot shows the ra/dec values of the 100 randomized rows above"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9e6cc6d7-2153-4567-8f5e-46426748c9cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ra = field_296_100rows.iloc[0:,4]\n",
    "dec = field_296_100rows.iloc[0:,5]\n",
    "plt.scatter(ra,dec)\n",
    "plt.xlabel('RA [deg]',fontsize=14)\n",
    "plt.ylabel('Dec [deg]',fontsize=14)\n",
    "plt.xticks(fontsize=14)\n",
    "plt.yticks(fontsize=14)\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "262e4e19-5e0d-4de2-a3ff-bd805b4c0391",
   "metadata": {},
   "source": [
    "#### Histogram shows the classification probability distributions of specific DNN and XGB classifiers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5673afe3-a97f-4685-a0e0-14c460877b00",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Light Curves')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plots - histogram (class probs) - variable or periodic - xaxis 0-1\n",
    "plt.hist(field_296_100rows['vnv_dnn'], bins = 10, range = (0, 1), label = 'vnv_dnn')\n",
    "plt.hist(field_296_100rows['vnv_xgb'], bins = 10, range = (0, 1), alpha = 0.7, label = 'vnv_xgb')\n",
    "plt.legend()\n",
    "plt.xlabel('Classification Probability')\n",
    "plt.ylabel('Number of Light Curves')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b2aa06e-7ea7-457c-b7d9-a54155d8695a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}