Skip to content

Instantly share code, notes, and snippets.

@Dr-T-Prabha

Dr-T-Prabha/thiazole.ipynb Secret

Created January 19, 2022 16:07
Show Gist options
  • Star 3 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save Dr-T-Prabha/c89c573afc07612ad83908d8dd6f3773 to your computer and use it in GitHub Desktop.
Save Dr-T-Prabha/c89c573afc07612ad83908d8dd6f3773 to your computer and use it in GitHub Desktop.
Download ZIP
Thiazole.ipynb
Display the source blob
Display the rendered blob
Raw
thiazole.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Thiazole.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyObbMjINjQZBseIl7OwnW2C",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/Dr-T-Prabha/c89c573afc07612ad83908d8dd6f3773/thiazole.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "TRsRyN2y7Fdw"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import sklearn"
]
},
{
"cell_type": "code",
"source": [
"df = pd.read_csv('Train.csv')\n",
"df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "TpjDyA1Z7Vkx",
"outputId": "a750509a-efd3-4812-bd2a-41de00f5efb3"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
" <div id=\"df-158d134e-5ec4-4b85-8195-0221a0019c61\">\n",
" <div class=\"colab-df-container\">\n",
" <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>code</th>\n",
" <th>ic50</th>\n",
" <th>pic50</th>\n",
" <th>vabc</th>\n",
" <th>chiPathCluster.1</th>\n",
" <th>chiPathCluster.0</th>\n",
" <th>chiPathCluster.3</th>\n",
" <th>chiPathCluster.5</th>\n",
" <th>chiPathCluster.4</th>\n",
" <th>vAdjMa</th>\n",
" <th>chiPath.12</th>\n",
" <th>chiPath.13</th>\n",
" <th>chiPath.10</th>\n",
" <th>chiPath.11</th>\n",
" <th>chiPath.14</th>\n",
" <th>chiPath.15</th>\n",
" <th>kierValues.1</th>\n",
" <th>kierValues.0</th>\n",
" <th>autoCorrelationMass.0</th>\n",
" <th>autoCorrelationMass.1</th>\n",
" <th>autoCorrelationMass.2</th>\n",
" <th>autoCorrelationMass.3</th>\n",
" <th>autoCorrelationMass.4</th>\n",
" <th>mde.16</th>\n",
" <th>xlogP</th>\n",
" <th>hBondacceptors</th>\n",
" <th>weight</th>\n",
" <th>ALOGP.2</th>\n",
" <th>ALOGP.0</th>\n",
" <th>ALOGP.1</th>\n",
" <th>chiCluster.4</th>\n",
" <th>petitjeanNumber</th>\n",
" <th>autoCorrelationCharge.1</th>\n",
" <th>autoCorrelationCharge.2</th>\n",
" <th>autoCorrelationCharge.3</th>\n",
" <th>autoCorrelationCharge.0</th>\n",
" <th>chiPath.8</th>\n",
" <th>chiPath.0</th>\n",
" <th>chiPath.1</th>\n",
" <th>chiPath.2</th>\n",
" <th>...</th>\n",
" <th>weightedPath.2</th>\n",
" <th>petitjeanShapeIndex.0</th>\n",
" <th>wienerNumbers.1</th>\n",
" <th>wienerNumbers.0</th>\n",
" <th>chiCluster.0</th>\n",
" <th>weightedPath.4</th>\n",
" <th>mde.7</th>\n",
" <th>mannholdLogP</th>\n",
" <th>mde.5</th>\n",
" <th>zagrebIndex</th>\n",
" <th>mde.4</th>\n",
" <th>rotatableBondsCount</th>\n",
" <th>chiPath.5</th>\n",
" <th>aromaticAtomsCount</th>\n",
" <th>fmf</th>\n",
" <th>largestPiSystem</th>\n",
" <th>chiChain.3</th>\n",
" <th>carbonTypes.6</th>\n",
" <th>bondCount</th>\n",
" <th>chiPathCluster.2</th>\n",
" <th>hBondDonors</th>\n",
" <th>chiPath.3</th>\n",
" <th>chiChain.8</th>\n",
" <th>ip</th>\n",
" <th>chiChain.4</th>\n",
" <th>atomCount</th>\n",
" <th>NilaComplexity</th>\n",
" <th>bpol</th>\n",
" <th>kierHallSmarts.16</th>\n",
" <th>kierHallSmarts.11</th>\n",
" <th>weightedPath.0</th>\n",
" <th>weightedPath.1</th>\n",
" <th>tpsa</th>\n",
" <th>carbonTypes.7</th>\n",
" <th>kierValues.2</th>\n",
" <th>eccentricConnectivityIndex</th>\n",
" <th>kierHallSmarts.23</th>\n",
" <th>chiChain.9</th>\n",
" <th>apol</th>\n",
" <th>largestChain</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>21</td>\n",
" <td>87.80</td>\n",
" <td>4.056505</td>\n",
" <td>406.762844</td>\n",
" <td>9.360463</td>\n",
" <td>6.352598</td>\n",
" <td>2.986742</td>\n",
" <td>4.837125</td>\n",
" <td>4.140526</td>\n",
" <td>5.954196</td>\n",
" <td>5.709481</td>\n",
" <td>4.093240</td>\n",
" <td>9.669710</td>\n",
" <td>7.752166</td>\n",
" <td>2.342887</td>\n",
" <td>1.479003</td>\n",
" <td>10.508122</td>\n",
" <td>24.134948</td>\n",
" <td>47.018834</td>\n",
" <td>47.758592</td>\n",
" <td>67.451231</td>\n",
" <td>74.338494</td>\n",
" <td>58.517266</td>\n",
" <td>1.000000</td>\n",
" <td>4.080</td>\n",
" <td>7</td>\n",
" <td>460.160283</td>\n",
" <td>75.9258</td>\n",
" <td>-2.9251</td>\n",
" <td>8.556210</td>\n",
" <td>1.223516</td>\n",
" <td>0.470588</td>\n",
" <td>-0.191421</td>\n",
" <td>-0.027326</td>\n",
" <td>-0.014661</td>\n",
" <td>0.457758</td>\n",
" <td>18.706619</td>\n",
" <td>22.009861</td>\n",
" <td>14.875047</td>\n",
" <td>13.766988</td>\n",
" <td>...</td>\n",
" <td>26.163489</td>\n",
" <td>0.888889</td>\n",
" <td>52</td>\n",
" <td>3122</td>\n",
" <td>2.468712</td>\n",
" <td>11.968430</td>\n",
" <td>8.126046</td>\n",
" <td>2.89</td>\n",
" <td>18.083288</td>\n",
" <td>166</td>\n",
" <td>13.742460</td>\n",
" <td>6</td>\n",
" <td>7.218046</td>\n",
" <td>11</td>\n",
" <td>0.838710</td>\n",
" <td>21</td>\n",
" <td>0.503768</td>\n",
" <td>15</td>\n",
" <td>34</td>\n",
" <td>11.956905</td>\n",
" <td>2</td>\n",
" <td>11.987876</td>\n",
" <td>0.360055</td>\n",
" <td>1.452163</td>\n",
" <td>0.663757</td>\n",
" <td>59</td>\n",
" <td>226.09</td>\n",
" <td>42.303796</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>63.205098</td>\n",
" <td>2.038874</td>\n",
" <td>141.48</td>\n",
" <td>2</td>\n",
" <td>5.399449</td>\n",
" <td>901</td>\n",
" <td>1</td>\n",
" <td>0.475372</td>\n",
" <td>69.996204</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20</td>\n",
" <td>75.30</td>\n",
" <td>4.123205</td>\n",
" <td>389.466859</td>\n",
" <td>9.360463</td>\n",
" <td>6.352598</td>\n",
" <td>2.986742</td>\n",
" <td>4.405939</td>\n",
" <td>4.140526</td>\n",
" <td>5.906891</td>\n",
" <td>5.547869</td>\n",
" <td>3.655095</td>\n",
" <td>9.316157</td>\n",
" <td>7.502166</td>\n",
" <td>2.139279</td>\n",
" <td>1.344019</td>\n",
" <td>9.868056</td>\n",
" <td>23.168044</td>\n",
" <td>46.018834</td>\n",
" <td>46.758592</td>\n",
" <td>66.451231</td>\n",
" <td>71.338494</td>\n",
" <td>53.847481</td>\n",
" <td>1.000000</td>\n",
" <td>3.511</td>\n",
" <td>7</td>\n",
" <td>446.144633</td>\n",
" <td>73.0142</td>\n",
" <td>-2.6371</td>\n",
" <td>6.954296</td>\n",
" <td>1.223516</td>\n",
" <td>0.470588</td>\n",
" <td>-0.191417</td>\n",
" <td>-0.027268</td>\n",
" <td>-0.014636</td>\n",
" <td>0.457759</td>\n",
" <td>17.999513</td>\n",
" <td>21.302754</td>\n",
" <td>14.375047</td>\n",
" <td>13.413434</td>\n",
" <td>...</td>\n",
" <td>26.136373</td>\n",
" <td>0.888889</td>\n",
" <td>49</td>\n",
" <td>2855</td>\n",
" <td>2.468712</td>\n",
" <td>11.958556</td>\n",
" <td>8.126046</td>\n",
" <td>2.78</td>\n",
" <td>16.578867</td>\n",
" <td>162</td>\n",
" <td>12.383367</td>\n",
" <td>6</td>\n",
" <td>6.684025</td>\n",
" <td>11</td>\n",
" <td>0.833333</td>\n",
" <td>21</td>\n",
" <td>0.571810</td>\n",
" <td>14</td>\n",
" <td>33</td>\n",
" <td>11.528752</td>\n",
" <td>2</td>\n",
" <td>11.737876</td>\n",
" <td>0.450003</td>\n",
" <td>1.464524</td>\n",
" <td>0.760269</td>\n",
" <td>56</td>\n",
" <td>219.09</td>\n",
" <td>40.117382</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>61.104480</td>\n",
" <td>2.036816</td>\n",
" <td>141.48</td>\n",
" <td>2</td>\n",
" <td>5.010178</td>\n",
" <td>867</td>\n",
" <td>1</td>\n",
" <td>0.523442</td>\n",
" <td>66.902618</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>17</td>\n",
" <td>74.60</td>\n",
" <td>4.127261</td>\n",
" <td>379.409312</td>\n",
" <td>9.608967</td>\n",
" <td>6.381825</td>\n",
" <td>2.244637</td>\n",
" <td>3.193202</td>\n",
" <td>2.794905</td>\n",
" <td>5.857981</td>\n",
" <td>3.939081</td>\n",
" <td>2.649204</td>\n",
" <td>7.827862</td>\n",
" <td>5.784340</td>\n",
" <td>1.385929</td>\n",
" <td>0.819803</td>\n",
" <td>10.080000</td>\n",
" <td>23.658689</td>\n",
" <td>40.025531</td>\n",
" <td>42.083477</td>\n",
" <td>58.156189</td>\n",
" <td>65.762171</td>\n",
" <td>58.335106</td>\n",
" <td>0.000000</td>\n",
" <td>0.305</td>\n",
" <td>9</td>\n",
" <td>419.162725</td>\n",
" <td>74.8637</td>\n",
" <td>-4.0342</td>\n",
" <td>16.274770</td>\n",
" <td>1.053833</td>\n",
" <td>0.466667</td>\n",
" <td>-0.207753</td>\n",
" <td>0.032206</td>\n",
" <td>-0.338312</td>\n",
" <td>0.657737</td>\n",
" <td>16.434246</td>\n",
" <td>21.181434</td>\n",
" <td>13.751256</td>\n",
" <td>12.766335</td>\n",
" <td>...</td>\n",
" <td>28.433372</td>\n",
" <td>0.875000</td>\n",
" <td>51</td>\n",
" <td>2438</td>\n",
" <td>2.537748</td>\n",
" <td>14.827022</td>\n",
" <td>6.325624</td>\n",
" <td>2.45</td>\n",
" <td>15.001023</td>\n",
" <td>152</td>\n",
" <td>12.092667</td>\n",
" <td>4</td>\n",
" <td>6.139810</td>\n",
" <td>6</td>\n",
" <td>0.724138</td>\n",
" <td>15</td>\n",
" <td>0.230756</td>\n",
" <td>10</td>\n",
" <td>31</td>\n",
" <td>12.350433</td>\n",
" <td>2</td>\n",
" <td>10.957567</td>\n",
" <td>0.137264</td>\n",
" <td>6.063225</td>\n",
" <td>0.341043</td>\n",
" <td>54</td>\n",
" <td>149.10</td>\n",
" <td>38.724175</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>58.158264</td>\n",
" <td>2.005457</td>\n",
" <td>148.47</td>\n",
" <td>2</td>\n",
" <td>5.257778</td>\n",
" <td>717</td>\n",
" <td>0</td>\n",
" <td>0.151693</td>\n",
" <td>61.717825</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>22</td>\n",
" <td>60.10</td>\n",
" <td>4.221126</td>\n",
" <td>445.655237</td>\n",
" <td>10.391852</td>\n",
" <td>6.754624</td>\n",
" <td>3.017207</td>\n",
" <td>4.814725</td>\n",
" <td>4.175415</td>\n",
" <td>6.087463</td>\n",
" <td>5.377917</td>\n",
" <td>3.609079</td>\n",
" <td>10.008321</td>\n",
" <td>7.481908</td>\n",
" <td>1.822329</td>\n",
" <td>1.148802</td>\n",
" <td>12.029904</td>\n",
" <td>27.046019</td>\n",
" <td>56.506568</td>\n",
" <td>52.926923</td>\n",
" <td>79.158668</td>\n",
" <td>83.176610</td>\n",
" <td>75.891212</td>\n",
" <td>1.000000</td>\n",
" <td>5.794</td>\n",
" <td>8</td>\n",
" <td>515.111953</td>\n",
" <td>83.9060</td>\n",
" <td>-1.8541</td>\n",
" <td>3.437687</td>\n",
" <td>1.376849</td>\n",
" <td>0.473684</td>\n",
" <td>-0.258123</td>\n",
" <td>0.060440</td>\n",
" <td>-0.094199</td>\n",
" <td>0.495392</td>\n",
" <td>20.436902</td>\n",
" <td>24.294318</td>\n",
" <td>16.285731</td>\n",
" <td>15.011321</td>\n",
" <td>...</td>\n",
" <td>32.081646</td>\n",
" <td>0.900000</td>\n",
" <td>57</td>\n",
" <td>4047</td>\n",
" <td>2.679443</td>\n",
" <td>15.407572</td>\n",
" <td>7.441931</td>\n",
" <td>2.78</td>\n",
" <td>18.230576</td>\n",
" <td>180</td>\n",
" <td>14.811967</td>\n",
" <td>7</td>\n",
" <td>7.746307</td>\n",
" <td>12</td>\n",
" <td>0.823529</td>\n",
" <td>27</td>\n",
" <td>0.535314</td>\n",
" <td>14</td>\n",
" <td>37</td>\n",
" <td>13.397632</td>\n",
" <td>2</td>\n",
" <td>12.872044</td>\n",
" <td>0.330756</td>\n",
" <td>-0.583728</td>\n",
" <td>0.627522</td>\n",
" <td>59</td>\n",
" <td>247.11</td>\n",
" <td>42.144175</td>\n",
" <td>3</td>\n",
" <td>9</td>\n",
" <td>68.991880</td>\n",
" <td>2.029173</td>\n",
" <td>173.87</td>\n",
" <td>1</td>\n",
" <td>6.297163</td>\n",
" <td>1081</td>\n",
" <td>1</td>\n",
" <td>0.353145</td>\n",
" <td>73.755825</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2d</td>\n",
" <td>56.10</td>\n",
" <td>4.251037</td>\n",
" <td>280.285810</td>\n",
" <td>4.510658</td>\n",
" <td>2.708391</td>\n",
" <td>1.155758</td>\n",
" <td>1.701637</td>\n",
" <td>1.642207</td>\n",
" <td>5.584963</td>\n",
" <td>3.291107</td>\n",
" <td>2.102408</td>\n",
" <td>6.227805</td>\n",
" <td>4.544963</td>\n",
" <td>1.152640</td>\n",
" <td>0.706013</td>\n",
" <td>8.589506</td>\n",
" <td>17.415638</td>\n",
" <td>31.567674</td>\n",
" <td>31.696642</td>\n",
" <td>43.586132</td>\n",
" <td>39.805040</td>\n",
" <td>36.169721</td>\n",
" <td>1.785490</td>\n",
" <td>6.832</td>\n",
" <td>4</td>\n",
" <td>332.109568</td>\n",
" <td>19.1057</td>\n",
" <td>-0.2386</td>\n",
" <td>0.056930</td>\n",
" <td>0.523594</td>\n",
" <td>0.500000</td>\n",
" <td>-0.129857</td>\n",
" <td>0.020971</td>\n",
" <td>0.056403</td>\n",
" <td>0.208795</td>\n",
" <td>13.754482</td>\n",
" <td>16.192024</td>\n",
" <td>11.898979</td>\n",
" <td>10.167526</td>\n",
" <td>...</td>\n",
" <td>15.505516</td>\n",
" <td>1.000000</td>\n",
" <td>34</td>\n",
" <td>1555</td>\n",
" <td>1.006874</td>\n",
" <td>12.413533</td>\n",
" <td>4.139512</td>\n",
" <td>3.00</td>\n",
" <td>18.124101</td>\n",
" <td>126</td>\n",
" <td>14.827805</td>\n",
" <td>5</td>\n",
" <td>5.895196</td>\n",
" <td>21</td>\n",
" <td>1.000000</td>\n",
" <td>13</td>\n",
" <td>0.404812</td>\n",
" <td>12</td>\n",
" <td>27</td>\n",
" <td>5.753816</td>\n",
" <td>2</td>\n",
" <td>8.808773</td>\n",
" <td>0.157544</td>\n",
" <td>8.352624</td>\n",
" <td>0.513564</td>\n",
" <td>40</td>\n",
" <td>177.05</td>\n",
" <td>22.411312</td>\n",
" <td>4</td>\n",
" <td>12</td>\n",
" <td>50.142495</td>\n",
" <td>2.089271</td>\n",
" <td>78.08</td>\n",
" <td>3</td>\n",
" <td>4.411458</td>\n",
" <td>594</td>\n",
" <td>2</td>\n",
" <td>0.162214</td>\n",
" <td>51.408688</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>12</td>\n",
" <td>51.20</td>\n",
" <td>4.290730</td>\n",
" <td>530.874400</td>\n",
" <td>12.964876</td>\n",
" <td>8.161922</td>\n",
" <td>2.681515</td>\n",
" <td>4.248985</td>\n",
" <td>3.549071</td>\n",
" <td>6.357552</td>\n",
" <td>5.049189</td>\n",
" <td>3.475679</td>\n",
" <td>9.846081</td>\n",
" <td>7.312835</td>\n",
" <td>1.924519</td>\n",
" <td>1.191787</td>\n",
" <td>15.328798</td>\n",
" <td>33.884298</td>\n",
" <td>53.574469</td>\n",
" <td>56.411845</td>\n",
" <td>77.899363</td>\n",
" <td>91.395331</td>\n",
" <td>92.158613</td>\n",
" <td>0.000000</td>\n",
" <td>4.588</td>\n",
" <td>10</td>\n",
" <td>577.199505</td>\n",
" <td>97.8062</td>\n",
" <td>-2.6551</td>\n",
" <td>7.049556</td>\n",
" <td>1.183063</td>\n",
" <td>0.500000</td>\n",
" <td>-0.488226</td>\n",
" <td>0.143684</td>\n",
" <td>-0.220318</td>\n",
" <td>0.982576</td>\n",
" <td>23.289127</td>\n",
" <td>29.733476</td>\n",
" <td>19.631796</td>\n",
" <td>17.544895</td>\n",
" <td>...</td>\n",
" <td>34.273995</td>\n",
" <td>1.000000</td>\n",
" <td>75</td>\n",
" <td>5988</td>\n",
" <td>3.087509</td>\n",
" <td>14.992649</td>\n",
" <td>15.291787</td>\n",
" <td>3.33</td>\n",
" <td>28.576240</td>\n",
" <td>214</td>\n",
" <td>16.386445</td>\n",
" <td>9</td>\n",
" <td>9.871255</td>\n",
" <td>12</td>\n",
" <td>0.658537</td>\n",
" <td>32</td>\n",
" <td>0.305766</td>\n",
" <td>13</td>\n",
" <td>44</td>\n",
" <td>18.675343</td>\n",
" <td>1</td>\n",
" <td>15.387669</td>\n",
" <td>0.148588</td>\n",
" <td>4.352407</td>\n",
" <td>0.417067</td>\n",
" <td>72</td>\n",
" <td>296.12</td>\n",
" <td>50.073417</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>82.679892</td>\n",
" <td>2.016583</td>\n",
" <td>163.77</td>\n",
" <td>2</td>\n",
" <td>7.631127</td>\n",
" <td>1310</td>\n",
" <td>0</td>\n",
" <td>0.145487</td>\n",
" <td>84.922583</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2f</td>\n",
" <td>50.60</td>\n",
" <td>4.295849</td>\n",
" <td>318.679557</td>\n",
" <td>5.157147</td>\n",
" <td>3.695859</td>\n",
" <td>1.174044</td>\n",
" <td>1.448040</td>\n",
" <td>1.502901</td>\n",
" <td>5.807355</td>\n",
" <td>3.228818</td>\n",
" <td>1.989410</td>\n",
" <td>6.675305</td>\n",
" <td>4.704570</td>\n",
" <td>1.124368</td>\n",
" <td>0.639330</td>\n",
" <td>10.346939</td>\n",
" <td>21.240375</td>\n",
" <td>37.891081</td>\n",
" <td>37.301568</td>\n",
" <td>52.186970</td>\n",
" <td>46.018690</td>\n",
" <td>43.217188</td>\n",
" <td>1.650964</td>\n",
" <td>8.091</td>\n",
" <td>3</td>\n",
" <td>390.078661</td>\n",
" <td>24.1536</td>\n",
" <td>0.6420</td>\n",
" <td>0.412164</td>\n",
" <td>0.612965</td>\n",
" <td>0.500000</td>\n",
" <td>-0.160635</td>\n",
" <td>-0.087162</td>\n",
" <td>0.129086</td>\n",
" <td>0.391461</td>\n",
" <td>15.148329</td>\n",
" <td>19.346724</td>\n",
" <td>13.686673</td>\n",
" <td>12.126186</td>\n",
" <td>...</td>\n",
" <td>23.384718</td>\n",
" <td>1.000000</td>\n",
" <td>38</td>\n",
" <td>2585</td>\n",
" <td>1.574915</td>\n",
" <td>12.322890</td>\n",
" <td>4.393832</td>\n",
" <td>2.78</td>\n",
" <td>19.325760</td>\n",
" <td>146</td>\n",
" <td>13.823798</td>\n",
" <td>6</td>\n",
" <td>5.989832</td>\n",
" <td>22</td>\n",
" <td>0.892857</td>\n",
" <td>28</td>\n",
" <td>0.488145</td>\n",
" <td>15</td>\n",
" <td>31</td>\n",
" <td>5.774160</td>\n",
" <td>1</td>\n",
" <td>10.130791</td>\n",
" <td>0.175562</td>\n",
" <td>8.372082</td>\n",
" <td>0.561677</td>\n",
" <td>42</td>\n",
" <td>205.08</td>\n",
" <td>22.736898</td>\n",
" <td>7</td>\n",
" <td>12</td>\n",
" <td>57.698080</td>\n",
" <td>2.060646</td>\n",
" <td>121.80</td>\n",
" <td>2</td>\n",
" <td>5.795610</td>\n",
" <td>855</td>\n",
" <td>1</td>\n",
" <td>0.170901</td>\n",
" <td>54.241102</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>18</td>\n",
" <td>49.30</td>\n",
" <td>4.307153</td>\n",
" <td>386.588410</td>\n",
" <td>9.482430</td>\n",
" <td>6.442993</td>\n",
" <td>2.694406</td>\n",
" <td>3.544649</td>\n",
" <td>3.387992</td>\n",
" <td>5.906891</td>\n",
" <td>4.451904</td>\n",
" <td>2.814509</td>\n",
" <td>8.516368</td>\n",
" <td>6.505144</td>\n",
" <td>1.427606</td>\n",
" <td>0.833551</td>\n",
" <td>10.744802</td>\n",
" <td>24.638672</td>\n",
" <td>46.738795</td>\n",
" <td>46.090956</td>\n",
" <td>65.227265</td>\n",
" <td>71.499618</td>\n",
" <td>59.040877</td>\n",
" <td>1.000000</td>\n",
" <td>1.712</td>\n",
" <td>9</td>\n",
" <td>448.135131</td>\n",
" <td>72.8067</td>\n",
" <td>-3.4960</td>\n",
" <td>12.222016</td>\n",
" <td>1.195100</td>\n",
" <td>0.470588</td>\n",
" <td>-0.187155</td>\n",
" <td>-0.000561</td>\n",
" <td>-0.129122</td>\n",
" <td>0.563233</td>\n",
" <td>17.519072</td>\n",
" <td>21.888541</td>\n",
" <td>14.251256</td>\n",
" <td>13.107983</td>\n",
" <td>...</td>\n",
" <td>30.977904</td>\n",
" <td>0.888889</td>\n",
" <td>50</td>\n",
" <td>2861</td>\n",
" <td>2.537748</td>\n",
" <td>16.901817</td>\n",
" <td>8.126046</td>\n",
" <td>2.34</td>\n",
" <td>12.953162</td>\n",
" <td>156</td>\n",
" <td>10.833032</td>\n",
" <td>6</td>\n",
" <td>6.076278</td>\n",
" <td>11</td>\n",
" <td>0.733333</td>\n",
" <td>13</td>\n",
" <td>0.443447</td>\n",
" <td>10</td>\n",
" <td>32</td>\n",
" <td>11.481294</td>\n",
" <td>4</td>\n",
" <td>11.291347</td>\n",
" <td>0.277691</td>\n",
" <td>-2.660505</td>\n",
" <td>0.586277</td>\n",
" <td>54</td>\n",
" <td>154.11</td>\n",
" <td>36.972968</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>60.088615</td>\n",
" <td>2.002954</td>\n",
" <td>194.45</td>\n",
" <td>2</td>\n",
" <td>5.688793</td>\n",
" <td>834</td>\n",
" <td>1</td>\n",
" <td>0.281086</td>\n",
" <td>64.249032</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>3</td>\n",
" <td>44.20</td>\n",
" <td>4.354578</td>\n",
" <td>320.090829</td>\n",
" <td>5.815576</td>\n",
" <td>4.340039</td>\n",
" <td>1.500977</td>\n",
" <td>1.999374</td>\n",
" <td>1.801408</td>\n",
" <td>5.584963</td>\n",
" <td>2.823074</td>\n",
" <td>1.927675</td>\n",
" <td>6.039783</td>\n",
" <td>4.290141</td>\n",
" <td>1.000224</td>\n",
" <td>0.639389</td>\n",
" <td>9.629758</td>\n",
" <td>20.313600</td>\n",
" <td>33.891081</td>\n",
" <td>35.419021</td>\n",
" <td>45.605908</td>\n",
" <td>47.883250</td>\n",
" <td>40.405114</td>\n",
" <td>1.000000</td>\n",
" <td>1.746</td>\n",
" <td>7</td>\n",
" <td>348.125612</td>\n",
" <td>59.5176</td>\n",
" <td>-2.4383</td>\n",
" <td>5.945307</td>\n",
" <td>0.714497</td>\n",
" <td>0.466667</td>\n",
" <td>-0.165511</td>\n",
" <td>-0.033672</td>\n",
" <td>-0.142792</td>\n",
" <td>0.518029</td>\n",
" <td>13.730417</td>\n",
" <td>17.579140</td>\n",
" <td>11.446726</td>\n",
" <td>10.216486</td>\n",
" <td>...</td>\n",
" <td>22.708105</td>\n",
" <td>0.875000</td>\n",
" <td>36</td>\n",
" <td>1543</td>\n",
" <td>1.890403</td>\n",
" <td>11.715539</td>\n",
" <td>1.894849</td>\n",
" <td>2.34</td>\n",
" <td>10.560011</td>\n",
" <td>118</td>\n",
" <td>12.336644</td>\n",
" <td>6</td>\n",
" <td>4.341669</td>\n",
" <td>6</td>\n",
" <td>0.541667</td>\n",
" <td>15</td>\n",
" <td>0.185395</td>\n",
" <td>9</td>\n",
" <td>25</td>\n",
" <td>7.007819</td>\n",
" <td>1</td>\n",
" <td>8.182428</td>\n",
" <td>0.106835</td>\n",
" <td>6.065555</td>\n",
" <td>0.140810</td>\n",
" <td>44</td>\n",
" <td>73.08</td>\n",
" <td>32.598140</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>47.698640</td>\n",
" <td>1.987443</td>\n",
" <td>111.01</td>\n",
" <td>1</td>\n",
" <td>5.761905</td>\n",
" <td>561</td>\n",
" <td>1</td>\n",
" <td>0.079271</td>\n",
" <td>51.201860</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>2</td>\n",
" <td>42.95</td>\n",
" <td>4.367037</td>\n",
" <td>231.459857</td>\n",
" <td>2.259032</td>\n",
" <td>1.703129</td>\n",
" <td>0.449432</td>\n",
" <td>0.447179</td>\n",
" <td>0.478816</td>\n",
" <td>5.247928</td>\n",
" <td>1.407129</td>\n",
" <td>0.890525</td>\n",
" <td>3.738716</td>\n",
" <td>2.318494</td>\n",
" <td>0.374554</td>\n",
" <td>0.186381</td>\n",
" <td>8.323200</td>\n",
" <td>15.390000</td>\n",
" <td>22.043368</td>\n",
" <td>21.993096</td>\n",
" <td>28.238630</td>\n",
" <td>26.653118</td>\n",
" <td>21.044559</td>\n",
" <td>0.500000</td>\n",
" <td>2.611</td>\n",
" <td>4</td>\n",
" <td>256.084792</td>\n",
" <td>19.9165</td>\n",
" <td>-1.1831</td>\n",
" <td>1.399726</td>\n",
" <td>0.300985</td>\n",
" <td>0.461538</td>\n",
" <td>-0.268114</td>\n",
" <td>-0.079532</td>\n",
" <td>0.136891</td>\n",
" <td>0.553795</td>\n",
" <td>10.075218</td>\n",
" <td>13.501789</td>\n",
" <td>9.275188</td>\n",
" <td>7.717260</td>\n",
" <td>...</td>\n",
" <td>14.136882</td>\n",
" <td>0.857143</td>\n",
" <td>23</td>\n",
" <td>854</td>\n",
" <td>0.901048</td>\n",
" <td>6.071686</td>\n",
" <td>1.486748</td>\n",
" <td>2.45</td>\n",
" <td>11.431898</td>\n",
" <td>90</td>\n",
" <td>10.254921</td>\n",
" <td>6</td>\n",
" <td>3.591645</td>\n",
" <td>12</td>\n",
" <td>0.842105</td>\n",
" <td>9</td>\n",
" <td>0.185395</td>\n",
" <td>8</td>\n",
" <td>20</td>\n",
" <td>2.653079</td>\n",
" <td>1</td>\n",
" <td>6.071838</td>\n",
" <td>0.052623</td>\n",
" <td>8.755445</td>\n",
" <td>0.190020</td>\n",
" <td>31</td>\n",
" <td>58.05</td>\n",
" <td>18.930484</td>\n",
" <td>3</td>\n",
" <td>8</td>\n",
" <td>38.286112</td>\n",
" <td>2.015059</td>\n",
" <td>68.29</td>\n",
" <td>1</td>\n",
" <td>5.479191</td>\n",
" <td>397</td>\n",
" <td>1</td>\n",
" <td>0.039800</td>\n",
" <td>37.247516</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>2g</td>\n",
" <td>39.60</td>\n",
" <td>4.402305</td>\n",
" <td>297.957438</td>\n",
" <td>4.251195</td>\n",
" <td>3.245849</td>\n",
" <td>1.091041</td>\n",
" <td>1.345021</td>\n",
" <td>1.416636</td>\n",
" <td>5.643856</td>\n",
" <td>2.970982</td>\n",
" <td>1.832412</td>\n",
" <td>6.067345</td>\n",
" <td>4.293582</td>\n",
" <td>1.064180</td>\n",
" <td>0.622551</td>\n",
" <td>9.796296</td>\n",
" <td>19.753086</td>\n",
" <td>34.891081</td>\n",
" <td>33.301568</td>\n",
" <td>45.522787</td>\n",
" <td>41.631410</td>\n",
" <td>37.663999</td>\n",
" <td>1.650964</td>\n",
" <td>5.410</td>\n",
" <td>3</td>\n",
" <td>356.094312</td>\n",
" <td>30.3115</td>\n",
" <td>0.3697</td>\n",
" <td>0.136678</td>\n",
" <td>0.588557</td>\n",
" <td>0.500000</td>\n",
" <td>-0.186755</td>\n",
" <td>0.004351</td>\n",
" <td>0.057985</td>\n",
" <td>0.382532</td>\n",
" <td>14.098821</td>\n",
" <td>17.648054</td>\n",
" <td>12.152198</td>\n",
" <td>10.595843</td>\n",
" <td>...</td>\n",
" <td>23.040385</td>\n",
" <td>1.000000</td>\n",
" <td>34</td>\n",
" <td>1845</td>\n",
" <td>1.445706</td>\n",
" <td>12.325901</td>\n",
" <td>3.293508</td>\n",
" <td>2.45</td>\n",
" <td>15.252178</td>\n",
" <td>126</td>\n",
" <td>9.373062</td>\n",
" <td>7</td>\n",
" <td>5.144109</td>\n",
" <td>17</td>\n",
" <td>0.800000</td>\n",
" <td>14</td>\n",
" <td>0.318041</td>\n",
" <td>11</td>\n",
" <td>27</td>\n",
" <td>4.992004</td>\n",
" <td>2</td>\n",
" <td>8.708141</td>\n",
" <td>0.134612</td>\n",
" <td>8.354099</td>\n",
" <td>0.417339</td>\n",
" <td>41</td>\n",
" <td>129.08</td>\n",
" <td>24.263312</td>\n",
" <td>6</td>\n",
" <td>9</td>\n",
" <td>50.882780</td>\n",
" <td>2.035311</td>\n",
" <td>117.56</td>\n",
" <td>2</td>\n",
" <td>5.736296</td>\n",
" <td>656</td>\n",
" <td>2</td>\n",
" <td>0.149685</td>\n",
" <td>50.294688</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>13</td>\n",
" <td>38.70</td>\n",
" <td>4.412289</td>\n",
" <td>539.664627</td>\n",
" <td>13.759328</td>\n",
" <td>8.694906</td>\n",
" <td>2.778109</td>\n",
" <td>4.420546</td>\n",
" <td>3.681125</td>\n",
" <td>6.392317</td>\n",
" <td>5.124636</td>\n",
" <td>3.527353</td>\n",
" <td>10.004208</td>\n",
" <td>7.402539</td>\n",
" <td>1.950002</td>\n",
" <td>1.211774</td>\n",
" <td>15.526627</td>\n",
" <td>34.865185</td>\n",
" <td>55.348938</td>\n",
" <td>57.743937</td>\n",
" <td>80.563547</td>\n",
" <td>95.833984</td>\n",
" <td>96.154889</td>\n",
" <td>0.000000</td>\n",
" <td>3.414</td>\n",
" <td>10</td>\n",
" <td>593.194420</td>\n",
" <td>100.3708</td>\n",
" <td>-3.1154</td>\n",
" <td>9.705717</td>\n",
" <td>1.238497</td>\n",
" <td>0.473684</td>\n",
" <td>-0.506172</td>\n",
" <td>0.069154</td>\n",
" <td>-0.129786</td>\n",
" <td>1.070630</td>\n",
" <td>23.658991</td>\n",
" <td>30.603719</td>\n",
" <td>20.042480</td>\n",
" <td>18.074585</td>\n",
" <td>...</td>\n",
" <td>36.815773</td>\n",
" <td>0.900000</td>\n",
" <td>78</td>\n",
" <td>6313</td>\n",
" <td>3.285753</td>\n",
" <td>14.993139</td>\n",
" <td>17.782459</td>\n",
" <td>3.22</td>\n",
" <td>27.887102</td>\n",
" <td>220</td>\n",
" <td>14.603161</td>\n",
" <td>9</td>\n",
" <td>10.135902</td>\n",
" <td>12</td>\n",
" <td>0.642857</td>\n",
" <td>33</td>\n",
" <td>0.290474</td>\n",
" <td>13</td>\n",
" <td>45</td>\n",
" <td>19.803764</td>\n",
" <td>2</td>\n",
" <td>15.846321</td>\n",
" <td>0.144866</td>\n",
" <td>4.349062</td>\n",
" <td>0.465467</td>\n",
" <td>73</td>\n",
" <td>303.13</td>\n",
" <td>50.073417</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>84.529674</td>\n",
" <td>2.012611</td>\n",
" <td>184.00</td>\n",
" <td>2</td>\n",
" <td>7.703704</td>\n",
" <td>1306</td>\n",
" <td>0</td>\n",
" <td>0.152865</td>\n",
" <td>85.724583</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>16</td>\n",
" <td>36.40</td>\n",
" <td>4.438899</td>\n",
" <td>381.615845</td>\n",
" <td>9.608967</td>\n",
" <td>6.381825</td>\n",
" <td>2.288374</td>\n",
" <td>3.297198</td>\n",
" <td>2.866106</td>\n",
" <td>5.857981</td>\n",
" <td>3.998572</td>\n",
" <td>2.688634</td>\n",
" <td>7.914592</td>\n",
" <td>5.846841</td>\n",
" <td>1.411164</td>\n",
" <td>0.824078</td>\n",
" <td>10.080000</td>\n",
" <td>23.658689</td>\n",
" <td>39.611042</td>\n",
" <td>41.917567</td>\n",
" <td>57.796798</td>\n",
" <td>65.236869</td>\n",
" <td>57.588797</td>\n",
" <td>0.000000</td>\n",
" <td>0.238</td>\n",
" <td>9</td>\n",
" <td>418.178710</td>\n",
" <td>76.5212</td>\n",
" <td>-4.3238</td>\n",
" <td>18.695246</td>\n",
" <td>1.077593</td>\n",
" <td>0.466667</td>\n",
" <td>-0.185400</td>\n",
" <td>0.021727</td>\n",
" <td>-0.318584</td>\n",
" <td>0.604324</td>\n",
" <td>16.564382</td>\n",
" <td>21.181434</td>\n",
" <td>13.751256</td>\n",
" <td>12.766335</td>\n",
" <td>...</td>\n",
" <td>28.433372</td>\n",
" <td>0.875000</td>\n",
" <td>51</td>\n",
" <td>2438</td>\n",
" <td>2.537748</td>\n",
" <td>17.370932</td>\n",
" <td>6.325624</td>\n",
" <td>2.45</td>\n",
" <td>15.001023</td>\n",
" <td>152</td>\n",
" <td>12.092667</td>\n",
" <td>4</td>\n",
" <td>6.139810</td>\n",
" <td>6</td>\n",
" <td>0.724138</td>\n",
" <td>15</td>\n",
" <td>0.230756</td>\n",
" <td>10</td>\n",
" <td>31</td>\n",
" <td>12.350433</td>\n",
" <td>2</td>\n",
" <td>10.957567</td>\n",
" <td>0.137264</td>\n",
" <td>6.062893</td>\n",
" <td>0.341043</td>\n",
" <td>55</td>\n",
" <td>149.10</td>\n",
" <td>39.157382</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>58.158264</td>\n",
" <td>2.005457</td>\n",
" <td>154.26</td>\n",
" <td>2</td>\n",
" <td>5.257778</td>\n",
" <td>717</td>\n",
" <td>0</td>\n",
" <td>0.155652</td>\n",
" <td>62.682618</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>14</td>\n",
" <td>34.40</td>\n",
" <td>4.463442</td>\n",
" <td>550.376918</td>\n",
" <td>13.431626</td>\n",
" <td>8.709563</td>\n",
" <td>3.028242</td>\n",
" <td>4.464448</td>\n",
" <td>3.797621</td>\n",
" <td>6.392317</td>\n",
" <td>5.217743</td>\n",
" <td>3.563706</td>\n",
" <td>10.558881</td>\n",
" <td>7.606519</td>\n",
" <td>2.017229</td>\n",
" <td>1.262559</td>\n",
" <td>15.526627</td>\n",
" <td>34.865185</td>\n",
" <td>54.159980</td>\n",
" <td>57.246207</td>\n",
" <td>79.567543</td>\n",
" <td>93.063511</td>\n",
" <td>93.992703</td>\n",
" <td>0.000000</td>\n",
" <td>4.631</td>\n",
" <td>11</td>\n",
" <td>590.231139</td>\n",
" <td>104.7818</td>\n",
" <td>-2.3855</td>\n",
" <td>5.690610</td>\n",
" <td>1.413164</td>\n",
" <td>0.500000</td>\n",
" <td>-0.455507</td>\n",
" <td>0.152124</td>\n",
" <td>-0.225297</td>\n",
" <td>0.905598</td>\n",
" <td>24.328093</td>\n",
" <td>30.603719</td>\n",
" <td>20.004475</td>\n",
" <td>18.274718</td>\n",
" <td>...</td>\n",
" <td>34.524106</td>\n",
" <td>1.000000</td>\n",
" <td>77</td>\n",
" <td>6414</td>\n",
" <td>3.383385</td>\n",
" <td>18.028769</td>\n",
" <td>15.291787</td>\n",
" <td>3.44</td>\n",
" <td>28.576240</td>\n",
" <td>220</td>\n",
" <td>16.386445</td>\n",
" <td>9</td>\n",
" <td>9.964897</td>\n",
" <td>12</td>\n",
" <td>0.642857</td>\n",
" <td>32</td>\n",
" <td>0.305766</td>\n",
" <td>13</td>\n",
" <td>45</td>\n",
" <td>19.130426</td>\n",
" <td>1</td>\n",
" <td>15.678213</td>\n",
" <td>0.148588</td>\n",
" <td>4.349740</td>\n",
" <td>0.406254</td>\n",
" <td>76</td>\n",
" <td>303.12</td>\n",
" <td>53.417038</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>84.517148</td>\n",
" <td>2.012313</td>\n",
" <td>157.78</td>\n",
" <td>2</td>\n",
" <td>7.877793</td>\n",
" <td>1349</td>\n",
" <td>0</td>\n",
" <td>0.146569</td>\n",
" <td>88.980962</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>2b</td>\n",
" <td>33.50</td>\n",
" <td>4.474955</td>\n",
" <td>271.871227</td>\n",
" <td>3.724375</td>\n",
" <td>2.753050</td>\n",
" <td>0.944432</td>\n",
" <td>1.240642</td>\n",
" <td>1.283548</td>\n",
" <td>5.523562</td>\n",
" <td>2.818117</td>\n",
" <td>1.737501</td>\n",
" <td>5.704869</td>\n",
" <td>3.977352</td>\n",
" <td>0.957261</td>\n",
" <td>0.554211</td>\n",
" <td>8.909091</td>\n",
" <td>17.811200</td>\n",
" <td>32.116612</td>\n",
" <td>30.637384</td>\n",
" <td>41.858603</td>\n",
" <td>36.967226</td>\n",
" <td>34.331907</td>\n",
" <td>1.650964</td>\n",
" <td>6.487</td>\n",
" <td>3</td>\n",
" <td>326.083747</td>\n",
" <td>22.9957</td>\n",
" <td>0.4215</td>\n",
" <td>0.177662</td>\n",
" <td>0.520516</td>\n",
" <td>0.500000</td>\n",
" <td>-0.091668</td>\n",
" <td>0.002166</td>\n",
" <td>0.043691</td>\n",
" <td>0.211935</td>\n",
" <td>12.767923</td>\n",
" <td>16.070703</td>\n",
" <td>11.220347</td>\n",
" <td>9.804879</td>\n",
" <td>...</td>\n",
" <td>20.248053</td>\n",
" <td>1.000000</td>\n",
" <td>30</td>\n",
" <td>1437</td>\n",
" <td>1.241582</td>\n",
" <td>12.320404</td>\n",
" <td>2.546845</td>\n",
" <td>2.45</td>\n",
" <td>13.760829</td>\n",
" <td>116</td>\n",
" <td>11.592077</td>\n",
" <td>6</td>\n",
" <td>4.809782</td>\n",
" <td>17</td>\n",
" <td>0.869565</td>\n",
" <td>13</td>\n",
" <td>0.336770</td>\n",
" <td>11</td>\n",
" <td>25</td>\n",
" <td>4.505315</td>\n",
" <td>2</td>\n",
" <td>7.889209</td>\n",
" <td>0.138910</td>\n",
" <td>8.358012</td>\n",
" <td>0.369227</td>\n",
" <td>37</td>\n",
" <td>119.07</td>\n",
" <td>20.160898</td>\n",
" <td>5</td>\n",
" <td>10</td>\n",
" <td>47.001891</td>\n",
" <td>2.043560</td>\n",
" <td>108.33</td>\n",
" <td>2</td>\n",
" <td>5.234979</td>\n",
" <td>546</td>\n",
" <td>2</td>\n",
" <td>0.140493</td>\n",
" <td>46.399102</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>3</td>\n",
" <td>33.21</td>\n",
" <td>4.478731</td>\n",
" <td>288.828461</td>\n",
" <td>2.480667</td>\n",
" <td>1.932018</td>\n",
" <td>0.532239</td>\n",
" <td>0.507769</td>\n",
" <td>0.550306</td>\n",
" <td>5.523562</td>\n",
" <td>1.637764</td>\n",
" <td>1.032738</td>\n",
" <td>4.794944</td>\n",
" <td>2.662063</td>\n",
" <td>0.488443</td>\n",
" <td>0.259454</td>\n",
" <td>10.780000</td>\n",
" <td>19.326389</td>\n",
" <td>32.476593</td>\n",
" <td>28.189315</td>\n",
" <td>37.991974</td>\n",
" <td>32.960916</td>\n",
" <td>27.881070</td>\n",
" <td>1.119035</td>\n",
" <td>3.228</td>\n",
" <td>6</td>\n",
" <td>329.094646</td>\n",
" <td>39.1071</td>\n",
" <td>-0.7535</td>\n",
" <td>0.567762</td>\n",
" <td>0.477762</td>\n",
" <td>0.500000</td>\n",
" <td>-0.252172</td>\n",
" <td>-0.102909</td>\n",
" <td>0.162259</td>\n",
" <td>0.505804</td>\n",
" <td>12.916278</td>\n",
" <td>16.493353</td>\n",
" <td>11.131030</td>\n",
" <td>9.633762</td>\n",
" <td>...</td>\n",
" <td>22.326986</td>\n",
" <td>1.000000</td>\n",
" <td>27</td>\n",
" <td>1554</td>\n",
" <td>1.309296</td>\n",
" <td>14.333281</td>\n",
" <td>1.922285</td>\n",
" <td>2.23</td>\n",
" <td>12.146713</td>\n",
" <td>108</td>\n",
" <td>10.254921</td>\n",
" <td>8</td>\n",
" <td>4.129102</td>\n",
" <td>12</td>\n",
" <td>0.695652</td>\n",
" <td>13</td>\n",
" <td>0.185395</td>\n",
" <td>8</td>\n",
" <td>24</td>\n",
" <td>2.925378</td>\n",
" <td>3</td>\n",
" <td>6.888335</td>\n",
" <td>0.052623</td>\n",
" <td>-0.257809</td>\n",
" <td>0.190020</td>\n",
" <td>38</td>\n",
" <td>70.08</td>\n",
" <td>22.392105</td>\n",
" <td>3</td>\n",
" <td>8</td>\n",
" <td>46.138507</td>\n",
" <td>2.006022</td>\n",
" <td>133.72</td>\n",
" <td>1</td>\n",
" <td>8.080808</td>\n",
" <td>582</td>\n",
" <td>2</td>\n",
" <td>0.039800</td>\n",
" <td>46.405895</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1d</td>\n",
" <td>28.90</td>\n",
" <td>4.539102</td>\n",
" <td>196.340226</td>\n",
" <td>2.632993</td>\n",
" <td>1.669357</td>\n",
" <td>0.597236</td>\n",
" <td>0.794295</td>\n",
" <td>0.759018</td>\n",
" <td>5.000000</td>\n",
" <td>1.448692</td>\n",
" <td>0.931126</td>\n",
" <td>3.591408</td>\n",
" <td>2.152435</td>\n",
" <td>0.466610</td>\n",
" <td>0.262452</td>\n",
" <td>6.074380</td>\n",
" <td>12.456747</td>\n",
" <td>23.567674</td>\n",
" <td>19.860675</td>\n",
" <td>27.583982</td>\n",
" <td>24.470527</td>\n",
" <td>19.999241</td>\n",
" <td>0.965489</td>\n",
" <td>3.296</td>\n",
" <td>4</td>\n",
" <td>230.062617</td>\n",
" <td>25.4845</td>\n",
" <td>0.2372</td>\n",
" <td>0.056264</td>\n",
" <td>0.396829</td>\n",
" <td>0.444444</td>\n",
" <td>-0.057619</td>\n",
" <td>-0.033045</td>\n",
" <td>0.032518</td>\n",
" <td>0.146137</td>\n",
" <td>9.237974</td>\n",
" <td>11.380469</td>\n",
" <td>7.770857</td>\n",
" <td>6.724125</td>\n",
" <td>...</td>\n",
" <td>13.769534</td>\n",
" <td>0.800000</td>\n",
" <td>21</td>\n",
" <td>467</td>\n",
" <td>0.877664</td>\n",
" <td>11.381677</td>\n",
" <td>2.406852</td>\n",
" <td>2.12</td>\n",
" <td>10.457144</td>\n",
" <td>78</td>\n",
" <td>7.829693</td>\n",
" <td>3</td>\n",
" <td>3.349967</td>\n",
" <td>10</td>\n",
" <td>0.625000</td>\n",
" <td>16</td>\n",
" <td>0.151375</td>\n",
" <td>6</td>\n",
" <td>17</td>\n",
" <td>3.455473</td>\n",
" <td>2</td>\n",
" <td>5.079589</td>\n",
" <td>0.046412</td>\n",
" <td>8.800059</td>\n",
" <td>0.251376</td>\n",
" <td>26</td>\n",
" <td>49.05</td>\n",
" <td>13.392070</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>32.395768</td>\n",
" <td>2.024735</td>\n",
" <td>95.39</td>\n",
" <td>2</td>\n",
" <td>3.495199</td>\n",
" <td>238</td>\n",
" <td>1</td>\n",
" <td>0.058586</td>\n",
" <td>33.327930</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>9</td>\n",
" <td>27.26</td>\n",
" <td>4.564474</td>\n",
" <td>415.817490</td>\n",
" <td>5.336093</td>\n",
" <td>3.763489</td>\n",
" <td>1.633801</td>\n",
" <td>1.779719</td>\n",
" <td>1.912557</td>\n",
" <td>6.044394</td>\n",
" <td>3.378222</td>\n",
" <td>2.034323</td>\n",
" <td>8.067090</td>\n",
" <td>5.177308</td>\n",
" <td>1.028078</td>\n",
" <td>0.583081</td>\n",
" <td>14.533081</td>\n",
" <td>27.585306</td>\n",
" <td>43.611042</td>\n",
" <td>41.855920</td>\n",
" <td>58.494274</td>\n",
" <td>56.185797</td>\n",
" <td>48.319054</td>\n",
" <td>1.828392</td>\n",
" <td>4.993</td>\n",
" <td>8</td>\n",
" <td>464.163060</td>\n",
" <td>67.1222</td>\n",
" <td>-0.6211</td>\n",
" <td>0.385765</td>\n",
" <td>1.019937</td>\n",
" <td>0.500000</td>\n",
" <td>-0.393961</td>\n",
" <td>-0.098295</td>\n",
" <td>0.151307</td>\n",
" <td>0.794483</td>\n",
" <td>19.296304</td>\n",
" <td>23.631181</td>\n",
" <td>15.901887</td>\n",
" <td>14.166965</td>\n",
" <td>...</td>\n",
" <td>29.497245</td>\n",
" <td>1.000000</td>\n",
" <td>43</td>\n",
" <td>4366</td>\n",
" <td>2.120907</td>\n",
" <td>18.250181</td>\n",
" <td>5.148835</td>\n",
" <td>2.89</td>\n",
" <td>16.462290</td>\n",
" <td>162</td>\n",
" <td>11.124380</td>\n",
" <td>11</td>\n",
" <td>6.484477</td>\n",
" <td>17</td>\n",
" <td>0.727273</td>\n",
" <td>20</td>\n",
" <td>0.405217</td>\n",
" <td>10</td>\n",
" <td>35</td>\n",
" <td>6.538055</td>\n",
" <td>2</td>\n",
" <td>10.691012</td>\n",
" <td>0.189554</td>\n",
" <td>5.097133</td>\n",
" <td>0.495852</td>\n",
" <td>57</td>\n",
" <td>169.10</td>\n",
" <td>38.288968</td>\n",
" <td>6</td>\n",
" <td>8</td>\n",
" <td>66.516908</td>\n",
" <td>2.015664</td>\n",
" <td>137.05</td>\n",
" <td>1</td>\n",
" <td>9.876543</td>\n",
" <td>1172</td>\n",
" <td>2</td>\n",
" <td>0.174431</td>\n",
" <td>68.389032</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>10</td>\n",
" <td>26.90</td>\n",
" <td>4.570248</td>\n",
" <td>360.175595</td>\n",
" <td>5.252780</td>\n",
" <td>3.415318</td>\n",
" <td>1.535917</td>\n",
" <td>1.911560</td>\n",
" <td>1.995515</td>\n",
" <td>5.954196</td>\n",
" <td>3.531165</td>\n",
" <td>2.080873</td>\n",
" <td>7.382967</td>\n",
" <td>5.170796</td>\n",
" <td>1.056018</td>\n",
" <td>0.587101</td>\n",
" <td>12.459259</td>\n",
" <td>24.134948</td>\n",
" <td>41.196553</td>\n",
" <td>40.717626</td>\n",
" <td>57.494818</td>\n",
" <td>52.244851</td>\n",
" <td>47.353746</td>\n",
" <td>3.384715</td>\n",
" <td>5.098</td>\n",
" <td>8</td>\n",
" <td>433.132094</td>\n",
" <td>41.2996</td>\n",
" <td>-0.8356</td>\n",
" <td>0.698227</td>\n",
" <td>0.767362</td>\n",
" <td>0.500000</td>\n",
" <td>-0.311454</td>\n",
" <td>-0.104931</td>\n",
" <td>0.195266</td>\n",
" <td>0.640644</td>\n",
" <td>17.388056</td>\n",
" <td>21.468045</td>\n",
" <td>15.169836</td>\n",
" <td>13.263020</td>\n",
" <td>...</td>\n",
" <td>30.045706</td>\n",
" <td>1.000000</td>\n",
" <td>40</td>\n",
" <td>3609</td>\n",
" <td>1.643623</td>\n",
" <td>21.312246</td>\n",
" <td>5.148835</td>\n",
" <td>2.67</td>\n",
" <td>16.462290</td>\n",
" <td>158</td>\n",
" <td>11.124380</td>\n",
" <td>9</td>\n",
" <td>6.457441</td>\n",
" <td>22</td>\n",
" <td>0.935484</td>\n",
" <td>20</td>\n",
" <td>0.488551</td>\n",
" <td>12</td>\n",
" <td>34</td>\n",
" <td>6.309384</td>\n",
" <td>3</td>\n",
" <td>10.766081</td>\n",
" <td>0.208188</td>\n",
" <td>5.645319</td>\n",
" <td>0.586619</td>\n",
" <td>50</td>\n",
" <td>226.10</td>\n",
" <td>30.544933</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>63.637792</td>\n",
" <td>2.052832</td>\n",
" <td>145.42</td>\n",
" <td>1</td>\n",
" <td>7.500000</td>\n",
" <td>1056</td>\n",
" <td>2</td>\n",
" <td>0.207904</td>\n",
" <td>61.833067</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>4a</td>\n",
" <td>25.78</td>\n",
" <td>4.588717</td>\n",
" <td>370.137586</td>\n",
" <td>4.358332</td>\n",
" <td>2.971052</td>\n",
" <td>1.029414</td>\n",
" <td>1.280119</td>\n",
" <td>1.324602</td>\n",
" <td>5.954196</td>\n",
" <td>3.311760</td>\n",
" <td>2.072493</td>\n",
" <td>7.252894</td>\n",
" <td>4.876910</td>\n",
" <td>1.065631</td>\n",
" <td>0.619705</td>\n",
" <td>13.032025</td>\n",
" <td>24.134948</td>\n",
" <td>40.476593</td>\n",
" <td>40.025282</td>\n",
" <td>53.994123</td>\n",
" <td>48.295429</td>\n",
" <td>44.051550</td>\n",
" <td>1.828392</td>\n",
" <td>7.409</td>\n",
" <td>6</td>\n",
" <td>429.125946</td>\n",
" <td>32.2671</td>\n",
" <td>-0.8547</td>\n",
" <td>0.730512</td>\n",
" <td>0.585799</td>\n",
" <td>0.476190</td>\n",
" <td>-0.318275</td>\n",
" <td>-0.067591</td>\n",
" <td>0.190554</td>\n",
" <td>0.579650</td>\n",
" <td>17.250243</td>\n",
" <td>21.304908</td>\n",
" <td>15.259153</td>\n",
" <td>13.077163</td>\n",
" <td>...</td>\n",
" <td>24.062332</td>\n",
" <td>0.909091</td>\n",
" <td>40</td>\n",
" <td>3675</td>\n",
" <td>1.438505</td>\n",
" <td>15.362682</td>\n",
" <td>3.620363</td>\n",
" <td>3.11</td>\n",
" <td>19.717256</td>\n",
" <td>156</td>\n",
" <td>17.677750</td>\n",
" <td>9</td>\n",
" <td>6.674331</td>\n",
" <td>23</td>\n",
" <td>0.967742</td>\n",
" <td>21</td>\n",
" <td>0.438832</td>\n",
" <td>14</td>\n",
" <td>34</td>\n",
" <td>5.223720</td>\n",
" <td>2</td>\n",
" <td>10.617518</td>\n",
" <td>0.163755</td>\n",
" <td>5.680282</td>\n",
" <td>0.452209</td>\n",
" <td>50</td>\n",
" <td>226.08</td>\n",
" <td>29.884933</td>\n",
" <td>6</td>\n",
" <td>14</td>\n",
" <td>63.884062</td>\n",
" <td>2.060776</td>\n",
" <td>116.74</td>\n",
" <td>2</td>\n",
" <td>8.065844</td>\n",
" <td>1097</td>\n",
" <td>2</td>\n",
" <td>0.138923</td>\n",
" <td>63.153067</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1c</td>\n",
" <td>24.70</td>\n",
" <td>4.607303</td>\n",
" <td>179.280873</td>\n",
" <td>1.159079</td>\n",
" <td>1.129936</td>\n",
" <td>0.425651</td>\n",
" <td>0.369643</td>\n",
" <td>0.356262</td>\n",
" <td>4.700440</td>\n",
" <td>0.875654</td>\n",
" <td>0.596169</td>\n",
" <td>3.084763</td>\n",
" <td>1.557001</td>\n",
" <td>0.265702</td>\n",
" <td>0.097817</td>\n",
" <td>5.671875</td>\n",
" <td>11.076923</td>\n",
" <td>20.207694</td>\n",
" <td>15.528311</td>\n",
" <td>21.085437</td>\n",
" <td>15.971981</td>\n",
" <td>11.500695</td>\n",
" <td>1.000000</td>\n",
" <td>4.020</td>\n",
" <td>3</td>\n",
" <td>193.067368</td>\n",
" <td>30.9866</td>\n",
" <td>0.8792</td>\n",
" <td>0.772993</td>\n",
" <td>0.439668</td>\n",
" <td>0.444444</td>\n",
" <td>-0.029086</td>\n",
" <td>-0.036543</td>\n",
" <td>0.028859</td>\n",
" <td>0.082948</td>\n",
" <td>8.136060</td>\n",
" <td>9.681798</td>\n",
" <td>6.181541</td>\n",
" <td>5.450648</td>\n",
" <td>...</td>\n",
" <td>10.633331</td>\n",
" <td>0.800000</td>\n",
" <td>13</td>\n",
" <td>292</td>\n",
" <td>0.901048</td>\n",
" <td>8.247870</td>\n",
" <td>0.685007</td>\n",
" <td>2.01</td>\n",
" <td>6.713078</td>\n",
" <td>58</td>\n",
" <td>4.883593</td>\n",
" <td>3</td>\n",
" <td>1.911231</td>\n",
" <td>6</td>\n",
" <td>0.461538</td>\n",
" <td>12</td>\n",
" <td>0.083333</td>\n",
" <td>4</td>\n",
" <td>13</td>\n",
" <td>1.341334</td>\n",
" <td>2</td>\n",
" <td>3.529275</td>\n",
" <td>0.027778</td>\n",
" <td>8.871875</td>\n",
" <td>0.142259</td>\n",
" <td>24</td>\n",
" <td>13.04</td>\n",
" <td>13.165277</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>25.397763</td>\n",
" <td>1.953674</td>\n",
" <td>82.50</td>\n",
" <td>2</td>\n",
" <td>4.687500</td>\n",
" <td>178</td>\n",
" <td>1</td>\n",
" <td>0.043815</td>\n",
" <td>29.374723</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>8</td>\n",
" <td>23.19</td>\n",
" <td>4.634699</td>\n",
" <td>355.569235</td>\n",
" <td>5.058077</td>\n",
" <td>3.473408</td>\n",
" <td>1.589813</td>\n",
" <td>1.639502</td>\n",
" <td>1.920349</td>\n",
" <td>5.857981</td>\n",
" <td>3.158888</td>\n",
" <td>1.796423</td>\n",
" <td>6.979677</td>\n",
" <td>4.835496</td>\n",
" <td>0.841392</td>\n",
" <td>0.444291</td>\n",
" <td>12.142772</td>\n",
" <td>23.658689</td>\n",
" <td>39.251062</td>\n",
" <td>37.357374</td>\n",
" <td>53.328092</td>\n",
" <td>50.687523</td>\n",
" <td>39.929625</td>\n",
" <td>1.828392</td>\n",
" <td>4.426</td>\n",
" <td>7</td>\n",
" <td>409.120861</td>\n",
" <td>48.7700</td>\n",
" <td>-0.6691</td>\n",
" <td>0.447695</td>\n",
" <td>0.804874</td>\n",
" <td>0.473684</td>\n",
" <td>-0.332614</td>\n",
" <td>-0.117021</td>\n",
" <td>0.195124</td>\n",
" <td>0.709133</td>\n",
" <td>16.694390</td>\n",
" <td>20.639617</td>\n",
" <td>14.008040</td>\n",
" <td>12.462500</td>\n",
" <td>...</td>\n",
" <td>26.347127</td>\n",
" <td>0.900000</td>\n",
" <td>38</td>\n",
" <td>3008</td>\n",
" <td>1.810290</td>\n",
" <td>15.254824</td>\n",
" <td>5.148835</td>\n",
" <td>2.67</td>\n",
" <td>13.695531</td>\n",
" <td>144</td>\n",
" <td>10.254921</td>\n",
" <td>9</td>\n",
" <td>5.682168</td>\n",
" <td>17</td>\n",
" <td>0.827586</td>\n",
" <td>17</td>\n",
" <td>0.405217</td>\n",
" <td>10</td>\n",
" <td>31</td>\n",
" <td>5.726235</td>\n",
" <td>2</td>\n",
" <td>9.617056</td>\n",
" <td>0.189554</td>\n",
" <td>6.473878</td>\n",
" <td>0.512124</td>\n",
" <td>48</td>\n",
" <td>149.09</td>\n",
" <td>30.842933</td>\n",
" <td>6</td>\n",
" <td>8</td>\n",
" <td>58.684243</td>\n",
" <td>2.023595</td>\n",
" <td>133.81</td>\n",
" <td>1</td>\n",
" <td>7.883382</td>\n",
" <td>908</td>\n",
" <td>2</td>\n",
" <td>0.188899</td>\n",
" <td>58.675067</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4b</td>\n",
" <td>22.84</td>\n",
" <td>4.641304</td>\n",
" <td>385.348654</td>\n",
" <td>4.707788</td>\n",
" <td>3.379300</td>\n",
" <td>1.247632</td>\n",
" <td>1.495667</td>\n",
" <td>1.489262</td>\n",
" <td>6.000000</td>\n",
" <td>3.449484</td>\n",
" <td>2.229658</td>\n",
" <td>7.830198</td>\n",
" <td>5.199319</td>\n",
" <td>1.201516</td>\n",
" <td>0.686789</td>\n",
" <td>13.185255</td>\n",
" <td>25.103673</td>\n",
" <td>49.189543</td>\n",
" <td>42.977053</td>\n",
" <td>59.897665</td>\n",
" <td>54.198970</td>\n",
" <td>47.003321</td>\n",
" <td>1.828392</td>\n",
" <td>6.872</td>\n",
" <td>6</td>\n",
" <td>463.086974</td>\n",
" <td>37.8827</td>\n",
" <td>-0.1104</td>\n",
" <td>0.012188</td>\n",
" <td>0.774781</td>\n",
" <td>0.500000</td>\n",
" <td>-0.330896</td>\n",
" <td>-0.072794</td>\n",
" <td>0.195165</td>\n",
" <td>0.619559</td>\n",
" <td>18.306786</td>\n",
" <td>22.175151</td>\n",
" <td>15.653000</td>\n",
" <td>13.699025</td>\n",
" <td>...</td>\n",
" <td>26.587981</td>\n",
" <td>1.000000</td>\n",
" <td>42</td>\n",
" <td>4030</td>\n",
" <td>1.727180</td>\n",
" <td>15.364217</td>\n",
" <td>4.414596</td>\n",
" <td>3.00</td>\n",
" <td>20.960124</td>\n",
" <td>162</td>\n",
" <td>15.604046</td>\n",
" <td>9</td>\n",
" <td>6.898359</td>\n",
" <td>23</td>\n",
" <td>0.937500</td>\n",
" <td>21</td>\n",
" <td>0.420103</td>\n",
" <td>14</td>\n",
" <td>35</td>\n",
" <td>5.721089</td>\n",
" <td>2</td>\n",
" <td>11.028201</td>\n",
" <td>0.159458</td>\n",
" <td>5.562080</td>\n",
" <td>0.524729</td>\n",
" <td>50</td>\n",
" <td>233.09</td>\n",
" <td>29.211726</td>\n",
" <td>7</td>\n",
" <td>13</td>\n",
" <td>65.742337</td>\n",
" <td>2.054448</td>\n",
" <td>116.74</td>\n",
" <td>2</td>\n",
" <td>8.322704</td>\n",
" <td>1174</td>\n",
" <td>2</td>\n",
" <td>0.168272</td>\n",
" <td>64.666274</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>15</td>\n",
" <td>20.60</td>\n",
" <td>4.686133</td>\n",
" <td>519.999257</td>\n",
" <td>12.787512</td>\n",
" <td>8.077371</td>\n",
" <td>2.753124</td>\n",
" <td>4.360154</td>\n",
" <td>3.580642</td>\n",
" <td>6.321928</td>\n",
" <td>5.034047</td>\n",
" <td>3.537934</td>\n",
" <td>10.060908</td>\n",
" <td>7.319015</td>\n",
" <td>1.951999</td>\n",
" <td>1.195556</td>\n",
" <td>14.650364</td>\n",
" <td>32.904273</td>\n",
" <td>59.512950</td>\n",
" <td>56.699432</td>\n",
" <td>80.138720</td>\n",
" <td>92.634688</td>\n",
" <td>91.778292</td>\n",
" <td>0.000000</td>\n",
" <td>5.128</td>\n",
" <td>10</td>\n",
" <td>581.149968</td>\n",
" <td>96.1060</td>\n",
" <td>-1.8590</td>\n",
" <td>3.455881</td>\n",
" <td>1.304004</td>\n",
" <td>0.473684</td>\n",
" <td>-0.405801</td>\n",
" <td>0.136399</td>\n",
" <td>-0.228441</td>\n",
" <td>0.851872</td>\n",
" <td>23.014772</td>\n",
" <td>29.026369</td>\n",
" <td>19.093791</td>\n",
" <td>17.375793</td>\n",
" <td>...</td>\n",
" <td>34.010847</td>\n",
" <td>0.900000</td>\n",
" <td>73</td>\n",
" <td>5564</td>\n",
" <td>3.172060</td>\n",
" <td>14.990835</td>\n",
" <td>15.291787</td>\n",
" <td>3.22</td>\n",
" <td>28.576240</td>\n",
" <td>210</td>\n",
" <td>16.386445</td>\n",
" <td>8</td>\n",
" <td>9.760955</td>\n",
" <td>12</td>\n",
" <td>0.675000</td>\n",
" <td>31</td>\n",
" <td>0.305766</td>\n",
" <td>13</td>\n",
" <td>43</td>\n",
" <td>18.686022</td>\n",
" <td>1</td>\n",
" <td>14.979421</td>\n",
" <td>0.148588</td>\n",
" <td>4.350582</td>\n",
" <td>0.441475</td>\n",
" <td>68</td>\n",
" <td>289.12</td>\n",
" <td>45.297796</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>80.656719</td>\n",
" <td>2.016418</td>\n",
" <td>154.54</td>\n",
" <td>2</td>\n",
" <td>7.394879</td>\n",
" <td>1234</td>\n",
" <td>0</td>\n",
" <td>0.165644</td>\n",
" <td>82.540204</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>5</td>\n",
" <td>18.51</td>\n",
" <td>4.732594</td>\n",
" <td>317.217739</td>\n",
" <td>3.403256</td>\n",
" <td>2.420660</td>\n",
" <td>0.791041</td>\n",
" <td>0.707142</td>\n",
" <td>0.921848</td>\n",
" <td>5.700440</td>\n",
" <td>2.550204</td>\n",
" <td>1.395245</td>\n",
" <td>6.054285</td>\n",
" <td>3.962134</td>\n",
" <td>0.625876</td>\n",
" <td>0.355697</td>\n",
" <td>11.111111</td>\n",
" <td>20.727041</td>\n",
" <td>36.251062</td>\n",
" <td>34.357374</td>\n",
" <td>46.713495</td>\n",
" <td>40.181771</td>\n",
" <td>31.766896</td>\n",
" <td>1.828392</td>\n",
" <td>3.569</td>\n",
" <td>7</td>\n",
" <td>369.089561</td>\n",
" <td>46.9703</td>\n",
" <td>-1.3640</td>\n",
" <td>1.860496</td>\n",
" <td>0.502465</td>\n",
" <td>0.500000</td>\n",
" <td>-0.375680</td>\n",
" <td>-0.044311</td>\n",
" <td>0.140039</td>\n",
" <td>0.710470</td>\n",
" <td>14.401497</td>\n",
" <td>18.192024</td>\n",
" <td>12.686673</td>\n",
" <td>11.024165</td>\n",
" <td>...</td>\n",
" <td>26.324756</td>\n",
" <td>1.000000</td>\n",
" <td>31</td>\n",
" <td>2223</td>\n",
" <td>1.393847</td>\n",
" <td>15.193994</td>\n",
" <td>2.598489</td>\n",
" <td>2.34</td>\n",
" <td>13.714599</td>\n",
" <td>128</td>\n",
" <td>10.767275</td>\n",
" <td>8</td>\n",
" <td>5.050200</td>\n",
" <td>12</td>\n",
" <td>0.923077</td>\n",
" <td>14</td>\n",
" <td>0.386580</td>\n",
" <td>8</td>\n",
" <td>28</td>\n",
" <td>3.698731</td>\n",
" <td>2</td>\n",
" <td>8.522649</td>\n",
" <td>0.140564</td>\n",
" <td>6.825824</td>\n",
" <td>0.332279</td>\n",
" <td>41</td>\n",
" <td>134.09</td>\n",
" <td>26.470105</td>\n",
" <td>3</td>\n",
" <td>8</td>\n",
" <td>52.957746</td>\n",
" <td>2.036836</td>\n",
" <td>130.34</td>\n",
" <td>1</td>\n",
" <td>7.510204</td>\n",
" <td>769</td>\n",
" <td>2</td>\n",
" <td>0.081215</td>\n",
" <td>50.727895</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>6a</td>\n",
" <td>15.42</td>\n",
" <td>4.811916</td>\n",
" <td>421.783323</td>\n",
" <td>5.219036</td>\n",
" <td>3.784541</td>\n",
" <td>1.436102</td>\n",
" <td>1.687593</td>\n",
" <td>1.691730</td>\n",
" <td>6.087463</td>\n",
" <td>3.610858</td>\n",
" <td>2.331738</td>\n",
" <td>8.264959</td>\n",
" <td>5.440152</td>\n",
" <td>1.163475</td>\n",
" <td>0.709984</td>\n",
" <td>14.074136</td>\n",
" <td>27.046019</td>\n",
" <td>44.251062</td>\n",
" <td>43.357374</td>\n",
" <td>61.383280</td>\n",
" <td>56.349830</td>\n",
" <td>47.770922</td>\n",
" <td>1.828392</td>\n",
" <td>7.851</td>\n",
" <td>7</td>\n",
" <td>471.136511</td>\n",
" <td>57.5567</td>\n",
" <td>-0.4992</td>\n",
" <td>0.249201</td>\n",
" <td>0.923228</td>\n",
" <td>0.478261</td>\n",
" <td>-0.389712</td>\n",
" <td>-0.024710</td>\n",
" <td>0.142438</td>\n",
" <td>0.699457</td>\n",
" <td>19.081141</td>\n",
" <td>23.752502</td>\n",
" <td>16.546847</td>\n",
" <td>14.676308</td>\n",
" <td>...</td>\n",
" <td>26.589644</td>\n",
" <td>0.916667</td>\n",
" <td>45</td>\n",
" <td>4749</td>\n",
" <td>2.000340</td>\n",
" <td>15.296211</td>\n",
" <td>5.687291</td>\n",
" <td>3.22</td>\n",
" <td>22.117813</td>\n",
" <td>172</td>\n",
" <td>15.194382</td>\n",
" <td>9</td>\n",
" <td>7.426040</td>\n",
" <td>18</td>\n",
" <td>0.911765</td>\n",
" <td>22</td>\n",
" <td>0.501037</td>\n",
" <td>12</td>\n",
" <td>37</td>\n",
" <td>6.585752</td>\n",
" <td>2</td>\n",
" <td>11.636683</td>\n",
" <td>0.182113</td>\n",
" <td>2.308890</td>\n",
" <td>0.603870</td>\n",
" <td>55</td>\n",
" <td>247.09</td>\n",
" <td>33.029347</td>\n",
" <td>5</td>\n",
" <td>12</td>\n",
" <td>69.608570</td>\n",
" <td>2.047311</td>\n",
" <td>130.34</td>\n",
" <td>3</td>\n",
" <td>9.119219</td>\n",
" <td>1297</td>\n",
" <td>2</td>\n",
" <td>0.168566</td>\n",
" <td>68.808653</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>6c</td>\n",
" <td>14.90</td>\n",
" <td>4.831208</td>\n",
" <td>423.030846</td>\n",
" <td>8.847693</td>\n",
" <td>5.834256</td>\n",
" <td>3.070704</td>\n",
" <td>3.939992</td>\n",
" <td>3.796514</td>\n",
" <td>6.044394</td>\n",
" <td>4.634115</td>\n",
" <td>3.194148</td>\n",
" <td>9.149880</td>\n",
" <td>7.199860</td>\n",
" <td>2.044606</td>\n",
" <td>1.353629</td>\n",
" <td>11.823145</td>\n",
" <td>26.074074</td>\n",
" <td>42.171121</td>\n",
" <td>42.052038</td>\n",
" <td>62.081743</td>\n",
" <td>67.773316</td>\n",
" <td>66.335389</td>\n",
" <td>0.500000</td>\n",
" <td>8.230</td>\n",
" <td>1</td>\n",
" <td>462.197714</td>\n",
" <td>53.0003</td>\n",
" <td>-0.4063</td>\n",
" <td>0.165080</td>\n",
" <td>1.413469</td>\n",
" <td>0.461538</td>\n",
" <td>-0.288903</td>\n",
" <td>-0.034696</td>\n",
" <td>0.118267</td>\n",
" <td>0.542577</td>\n",
" <td>20.584420</td>\n",
" <td>23.424074</td>\n",
" <td>16.012812</td>\n",
" <td>13.944240</td>\n",
" <td>...</td>\n",
" <td>18.098770</td>\n",
" <td>0.857143</td>\n",
" <td>56</td>\n",
" <td>3091</td>\n",
" <td>2.348772</td>\n",
" <td>6.282993</td>\n",
" <td>12.662750</td>\n",
" <td>3.77</td>\n",
" <td>26.939653</td>\n",
" <td>174</td>\n",
" <td>12.702472</td>\n",
" <td>9</td>\n",
" <td>8.204842</td>\n",
" <td>21</td>\n",
" <td>0.636364</td>\n",
" <td>25</td>\n",
" <td>0.401375</td>\n",
" <td>16</td>\n",
" <td>36</td>\n",
" <td>11.359295</td>\n",
" <td>1</td>\n",
" <td>12.605818</td>\n",
" <td>0.179087</td>\n",
" <td>8.001254</td>\n",
" <td>0.661870</td>\n",
" <td>63</td>\n",
" <td>240.06</td>\n",
" <td>41.484210</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>67.438212</td>\n",
" <td>2.043582</td>\n",
" <td>80.85</td>\n",
" <td>5</td>\n",
" <td>5.877551</td>\n",
" <td>707</td>\n",
" <td>1</td>\n",
" <td>0.237718</td>\n",
" <td>75.029790</td>\n",
" <td>8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>2i</td>\n",
" <td>13.80</td>\n",
" <td>4.860121</td>\n",
" <td>344.765768</td>\n",
" <td>5.683967</td>\n",
" <td>4.188658</td>\n",
" <td>1.320653</td>\n",
" <td>1.552420</td>\n",
" <td>1.635989</td>\n",
" <td>5.906891</td>\n",
" <td>3.381684</td>\n",
" <td>2.084321</td>\n",
" <td>7.037781</td>\n",
" <td>5.020799</td>\n",
" <td>1.231287</td>\n",
" <td>0.707671</td>\n",
" <td>11.227654</td>\n",
" <td>23.168044</td>\n",
" <td>40.665550</td>\n",
" <td>39.965751</td>\n",
" <td>55.851154</td>\n",
" <td>50.682874</td>\n",
" <td>46.549280</td>\n",
" <td>1.650964</td>\n",
" <td>7.014</td>\n",
" <td>3</td>\n",
" <td>420.089226</td>\n",
" <td>31.4694</td>\n",
" <td>0.5902</td>\n",
" <td>0.348336</td>\n",
" <td>0.681006</td>\n",
" <td>0.500000</td>\n",
" <td>-0.255723</td>\n",
" <td>-0.084977</td>\n",
" <td>0.143385</td>\n",
" <td>0.562058</td>\n",
" <td>16.479227</td>\n",
" <td>20.924074</td>\n",
" <td>14.618525</td>\n",
" <td>12.917150</td>\n",
" <td>...</td>\n",
" <td>26.177081</td>\n",
" <td>1.000000</td>\n",
" <td>42</td>\n",
" <td>3180</td>\n",
" <td>1.779039</td>\n",
" <td>12.328380</td>\n",
" <td>5.179029</td>\n",
" <td>2.78</td>\n",
" <td>20.682550</td>\n",
" <td>156</td>\n",
" <td>11.698153</td>\n",
" <td>7</td>\n",
" <td>6.324160</td>\n",
" <td>22</td>\n",
" <td>0.833333</td>\n",
" <td>29</td>\n",
" <td>0.469416</td>\n",
" <td>15</td>\n",
" <td>33</td>\n",
" <td>6.260848</td>\n",
" <td>1</td>\n",
" <td>10.949723</td>\n",
" <td>0.171265</td>\n",
" <td>8.368169</td>\n",
" <td>0.609789</td>\n",
" <td>46</td>\n",
" <td>219.09</td>\n",
" <td>26.839312</td>\n",
" <td>8</td>\n",
" <td>11</td>\n",
" <td>61.578970</td>\n",
" <td>2.052632</td>\n",
" <td>131.03</td>\n",
" <td>2</td>\n",
" <td>6.292509</td>\n",
" <td>997</td>\n",
" <td>1</td>\n",
" <td>0.180092</td>\n",
" <td>58.136688</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>6b</td>\n",
" <td>12.68</td>\n",
" <td>4.896881</td>\n",
" <td>430.573550</td>\n",
" <td>5.396400</td>\n",
" <td>3.869092</td>\n",
" <td>1.390260</td>\n",
" <td>1.595376</td>\n",
" <td>1.680481</td>\n",
" <td>6.129283</td>\n",
" <td>3.648315</td>\n",
" <td>2.285897</td>\n",
" <td>8.127435</td>\n",
" <td>5.478604</td>\n",
" <td>1.180696</td>\n",
" <td>0.703202</td>\n",
" <td>14.810400</td>\n",
" <td>28.019391</td>\n",
" <td>46.025531</td>\n",
" <td>45.021558</td>\n",
" <td>63.047464</td>\n",
" <td>59.014014</td>\n",
" <td>50.103014</td>\n",
" <td>1.828392</td>\n",
" <td>6.029</td>\n",
" <td>7</td>\n",
" <td>487.131425</td>\n",
" <td>59.3704</td>\n",
" <td>-1.1930</td>\n",
" <td>1.423249</td>\n",
" <td>0.824602</td>\n",
" <td>0.500000</td>\n",
" <td>-0.484548</td>\n",
" <td>-0.022173</td>\n",
" <td>0.150624</td>\n",
" <td>0.870126</td>\n",
" <td>19.489389</td>\n",
" <td>24.459608</td>\n",
" <td>17.084851</td>\n",
" <td>14.845410</td>\n",
" <td>...</td>\n",
" <td>29.375339</td>\n",
" <td>1.000000</td>\n",
" <td>47</td>\n",
" <td>5176</td>\n",
" <td>1.915789</td>\n",
" <td>15.297342</td>\n",
" <td>5.687291</td>\n",
" <td>3.11</td>\n",
" <td>22.117813</td>\n",
" <td>176</td>\n",
" <td>15.194382</td>\n",
" <td>10</td>\n",
" <td>7.523671</td>\n",
" <td>18</td>\n",
" <td>0.885714</td>\n",
" <td>23</td>\n",
" <td>0.501037</td>\n",
" <td>13</td>\n",
" <td>38</td>\n",
" <td>6.557156</td>\n",
" <td>2</td>\n",
" <td>12.044931</td>\n",
" <td>0.182113</td>\n",
" <td>2.309467</td>\n",
" <td>0.579463</td>\n",
" <td>56</td>\n",
" <td>254.10</td>\n",
" <td>34.945347</td>\n",
" <td>5</td>\n",
" <td>12</td>\n",
" <td>71.630634</td>\n",
" <td>2.046590</td>\n",
" <td>139.57</td>\n",
" <td>2</td>\n",
" <td>9.356625</td>\n",
" <td>1381</td>\n",
" <td>2</td>\n",
" <td>0.152129</td>\n",
" <td>69.610653</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>6e</td>\n",
" <td>12.27</td>\n",
" <td>4.911155</td>\n",
" <td>385.802418</td>\n",
" <td>7.746355</td>\n",
" <td>5.152185</td>\n",
" <td>2.304603</td>\n",
" <td>3.985831</td>\n",
" <td>3.077660</td>\n",
" <td>5.954196</td>\n",
" <td>4.400754</td>\n",
" <td>3.236828</td>\n",
" <td>8.432694</td>\n",
" <td>6.092575</td>\n",
" <td>2.023894</td>\n",
" <td>1.391892</td>\n",
" <td>10.950521</td>\n",
" <td>24.134948</td>\n",
" <td>40.171121</td>\n",
" <td>39.664758</td>\n",
" <td>58.638929</td>\n",
" <td>62.665332</td>\n",
" <td>66.448702</td>\n",
" <td>0.500000</td>\n",
" <td>6.105</td>\n",
" <td>3</td>\n",
" <td>432.150764</td>\n",
" <td>44.9532</td>\n",
" <td>0.5865</td>\n",
" <td>0.343982</td>\n",
" <td>1.120333</td>\n",
" <td>0.500000</td>\n",
" <td>-0.367613</td>\n",
" <td>0.129895</td>\n",
" <td>-0.109926</td>\n",
" <td>0.595147</td>\n",
" <td>18.747556</td>\n",
" <td>21.957455</td>\n",
" <td>15.011570</td>\n",
" <td>13.344801</td>\n",
" <td>...</td>\n",
" <td>17.521948</td>\n",
" <td>1.000000</td>\n",
" <td>52</td>\n",
" <td>2557</td>\n",
" <td>1.991031</td>\n",
" <td>6.234327</td>\n",
" <td>15.897214</td>\n",
" <td>3.55</td>\n",
" <td>26.805977</td>\n",
" <td>164</td>\n",
" <td>10.902736</td>\n",
" <td>7</td>\n",
" <td>8.028586</td>\n",
" <td>21</td>\n",
" <td>0.677419</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>14</td>\n",
" <td>34</td>\n",
" <td>11.483949</td>\n",
" <td>1</td>\n",
" <td>11.585762</td>\n",
" <td>0.179087</td>\n",
" <td>7.986986</td>\n",
" <td>0.653042</td>\n",
" <td>55</td>\n",
" <td>226.06</td>\n",
" <td>35.286968</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>63.503242</td>\n",
" <td>2.048492</td>\n",
" <td>88.69</td>\n",
" <td>5</td>\n",
" <td>5.399449</td>\n",
" <td>625</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>67.509032</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>1f</td>\n",
" <td>11.00</td>\n",
" <td>4.958607</td>\n",
" <td>237.370432</td>\n",
" <td>3.279483</td>\n",
" <td>2.656824</td>\n",
" <td>0.676869</td>\n",
" <td>0.675690</td>\n",
" <td>0.728605</td>\n",
" <td>5.321928</td>\n",
" <td>1.554822</td>\n",
" <td>0.949655</td>\n",
" <td>4.217356</td>\n",
" <td>2.489722</td>\n",
" <td>0.546469</td>\n",
" <td>0.283616</td>\n",
" <td>7.852041</td>\n",
" <td>16.371882</td>\n",
" <td>29.891081</td>\n",
" <td>25.465600</td>\n",
" <td>36.184821</td>\n",
" <td>30.684177</td>\n",
" <td>27.046708</td>\n",
" <td>1.000000</td>\n",
" <td>3.910</td>\n",
" <td>3</td>\n",
" <td>290.047361</td>\n",
" <td>30.9936</td>\n",
" <td>0.7432</td>\n",
" <td>0.552346</td>\n",
" <td>0.504928</td>\n",
" <td>0.461538</td>\n",
" <td>-0.094321</td>\n",
" <td>-0.121634</td>\n",
" <td>0.101138</td>\n",
" <td>0.317666</td>\n",
" <td>10.814364</td>\n",
" <td>14.535169</td>\n",
" <td>9.558551</td>\n",
" <td>8.682785</td>\n",
" <td>...</td>\n",
" <td>21.642128</td>\n",
" <td>0.857143</td>\n",
" <td>25</td>\n",
" <td>965</td>\n",
" <td>1.445706</td>\n",
" <td>11.293503</td>\n",
" <td>2.593706</td>\n",
" <td>1.90</td>\n",
" <td>12.367103</td>\n",
" <td>98</td>\n",
" <td>6.977339</td>\n",
" <td>5</td>\n",
" <td>3.444603</td>\n",
" <td>11</td>\n",
" <td>0.550000</td>\n",
" <td>20</td>\n",
" <td>0.234708</td>\n",
" <td>9</td>\n",
" <td>21</td>\n",
" <td>3.475817</td>\n",
" <td>2</td>\n",
" <td>6.401608</td>\n",
" <td>0.064430</td>\n",
" <td>8.615405</td>\n",
" <td>0.299488</td>\n",
" <td>30</td>\n",
" <td>61.08</td>\n",
" <td>15.244070</td>\n",
" <td>4</td>\n",
" <td>6</td>\n",
" <td>39.952616</td>\n",
" <td>1.997631</td>\n",
" <td>138.78</td>\n",
" <td>1</td>\n",
" <td>5.057851</td>\n",
" <td>406</td>\n",
" <td>1</td>\n",
" <td>0.071778</td>\n",
" <td>37.493930</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>1e</td>\n",
" <td>10.90</td>\n",
" <td>4.962574</td>\n",
" <td>155.685664</td>\n",
" <td>0.816497</td>\n",
" <td>0.721688</td>\n",
" <td>0.233201</td>\n",
" <td>0.138025</td>\n",
" <td>0.198616</td>\n",
" <td>4.584963</td>\n",
" <td>0.672646</td>\n",
" <td>0.375715</td>\n",
" <td>2.454626</td>\n",
" <td>1.185755</td>\n",
" <td>0.158833</td>\n",
" <td>0.072339</td>\n",
" <td>5.612245</td>\n",
" <td>10.083333</td>\n",
" <td>19.567674</td>\n",
" <td>14.860675</td>\n",
" <td>19.417801</td>\n",
" <td>14.138163</td>\n",
" <td>10.666877</td>\n",
" <td>0.965489</td>\n",
" <td>1.668</td>\n",
" <td>4</td>\n",
" <td>180.046967</td>\n",
" <td>25.4845</td>\n",
" <td>0.2372</td>\n",
" <td>0.056264</td>\n",
" <td>0.273002</td>\n",
" <td>0.500000</td>\n",
" <td>-0.061447</td>\n",
" <td>-0.027997</td>\n",
" <td>0.032191</td>\n",
" <td>0.147961</td>\n",
" <td>7.083274</td>\n",
" <td>8.811555</td>\n",
" <td>5.787694</td>\n",
" <td>4.828786</td>\n",
" <td>...</td>\n",
" <td>13.623874</td>\n",
" <td>1.000000</td>\n",
" <td>11</td>\n",
" <td>233</td>\n",
" <td>0.612372</td>\n",
" <td>11.238599</td>\n",
" <td>0.250000</td>\n",
" <td>1.68</td>\n",
" <td>3.950551</td>\n",
" <td>52</td>\n",
" <td>4.883593</td>\n",
" <td>3</td>\n",
" <td>1.627114</td>\n",
" <td>6</td>\n",
" <td>0.500000</td>\n",
" <td>12</td>\n",
" <td>0.102062</td>\n",
" <td>2</td>\n",
" <td>12</td>\n",
" <td>0.754127</td>\n",
" <td>2</td>\n",
" <td>3.118592</td>\n",
" <td>0.024845</td>\n",
" <td>8.873285</td>\n",
" <td>0.072169</td>\n",
" <td>20</td>\n",
" <td>12.05</td>\n",
" <td>11.205656</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>23.540004</td>\n",
" <td>1.961667</td>\n",
" <td>95.39</td>\n",
" <td>1</td>\n",
" <td>4.591837</td>\n",
" <td>150</td>\n",
" <td>1</td>\n",
" <td>0.014344</td>\n",
" <td>24.954344</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>6g</td>\n",
" <td>9.61</td>\n",
" <td>5.017277</td>\n",
" <td>385.802418</td>\n",
" <td>7.630862</td>\n",
" <td>4.371218</td>\n",
" <td>1.983425</td>\n",
" <td>3.814391</td>\n",
" <td>3.029247</td>\n",
" <td>5.954196</td>\n",
" <td>4.501402</td>\n",
" <td>3.216522</td>\n",
" <td>7.919361</td>\n",
" <td>5.980834</td>\n",
" <td>2.036959</td>\n",
" <td>1.405459</td>\n",
" <td>11.421458</td>\n",
" <td>24.134948</td>\n",
" <td>40.171121</td>\n",
" <td>39.664758</td>\n",
" <td>57.971021</td>\n",
" <td>61.167058</td>\n",
" <td>67.448702</td>\n",
" <td>0.500000</td>\n",
" <td>6.235</td>\n",
" <td>3</td>\n",
" <td>432.150764</td>\n",
" <td>44.6083</td>\n",
" <td>0.1887</td>\n",
" <td>0.035608</td>\n",
" <td>0.844901</td>\n",
" <td>0.461538</td>\n",
" <td>-0.350741</td>\n",
" <td>0.107967</td>\n",
" <td>-0.102622</td>\n",
" <td>0.589640</td>\n",
" <td>18.584420</td>\n",
" <td>21.794318</td>\n",
" <td>15.138892</td>\n",
" <td>13.017347</td>\n",
" <td>...</td>\n",
" <td>17.647422</td>\n",
" <td>0.857143</td>\n",
" <td>51</td>\n",
" <td>2579</td>\n",
" <td>1.710671</td>\n",
" <td>6.225321</td>\n",
" <td>14.150084</td>\n",
" <td>3.55</td>\n",
" <td>29.423014</td>\n",
" <td>162</td>\n",
" <td>13.297539</td>\n",
" <td>8</td>\n",
" <td>8.061571</td>\n",
" <td>21</td>\n",
" <td>0.677419</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>15</td>\n",
" <td>34</td>\n",
" <td>11.102627</td>\n",
" <td>1</td>\n",
" <td>11.294771</td>\n",
" <td>0.179087</td>\n",
" <td>8.000413</td>\n",
" <td>0.653042</td>\n",
" <td>55</td>\n",
" <td>226.06</td>\n",
" <td>35.286968</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>63.682753</td>\n",
" <td>2.054282</td>\n",
" <td>88.69</td>\n",
" <td>4</td>\n",
" <td>5.566864</td>\n",
" <td>659</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>67.509032</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>1a</td>\n",
" <td>8.50</td>\n",
" <td>5.070581</td>\n",
" <td>161.984888</td>\n",
" <td>0.816497</td>\n",
" <td>0.721688</td>\n",
" <td>0.233201</td>\n",
" <td>0.161188</td>\n",
" <td>0.213076</td>\n",
" <td>4.584963</td>\n",
" <td>0.762240</td>\n",
" <td>0.444754</td>\n",
" <td>2.584763</td>\n",
" <td>1.279223</td>\n",
" <td>0.179248</td>\n",
" <td>0.082105</td>\n",
" <td>5.612245</td>\n",
" <td>10.083333</td>\n",
" <td>19.207694</td>\n",
" <td>14.528311</td>\n",
" <td>19.085437</td>\n",
" <td>13.971981</td>\n",
" <td>10.500695</td>\n",
" <td>1.000000</td>\n",
" <td>3.697</td>\n",
" <td>3</td>\n",
" <td>179.051718</td>\n",
" <td>25.4845</td>\n",
" <td>0.2372</td>\n",
" <td>0.056264</td>\n",
" <td>0.273002</td>\n",
" <td>0.500000</td>\n",
" <td>-0.029086</td>\n",
" <td>-0.036543</td>\n",
" <td>0.028859</td>\n",
" <td>0.082948</td>\n",
" <td>7.213410</td>\n",
" <td>8.811555</td>\n",
" <td>5.787694</td>\n",
" <td>4.828786</td>\n",
" <td>...</td>\n",
" <td>10.630590</td>\n",
" <td>1.000000</td>\n",
" <td>11</td>\n",
" <td>233</td>\n",
" <td>0.612372</td>\n",
" <td>8.245315</td>\n",
" <td>0.250000</td>\n",
" <td>1.90</td>\n",
" <td>4.294154</td>\n",
" <td>52</td>\n",
" <td>7.732316</td>\n",
" <td>3</td>\n",
" <td>1.627114</td>\n",
" <td>6</td>\n",
" <td>0.500000</td>\n",
" <td>12</td>\n",
" <td>0.102062</td>\n",
" <td>5</td>\n",
" <td>12</td>\n",
" <td>0.754127</td>\n",
" <td>2</td>\n",
" <td>3.118592</td>\n",
" <td>0.032075</td>\n",
" <td>8.872994</td>\n",
" <td>0.072169</td>\n",
" <td>21</td>\n",
" <td>12.04</td>\n",
" <td>10.978863</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>23.540004</td>\n",
" <td>1.961667</td>\n",
" <td>82.50</td>\n",
" <td>1</td>\n",
" <td>4.591837</td>\n",
" <td>150</td>\n",
" <td>1</td>\n",
" <td>0.018519</td>\n",
" <td>26.281137</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>6i</td>\n",
" <td>7.69</td>\n",
" <td>5.114074</td>\n",
" <td>403.098403</td>\n",
" <td>7.813899</td>\n",
" <td>5.092399</td>\n",
" <td>2.284674</td>\n",
" <td>4.015305</td>\n",
" <td>3.104302</td>\n",
" <td>6.000000</td>\n",
" <td>4.530233</td>\n",
" <td>3.296508</td>\n",
" <td>8.661583</td>\n",
" <td>6.167877</td>\n",
" <td>2.070172</td>\n",
" <td>1.436712</td>\n",
" <td>11.620158</td>\n",
" <td>25.103673</td>\n",
" <td>41.171121</td>\n",
" <td>40.664758</td>\n",
" <td>59.971021</td>\n",
" <td>63.665332</td>\n",
" <td>68.448702</td>\n",
" <td>0.500000</td>\n",
" <td>6.528</td>\n",
" <td>3</td>\n",
" <td>446.166414</td>\n",
" <td>49.2470</td>\n",
" <td>0.8369</td>\n",
" <td>0.700402</td>\n",
" <td>1.120333</td>\n",
" <td>0.461538</td>\n",
" <td>-0.351931</td>\n",
" <td>0.113502</td>\n",
" <td>-0.107899</td>\n",
" <td>0.588158</td>\n",
" <td>19.454663</td>\n",
" <td>22.664561</td>\n",
" <td>15.511570</td>\n",
" <td>13.725227</td>\n",
" <td>...</td>\n",
" <td>17.671522</td>\n",
" <td>0.857143</td>\n",
" <td>53</td>\n",
" <td>2814</td>\n",
" <td>1.991031</td>\n",
" <td>6.235551</td>\n",
" <td>15.897214</td>\n",
" <td>3.66</td>\n",
" <td>28.311405</td>\n",
" <td>168</td>\n",
" <td>12.280171</td>\n",
" <td>8</td>\n",
" <td>8.185798</td>\n",
" <td>21</td>\n",
" <td>0.656250</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>14</td>\n",
" <td>35</td>\n",
" <td>11.575186</td>\n",
" <td>1</td>\n",
" <td>11.705335</td>\n",
" <td>0.179087</td>\n",
" <td>7.982510</td>\n",
" <td>0.653042</td>\n",
" <td>58</td>\n",
" <td>233.06</td>\n",
" <td>37.473382</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>65.515586</td>\n",
" <td>2.047362</td>\n",
" <td>88.69</td>\n",
" <td>5</td>\n",
" <td>5.814213</td>\n",
" <td>682</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>70.602618</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>6h</td>\n",
" <td>7.18</td>\n",
" <td>5.143876</td>\n",
" <td>440.326831</td>\n",
" <td>8.915238</td>\n",
" <td>5.774469</td>\n",
" <td>3.050776</td>\n",
" <td>3.969466</td>\n",
" <td>3.823156</td>\n",
" <td>6.087463</td>\n",
" <td>4.763594</td>\n",
" <td>3.253828</td>\n",
" <td>9.378768</td>\n",
" <td>7.275162</td>\n",
" <td>2.090884</td>\n",
" <td>1.398448</td>\n",
" <td>12.497041</td>\n",
" <td>27.046019</td>\n",
" <td>43.171121</td>\n",
" <td>43.052038</td>\n",
" <td>63.413835</td>\n",
" <td>68.773316</td>\n",
" <td>68.335389</td>\n",
" <td>0.500000</td>\n",
" <td>8.653</td>\n",
" <td>1</td>\n",
" <td>476.213364</td>\n",
" <td>57.2941</td>\n",
" <td>-0.1559</td>\n",
" <td>0.024305</td>\n",
" <td>1.413469</td>\n",
" <td>0.461538</td>\n",
" <td>-0.273221</td>\n",
" <td>-0.051090</td>\n",
" <td>0.120295</td>\n",
" <td>0.535588</td>\n",
" <td>21.291526</td>\n",
" <td>24.131181</td>\n",
" <td>16.512812</td>\n",
" <td>14.324666</td>\n",
" <td>...</td>\n",
" <td>18.248443</td>\n",
" <td>0.857143</td>\n",
" <td>57</td>\n",
" <td>3375</td>\n",
" <td>2.348772</td>\n",
" <td>6.284217</td>\n",
" <td>12.662750</td>\n",
" <td>3.88</td>\n",
" <td>28.335424</td>\n",
" <td>178</td>\n",
" <td>14.318107</td>\n",
" <td>10</td>\n",
" <td>8.362054</td>\n",
" <td>21</td>\n",
" <td>0.617647</td>\n",
" <td>25</td>\n",
" <td>0.401375</td>\n",
" <td>16</td>\n",
" <td>37</td>\n",
" <td>11.450532</td>\n",
" <td>1</td>\n",
" <td>12.725391</td>\n",
" <td>0.179087</td>\n",
" <td>7.996778</td>\n",
" <td>0.661870</td>\n",
" <td>66</td>\n",
" <td>247.06</td>\n",
" <td>43.670624</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>69.450571</td>\n",
" <td>2.042664</td>\n",
" <td>80.85</td>\n",
" <td>5</td>\n",
" <td>6.297163</td>\n",
" <td>734</td>\n",
" <td>1</td>\n",
" <td>0.237718</td>\n",
" <td>78.123376</td>\n",
" <td>8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>2c</td>\n",
" <td>4.30</td>\n",
" <td>5.366532</td>\n",
" <td>263.226456</td>\n",
" <td>3.036743</td>\n",
" <td>2.168970</td>\n",
" <td>0.970919</td>\n",
" <td>1.231133</td>\n",
" <td>1.197394</td>\n",
" <td>5.392317</td>\n",
" <td>2.694647</td>\n",
" <td>1.765544</td>\n",
" <td>5.726179</td>\n",
" <td>3.939895</td>\n",
" <td>0.947545</td>\n",
" <td>0.531561</td>\n",
" <td>8.022222</td>\n",
" <td>15.879017</td>\n",
" <td>28.207694</td>\n",
" <td>27.364278</td>\n",
" <td>37.087586</td>\n",
" <td>31.306494</td>\n",
" <td>27.671175</td>\n",
" <td>1.650964</td>\n",
" <td>7.556</td>\n",
" <td>3</td>\n",
" <td>295.114319</td>\n",
" <td>24.6078</td>\n",
" <td>0.4034</td>\n",
" <td>0.162732</td>\n",
" <td>0.569331</td>\n",
" <td>0.500000</td>\n",
" <td>-0.099877</td>\n",
" <td>0.018761</td>\n",
" <td>0.043739</td>\n",
" <td>0.146313</td>\n",
" <td>12.652568</td>\n",
" <td>14.493353</td>\n",
" <td>10.309663</td>\n",
" <td>8.894049</td>\n",
" <td>...</td>\n",
" <td>12.367510</td>\n",
" <td>1.000000</td>\n",
" <td>26</td>\n",
" <td>1127</td>\n",
" <td>1.030257</td>\n",
" <td>9.277363</td>\n",
" <td>2.355091</td>\n",
" <td>2.89</td>\n",
" <td>13.845675</td>\n",
" <td>106</td>\n",
" <td>11.686182</td>\n",
" <td>5</td>\n",
" <td>4.456460</td>\n",
" <td>17</td>\n",
" <td>0.952381</td>\n",
" <td>13</td>\n",
" <td>0.336770</td>\n",
" <td>10</td>\n",
" <td>23</td>\n",
" <td>3.639677</td>\n",
" <td>2</td>\n",
" <td>7.258458</td>\n",
" <td>0.138910</td>\n",
" <td>8.359218</td>\n",
" <td>0.404448</td>\n",
" <td>38</td>\n",
" <td>109.04</td>\n",
" <td>22.184519</td>\n",
" <td>5</td>\n",
" <td>10</td>\n",
" <td>43.142551</td>\n",
" <td>2.054407</td>\n",
" <td>65.19</td>\n",
" <td>3</td>\n",
" <td>4.733382</td>\n",
" <td>494</td>\n",
" <td>2</td>\n",
" <td>0.148629</td>\n",
" <td>47.455481</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>1b</td>\n",
" <td>2.60</td>\n",
" <td>5.585027</td>\n",
" <td>187.925643</td>\n",
" <td>1.846711</td>\n",
" <td>1.714015</td>\n",
" <td>0.400838</td>\n",
" <td>0.373304</td>\n",
" <td>0.428353</td>\n",
" <td>4.906891</td>\n",
" <td>0.986337</td>\n",
" <td>0.574449</td>\n",
" <td>3.063453</td>\n",
" <td>1.597356</td>\n",
" <td>0.277974</td>\n",
" <td>0.119343</td>\n",
" <td>6.554017</td>\n",
" <td>13.066667</td>\n",
" <td>24.116612</td>\n",
" <td>18.801416</td>\n",
" <td>25.856454</td>\n",
" <td>21.632713</td>\n",
" <td>18.161427</td>\n",
" <td>1.000000</td>\n",
" <td>2.951</td>\n",
" <td>3</td>\n",
" <td>224.036797</td>\n",
" <td>29.3745</td>\n",
" <td>0.8973</td>\n",
" <td>0.805147</td>\n",
" <td>0.390853</td>\n",
" <td>0.444444</td>\n",
" <td>-0.019480</td>\n",
" <td>-0.049229</td>\n",
" <td>0.025092</td>\n",
" <td>0.148929</td>\n",
" <td>8.251415</td>\n",
" <td>11.259149</td>\n",
" <td>7.092224</td>\n",
" <td>6.361478</td>\n",
" <td>...</td>\n",
" <td>18.511266</td>\n",
" <td>0.800000</td>\n",
" <td>17</td>\n",
" <td>420</td>\n",
" <td>1.112372</td>\n",
" <td>11.289712</td>\n",
" <td>0.825482</td>\n",
" <td>1.57</td>\n",
" <td>6.416659</td>\n",
" <td>68</td>\n",
" <td>4.941454</td>\n",
" <td>4</td>\n",
" <td>2.264553</td>\n",
" <td>6</td>\n",
" <td>0.400000</td>\n",
" <td>15</td>\n",
" <td>0.083333</td>\n",
" <td>5</td>\n",
" <td>15</td>\n",
" <td>2.206973</td>\n",
" <td>2</td>\n",
" <td>4.160026</td>\n",
" <td>0.027778</td>\n",
" <td>8.611811</td>\n",
" <td>0.107038</td>\n",
" <td>23</td>\n",
" <td>15.07</td>\n",
" <td>11.141656</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>29.256577</td>\n",
" <td>1.950438</td>\n",
" <td>125.64</td>\n",
" <td>1</td>\n",
" <td>5.040000</td>\n",
" <td>210</td>\n",
" <td>1</td>\n",
" <td>0.035679</td>\n",
" <td>28.318344</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>6b</td>\n",
" <td>14.75</td>\n",
" <td>5.665546</td>\n",
" <td>368.506434</td>\n",
" <td>7.563318</td>\n",
" <td>4.431004</td>\n",
" <td>2.003353</td>\n",
" <td>3.784917</td>\n",
" <td>3.002605</td>\n",
" <td>5.906891</td>\n",
" <td>4.371923</td>\n",
" <td>3.156843</td>\n",
" <td>7.690473</td>\n",
" <td>5.905532</td>\n",
" <td>1.990681</td>\n",
" <td>1.360640</td>\n",
" <td>10.744802</td>\n",
" <td>23.168044</td>\n",
" <td>39.171121</td>\n",
" <td>38.664758</td>\n",
" <td>56.638929</td>\n",
" <td>60.167058</td>\n",
" <td>65.448702</td>\n",
" <td>0.500000</td>\n",
" <td>5.812</td>\n",
" <td>3</td>\n",
" <td>418.135114</td>\n",
" <td>40.3145</td>\n",
" <td>-0.0617</td>\n",
" <td>0.003807</td>\n",
" <td>0.844901</td>\n",
" <td>0.500000</td>\n",
" <td>-0.366424</td>\n",
" <td>0.124360</td>\n",
" <td>-0.104649</td>\n",
" <td>0.596628</td>\n",
" <td>17.877313</td>\n",
" <td>21.087211</td>\n",
" <td>14.638892</td>\n",
" <td>12.636920</td>\n",
" <td>...</td>\n",
" <td>17.497848</td>\n",
" <td>1.000000</td>\n",
" <td>50</td>\n",
" <td>2334</td>\n",
" <td>1.710671</td>\n",
" <td>6.224096</td>\n",
" <td>14.150084</td>\n",
" <td>3.44</td>\n",
" <td>27.993263</td>\n",
" <td>158</td>\n",
" <td>11.777140</td>\n",
" <td>7</td>\n",
" <td>7.904360</td>\n",
" <td>21</td>\n",
" <td>0.700000</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>15</td>\n",
" <td>33</td>\n",
" <td>11.011390</td>\n",
" <td>1</td>\n",
" <td>11.175198</td>\n",
" <td>0.179087</td>\n",
" <td>8.004889</td>\n",
" <td>0.653042</td>\n",
" <td>52</td>\n",
" <td>219.06</td>\n",
" <td>33.100554</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>61.670413</td>\n",
" <td>2.055680</td>\n",
" <td>88.69</td>\n",
" <td>4</td>\n",
" <td>5.167969</td>\n",
" <td>602</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>64.415446</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5a</td>\n",
" <td>1.80</td>\n",
" <td>5.744727</td>\n",
" <td>310.464712</td>\n",
" <td>7.010623</td>\n",
" <td>3.955442</td>\n",
" <td>1.847818</td>\n",
" <td>3.511993</td>\n",
" <td>2.795922</td>\n",
" <td>5.700440</td>\n",
" <td>3.978266</td>\n",
" <td>2.825019</td>\n",
" <td>6.853406</td>\n",
" <td>5.268335</td>\n",
" <td>1.700642</td>\n",
" <td>1.103428</td>\n",
" <td>8.566330</td>\n",
" <td>19.322235</td>\n",
" <td>34.396652</td>\n",
" <td>34.166484</td>\n",
" <td>50.587193</td>\n",
" <td>51.500725</td>\n",
" <td>53.502874</td>\n",
" <td>0.000000</td>\n",
" <td>5.283</td>\n",
" <td>2</td>\n",
" <td>362.108899</td>\n",
" <td>26.6472</td>\n",
" <td>-0.2629</td>\n",
" <td>0.069116</td>\n",
" <td>0.793915</td>\n",
" <td>0.500000</td>\n",
" <td>-0.290079</td>\n",
" <td>0.065624</td>\n",
" <td>0.012116</td>\n",
" <td>0.456120</td>\n",
" <td>15.339308</td>\n",
" <td>18.095647</td>\n",
" <td>12.707040</td>\n",
" <td>11.126944</td>\n",
" <td>...</td>\n",
" <td>14.367681</td>\n",
" <td>1.000000</td>\n",
" <td>44</td>\n",
" <td>1568</td>\n",
" <td>1.506546</td>\n",
" <td>5.661727</td>\n",
" <td>12.662750</td>\n",
" <td>3.22</td>\n",
" <td>25.166892</td>\n",
" <td>140</td>\n",
" <td>10.902736</td>\n",
" <td>4</td>\n",
" <td>7.327856</td>\n",
" <td>21</td>\n",
" <td>0.807692</td>\n",
" <td>24</td>\n",
" <td>0.429558</td>\n",
" <td>14</td>\n",
" <td>29</td>\n",
" <td>10.382997</td>\n",
" <td>1</td>\n",
" <td>9.880643</td>\n",
" <td>0.184383</td>\n",
" <td>8.137528</td>\n",
" <td>0.646302</td>\n",
" <td>44</td>\n",
" <td>191.05</td>\n",
" <td>26.449726</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>53.791353</td>\n",
" <td>2.068898</td>\n",
" <td>85.61</td>\n",
" <td>4</td>\n",
" <td>3.938169</td>\n",
" <td>518</td>\n",
" <td>0</td>\n",
" <td>0.229039</td>\n",
" <td>55.666274</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>6d</td>\n",
" <td>1.03</td>\n",
" <td>5.987163</td>\n",
" <td>396.843653</td>\n",
" <td>8.503114</td>\n",
" <td>6.184284</td>\n",
" <td>2.970018</td>\n",
" <td>4.501532</td>\n",
" <td>3.593563</td>\n",
" <td>6.000000</td>\n",
" <td>4.452856</td>\n",
" <td>3.342886</td>\n",
" <td>10.021858</td>\n",
" <td>6.330922</td>\n",
" <td>2.072881</td>\n",
" <td>1.439711</td>\n",
" <td>10.726644</td>\n",
" <td>25.103673</td>\n",
" <td>64.309970</td>\n",
" <td>46.520070</td>\n",
" <td>90.633090</td>\n",
" <td>79.791779</td>\n",
" <td>73.304014</td>\n",
" <td>0.500000</td>\n",
" <td>6.669</td>\n",
" <td>3</td>\n",
" <td>506.002547</td>\n",
" <td>50.8056</td>\n",
" <td>1.5404</td>\n",
" <td>2.372832</td>\n",
" <td>2.516980</td>\n",
" <td>0.500000</td>\n",
" <td>-0.418292</td>\n",
" <td>-0.030187</td>\n",
" <td>0.063725</td>\n",
" <td>0.768409</td>\n",
" <td>20.071886</td>\n",
" <td>22.880104</td>\n",
" <td>15.312212</td>\n",
" <td>14.390573</td>\n",
" <td>...</td>\n",
" <td>24.580498</td>\n",
" <td>1.000000</td>\n",
" <td>54</td>\n",
" <td>2782</td>\n",
" <td>2.992145</td>\n",
" <td>6.235985</td>\n",
" <td>14.150084</td>\n",
" <td>3.00</td>\n",
" <td>26.097311</td>\n",
" <td>172</td>\n",
" <td>10.902736</td>\n",
" <td>7</td>\n",
" <td>8.128800</td>\n",
" <td>21</td>\n",
" <td>0.656250</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>14</td>\n",
" <td>35</td>\n",
" <td>12.248087</td>\n",
" <td>1</td>\n",
" <td>11.907857</td>\n",
" <td>0.179087</td>\n",
" <td>7.939242</td>\n",
" <td>0.653042</td>\n",
" <td>49</td>\n",
" <td>233.09</td>\n",
" <td>28.894519</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>65.273622</td>\n",
" <td>2.039801</td>\n",
" <td>88.69</td>\n",
" <td>4</td>\n",
" <td>5.644464</td>\n",
" <td>648</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>65.861481</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>6l</td>\n",
" <td>0.61</td>\n",
" <td>6.214670</td>\n",
" <td>468.299694</td>\n",
" <td>11.585590</td>\n",
" <td>7.740377</td>\n",
" <td>3.921857</td>\n",
" <td>6.956740</td>\n",
" <td>5.368955</td>\n",
" <td>6.209453</td>\n",
" <td>5.773760</td>\n",
" <td>4.171362</td>\n",
" <td>11.589767</td>\n",
" <td>7.784555</td>\n",
" <td>2.670055</td>\n",
" <td>1.776508</td>\n",
" <td>12.668773</td>\n",
" <td>29.970000</td>\n",
" <td>114.116999</td>\n",
" <td>58.501113</td>\n",
" <td>111.266809</td>\n",
" <td>121.489087</td>\n",
" <td>134.984344</td>\n",
" <td>0.500000</td>\n",
" <td>6.215</td>\n",
" <td>3</td>\n",
" <td>643.934188</td>\n",
" <td>74.0363</td>\n",
" <td>2.3256</td>\n",
" <td>5.408415</td>\n",
" <td>2.844257</td>\n",
" <td>0.461538</td>\n",
" <td>-0.605285</td>\n",
" <td>-0.182335</td>\n",
" <td>0.306880</td>\n",
" <td>1.166592</td>\n",
" <td>24.620293</td>\n",
" <td>26.905048</td>\n",
" <td>17.637109</td>\n",
" <td>16.260821</td>\n",
" <td>...</td>\n",
" <td>32.790216</td>\n",
" <td>0.857143</td>\n",
" <td>68</td>\n",
" <td>3977</td>\n",
" <td>3.388719</td>\n",
" <td>6.237693</td>\n",
" <td>22.667569</td>\n",
" <td>2.89</td>\n",
" <td>22.003319</td>\n",
" <td>198</td>\n",
" <td>6.505178</td>\n",
" <td>9</td>\n",
" <td>9.569856</td>\n",
" <td>21</td>\n",
" <td>0.567568</td>\n",
" <td>28</td>\n",
" <td>0.363402</td>\n",
" <td>14</td>\n",
" <td>40</td>\n",
" <td>17.002747</td>\n",
" <td>1</td>\n",
" <td>13.999817</td>\n",
" <td>0.169351</td>\n",
" <td>7.827021</td>\n",
" <td>0.706570</td>\n",
" <td>57</td>\n",
" <td>268.12</td>\n",
" <td>37.296140</td>\n",
" <td>10</td>\n",
" <td>7</td>\n",
" <td>74.849670</td>\n",
" <td>2.022964</td>\n",
" <td>107.15</td>\n",
" <td>4</td>\n",
" <td>6.189173</td>\n",
" <td>791</td>\n",
" <td>1</td>\n",
" <td>0.279535</td>\n",
" <td>76.035860</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>5c</td>\n",
" <td>31.05</td>\n",
" <td>6.318759</td>\n",
" <td>327.760696</td>\n",
" <td>7.078168</td>\n",
" <td>3.895656</td>\n",
" <td>1.827889</td>\n",
" <td>3.541467</td>\n",
" <td>2.822565</td>\n",
" <td>5.754888</td>\n",
" <td>4.107745</td>\n",
" <td>2.884698</td>\n",
" <td>7.082295</td>\n",
" <td>5.343637</td>\n",
" <td>1.746920</td>\n",
" <td>1.148247</td>\n",
" <td>9.212018</td>\n",
" <td>20.280000</td>\n",
" <td>35.396652</td>\n",
" <td>35.166484</td>\n",
" <td>51.919285</td>\n",
" <td>52.500725</td>\n",
" <td>55.502874</td>\n",
" <td>0.000000</td>\n",
" <td>5.706</td>\n",
" <td>2</td>\n",
" <td>376.124549</td>\n",
" <td>30.9410</td>\n",
" <td>-0.0125</td>\n",
" <td>0.000156</td>\n",
" <td>0.793915</td>\n",
" <td>0.461538</td>\n",
" <td>-0.274546</td>\n",
" <td>0.049429</td>\n",
" <td>0.014146</td>\n",
" <td>0.449120</td>\n",
" <td>16.046415</td>\n",
" <td>18.802754</td>\n",
" <td>13.207040</td>\n",
" <td>11.507371</td>\n",
" <td>...</td>\n",
" <td>14.517322</td>\n",
" <td>0.857143</td>\n",
" <td>45</td>\n",
" <td>1769</td>\n",
" <td>1.506546</td>\n",
" <td>5.663108</td>\n",
" <td>12.662750</td>\n",
" <td>3.33</td>\n",
" <td>26.457900</td>\n",
" <td>144</td>\n",
" <td>12.280171</td>\n",
" <td>5</td>\n",
" <td>7.485068</td>\n",
" <td>21</td>\n",
" <td>0.777778</td>\n",
" <td>24</td>\n",
" <td>0.429558</td>\n",
" <td>14</td>\n",
" <td>30</td>\n",
" <td>10.474233</td>\n",
" <td>1</td>\n",
" <td>10.000217</td>\n",
" <td>0.184383</td>\n",
" <td>8.133052</td>\n",
" <td>0.646302</td>\n",
" <td>47</td>\n",
" <td>198.05</td>\n",
" <td>28.636140</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>55.803500</td>\n",
" <td>2.066796</td>\n",
" <td>85.61</td>\n",
" <td>4</td>\n",
" <td>4.302212</td>\n",
" <td>575</td>\n",
" <td>0</td>\n",
" <td>0.229039</td>\n",
" <td>58.759860</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>43 rows × 85 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-158d134e-5ec4-4b85-8195-0221a0019c61')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-158d134e-5ec4-4b85-8195-0221a0019c61 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-158d134e-5ec4-4b85-8195-0221a0019c61');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
],
"text/plain": [
" code ic50 pic50 ... chiChain.9 apol largestChain\n",
"0 21 87.80 4.056505 ... 0.475372 69.996204 6\n",
"1 20 75.30 4.123205 ... 0.523442 66.902618 6\n",
"2 17 74.60 4.127261 ... 0.151693 61.717825 3\n",
"3 22 60.10 4.221126 ... 0.353145 73.755825 6\n",
"4 2d 56.10 4.251037 ... 0.162214 51.408688 3\n",
"5 12 51.20 4.290730 ... 0.145487 84.922583 5\n",
"6 2f 50.60 4.295849 ... 0.170901 54.241102 3\n",
"7 18 49.30 4.307153 ... 0.281086 64.249032 6\n",
"8 3 44.20 4.354578 ... 0.079271 51.201860 9\n",
"9 2 42.95 4.367037 ... 0.039800 37.247516 5\n",
"10 2g 39.60 4.402305 ... 0.149685 50.294688 3\n",
"11 13 38.70 4.412289 ... 0.152865 85.724583 5\n",
"12 16 36.40 4.438899 ... 0.155652 62.682618 3\n",
"13 14 34.40 4.463442 ... 0.146569 88.980962 5\n",
"14 2b 33.50 4.474955 ... 0.140493 46.399102 3\n",
"15 3 33.21 4.478731 ... 0.039800 46.405895 6\n",
"16 1d 28.90 4.539102 ... 0.058586 33.327930 6\n",
"17 9 27.26 4.564474 ... 0.174431 68.389032 7\n",
"18 10 26.90 4.570248 ... 0.207904 61.833067 5\n",
"19 4a 25.78 4.588717 ... 0.138923 63.153067 5\n",
"20 1c 24.70 4.607303 ... 0.043815 29.374723 6\n",
"21 8 23.19 4.634699 ... 0.188899 58.675067 5\n",
"22 4b 22.84 4.641304 ... 0.168272 64.666274 5\n",
"23 15 20.60 4.686133 ... 0.165644 82.540204 5\n",
"24 5 18.51 4.732594 ... 0.081215 50.727895 5\n",
"25 6a 15.42 4.811916 ... 0.168566 68.808653 5\n",
"26 6c 14.90 4.831208 ... 0.237718 75.029790 8\n",
"27 2i 13.80 4.860121 ... 0.180092 58.136688 3\n",
"28 6b 12.68 4.896881 ... 0.152129 69.610653 5\n",
"29 6e 12.27 4.911155 ... 0.240859 67.509032 6\n",
"30 1f 11.00 4.958607 ... 0.071778 37.493930 6\n",
"31 1e 10.90 4.962574 ... 0.014344 24.954344 6\n",
"32 6g 9.61 5.017277 ... 0.240859 67.509032 5\n",
"33 1a 8.50 5.070581 ... 0.018519 26.281137 6\n",
"34 6i 7.69 5.114074 ... 0.240859 70.602618 6\n",
"35 6h 7.18 5.143876 ... 0.237718 78.123376 8\n",
"36 2c 4.30 5.366532 ... 0.148629 47.455481 3\n",
"37 1b 2.60 5.585027 ... 0.035679 28.318344 6\n",
"38 6b 14.75 5.665546 ... 0.240859 64.415446 5\n",
"39 5a 1.80 5.744727 ... 0.229039 55.666274 1\n",
"40 6d 1.03 5.987163 ... 0.240859 65.861481 7\n",
"41 6l 0.61 6.214670 ... 0.279535 76.035860 7\n",
"42 5c 31.05 6.318759 ... 0.229039 58.759860 3\n",
"\n",
"[43 rows x 85 columns]"
]
},
"metadata": {},
"execution_count": 3
}
]
},
{
"cell_type": "markdown",
"source": [
"**Preprocessing**\n",
"\n",
"**Defining dependent and independent variables**"
],
"metadata": {
"id": "wZPEryownPLs"
}
},
{
"cell_type": "code",
"source": [
"X = df.drop(['code','ic50','pic50'],axis = 'columns')\n",
"X.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3A9hOzJt7Vq-",
"outputId": "7f95dba1-7388-4a48-ee5c-484089f63e4f"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(43, 82)"
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"source": [
"Y = df.pic50\n",
"Y.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "gfkIjHB37pvk",
"outputId": "3a897919-9a4c-49da-8c4e-93cf57f7cfd5"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(43,)"
]
},
"metadata": {},
"execution_count": 5
}
]
},
{
"cell_type": "code",
"source": [
"print(model.coef_)\n",
"print(model.intercept_)\n",
"model.predict(X)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "TG7dvbzw7unS",
"outputId": "ed26e542-e857-47c0-d319-4f5d5e012b59"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[-2.86677313e+00 4.56625811e+00 -1.02993127e+00 -4.82704293e+00\n",
" -5.92127498e-01 -6.90325414e+00 7.47395649e+00 2.66263019e+00\n",
" -1.40536961e+00 4.77863082e+00 -6.98371446e-01 -5.80394688e+00\n",
" 6.41690716e-01 -3.77883817e+00 1.05955193e+01 -2.13501589e+00\n",
" 5.31397216e+00 1.19700277e+00 3.84405112e+00 -1.44332265e-01\n",
" 4.79585295e+00 -3.07437297e-01 3.35511849e+00 1.22744390e+00\n",
" -2.85274197e+00 -5.17614452e+00 -1.64115622e+00 -3.93906750e+00\n",
" 3.69905438e+00 6.19751880e-01 3.44972247e+00 -6.19014924e+00\n",
" 1.12383879e+00 -6.23664367e+00 1.62157097e+00 -1.64436947e+00\n",
" 3.19875790e-01 1.18488691e+01 -3.90553867e+00 3.11744874e+00\n",
" -1.40403199e+00 1.11931218e+01 -7.83815892e+00 1.24393635e+01\n",
" -1.04298232e+00 8.72621294e-03 -3.72315619e+00 1.41669792e+00\n",
" 2.29387574e+00 4.26840944e-01 3.20829426e+00 -6.92782488e-01\n",
" -5.32582664e+00 9.78011225e-01 -8.42805006e+00 -1.02803768e+01\n",
" 9.34747450e+00 1.47816842e+00 6.45701509e-01 -9.15526855e-01\n",
" -1.55580876e+00 -6.42517399e+00 -2.15408318e+00 -9.68007648e-01\n",
" -7.63240025e-01 1.96590459e+00 3.52885203e+00 1.29194891e+01\n",
" -3.39923393e-01 -5.89755752e+00 -3.31147505e+00 5.43561003e+00\n",
" -4.18214578e+00 8.61586576e-01 1.86909293e-01 -1.41478315e+00\n",
" 1.43067495e+01 4.43312065e-02 -2.43717220e+00 -1.14220307e+00\n",
" 3.13222059e+00 8.08883668e-01]\n",
"-54.93855141220136\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([4.05650548, 4.12320502, 4.12726117, 4.22112553, 4.25103714,\n",
" 4.29073004, 4.29584948, 4.30715308, 4.35457773, 4.36703683,\n",
" 4.40230481, 4.41228903, 4.43889862, 4.46344156, 4.47495519,\n",
" 4.47873112, 4.53910216, 4.56447415, 4.57024772, 4.58871709,\n",
" 4.60730305, 4.63469925, 4.6413039 , 4.68613278, 4.73259358,\n",
" 4.81191563, 4.83120798, 4.86012091, 4.89688075, 4.91115544,\n",
" 4.95860732, 4.9625735 , 5.01727661, 5.07058107, 5.11407366,\n",
" 5.14387556, 5.36653154, 5.58502665, 5.66554625, 5.7447275 ,\n",
" 5.98716277, 6.21467017, 6.31875876])"
]
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"source": [
"df1 = pd.read_csv('Test.csv')\n",
"df1"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 456
},
"id": "0CLhnQDV7uq0",
"outputId": "5f8175a1-88be-4138-d9e1-4e96a28e5a4a"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
" <div id=\"df-84560973-efc8-4c53-929a-7aaf3d90afeb\">\n",
" <div class=\"colab-df-container\">\n",
" <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>code</th>\n",
" <th>ic50</th>\n",
" <th>pic50</th>\n",
" <th>vabc</th>\n",
" <th>chiPathCluster.1</th>\n",
" <th>chiPathCluster.0</th>\n",
" <th>chiPathCluster.3</th>\n",
" <th>chiPathCluster.5</th>\n",
" <th>chiPathCluster.4</th>\n",
" <th>vAdjMa</th>\n",
" <th>chiPath.12</th>\n",
" <th>chiPath.13</th>\n",
" <th>chiPath.10</th>\n",
" <th>chiPath.11</th>\n",
" <th>chiPath.14</th>\n",
" <th>chiPath.15</th>\n",
" <th>kierValues.1</th>\n",
" <th>kierValues.0</th>\n",
" <th>autoCorrelationMass.0</th>\n",
" <th>autoCorrelationMass.1</th>\n",
" <th>autoCorrelationMass.2</th>\n",
" <th>autoCorrelationMass.3</th>\n",
" <th>autoCorrelationMass.4</th>\n",
" <th>mde.16</th>\n",
" <th>xlogP</th>\n",
" <th>hBondacceptors</th>\n",
" <th>weight</th>\n",
" <th>ALOGP.2</th>\n",
" <th>ALOGP.0</th>\n",
" <th>ALOGP.1</th>\n",
" <th>chiCluster.4</th>\n",
" <th>petitjeanNumber</th>\n",
" <th>autoCorrelationCharge.1</th>\n",
" <th>autoCorrelationCharge.2</th>\n",
" <th>autoCorrelationCharge.3</th>\n",
" <th>autoCorrelationCharge.0</th>\n",
" <th>chiPath.8</th>\n",
" <th>chiPath.0</th>\n",
" <th>chiPath.1</th>\n",
" <th>chiPath.2</th>\n",
" <th>...</th>\n",
" <th>weightedPath.2</th>\n",
" <th>petitjeanShapeIndex.0</th>\n",
" <th>wienerNumbers.1</th>\n",
" <th>wienerNumbers.0</th>\n",
" <th>chiCluster.0</th>\n",
" <th>weightedPath.4</th>\n",
" <th>mde.7</th>\n",
" <th>mannholdLogP</th>\n",
" <th>mde.5</th>\n",
" <th>zagrebIndex</th>\n",
" <th>mde.4</th>\n",
" <th>rotatableBondsCount</th>\n",
" <th>chiPath.5</th>\n",
" <th>aromaticAtomsCount</th>\n",
" <th>fmf</th>\n",
" <th>largestPiSystem</th>\n",
" <th>chiChain.3</th>\n",
" <th>carbonTypes.6</th>\n",
" <th>bondCount</th>\n",
" <th>chiPathCluster.2</th>\n",
" <th>hBondDonors</th>\n",
" <th>chiPath.3</th>\n",
" <th>chiChain.8</th>\n",
" <th>ip</th>\n",
" <th>chiChain.4</th>\n",
" <th>atomCount</th>\n",
" <th>NilaComplexity</th>\n",
" <th>bpol</th>\n",
" <th>kierHallSmarts.16</th>\n",
" <th>kierHallSmarts.11</th>\n",
" <th>weightedPath.0</th>\n",
" <th>weightedPath.1</th>\n",
" <th>tpsa</th>\n",
" <th>carbonTypes.7</th>\n",
" <th>kierValues.2</th>\n",
" <th>eccentricConnectivityIndex</th>\n",
" <th>kierHallSmarts.23</th>\n",
" <th>chiChain.9</th>\n",
" <th>apol</th>\n",
" <th>largestChain</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2h</td>\n",
" <td>58.70</td>\n",
" <td>4.231362</td>\n",
" <td>306.372021</td>\n",
" <td>5.037478</td>\n",
" <td>3.201191</td>\n",
" <td>1.302367</td>\n",
" <td>1.806016</td>\n",
" <td>1.775295</td>\n",
" <td>5.700440</td>\n",
" <td>3.443973</td>\n",
" <td>2.197319</td>\n",
" <td>6.590281</td>\n",
" <td>4.861192</td>\n",
" <td>1.259559</td>\n",
" <td>0.774353</td>\n",
" <td>9.467456</td>\n",
" <td>19.322235</td>\n",
" <td>34.342143</td>\n",
" <td>34.360826</td>\n",
" <td>47.250315</td>\n",
" <td>44.469224</td>\n",
" <td>39.501813</td>\n",
" <td>1.785490</td>\n",
" <td>5.755</td>\n",
" <td>4</td>\n",
" <td>362.120132</td>\n",
" <td>26.4215</td>\n",
" <td>-0.2904</td>\n",
" <td>0.084332</td>\n",
" <td>0.591636</td>\n",
" <td>0.500000</td>\n",
" <td>-0.224998</td>\n",
" <td>0.023323</td>\n",
" <td>0.070675</td>\n",
" <td>0.379171</td>\n",
" <td>15.085380</td>\n",
" <td>17.769374</td>\n",
" <td>12.830831</td>\n",
" <td>10.958490</td>\n",
" <td>...</td>\n",
" <td>18.297866</td>\n",
" <td>1.000000</td>\n",
" <td>38</td>\n",
" <td>1988</td>\n",
" <td>1.210998</td>\n",
" <td>12.419038</td>\n",
" <td>4.850526</td>\n",
" <td>3.00</td>\n",
" <td>19.492541</td>\n",
" <td>136</td>\n",
" <td>12.624246</td>\n",
" <td>6</td>\n",
" <td>6.229523</td>\n",
" <td>21</td>\n",
" <td>0.923077</td>\n",
" <td>14</td>\n",
" <td>0.386083</td>\n",
" <td>12</td>\n",
" <td>29</td>\n",
" <td>6.240504</td>\n",
" <td>2</td>\n",
" <td>9.627704</td>\n",
" <td>0.153246</td>\n",
" <td>8.348711</td>\n",
" <td>0.561677</td>\n",
" <td>44</td>\n",
" <td>191.06</td>\n",
" <td>26.513726</td>\n",
" <td>5</td>\n",
" <td>11</td>\n",
" <td>54.023391</td>\n",
" <td>2.077823</td>\n",
" <td>87.31</td>\n",
" <td>3</td>\n",
" <td>4.899408</td>\n",
" <td>712</td>\n",
" <td>2</td>\n",
" <td>0.171405</td>\n",
" <td>55.304274</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2e</td>\n",
" <td>44.90</td>\n",
" <td>4.347754</td>\n",
" <td>239.631247</td>\n",
" <td>2.694161</td>\n",
" <td>1.760722</td>\n",
" <td>0.778469</td>\n",
" <td>0.972053</td>\n",
" <td>1.038430</td>\n",
" <td>5.321928</td>\n",
" <td>2.489356</td>\n",
" <td>1.520468</td>\n",
" <td>5.096042</td>\n",
" <td>3.568649</td>\n",
" <td>0.822215</td>\n",
" <td>0.496673</td>\n",
" <td>7.852041</td>\n",
" <td>14.917355</td>\n",
" <td>27.567674</td>\n",
" <td>26.696642</td>\n",
" <td>35.419950</td>\n",
" <td>29.472676</td>\n",
" <td>26.837357</td>\n",
" <td>1.785490</td>\n",
" <td>5.204</td>\n",
" <td>4</td>\n",
" <td>282.093918</td>\n",
" <td>19.1057</td>\n",
" <td>-0.2386</td>\n",
" <td>0.056930</td>\n",
" <td>0.402665</td>\n",
" <td>0.461538</td>\n",
" <td>-0.133831</td>\n",
" <td>0.025816</td>\n",
" <td>0.056832</td>\n",
" <td>0.210569</td>\n",
" <td>11.599782</td>\n",
" <td>13.623110</td>\n",
" <td>9.915816</td>\n",
" <td>8.272187</td>\n",
" <td>...</td>\n",
" <td>15.362113</td>\n",
" <td>0.857143</td>\n",
" <td>24</td>\n",
" <td>973</td>\n",
" <td>0.741582</td>\n",
" <td>12.272108</td>\n",
" <td>1.894849</td>\n",
" <td>2.56</td>\n",
" <td>11.625250</td>\n",
" <td>100</td>\n",
" <td>11.686182</td>\n",
" <td>5</td>\n",
" <td>4.172343</td>\n",
" <td>17</td>\n",
" <td>1.000000</td>\n",
" <td>13</td>\n",
" <td>0.355499</td>\n",
" <td>8</td>\n",
" <td>22</td>\n",
" <td>3.052470</td>\n",
" <td>2</td>\n",
" <td>6.847775</td>\n",
" <td>0.135977</td>\n",
" <td>8.360628</td>\n",
" <td>0.334357</td>\n",
" <td>34</td>\n",
" <td>104.05</td>\n",
" <td>20.224898</td>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>41.284642</td>\n",
" <td>2.064232</td>\n",
" <td>78.08</td>\n",
" <td>2</td>\n",
" <td>4.496327</td>\n",
" <td>442</td>\n",
" <td>2</td>\n",
" <td>0.118778</td>\n",
" <td>43.035102</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10</td>\n",
" <td>37.90</td>\n",
" <td>4.421361</td>\n",
" <td>522.084174</td>\n",
" <td>12.787512</td>\n",
" <td>8.077371</td>\n",
" <td>2.727356</td>\n",
" <td>4.332393</td>\n",
" <td>3.560320</td>\n",
" <td>6.321928</td>\n",
" <td>5.011731</td>\n",
" <td>3.513892</td>\n",
" <td>9.983605</td>\n",
" <td>7.274384</td>\n",
" <td>1.933403</td>\n",
" <td>1.184398</td>\n",
" <td>14.650364</td>\n",
" <td>32.904273</td>\n",
" <td>51.800000</td>\n",
" <td>54.747661</td>\n",
" <td>76.235179</td>\n",
" <td>88.731147</td>\n",
" <td>89.826521</td>\n",
" <td>0.000000</td>\n",
" <td>6.410</td>\n",
" <td>10</td>\n",
" <td>561.204590</td>\n",
" <td>95.9925</td>\n",
" <td>-1.9613</td>\n",
" <td>3.846698</td>\n",
" <td>1.281688</td>\n",
" <td>0.473684</td>\n",
" <td>-0.393398</td>\n",
" <td>0.140997</td>\n",
" <td>-0.230225</td>\n",
" <td>0.811907</td>\n",
" <td>22.880879</td>\n",
" <td>29.026369</td>\n",
" <td>19.093791</td>\n",
" <td>17.375793</td>\n",
" <td>...</td>\n",
" <td>31.484743</td>\n",
" <td>0.900000</td>\n",
" <td>73</td>\n",
" <td>5564</td>\n",
" <td>3.172060</td>\n",
" <td>14.990835</td>\n",
" <td>15.291787</td>\n",
" <td>3.44</td>\n",
" <td>28.576240</td>\n",
" <td>210</td>\n",
" <td>16.386445</td>\n",
" <td>8</td>\n",
" <td>9.760955</td>\n",
" <td>12</td>\n",
" <td>0.675000</td>\n",
" <td>31</td>\n",
" <td>0.305766</td>\n",
" <td>12</td>\n",
" <td>43</td>\n",
" <td>18.686022</td>\n",
" <td>1</td>\n",
" <td>14.979421</td>\n",
" <td>0.148588</td>\n",
" <td>4.352070</td>\n",
" <td>0.441475</td>\n",
" <td>71</td>\n",
" <td>289.11</td>\n",
" <td>48.157417</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>80.656719</td>\n",
" <td>2.016418</td>\n",
" <td>154.54</td>\n",
" <td>3</td>\n",
" <td>7.394879</td>\n",
" <td>1234</td>\n",
" <td>0</td>\n",
" <td>0.161925</td>\n",
" <td>84.120583</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6a</td>\n",
" <td>2.16</td>\n",
" <td>4.507938</td>\n",
" <td>351.210449</td>\n",
" <td>7.528800</td>\n",
" <td>4.211365</td>\n",
" <td>1.946131</td>\n",
" <td>3.716908</td>\n",
" <td>3.011564</td>\n",
" <td>5.857981</td>\n",
" <td>4.344748</td>\n",
" <td>3.039668</td>\n",
" <td>7.469929</td>\n",
" <td>5.621029</td>\n",
" <td>1.947396</td>\n",
" <td>1.321781</td>\n",
" <td>10.080000</td>\n",
" <td>22.203125</td>\n",
" <td>38.171121</td>\n",
" <td>37.664758</td>\n",
" <td>55.638929</td>\n",
" <td>57.668784</td>\n",
" <td>64.448702</td>\n",
" <td>0.500000</td>\n",
" <td>5.559</td>\n",
" <td>3</td>\n",
" <td>404.119464</td>\n",
" <td>35.2910</td>\n",
" <td>-0.1379</td>\n",
" <td>0.019016</td>\n",
" <td>0.874794</td>\n",
" <td>0.500000</td>\n",
" <td>-0.365252</td>\n",
" <td>0.118258</td>\n",
" <td>-0.098748</td>\n",
" <td>0.598435</td>\n",
" <td>17.170206</td>\n",
" <td>20.380104</td>\n",
" <td>14.100887</td>\n",
" <td>12.517347</td>\n",
" <td>...</td>\n",
" <td>17.362622</td>\n",
" <td>1.000000</td>\n",
" <td>48</td>\n",
" <td>2113</td>\n",
" <td>1.830244</td>\n",
" <td>6.166693</td>\n",
" <td>14.150084</td>\n",
" <td>3.33</td>\n",
" <td>26.097311</td>\n",
" <td>154</td>\n",
" <td>10.902736</td>\n",
" <td>6</td>\n",
" <td>7.725025</td>\n",
" <td>21</td>\n",
" <td>0.724138</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>14</td>\n",
" <td>32</td>\n",
" <td>10.823098</td>\n",
" <td>1</td>\n",
" <td>10.547310</td>\n",
" <td>0.179087</td>\n",
" <td>8.022793</td>\n",
" <td>0.653042</td>\n",
" <td>49</td>\n",
" <td>212.06</td>\n",
" <td>30.914140</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>59.672074</td>\n",
" <td>2.057658</td>\n",
" <td>88.69</td>\n",
" <td>4</td>\n",
" <td>4.924037</td>\n",
" <td>579</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>61.321860</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>11</td>\n",
" <td>25.50</td>\n",
" <td>4.593460</td>\n",
" <td>513.578416</td>\n",
" <td>12.787512</td>\n",
" <td>8.077371</td>\n",
" <td>2.620972</td>\n",
" <td>4.217780</td>\n",
" <td>3.476418</td>\n",
" <td>6.321928</td>\n",
" <td>4.919600</td>\n",
" <td>3.414635</td>\n",
" <td>9.664454</td>\n",
" <td>7.090121</td>\n",
" <td>1.856627</td>\n",
" <td>1.138333</td>\n",
" <td>14.650364</td>\n",
" <td>32.904273</td>\n",
" <td>52.574469</td>\n",
" <td>55.079753</td>\n",
" <td>76.899363</td>\n",
" <td>89.395331</td>\n",
" <td>90.158613</td>\n",
" <td>0.000000</td>\n",
" <td>4.069</td>\n",
" <td>10</td>\n",
" <td>563.183855</td>\n",
" <td>93.0550</td>\n",
" <td>-3.0636</td>\n",
" <td>9.385645</td>\n",
" <td>1.189557</td>\n",
" <td>0.473684</td>\n",
" <td>-0.416608</td>\n",
" <td>0.130898</td>\n",
" <td>-0.228052</td>\n",
" <td>0.887461</td>\n",
" <td>22.328093</td>\n",
" <td>29.026369</td>\n",
" <td>19.093791</td>\n",
" <td>17.375793</td>\n",
" <td>...</td>\n",
" <td>34.010847</td>\n",
" <td>0.900000</td>\n",
" <td>73</td>\n",
" <td>5564</td>\n",
" <td>3.172060</td>\n",
" <td>14.990835</td>\n",
" <td>15.291787</td>\n",
" <td>3.22</td>\n",
" <td>28.576240</td>\n",
" <td>210</td>\n",
" <td>16.386445</td>\n",
" <td>8</td>\n",
" <td>9.760955</td>\n",
" <td>12</td>\n",
" <td>0.675000</td>\n",
" <td>32</td>\n",
" <td>0.305766</td>\n",
" <td>13</td>\n",
" <td>43</td>\n",
" <td>18.686022</td>\n",
" <td>2</td>\n",
" <td>14.979421</td>\n",
" <td>0.148588</td>\n",
" <td>4.353746</td>\n",
" <td>0.441475</td>\n",
" <td>69</td>\n",
" <td>289.12</td>\n",
" <td>45.971003</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>80.656719</td>\n",
" <td>2.016418</td>\n",
" <td>174.77</td>\n",
" <td>2</td>\n",
" <td>7.394879</td>\n",
" <td>1234</td>\n",
" <td>0</td>\n",
" <td>0.146569</td>\n",
" <td>81.828997</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2a</td>\n",
" <td>19.30</td>\n",
" <td>4.714443</td>\n",
" <td>245.930472</td>\n",
" <td>2.694161</td>\n",
" <td>1.760722</td>\n",
" <td>0.778469</td>\n",
" <td>1.001357</td>\n",
" <td>1.056139</td>\n",
" <td>5.321928</td>\n",
" <td>2.584579</td>\n",
" <td>1.596893</td>\n",
" <td>5.226179</td>\n",
" <td>3.662117</td>\n",
" <td>0.848962</td>\n",
" <td>0.510047</td>\n",
" <td>7.852041</td>\n",
" <td>14.917355</td>\n",
" <td>27.207694</td>\n",
" <td>26.364278</td>\n",
" <td>35.087586</td>\n",
" <td>29.306494</td>\n",
" <td>26.671175</td>\n",
" <td>1.650964</td>\n",
" <td>7.233</td>\n",
" <td>3</td>\n",
" <td>281.098669</td>\n",
" <td>19.1057</td>\n",
" <td>-0.2386</td>\n",
" <td>0.056930</td>\n",
" <td>0.402665</td>\n",
" <td>0.461538</td>\n",
" <td>-0.099877</td>\n",
" <td>0.018761</td>\n",
" <td>0.043739</td>\n",
" <td>0.146313</td>\n",
" <td>11.729918</td>\n",
" <td>13.623110</td>\n",
" <td>9.915816</td>\n",
" <td>8.272187</td>\n",
" <td>...</td>\n",
" <td>12.364856</td>\n",
" <td>0.857143</td>\n",
" <td>24</td>\n",
" <td>973</td>\n",
" <td>0.741582</td>\n",
" <td>9.274851</td>\n",
" <td>1.894849</td>\n",
" <td>2.78</td>\n",
" <td>12.108827</td>\n",
" <td>100</td>\n",
" <td>13.967822</td>\n",
" <td>5</td>\n",
" <td>4.172343</td>\n",
" <td>17</td>\n",
" <td>1.000000</td>\n",
" <td>13</td>\n",
" <td>0.355499</td>\n",
" <td>11</td>\n",
" <td>22</td>\n",
" <td>3.052470</td>\n",
" <td>2</td>\n",
" <td>6.847775</td>\n",
" <td>0.143207</td>\n",
" <td>8.360337</td>\n",
" <td>0.334357</td>\n",
" <td>35</td>\n",
" <td>104.04</td>\n",
" <td>19.998105</td>\n",
" <td>4</td>\n",
" <td>11</td>\n",
" <td>41.284642</td>\n",
" <td>2.064232</td>\n",
" <td>65.19</td>\n",
" <td>2</td>\n",
" <td>4.496327</td>\n",
" <td>442</td>\n",
" <td>2</td>\n",
" <td>0.123890</td>\n",
" <td>44.361895</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>6n</td>\n",
" <td>13.49</td>\n",
" <td>4.869988</td>\n",
" <td>480.708213</td>\n",
" <td>12.870920</td>\n",
" <td>7.024906</td>\n",
" <td>3.341418</td>\n",
" <td>7.016250</td>\n",
" <td>5.491300</td>\n",
" <td>6.247928</td>\n",
" <td>6.237167</td>\n",
" <td>4.258171</td>\n",
" <td>9.914243</td>\n",
" <td>7.908180</td>\n",
" <td>2.770585</td>\n",
" <td>1.888442</td>\n",
" <td>13.775352</td>\n",
" <td>30.947055</td>\n",
" <td>92.752619</td>\n",
" <td>54.144075</td>\n",
" <td>83.324383</td>\n",
" <td>112.696609</td>\n",
" <td>144.513513</td>\n",
" <td>0.000000</td>\n",
" <td>5.950</td>\n",
" <td>4</td>\n",
" <td>598.077320</td>\n",
" <td>73.9111</td>\n",
" <td>0.6099</td>\n",
" <td>0.371978</td>\n",
" <td>1.297291</td>\n",
" <td>0.461538</td>\n",
" <td>-0.628646</td>\n",
" <td>0.069479</td>\n",
" <td>-0.048655</td>\n",
" <td>1.128557</td>\n",
" <td>24.281181</td>\n",
" <td>27.559749</td>\n",
" <td>18.301993</td>\n",
" <td>15.858999</td>\n",
" <td>...</td>\n",
" <td>28.517561</td>\n",
" <td>0.857143</td>\n",
" <td>72</td>\n",
" <td>4151</td>\n",
" <td>2.461259</td>\n",
" <td>6.587735</td>\n",
" <td>25.061141</td>\n",
" <td>3.44</td>\n",
" <td>25.317286</td>\n",
" <td>200</td>\n",
" <td>6.865828</td>\n",
" <td>10</td>\n",
" <td>9.878255</td>\n",
" <td>21</td>\n",
" <td>0.552632</td>\n",
" <td>30</td>\n",
" <td>0.350916</td>\n",
" <td>15</td>\n",
" <td>41</td>\n",
" <td>18.301103</td>\n",
" <td>0</td>\n",
" <td>14.388512</td>\n",
" <td>0.165737</td>\n",
" <td>7.424735</td>\n",
" <td>0.717019</td>\n",
" <td>65</td>\n",
" <td>275.10</td>\n",
" <td>45.966589</td>\n",
" <td>10</td>\n",
" <td>7</td>\n",
" <td>76.929879</td>\n",
" <td>2.024471</td>\n",
" <td>115.43</td>\n",
" <td>4</td>\n",
" <td>6.133045</td>\n",
" <td>806</td>\n",
" <td>0</td>\n",
" <td>0.289423</td>\n",
" <td>80.245411</td>\n",
" <td>8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>6c</td>\n",
" <td>10.63</td>\n",
" <td>4.973467</td>\n",
" <td>419.698406</td>\n",
" <td>5.219036</td>\n",
" <td>3.784541</td>\n",
" <td>1.461869</td>\n",
" <td>1.717347</td>\n",
" <td>1.712052</td>\n",
" <td>6.087463</td>\n",
" <td>3.633173</td>\n",
" <td>2.357506</td>\n",
" <td>8.342262</td>\n",
" <td>5.484784</td>\n",
" <td>1.177355</td>\n",
" <td>0.721095</td>\n",
" <td>14.074136</td>\n",
" <td>27.046019</td>\n",
" <td>51.964012</td>\n",
" <td>45.309145</td>\n",
" <td>65.286821</td>\n",
" <td>60.253371</td>\n",
" <td>49.722693</td>\n",
" <td>1.828392</td>\n",
" <td>6.569</td>\n",
" <td>7</td>\n",
" <td>491.081888</td>\n",
" <td>57.6702</td>\n",
" <td>-0.3969</td>\n",
" <td>0.157530</td>\n",
" <td>0.945543</td>\n",
" <td>0.478261</td>\n",
" <td>-0.402120</td>\n",
" <td>-0.029420</td>\n",
" <td>0.142894</td>\n",
" <td>0.739422</td>\n",
" <td>19.215035</td>\n",
" <td>23.752502</td>\n",
" <td>16.546847</td>\n",
" <td>14.676308</td>\n",
" <td>...</td>\n",
" <td>29.110393</td>\n",
" <td>0.916667</td>\n",
" <td>45</td>\n",
" <td>4749</td>\n",
" <td>2.000340</td>\n",
" <td>15.296211</td>\n",
" <td>5.687291</td>\n",
" <td>3.00</td>\n",
" <td>22.117813</td>\n",
" <td>172</td>\n",
" <td>15.194382</td>\n",
" <td>9</td>\n",
" <td>7.426040</td>\n",
" <td>18</td>\n",
" <td>0.911765</td>\n",
" <td>22</td>\n",
" <td>0.501037</td>\n",
" <td>13</td>\n",
" <td>37</td>\n",
" <td>6.585752</td>\n",
" <td>2</td>\n",
" <td>11.636683</td>\n",
" <td>0.182113</td>\n",
" <td>2.306414</td>\n",
" <td>0.603870</td>\n",
" <td>52</td>\n",
" <td>247.10</td>\n",
" <td>30.169726</td>\n",
" <td>5</td>\n",
" <td>12</td>\n",
" <td>69.608570</td>\n",
" <td>2.047311</td>\n",
" <td>130.34</td>\n",
" <td>2</td>\n",
" <td>9.119219</td>\n",
" <td>1297</td>\n",
" <td>2</td>\n",
" <td>0.172286</td>\n",
" <td>67.228274</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>6f</td>\n",
" <td>5.49</td>\n",
" <td>5.260428</td>\n",
" <td>368.506434</td>\n",
" <td>7.596344</td>\n",
" <td>4.151578</td>\n",
" <td>1.926202</td>\n",
" <td>3.746382</td>\n",
" <td>3.038206</td>\n",
" <td>5.906891</td>\n",
" <td>4.474227</td>\n",
" <td>3.099347</td>\n",
" <td>7.698818</td>\n",
" <td>5.696331</td>\n",
" <td>1.993674</td>\n",
" <td>1.366600</td>\n",
" <td>10.744802</td>\n",
" <td>23.168044</td>\n",
" <td>39.171121</td>\n",
" <td>38.664758</td>\n",
" <td>56.971021</td>\n",
" <td>58.668784</td>\n",
" <td>66.448702</td>\n",
" <td>0.500000</td>\n",
" <td>5.982</td>\n",
" <td>3</td>\n",
" <td>418.135114</td>\n",
" <td>39.5848</td>\n",
" <td>0.1125</td>\n",
" <td>0.012656</td>\n",
" <td>0.874794</td>\n",
" <td>0.461538</td>\n",
" <td>-0.349570</td>\n",
" <td>0.101865</td>\n",
" <td>-0.096720</td>\n",
" <td>0.591447</td>\n",
" <td>17.877313</td>\n",
" <td>21.087211</td>\n",
" <td>14.600887</td>\n",
" <td>12.897773</td>\n",
" <td>...</td>\n",
" <td>17.512196</td>\n",
" <td>0.857143</td>\n",
" <td>49</td>\n",
" <td>2346</td>\n",
" <td>1.830244</td>\n",
" <td>6.167917</td>\n",
" <td>14.150084</td>\n",
" <td>3.44</td>\n",
" <td>27.502414</td>\n",
" <td>158</td>\n",
" <td>12.280171</td>\n",
" <td>7</td>\n",
" <td>7.882236</td>\n",
" <td>21</td>\n",
" <td>0.700000</td>\n",
" <td>26</td>\n",
" <td>0.401375</td>\n",
" <td>14</td>\n",
" <td>33</td>\n",
" <td>10.914334</td>\n",
" <td>1</td>\n",
" <td>10.666883</td>\n",
" <td>0.179087</td>\n",
" <td>8.018317</td>\n",
" <td>0.653042</td>\n",
" <td>52</td>\n",
" <td>219.06</td>\n",
" <td>33.100554</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>61.684396</td>\n",
" <td>2.056147</td>\n",
" <td>88.69</td>\n",
" <td>4</td>\n",
" <td>5.333333</td>\n",
" <td>636</td>\n",
" <td>1</td>\n",
" <td>0.240859</td>\n",
" <td>64.415446</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>5b</td>\n",
" <td>0.48</td>\n",
" <td>5.744727</td>\n",
" <td>327.760696</td>\n",
" <td>7.078168</td>\n",
" <td>3.895656</td>\n",
" <td>1.827889</td>\n",
" <td>3.541467</td>\n",
" <td>2.822565</td>\n",
" <td>5.754888</td>\n",
" <td>4.107745</td>\n",
" <td>2.884698</td>\n",
" <td>7.082295</td>\n",
" <td>5.343637</td>\n",
" <td>1.746920</td>\n",
" <td>1.148247</td>\n",
" <td>9.212018</td>\n",
" <td>20.280000</td>\n",
" <td>35.396652</td>\n",
" <td>35.166484</td>\n",
" <td>51.919285</td>\n",
" <td>52.500725</td>\n",
" <td>55.502874</td>\n",
" <td>0.000000</td>\n",
" <td>5.706</td>\n",
" <td>2</td>\n",
" <td>376.124549</td>\n",
" <td>30.9410</td>\n",
" <td>-0.0125</td>\n",
" <td>0.000156</td>\n",
" <td>0.793915</td>\n",
" <td>0.461538</td>\n",
" <td>-0.274546</td>\n",
" <td>0.049429</td>\n",
" <td>0.014146</td>\n",
" <td>0.449120</td>\n",
" <td>16.046415</td>\n",
" <td>18.802754</td>\n",
" <td>13.207040</td>\n",
" <td>11.507371</td>\n",
" <td>...</td>\n",
" <td>14.517322</td>\n",
" <td>0.857143</td>\n",
" <td>45</td>\n",
" <td>1769</td>\n",
" <td>1.506546</td>\n",
" <td>5.663108</td>\n",
" <td>12.662750</td>\n",
" <td>3.33</td>\n",
" <td>26.457900</td>\n",
" <td>144</td>\n",
" <td>12.280171</td>\n",
" <td>5</td>\n",
" <td>7.485068</td>\n",
" <td>21</td>\n",
" <td>0.777778</td>\n",
" <td>24</td>\n",
" <td>0.429558</td>\n",
" <td>14</td>\n",
" <td>30</td>\n",
" <td>10.474233</td>\n",
" <td>1</td>\n",
" <td>10.000217</td>\n",
" <td>0.184383</td>\n",
" <td>8.133052</td>\n",
" <td>0.646302</td>\n",
" <td>47</td>\n",
" <td>198.05</td>\n",
" <td>28.636140</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>55.803500</td>\n",
" <td>2.066796</td>\n",
" <td>85.61</td>\n",
" <td>4</td>\n",
" <td>4.302212</td>\n",
" <td>575</td>\n",
" <td>0</td>\n",
" <td>0.229039</td>\n",
" <td>58.759860</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10 rows × 85 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-84560973-efc8-4c53-929a-7aaf3d90afeb')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-84560973-efc8-4c53-929a-7aaf3d90afeb button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-84560973-efc8-4c53-929a-7aaf3d90afeb');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
],
"text/plain": [
" code ic50 pic50 ... chiChain.9 apol largestChain\n",
"0 2h 58.70 4.231362 ... 0.171405 55.304274 3\n",
"1 2e 44.90 4.347754 ... 0.118778 43.035102 3\n",
"2 10 37.90 4.421361 ... 0.161925 84.120583 5\n",
"3 6a 2.16 4.507938 ... 0.240859 61.321860 4\n",
"4 11 25.50 4.593460 ... 0.146569 81.828997 5\n",
"5 2a 19.30 4.714443 ... 0.123890 44.361895 3\n",
"6 6n 13.49 4.869988 ... 0.289423 80.245411 8\n",
"7 6c 10.63 4.973467 ... 0.172286 67.228274 5\n",
"8 6f 5.49 5.260428 ... 0.240859 64.415446 4\n",
"9 5b 0.48 5.744727 ... 0.229039 58.759860 3\n",
"\n",
"[10 rows x 85 columns]"
]
},
"metadata": {},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"source": [
"X1 = df1.drop(['code','ic50','pic50'],axis = 'columns')\n",
"X1.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8YGKP6iHLMiZ",
"outputId": "b1918071-fe8b-4bc1-c875-7081ab0e01a4"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(10, 82)"
]
},
"metadata": {},
"execution_count": 10
}
]
},
{
"cell_type": "code",
"source": [
"Y1 = df1.pic50\n",
"Y1.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PA4T8ZjW8CFB",
"outputId": "e5256a9c-1f46-4c33-a193-2956c5f2a218"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(10,)"
]
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"source": [
"model.predict(X1)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "-zEUCSJG8SRg",
"outputId": "84283f89-5577-40bc-d986-6e75b2256a8e"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([ 2.08342546, 1.28511155, 7.17476171, 4.5351986 , 7.53395825,\n",
" 4.08764708, 16.71022722, 1.90393719, 4.69713899, 6.31875876])"
]
},
"metadata": {},
"execution_count": 12
}
]
},
{
"cell_type": "markdown",
"source": [
"**Preprocessing Step 1**\n",
"\n",
"Model development using: PCA\n",
"\n",
"Applying dimensionality reduction using PCA\n",
"\n",
"StandardScaler to transform the X_scaled value"
],
"metadata": {
"id": "KPn63Gj7nfdc"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"scaler = StandardScaler()\n",
"scaler.fit(X)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VKehOyRo8Ujk",
"outputId": "ebbde98a-aeec-4788-9d3a-4b536e98e292"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"StandardScaler()"
]
},
"metadata": {},
"execution_count": 13
}
]
},
{
"cell_type": "code",
"source": [
"X_scaled = scaler.transform(X)"
],
"metadata": {
"id": "zAPw5ZsR8Z4j"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**Preprocessing Step 2**\n",
"\n",
"Applying PCA"
],
"metadata": {
"id": "sNmUDn_InqFP"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.decomposition import PCA\n",
"pca_20 = PCA(n_components=20,random_state=2)\n",
"pca_20.fit(X_scaled)\n",
"X_pca_20 = pca_20.transform(X_scaled)"
],
"metadata": {
"id": "JsUBETEL8Z_r"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**Checking the Explained variance ratio**\n",
"\n",
"i.e. to know about how well the PCA components are represented without any loss between the variables (selected descriptors).\n",
"\n",
"In our case it captured 99.98%. i.e. the variables (descriptor informations) are not missed their information and presented 99.98% within this 20 selected Principle components."
],
"metadata": {
"id": "gtxtnjc0nyiL"
}
},
{
"cell_type": "code",
"source": [
"print('Variance explained by all 20 principle components =' , sum(pca_20.explained_variance_ratio_ *100))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "IrCHGI4h8aDJ",
"outputId": "5714c362-5ed9-45c1-8c08-c8bd65f5c1d2"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Variance explained by all 20 principle components = 99.7806990830417\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"np.cumsum(pca_20.explained_variance_ratio_ *100)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "jROioKBt8aHI",
"outputId": "56072899-8e8e-4066-cd33-64c39c57711a"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([61.14384868, 73.75873044, 83.4249478 , 87.74120737, 91.75975 ,\n",
" 93.75116399, 95.13588419, 96.11411288, 96.89168101, 97.5556162 ,\n",
" 98.09043414, 98.52339588, 98.81767033, 99.06202044, 99.28748622,\n",
" 99.43264599, 99.5497984 , 99.63979808, 99.71665017, 99.78069908])"
]
},
"metadata": {},
"execution_count": 17
}
]
},
{
"cell_type": "code",
"source": [
"plt.plot(np.cumsum(pca_20.explained_variance_ratio_))\n",
"plt.xlabel('No. of Components')\n",
"plt.ylabel('Explained variance')\n",
"plt.savefig('Elbow_plot.png',dpi=100)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 279
},
"id": "FiUFRoaI8aK9",
"outputId": "125b1653-17e0-458d-f1b3-860b16dd82e2"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"source": [
"print('Variance explained by 1st PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[0])\n",
"print('Variance explained by 2nd PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[1])\n",
"print('Variance explained by 3rd PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[2])\n",
"print('Variance explained by 4th PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[3])\n",
"print('Variance explained by 5th PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[4])\n",
"print('Variance explained by 6th PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[5])\n",
"print('Variance explained by 7th PC =', np.cumsum(pca_20.explained_variance_ratio_ *100)[6])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "LJjtMZGD8qRE",
"outputId": "db8cba66-3126-4d9f-dcac-a703c3414f96"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Variance explained by 1st PC = 61.14384868294579\n",
"Variance explained by 2nd PC = 73.75873043604625\n",
"Variance explained by 3rd PC = 83.42494780316197\n",
"Variance explained by 4th PC = 87.74120736884822\n",
"Variance explained by 5th PC = 91.75975000380961\n",
"Variance explained by 6th PC = 93.75116399484531\n",
"Variance explained by 7th PC = 95.13588419267371\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"**Applying PCA with n=2**"
],
"metadata": {
"id": "aY85SNQnn7ZS"
}
},
{
"cell_type": "code",
"source": [
"pca_2 = PCA(n_components=2, random_state=2)\n",
"pca_2.fit(X_scaled)\n",
"X_pca_2 = pca_2.transform(X_scaled)"
],
"metadata": {
"id": "aqQWc7S-8qYF"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**2D Plot of 90% variability captured via PCA**\n",
"\n",
"Plot for 2 Principle Components"
],
"metadata": {
"id": "p2csE6TLoIoI"
}
},
{
"cell_type": "code",
"source": [
"import seaborn as sns\n",
"plt.figure(figsize=(10,7))\n",
"sns.scatterplot(x=X_pca_2[:,0], y=X_pca_2[:,1], s=70, hue=Y)\n",
"plt.title('2D Scatter Plot: 90% Variability Captured')\n",
"plt.xlabel('First Principle Component')\n",
"plt.ylabel('Second Principle Component')\n",
"plt.savefig('2D Scatter Plot')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 458
},
"id": "5taNRVfu8qeT",
"outputId": "9ef53856-ff67-4b7e-9df1-8f16fd13f4b9"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 720x504 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "markdown",
"source": [
"**Applying PCA with n=3**"
],
"metadata": {
"id": "ZKDNMZ2uoRVg"
}
},
{
"cell_type": "code",
"source": [
"pca_3 = PCA(n_components=3, random_state=2)\n",
"pca_3.fit(X_scaled)\n",
"X_pca_3 = pca_3.transform(X_scaled)"
],
"metadata": {
"id": "YiQQJK4A83JB"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**Plot for 3 Principle Components**"
],
"metadata": {
"id": "2JB9sd4qoXB1"
}
},
{
"cell_type": "code",
"source": [
"from mpl_toolkits import mplot3d\n",
"fig = plt.figure(figsize=(12,8))\n",
"ax = plt.axes(projection='3d')\n",
"sctt = ax.scatter3D(X_pca_3[:,0], X_pca_3[:,1],X_pca_3[:,2], c = Y, s = 50, alpha = 0.6)\n",
"plt.title('3D Scatter Plot')\n",
"ax.set_xlabel('First Principle Component')\n",
"ax.set_ylabel('Second Principle Component')\n",
"ax.set_zlabel('Third Principle Component')\n",
"plt.savefig('3D Scatter Plot')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 466
},
"id": "aMgnpEVd83Qj",
"outputId": "c24edd61-33d2-4ef7-e55e-dba725ed2ef1"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 864x576 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "markdown",
"source": [
"**Applying PCA setting n_components=0.90**\n",
"\n",
"This will pick adequate principle components to preserve 90% variability"
],
"metadata": {
"id": "A-hG0Fvaodoi"
}
},
{
"cell_type": "code",
"source": [
"pca_90 = PCA(n_components=0.90, random_state=1)\n",
"pca_90.fit(X_scaled)\n",
"X_pca_90 = pca_90.transform(X_scaled)"
],
"metadata": {
"id": "XxA4t85D83aa"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Picking adequate number of Principle Components to preserve 90% of variability\n",
"\n",
"In our case it picked 5 Principle Components\n"
],
"metadata": {
"id": "hxcWaFehoplt"
}
},
{
"cell_type": "code",
"source": [
"X_pca_90.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QIPrsltC9E9l",
"outputId": "09de2aa0-a186-4077-ab96-0d2ce85ed9d8"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(43, 5)"
]
},
"metadata": {},
"execution_count": 25
}
]
},
{
"cell_type": "code",
"source": [
"pca_90.n_components_"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3y6yJ2fy9FGj",
"outputId": "9eb1881f-ae7f-49d6-f6b1-0110f4ab1d94"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"5"
]
},
"metadata": {},
"execution_count": 26
}
]
},
{
"cell_type": "code",
"source": [
"pca_90.n_features_"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "SeRlS-gP9FKy",
"outputId": "696c767e-e49c-4e0a-c756-08447864ffd5"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"82"
]
},
"metadata": {},
"execution_count": 27
}
]
},
{
"cell_type": "markdown",
"source": [
"**Visualizing the Principle components**\n"
],
"metadata": {
"id": "U49wUHGEo2u8"
}
},
{
"cell_type": "code",
"source": [
"plt.figure(figsize=(10,7))\n",
"plt.plot(X_pca_90)\n",
"plt.xlabel('Observation')\n",
"plt.ylabel('Transformed')\n",
"plt.title('Transformed data by principle components (90% variabiity)')\n",
"plt.savefig('Principle components 90% Variability')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 458
},
"id": "BxQXcq7K9Oon",
"outputId": "118dae22-7e8f-41b9-d779-fdd97bae4aae"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 720x504 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "markdown",
"source": [
"**Creating pandas DataFrame for the 5 principle components** \n",
"\n",
"So that it can be used for further regression analysis"
],
"metadata": {
"id": "qEICLUfrpDM8"
}
},
{
"cell_type": "code",
"source": [
"df_new = pd.DataFrame(X_pca_90,columns=['PC1','PC2','PC3','PC4','PC5'])\n",
"df_new['target'] = Y\n",
"df_new.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "wsAP60eE9Owm",
"outputId": "4ce9caaa-7bd1-494e-8c48-af52b0dd872f"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
" <div id=\"df-22773bcc-fb34-46bb-9908-5948cd9d8f73\">\n",
" <div class=\"colab-df-container\">\n",
" <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>PC1</th>\n",
" <th>PC2</th>\n",
" <th>PC3</th>\n",
" <th>PC4</th>\n",
" <th>PC5</th>\n",
" <th>target</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-5.137548</td>\n",
" <td>2.235943</td>\n",
" <td>-0.941772</td>\n",
" <td>4.759852</td>\n",
" <td>2.001487</td>\n",
" <td>4.056505</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-4.396323</td>\n",
" <td>2.043850</td>\n",
" <td>-0.942504</td>\n",
" <td>5.444976</td>\n",
" <td>2.489944</td>\n",
" <td>4.123205</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.870976</td>\n",
" <td>6.584207</td>\n",
" <td>-1.585581</td>\n",
" <td>1.637149</td>\n",
" <td>-1.793500</td>\n",
" <td>4.127261</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-6.727808</td>\n",
" <td>2.705131</td>\n",
" <td>0.932989</td>\n",
" <td>2.808784</td>\n",
" <td>1.069419</td>\n",
" <td>4.221126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3.569939</td>\n",
" <td>-4.159506</td>\n",
" <td>0.951070</td>\n",
" <td>2.530539</td>\n",
" <td>-2.001315</td>\n",
" <td>4.251037</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-22773bcc-fb34-46bb-9908-5948cd9d8f73')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-22773bcc-fb34-46bb-9908-5948cd9d8f73 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-22773bcc-fb34-46bb-9908-5948cd9d8f73');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
],
"text/plain": [
" PC1 PC2 PC3 PC4 PC5 target\n",
"0 -5.137548 2.235943 -0.941772 4.759852 2.001487 4.056505\n",
"1 -4.396323 2.043850 -0.942504 5.444976 2.489944 4.123205\n",
"2 -0.870976 6.584207 -1.585581 1.637149 -1.793500 4.127261\n",
"3 -6.727808 2.705131 0.932989 2.808784 1.069419 4.221126\n",
"4 3.569939 -4.159506 0.951070 2.530539 -2.001315 4.251037"
]
},
"metadata": {},
"execution_count": 29
}
]
},
{
"cell_type": "markdown",
"source": [
"**Save the DataFrame in .csv file for use in regression analysis**"
],
"metadata": {
"id": "Yyh0KgGspOZ7"
}
},
{
"cell_type": "code",
"source": [
"df_new.to_excel('cd_pca_90.xlsx', index=False)\n",
"df_new.to_csv('cd_pca_90.csv', index=False)"
],
"metadata": {
"id": "9Kj84FCG9O0C"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"df = pd.read_csv('cd_pca_90.csv')\n",
"df.head"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "U0V7h--L9O85",
"outputId": "58752687-1f07-425e-c928-a1fabc4871e4"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<bound method NDFrame.head of PC1 PC2 PC3 PC4 PC5 target\n",
"0 -5.137548 2.235943 -0.941772 4.759852 2.001487 4.056505\n",
"1 -4.396323 2.043850 -0.942504 5.444976 2.489944 4.123205\n",
"2 -0.870976 6.584207 -1.585581 1.637149 -1.793500 4.127261\n",
"3 -6.727808 2.705131 0.932989 2.808784 1.069419 4.221126\n",
"4 3.569939 -4.159506 0.951070 2.530539 -2.001315 4.251037\n",
"5 -10.706043 3.940880 0.430439 -2.302542 -3.062111 4.290730\n",
"6 0.950193 -4.039539 1.594313 0.708140 -0.981266 4.295849\n",
"7 -2.430221 5.475397 1.165472 3.901355 2.262624 4.307153\n",
"8 4.288545 4.463785 -0.970727 -1.010604 0.425897 4.354578\n",
"9 9.495627 -0.062370 -0.562686 -1.259342 -0.632657 4.367037\n",
"10 3.828626 -1.815280 1.375247 0.500763 -0.393917 4.402305\n",
"11 -11.380050 4.976545 0.312633 -2.182780 -1.363739 4.412289\n",
"12 -0.954259 6.878192 -1.413235 1.900024 -1.743870 4.438899\n",
"13 -11.625584 4.243457 0.527558 -2.386029 -2.980421 4.463442\n",
"14 5.353607 -2.347988 1.242633 1.299674 -0.912544 4.474955\n",
"15 6.772317 1.446196 3.707225 -1.434756 0.655197 4.478731\n",
"16 11.112346 0.970772 -2.342205 -0.130944 0.190351 4.539102\n",
"17 -1.960547 0.385813 4.922903 -1.909668 1.710456 4.564474\n",
"18 -0.832605 -1.538836 5.686459 1.026328 1.486494 4.570248\n",
"19 -0.675140 -3.105909 4.294809 -0.208595 -0.306297 4.588717\n",
"20 13.899597 2.006913 -2.953807 -1.252517 1.115512 4.607303\n",
"21 0.954391 -0.162333 3.339715 -0.357707 1.927814 4.634699\n",
"22 -1.721210 -3.137495 4.501334 -0.550436 0.075050 4.641304\n",
"23 -10.093371 3.736008 -0.491294 -1.985991 -2.116527 4.686133\n",
"24 3.908269 0.498037 4.062731 -0.504486 -0.145844 4.732594\n",
"25 -3.148057 -1.676288 4.344975 -0.534455 0.202648 4.811916\n",
"26 -5.399481 -3.251518 -3.239073 -0.818057 1.331853 4.831208\n",
"27 -0.602690 -3.512764 1.776146 -0.083360 -0.485033 4.860121\n",
"28 -3.828855 -1.191354 5.391197 -1.015483 -0.283293 4.896881\n",
"29 -3.900385 -3.269362 -3.157842 -0.270259 -1.281275 4.911155\n",
"30 8.571278 1.026001 -0.675334 -1.194541 1.442103 4.958607\n",
"31 14.904487 2.363764 -1.126852 -1.218268 -0.266391 4.962574\n",
"32 -3.729794 -3.077116 -3.187933 -0.115629 -1.038061 5.017277\n",
"33 14.686746 1.464710 -1.403481 -1.023094 -0.544504 5.070581\n",
"34 -4.562388 -2.954557 -3.577554 -0.555352 -0.507471 5.114074\n",
"35 -6.100856 -3.350442 -2.956629 -1.113026 1.311121 5.143876\n",
"36 6.308808 -3.501075 0.285150 1.861776 -1.357109 5.366532\n",
"37 12.881432 3.082646 -2.003964 -1.728631 1.467364 5.585027\n",
"38 -3.069749 -3.376873 -2.771472 0.178138 -1.805437 5.665546\n",
"39 -0.119992 -3.807072 -3.518305 1.778546 -2.658646 5.744727\n",
"40 -5.571679 -2.656794 -2.917180 -1.301775 2.103347 5.987163\n",
"41 -11.163604 -1.111208 -4.084646 -3.128762 6.854887 6.214670\n",
"42 -0.776991 -3.422569 -4.020923 1.241043 -1.462339 6.318759>"
]
},
"metadata": {},
"execution_count": 31
}
]
},
{
"cell_type": "markdown",
"source": [
"**Preprocessing**\n",
"\n",
"Defining X (Independent Variable)"
],
"metadata": {
"id": "wCvrzXnipWGv"
}
},
{
"cell_type": "code",
"source": [
"X = df[['PC1','PC2','PC3','PC4','PC5']]\n",
"X.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "vV1vgOJN9dBk",
"outputId": "2e94f687-d8ca-4162-83b6-48afd5369272"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(43, 5)"
]
},
"metadata": {},
"execution_count": 32
}
]
},
{
"cell_type": "markdown",
"source": [
"**Preprocessing**\n",
"\n",
"Defining Y (Dependent Variable)"
],
"metadata": {
"id": "YD9UIl-Qpdvj"
}
},
{
"cell_type": "code",
"source": [
"Y = df[['target']]\n",
"Y.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "gXVY305u9dNL",
"outputId": "fef42b3b-8ee1-4a30-8196-44c28cff59ec"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(43, 1)"
]
},
"metadata": {},
"execution_count": 33
}
]
},
{
"cell_type": "markdown",
"source": [
"#Algorithm or Classifier used\n",
"\n",
"**1. Multiple Linear Regression (MLS)**"
],
"metadata": {
"id": "Ad9oPIcfqY8W"
}
},
{
"cell_type": "code",
"source": [
"from sklearn import linear_model\n",
"model=linear_model.LinearRegression()\n",
"model.fit(X,Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2POrGi5K9lcG",
"outputId": "31e0d1e4-e75f-4e04-ce65-40d54bef4911"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"LinearRegression()"
]
},
"metadata": {},
"execution_count": 34
}
]
},
{
"cell_type": "code",
"source": [
"print(model.coef_)\n",
"print(model.intercept_)\n",
"model.score(X,Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "hsfQH14v9ltT",
"outputId": "b718a259-9450-4361-dd7c-29d737837a6a"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[-0.00064344 -0.07753571 -0.09078846 -0.08986122 0.0504435 ]]\n",
"[4.79279925]\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.5424403112751333"
]
},
"metadata": {},
"execution_count": 35
}
]
},
{
"cell_type": "markdown",
"source": [
"**2. Support Vector Machine (SVM)**"
],
"metadata": {
"id": "ZvOnNU5mqwKE"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.svm import SVR\n",
"model = SVR()\n",
"model.fit(X,Y)\n",
"model.score(X, Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2xOc6Hss9l2m",
"outputId": "9942541e-5e25-4bf1-de58-0e25e5d0bc14"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:985: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.6421642480442185"
]
},
"metadata": {},
"execution_count": 36
}
]
},
{
"cell_type": "markdown",
"source": [
"**3. Partial Least Square Regression (PLS)**"
],
"metadata": {
"id": "LNdkz1oTq3-8"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.cross_decomposition import PLSRegression"
],
"metadata": {
"id": "F-mFsY999-Nq"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"pls = PLSRegression(n_components=2)\n",
"pls.fit(X, Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ZhoY_AEW9-Zf",
"outputId": "754ff22f-5fd7-4637-f1c4-2c8312ae1dd7"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"PLSRegression()"
]
},
"metadata": {},
"execution_count": 43
}
]
},
{
"cell_type": "code",
"source": [
"model.score(X,Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "37I3ecOK-zq9",
"outputId": "06f3ce79-b42a-42e8-9ec8-40b85a15ebb4"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.6421642480442185"
]
},
"metadata": {},
"execution_count": 45
}
]
},
{
"cell_type": "code",
"source": [
"Y_pred = model.predict(X)\n",
"Y_pred"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "LYaq0UeXFoiQ",
"outputId": "a51dea25-cd42-42ce-9f08-26af5defb94e"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([4.19061367, 4.19211787, 4.34540535, 4.26743104, 4.6534956 ,\n",
" 4.48537167, 4.71416922, 4.20757115, 4.4544186 , 4.54081026,\n",
" 4.51332991, 4.51250119, 4.33880275, 4.48884761, 4.49143226,\n",
" 4.57887516, 4.63866369, 4.66473208, 4.63033342, 4.68891347,\n",
" 4.87552288, 4.53412506, 4.74151595, 4.51688128, 4.51346439,\n",
" 4.74314931, 5.09533094, 4.75978221, 4.79647464, 5.12949175,\n",
" 4.585252 , 4.98335545, 5.11744226, 4.92159993, 5.09723641,\n",
" 5.10155062, 4.56003672, 4.89725618, 5.15674818, 5.32839412,\n",
" 5.09897188, 5.74426955, 5.29845624])"
]
},
"metadata": {},
"execution_count": 73
}
]
},
{
"cell_type": "code",
"source": [
"df1 = pd.DataFrame(Y_pred, columns=['Y_pred'])\n",
"df1"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "RiHHHg-nHEu2",
"outputId": "aec1944f-0154-4413-c3f9-c0b9705113fb"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
" <div id=\"df-dae0dcd5-3c05-4ab2-99ed-a0029bd6ff18\">\n",
" <div class=\"colab-df-container\">\n",
" <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>Y_pred</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.190614</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.192118</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.345405</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.267431</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4.653496</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4.485372</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.714169</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>4.207571</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4.454419</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>4.540810</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>4.513330</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>4.512501</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>4.338803</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>4.488848</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>4.491432</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>4.578875</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>4.638664</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>4.664732</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>4.630333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>4.688913</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>4.875523</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>4.534125</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.741516</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>4.516881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>4.513464</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>4.743149</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>5.095331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>4.759782</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>4.796475</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>5.129492</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.585252</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>4.983355</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>5.117442</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>4.921600</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>5.097236</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>5.101551</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>4.560037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>4.897256</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>5.156748</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.328394</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>5.098972</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>5.744270</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>5.298456</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-dae0dcd5-3c05-4ab2-99ed-a0029bd6ff18')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-dae0dcd5-3c05-4ab2-99ed-a0029bd6ff18 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-dae0dcd5-3c05-4ab2-99ed-a0029bd6ff18');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
],
"text/plain": [
" Y_pred\n",
"0 4.190614\n",
"1 4.192118\n",
"2 4.345405\n",
"3 4.267431\n",
"4 4.653496\n",
"5 4.485372\n",
"6 4.714169\n",
"7 4.207571\n",
"8 4.454419\n",
"9 4.540810\n",
"10 4.513330\n",
"11 4.512501\n",
"12 4.338803\n",
"13 4.488848\n",
"14 4.491432\n",
"15 4.578875\n",
"16 4.638664\n",
"17 4.664732\n",
"18 4.630333\n",
"19 4.688913\n",
"20 4.875523\n",
"21 4.534125\n",
"22 4.741516\n",
"23 4.516881\n",
"24 4.513464\n",
"25 4.743149\n",
"26 5.095331\n",
"27 4.759782\n",
"28 4.796475\n",
"29 5.129492\n",
"30 4.585252\n",
"31 4.983355\n",
"32 5.117442\n",
"33 4.921600\n",
"34 5.097236\n",
"35 5.101551\n",
"36 4.560037\n",
"37 4.897256\n",
"38 5.156748\n",
"39 5.328394\n",
"40 5.098972\n",
"41 5.744270\n",
"42 5.298456"
]
},
"metadata": {},
"execution_count": 81
}
]
},
{
"cell_type": "code",
"source": [
"df1['target'] = df.target\n",
"df1"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "S4i5KgRHHE7H",
"outputId": "93be6ef6-d28f-4569-cf76-67c0c8d8cb58"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
" <div id=\"df-edf10cbb-17f2-468e-bb24-e72eec2fc2c7\">\n",
" <div class=\"colab-df-container\">\n",
" <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>Y_pred</th>\n",
" <th>target</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.190614</td>\n",
" <td>4.056505</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.192118</td>\n",
" <td>4.123205</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.345405</td>\n",
" <td>4.127261</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.267431</td>\n",
" <td>4.221126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4.653496</td>\n",
" <td>4.251037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4.485372</td>\n",
" <td>4.290730</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.714169</td>\n",
" <td>4.295849</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>4.207571</td>\n",
" <td>4.307153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4.454419</td>\n",
" <td>4.354578</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>4.540810</td>\n",
" <td>4.367037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>4.513330</td>\n",
" <td>4.402305</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>4.512501</td>\n",
" <td>4.412289</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>4.338803</td>\n",
" <td>4.438899</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>4.488848</td>\n",
" <td>4.463442</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>4.491432</td>\n",
" <td>4.474955</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>4.578875</td>\n",
" <td>4.478731</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>4.638664</td>\n",
" <td>4.539102</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>4.664732</td>\n",
" <td>4.564474</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>4.630333</td>\n",
" <td>4.570248</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>4.688913</td>\n",
" <td>4.588717</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>4.875523</td>\n",
" <td>4.607303</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>4.534125</td>\n",
" <td>4.634699</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.741516</td>\n",
" <td>4.641304</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>4.516881</td>\n",
" <td>4.686133</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>4.513464</td>\n",
" <td>4.732594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>4.743149</td>\n",
" <td>4.811916</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>5.095331</td>\n",
" <td>4.831208</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>4.759782</td>\n",
" <td>4.860121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>4.796475</td>\n",
" <td>4.896881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>5.129492</td>\n",
" <td>4.911155</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.585252</td>\n",
" <td>4.958607</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>4.983355</td>\n",
" <td>4.962574</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>5.117442</td>\n",
" <td>5.017277</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>4.921600</td>\n",
" <td>5.070581</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>5.097236</td>\n",
" <td>5.114074</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>5.101551</td>\n",
" <td>5.143876</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>4.560037</td>\n",
" <td>5.366532</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>4.897256</td>\n",
" <td>5.585027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>5.156748</td>\n",
" <td>5.665546</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.328394</td>\n",
" <td>5.744727</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>5.098972</td>\n",
" <td>5.987163</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>5.744270</td>\n",
" <td>6.214670</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>5.298456</td>\n",
" <td>6.318759</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-edf10cbb-17f2-468e-bb24-e72eec2fc2c7')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-edf10cbb-17f2-468e-bb24-e72eec2fc2c7 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-edf10cbb-17f2-468e-bb24-e72eec2fc2c7');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
],
"text/plain": [
" Y_pred target\n",
"0 4.190614 4.056505\n",
"1 4.192118 4.123205\n",
"2 4.345405 4.127261\n",
"3 4.267431 4.221126\n",
"4 4.653496 4.251037\n",
"5 4.485372 4.290730\n",
"6 4.714169 4.295849\n",
"7 4.207571 4.307153\n",
"8 4.454419 4.354578\n",
"9 4.540810 4.367037\n",
"10 4.513330 4.402305\n",
"11 4.512501 4.412289\n",
"12 4.338803 4.438899\n",
"13 4.488848 4.463442\n",
"14 4.491432 4.474955\n",
"15 4.578875 4.478731\n",
"16 4.638664 4.539102\n",
"17 4.664732 4.564474\n",
"18 4.630333 4.570248\n",
"19 4.688913 4.588717\n",
"20 4.875523 4.607303\n",
"21 4.534125 4.634699\n",
"22 4.741516 4.641304\n",
"23 4.516881 4.686133\n",
"24 4.513464 4.732594\n",
"25 4.743149 4.811916\n",
"26 5.095331 4.831208\n",
"27 4.759782 4.860121\n",
"28 4.796475 4.896881\n",
"29 5.129492 4.911155\n",
"30 4.585252 4.958607\n",
"31 4.983355 4.962574\n",
"32 5.117442 5.017277\n",
"33 4.921600 5.070581\n",
"34 5.097236 5.114074\n",
"35 5.101551 5.143876\n",
"36 4.560037 5.366532\n",
"37 4.897256 5.585027\n",
"38 5.156748 5.665546\n",
"39 5.328394 5.744727\n",
"40 5.098972 5.987163\n",
"41 5.744270 6.214670\n",
"42 5.298456 6.318759"
]
},
"metadata": {},
"execution_count": 87
}
]
},
{
"cell_type": "markdown",
"source": [
"**Linear Regression Plot**"
],
"metadata": {
"id": "8xx2aG3VrDhn"
}
},
{
"cell_type": "code",
"source": [
"sns.set(color_codes=True)\n",
"sns.set_style(\"white\")\n",
"\n",
"ax = sns.regplot(Y, Y_pred, scatter_kws={'alpha':0.6})\n",
"ax.set_xlabel('Experimental pIC50', fontsize='large', fontweight='bold')\n",
"ax.set_ylabel('Predicted pIC50', fontsize='large', fontweight='bold')\n",
"ax.set_xlim(3, 7)\n",
"ax.set_ylim(3, 7)\n",
"ax.figure.set_size_inches(7, 7)\n",
"plt.show\n",
"plt.savefig('Linear regression plot')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 508
},
"id": "6c5_fZ9CF0J4",
"outputId": "a2c6a96f-6e24-40df-e92d-22230f2c3065"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
" FutureWarning\n"
]
},
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 504x504 with 1 Axes>"
]
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"**Statistical Model**\n",
"\n",
"Ordinary Least Square Regression"
],
"metadata": {
"id": "xHJKfQ1TrLN2"
}
},
{
"cell_type": "code",
"source": [
"import statsmodels.formula.api as sm"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qMKW-vcNIQ9p",
"outputId": "96e9971c-54f6-4c76-b164-e6cb9c6d20bb"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
" import pandas.util.testing as tm\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model = sm.ols(formula='target ~ PC1+PC2+PC3+PC4+PC5', data=df)\n",
"fitted1 = model.fit()\n",
"fitted1.summary()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 537
},
"id": "taunOTmnIVp2",
"outputId": "958910e9-52a5-403c-dc38-b923de7ee031"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>OLS Regression Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>target</td> <th> R-squared: </th> <td> 0.542</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>OLS</td> <th> Adj. R-squared: </th> <td> 0.481</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Method:</th> <td>Least Squares</td> <th> F-statistic: </th> <td> 8.773</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Mon, 27 Dec 2021</td> <th> Prob (F-statistic):</th> <td>1.47e-05</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>13:43:07</td> <th> Log-Likelihood: </th> <td> -18.552</td>\n",
"</tr>\n",
"<tr>\n",
" <th>No. Observations:</th> <td> 43</td> <th> AIC: </th> <td> 49.10</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Residuals:</th> <td> 37</td> <th> BIC: </th> <td> 59.67</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Model:</th> <td> 5</td> <th> </th> <td> </td> \n",
"</tr>\n",
"<tr>\n",
" <th>Covariance Type:</th> <td>nonrobust</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>t</th> <th>P>|t|</th> <th>[0.025</th> <th>0.975]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>Intercept</th> <td> 4.7928</td> <td> 0.061</td> <td> 78.262</td> <td> 0.000</td> <td> 4.669</td> <td> 4.917</td>\n",
"</tr>\n",
"<tr>\n",
" <th>PC1</th> <td> -0.0006</td> <td> 0.009</td> <td> -0.074</td> <td> 0.941</td> <td> -0.018</td> <td> 0.017</td>\n",
"</tr>\n",
"<tr>\n",
" <th>PC2</th> <td> -0.0775</td> <td> 0.019</td> <td> -4.072</td> <td> 0.000</td> <td> -0.116</td> <td> -0.039</td>\n",
"</tr>\n",
"<tr>\n",
" <th>PC3</th> <td> -0.0908</td> <td> 0.022</td> <td> -4.174</td> <td> 0.000</td> <td> -0.135</td> <td> -0.047</td>\n",
"</tr>\n",
"<tr>\n",
" <th>PC4</th> <td> -0.0899</td> <td> 0.033</td> <td> -2.761</td> <td> 0.009</td> <td> -0.156</td> <td> -0.024</td>\n",
"</tr>\n",
"<tr>\n",
" <th>PC5</th> <td> 0.0504</td> <td> 0.034</td> <td> 1.495</td> <td> 0.143</td> <td> -0.018</td> <td> 0.119</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Omnibus:</th> <td> 2.933</td> <th> Durbin-Watson: </th> <td> 1.185</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Omnibus):</th> <td> 0.231</td> <th> Jarque-Bera (JB): </th> <td> 2.283</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Skew:</th> <td> 0.564</td> <th> Prob(JB): </th> <td> 0.319</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Kurtosis:</th> <td> 3.054</td> <th> Cond. No. </th> <td> 7.08</td>\n",
"</tr>\n",
"</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: target R-squared: 0.542\n",
"Model: OLS Adj. R-squared: 0.481\n",
"Method: Least Squares F-statistic: 8.773\n",
"Date: Mon, 27 Dec 2021 Prob (F-statistic): 1.47e-05\n",
"Time: 13:43:07 Log-Likelihood: -18.552\n",
"No. Observations: 43 AIC: 49.10\n",
"Df Residuals: 37 BIC: 59.67\n",
"Df Model: 5 \n",
"Covariance Type: nonrobust \n",
"==============================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"------------------------------------------------------------------------------\n",
"Intercept 4.7928 0.061 78.262 0.000 4.669 4.917\n",
"PC1 -0.0006 0.009 -0.074 0.941 -0.018 0.017\n",
"PC2 -0.0775 0.019 -4.072 0.000 -0.116 -0.039\n",
"PC3 -0.0908 0.022 -4.174 0.000 -0.135 -0.047\n",
"PC4 -0.0899 0.033 -2.761 0.009 -0.156 -0.024\n",
"PC5 0.0504 0.034 1.495 0.143 -0.018 0.119\n",
"==============================================================================\n",
"Omnibus: 2.933 Durbin-Watson: 1.185\n",
"Prob(Omnibus): 0.231 Jarque-Bera (JB): 2.283\n",
"Skew: 0.564 Prob(JB): 0.319\n",
"Kurtosis: 3.054 Cond. No. 7.08\n",
"==============================================================================\n",
"\n",
"Warnings:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
"\"\"\""
]
},
"metadata": {},
"execution_count": 89
}
]
},
{
"cell_type": "markdown",
"source": [
"**Saving the Model into pickle**"
],
"metadata": {
"id": "SMEJMrb3rX8A"
}
},
{
"cell_type": "code",
"source": [
"import pickle\n",
"\n",
"with open(\"model.pickle\", \"wb\") as f:\n",
" pickle.dump(model,f)"
],
"metadata": {
"id": "MoupFHbgBOAa"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**Retrive the model for newer compounds bioactivity prediction**"
],
"metadata": {
"id": "L6tp6B7jrgtq"
}
},
{
"cell_type": "code",
"source": [
"with open(\"model.pickle\", \"rb\") as f:\n",
" model_01 = pickle.load(f)"
],
"metadata": {
"id": "Xo4YibhGDpre"
},
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment