Predicting a Biological Response.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bioresponse\n",
    "https://www.kaggle.com/c/bioresponse/data\n",
    "\n",
    "This data has biological response **Activity** in the first column as [1,0]. The remaining columns are descriptors (d1 through d1776), where each row in this dataset represents a molecule.Each molecule has a response (Activity) value associated to it, these descriptor has some information of the molecule  - for example size, shape, or elemental constitution."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import pylab as pl\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## File import\n",
    "There are two input csv files, one is for training with labelled response data and other is for testing the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "file=pd.read_csv('train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "test=pd.read_csv('test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>D1</th>\n",
       "      <th>D2</th>\n",
       "      <th>D3</th>\n",
       "      <th>D4</th>\n",
       "      <th>D5</th>\n",
       "      <th>D6</th>\n",
       "      <th>D7</th>\n",
       "      <th>D8</th>\n",
       "      <th>D9</th>\n",
       "      <th>D10</th>\n",
       "      <th>...</th>\n",
       "      <th>D1767</th>\n",
       "      <th>D1768</th>\n",
       "      <th>D1769</th>\n",
       "      <th>D1770</th>\n",
       "      <th>D1771</th>\n",
       "      <th>D1772</th>\n",
       "      <th>D1773</th>\n",
       "      <th>D1774</th>\n",
       "      <th>D1775</th>\n",
       "      <th>D1776</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.366667</td>\n",
       "      <td>0.611765</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.110435</td>\n",
       "      <td>0.803973</td>\n",
       "      <td>0.106075</td>\n",
       "      <td>0.473965</td>\n",
       "      <td>0.835617</td>\n",
       "      <td>0.106452</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.758175</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.180128</td>\n",
       "      <td>0.621378</td>\n",
       "      <td>0.287144</td>\n",
       "      <td>0.503919</td>\n",
       "      <td>0.674919</td>\n",
       "      <td>0.403616</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.658812</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.243421</td>\n",
       "      <td>0.640959</td>\n",
       "      <td>0.312765</td>\n",
       "      <td>0.279784</td>\n",
       "      <td>0.686775</td>\n",
       "      <td>0.280301</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.655752</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.226978</td>\n",
       "      <td>0.776996</td>\n",
       "      <td>0.150657</td>\n",
       "      <td>0.336948</td>\n",
       "      <td>0.802121</td>\n",
       "      <td>0.125608</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.484851</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.561200</td>\n",
       "      <td>0.771463</td>\n",
       "      <td>0.244287</td>\n",
       "      <td>0.293096</td>\n",
       "      <td>0.717575</td>\n",
       "      <td>0.230842</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1776 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         D1        D2    D3   D4        D5        D6        D7        D8  \\\n",
       "0  0.366667  0.611765  0.05  0.0  0.110435  0.803973  0.106075  0.473965   \n",
       "1  0.100000  0.758175  0.30  0.0  0.180128  0.621378  0.287144  0.503919   \n",
       "2  0.100000  0.658812  0.10  0.0  0.243421  0.640959  0.312765  0.279784   \n",
       "3  0.100000  0.655752  0.10  0.0  0.226978  0.776996  0.150657  0.336948   \n",
       "4  0.000000  0.484851  0.00  0.0  0.561200  0.771463  0.244287  0.293096   \n",
       "\n",
       "         D9       D10  ...  D1767  D1768  D1769  D1770  D1771  D1772  D1773  \\\n",
       "0  0.835617  0.106452  ...      1      1      1      1      0      1      0   \n",
       "1  0.674919  0.403616  ...      0      0      0      0      0      0      0   \n",
       "2  0.686775  0.280301  ...      0      0      0      0      0      0      0   \n",
       "3  0.802121  0.125608  ...      0      0      0      0      0      0      0   \n",
       "4  0.717575  0.230842  ...      0      0      0      0      0      0      0   \n",
       "\n",
       "   D1774  D1775  D1776  \n",
       "0      0      1      0  \n",
       "1      0      0      0  \n",
       "2      0      0      0  \n",
       "3      0      0      0  \n",
       "4      0      0      0  \n",
       "\n",
       "[5 rows x 1776 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Activity</th>\n",
       "      <th>D1</th>\n",
       "      <th>D2</th>\n",
       "      <th>D3</th>\n",
       "      <th>D4</th>\n",
       "      <th>D5</th>\n",
       "      <th>D6</th>\n",
       "      <th>D7</th>\n",
       "      <th>D8</th>\n",
       "      <th>D9</th>\n",
       "      <th>...</th>\n",
       "      <th>D1767</th>\n",
       "      <th>D1768</th>\n",
       "      <th>D1769</th>\n",
       "      <th>D1770</th>\n",
       "      <th>D1771</th>\n",
       "      <th>D1772</th>\n",
       "      <th>D1773</th>\n",
       "      <th>D1774</th>\n",
       "      <th>D1775</th>\n",
       "      <th>D1776</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.497009</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.132956</td>\n",
       "      <td>0.678031</td>\n",
       "      <td>0.273166</td>\n",
       "      <td>0.585445</td>\n",
       "      <td>0.743663</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0.366667</td>\n",
       "      <td>0.606291</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.111209</td>\n",
       "      <td>0.803455</td>\n",
       "      <td>0.106105</td>\n",
       "      <td>0.411754</td>\n",
       "      <td>0.836582</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0.033300</td>\n",
       "      <td>0.480124</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.209791</td>\n",
       "      <td>0.610350</td>\n",
       "      <td>0.356453</td>\n",
       "      <td>0.517720</td>\n",
       "      <td>0.679051</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.538825</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.196344</td>\n",
       "      <td>0.724230</td>\n",
       "      <td>0.235606</td>\n",
       "      <td>0.288764</td>\n",
       "      <td>0.805110</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.517794</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.494734</td>\n",
       "      <td>0.781422</td>\n",
       "      <td>0.154361</td>\n",
       "      <td>0.303809</td>\n",
       "      <td>0.812646</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1777 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Activity        D1        D2    D3   D4        D5        D6        D7  \\\n",
       "0         1  0.000000  0.497009  0.10  0.0  0.132956  0.678031  0.273166   \n",
       "1         1  0.366667  0.606291  0.05  0.0  0.111209  0.803455  0.106105   \n",
       "2         1  0.033300  0.480124  0.00  0.0  0.209791  0.610350  0.356453   \n",
       "3         1  0.000000  0.538825  0.00  0.5  0.196344  0.724230  0.235606   \n",
       "4         0  0.100000  0.517794  0.00  0.0  0.494734  0.781422  0.154361   \n",
       "\n",
       "         D8        D9  ...  D1767  D1768  D1769  D1770  D1771  D1772  D1773  \\\n",
       "0  0.585445  0.743663  ...      0      0      0      0      0      0      0   \n",
       "1  0.411754  0.836582  ...      1      1      1      1      0      1      0   \n",
       "2  0.517720  0.679051  ...      0      0      0      0      0      0      0   \n",
       "3  0.288764  0.805110  ...      0      0      0      0      0      0      0   \n",
       "4  0.303809  0.812646  ...      0      0      0      0      0      0      0   \n",
       "\n",
       "   D1774  D1775  D1776  \n",
       "0      0      0      0  \n",
       "1      0      1      0  \n",
       "2      0      0      0  \n",
       "3      0      0      0  \n",
       "4      0      0      0  \n",
       "\n",
       "[5 rows x 1777 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scaling and standardisation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.decomposition import PCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "x=file.drop('Activity', axis=1)\n",
    "y=file['Activity']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Standardizing the features\n",
    "x = StandardScaler().fit_transform(x)\n",
    "#Splitting the train data into training and testing data using train test split\n",
    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>1766</th>\n",
       "      <th>1767</th>\n",
       "      <th>1768</th>\n",
       "      <th>1769</th>\n",
       "      <th>1770</th>\n",
       "      <th>1771</th>\n",
       "      <th>1772</th>\n",
       "      <th>1773</th>\n",
       "      <th>1774</th>\n",
       "      <th>1775</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.962112</td>\n",
       "      <td>-0.901566</td>\n",
       "      <td>0.406335</td>\n",
       "      <td>-0.336495</td>\n",
       "      <td>-0.771664</td>\n",
       "      <td>-0.109575</td>\n",
       "      <td>-0.017182</td>\n",
       "      <td>0.800886</td>\n",
       "      <td>-0.081646</td>\n",
       "      <td>-0.283699</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.166347</td>\n",
       "      <td>-0.121988</td>\n",
       "      <td>-0.118566</td>\n",
       "      <td>-0.149497</td>\n",
       "      <td>-0.124219</td>\n",
       "      <td>-0.130700</td>\n",
       "      <td>-0.111426</td>\n",
       "      <td>-0.108947</td>\n",
       "      <td>-0.143806</td>\n",
       "      <td>-0.106413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.622473</td>\n",
       "      <td>0.130899</td>\n",
       "      <td>-0.231390</td>\n",
       "      <td>-0.336495</td>\n",
       "      <td>-0.983668</td>\n",
       "      <td>1.484291</td>\n",
       "      <td>-1.873312</td>\n",
       "      <td>-0.266603</td>\n",
       "      <td>1.214430</td>\n",
       "      <td>-1.705571</td>\n",
       "      <td>...</td>\n",
       "      <td>6.011540</td>\n",
       "      <td>8.197561</td>\n",
       "      <td>8.434134</td>\n",
       "      <td>6.689088</td>\n",
       "      <td>-0.124219</td>\n",
       "      <td>7.651123</td>\n",
       "      <td>-0.111426</td>\n",
       "      <td>-0.108947</td>\n",
       "      <td>6.953795</td>\n",
       "      <td>-0.106413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.545748</td>\n",
       "      <td>-1.061088</td>\n",
       "      <td>-0.869114</td>\n",
       "      <td>-0.336495</td>\n",
       "      <td>-0.022620</td>\n",
       "      <td>-0.969645</td>\n",
       "      <td>0.908173</td>\n",
       "      <td>0.384653</td>\n",
       "      <td>-0.982879</td>\n",
       "      <td>0.852064</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.166347</td>\n",
       "      <td>-0.121988</td>\n",
       "      <td>-0.118566</td>\n",
       "      <td>-0.149497</td>\n",
       "      <td>-0.124219</td>\n",
       "      <td>-0.130700</td>\n",
       "      <td>-0.111426</td>\n",
       "      <td>-0.108947</td>\n",
       "      <td>-0.143806</td>\n",
       "      <td>-0.106413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.962112</td>\n",
       "      <td>-0.506505</td>\n",
       "      <td>-0.869114</td>\n",
       "      <td>3.978691</td>\n",
       "      <td>-0.153712</td>\n",
       "      <td>0.477511</td>\n",
       "      <td>-0.434494</td>\n",
       "      <td>-1.022490</td>\n",
       "      <td>0.775435</td>\n",
       "      <td>-0.639053</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.166347</td>\n",
       "      <td>-0.121988</td>\n",
       "      <td>-0.118566</td>\n",
       "      <td>-0.149497</td>\n",
       "      <td>-0.124219</td>\n",
       "      <td>-0.130700</td>\n",
       "      <td>-0.111426</td>\n",
       "      <td>-0.108947</td>\n",
       "      <td>-0.143806</td>\n",
       "      <td>-0.106413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.288230</td>\n",
       "      <td>-0.705193</td>\n",
       "      <td>-0.869114</td>\n",
       "      <td>-0.336495</td>\n",
       "      <td>2.755187</td>\n",
       "      <td>1.204300</td>\n",
       "      <td>-1.337163</td>\n",
       "      <td>-0.930022</td>\n",
       "      <td>0.880558</td>\n",
       "      <td>-1.511041</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.166347</td>\n",
       "      <td>-0.121988</td>\n",
       "      <td>-0.118566</td>\n",
       "      <td>-0.149497</td>\n",
       "      <td>-0.124219</td>\n",
       "      <td>-0.130700</td>\n",
       "      <td>-0.111426</td>\n",
       "      <td>-0.108947</td>\n",
       "      <td>-0.143806</td>\n",
       "      <td>-0.106413</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1776 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       0         1         2         3         4         5         6     \\\n",
       "0 -0.962112 -0.901566  0.406335 -0.336495 -0.771664 -0.109575 -0.017182   \n",
       "1  3.622473  0.130899 -0.231390 -0.336495 -0.983668  1.484291 -1.873312   \n",
       "2 -0.545748 -1.061088 -0.869114 -0.336495 -0.022620 -0.969645  0.908173   \n",
       "3 -0.962112 -0.506505 -0.869114  3.978691 -0.153712  0.477511 -0.434494   \n",
       "4  0.288230 -0.705193 -0.869114 -0.336495  2.755187  1.204300 -1.337163   \n",
       "\n",
       "       7         8         9     ...      1766      1767      1768      1769  \\\n",
       "0  0.800886 -0.081646 -0.283699  ... -0.166347 -0.121988 -0.118566 -0.149497   \n",
       "1 -0.266603  1.214430 -1.705571  ...  6.011540  8.197561  8.434134  6.689088   \n",
       "2  0.384653 -0.982879  0.852064  ... -0.166347 -0.121988 -0.118566 -0.149497   \n",
       "3 -1.022490  0.775435 -0.639053  ... -0.166347 -0.121988 -0.118566 -0.149497   \n",
       "4 -0.930022  0.880558 -1.511041  ... -0.166347 -0.121988 -0.118566 -0.149497   \n",
       "\n",
       "       1770      1771      1772      1773      1774      1775  \n",
       "0 -0.124219 -0.130700 -0.111426 -0.108947 -0.143806 -0.106413  \n",
       "1 -0.124219  7.651123 -0.111426 -0.108947  6.953795 -0.106413  \n",
       "2 -0.124219 -0.130700 -0.111426 -0.108947 -0.143806 -0.106413  \n",
       "3 -0.124219 -0.130700 -0.111426 -0.108947 -0.143806 -0.106413  \n",
       "4 -0.124219 -0.130700 -0.111426 -0.108947 -0.143806 -0.106413  \n",
       "\n",
       "[5 rows x 1776 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(x).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Principal component analysis\n",
    "Finding number of components to reduce dimensions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Explained variance\n",
    "pca = PCA(n_components=1176).fit(x)\n",
    "cumpca=np.cumsum(pca.explained_variance_ratio_)\n",
    "plt.plot(np.cumsum(pca.explained_variance_ratio_))\n",
    "plt.xlabel('number of components')\n",
    "plt.ylabel('cumulative explained variance')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "#250 components seems to be a good number covering 90% of the varience\n",
    "pca=PCA(n_components=250)\n",
    "\n",
    "#Transforming train and test data using principal copmponents\n",
    "X_train = pca.fit_transform(X_train)\n",
    "X_test = pca.transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Decesion tree with pca\n",
    "Fitting decesion tree on the principal components"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-validation scores (3-fold): [0.75059952 0.7384     0.7616    ]\n",
      "Mean cross-validation score (3-fold): 0.750\n",
      "Decision tree classifier (max_depth = 2)\n",
      " [[396 149]\n",
      " [163 530]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.71      0.73      0.72       545\n",
      "           1       0.78      0.76      0.77       693\n",
      "\n",
      "    accuracy                           0.75      1238\n",
      "   macro avg       0.74      0.75      0.74      1238\n",
      "weighted avg       0.75      0.75      0.75      1238\n",
      "\n",
      "Accuracy of DT classifier on training set: 0.75\n",
      "Accuracy of DT classifier on test set: 0.75\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.metrics import confusion_matrix,classification_report\n",
    "dt = DecisionTreeClassifier(max_depth=2).fit(X_train, y_train)\n",
    "tree_predicted = dt.predict(X_test)\n",
    "confusion = confusion_matrix(y_test, tree_predicted)\n",
    "cv_scores = cross_val_score(dt,x, y)\n",
    "\n",
    "print('Cross-validation scores (3-fold):', cv_scores)\n",
    "print('Mean cross-validation score (3-fold): {:.3f}'.format(np.mean(cv_scores)))\n",
    "\n",
    "print('Decision tree classifier (max_depth = 2)\\n', confusion)\n",
    "print(classification_report(y_test,tree_predicted))\n",
    "print('Accuracy of DT classifier on training set: {:.2f}'\n",
    "     .format(dt.score(X_train, y_train)))\n",
    "print('Accuracy of DT classifier on test set: {:.2f}'\n",
    "     .format(dt.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Decesion tree without pca"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-validation scores (3-fold): [0.75059952 0.7384     0.7616    ]\n",
      "Mean cross-validation score (3-fold): 0.750\n",
      "Decision tree classifier (max_depth = 2)\n",
      " [[396 149]\n",
      " [163 530]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.71      0.73      0.72       545\n",
      "           1       0.78      0.76      0.77       693\n",
      "\n",
      "    accuracy                           0.75      1238\n",
      "   macro avg       0.74      0.75      0.74      1238\n",
      "weighted avg       0.75      0.75      0.75      1238\n",
      "\n",
      "Accuracy of DT classifier on training set: 0.75\n",
      "Accuracy of DT classifier on test set: 0.75\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.metrics import confusion_matrix,classification_report\n",
    "dt = DecisionTreeClassifier(max_depth=2).fit(X_train, y_train)\n",
    "tree_predicted = dt.predict(X_test)\n",
    "confusion = confusion_matrix(y_test, tree_predicted)\n",
    "cv_scores = cross_val_score(dt,x, y)\n",
    "\n",
    "print('Cross-validation scores (3-fold):', cv_scores)\n",
    "print('Mean cross-validation score (3-fold): {:.3f}'.format(np.mean(cv_scores)))\n",
    "\n",
    "print('Decision tree classifier (max_depth = 2)\\n', confusion)\n",
    "print(classification_report(y_test,tree_predicted))\n",
    "print('Accuracy of DT classifier on training set: {:.2f}'\n",
    "     .format(dt.score(X_train, y_train)))\n",
    "print('Accuracy of DT classifier on test set: {:.2f}'\n",
    "     .format(dt.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Decision tree performs better when fitted without pca. Reduction in 10% accuracy is observed when decesion tree is fit on pca. This is likely due to the fact that there are many binary cattegorical parameters in the predictors which has low varience but has significant co-orrelation with response."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Random forest classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\ensemble\\forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n",
      "  \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n",
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-validation scores (3-fold): [0.75059952 0.7384     0.7616    ]\n",
      "Mean cross-validation score (3-fold): 0.750\n",
      "Accuracy of RF classifier on training set: 0.99\n",
      "Accuracy of RF classifier on test set: 0.72\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "#random forest\n",
    "X_train, X_test, y_train, y_test = train_test_split(x,y, random_state = 0)\n",
    "\n",
    "clf = RandomForestClassifier(max_features = 8, random_state = 0)\n",
    "clf.fit(X_train, y_train)\n",
    "predict=clf.predict(X_test)\n",
    "\n",
    "print('Accuracy of RF classifier on training set: {:.2f}'\n",
    "     .format(clf.score(X_train, y_train)))\n",
    "print('Accuracy of RF classifier on test set: {:.2f}'\n",
    "     .format(clf.score(X_test, y_test)))\n",
    "predict[1:12]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\n",
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\ensemble\\forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n",
      "  \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n",
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\ensemble\\forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n",
      "  \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-validation scores (3-fold): [0.75379696 0.7096     0.7624    ]\n",
      "Mean cross-validation score (3-fold): 0.742\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Som\\Anaconda3\\envs\\env1\\lib\\site-packages\\sklearn\\ensemble\\forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n",
      "  \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "clf = RandomForestClassifier(max_features = 8, random_state = 0)\n",
    "\n",
    "cv_scores = cross_val_score(clf,x, y)\n",
    "\n",
    "print('Cross-validation scores (3-fold):', cv_scores)\n",
    "print('Mean cross-validation score (3-fold): {:.3f}'.format(np.mean(cv_scores)))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Conclusion\n",
    "Decesion tree without pca performs as the best model with test accuracy of 75%. Random forest well on training data with 99% accuracy but performs poorly on test data with 72% accuracy. Therefore, decesion tree is used to generate predicted values on the test data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_prediction = dt.predict(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(test_prediction)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Decesion tree predict all the response values to be zero. Which is probably not expected. Trying random forest classifier to check for number of reponse variables as 1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_prediction = clf.predict_proba(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1092.1, 1408.9])"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(test_prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_prediction=pd.DataFrame(test_prediction)\n",
    "pred=pd.DataFrame(test_prediction[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PredictedProbability</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MoleculeId</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            PredictedProbability\n",
       "MoleculeId                      \n",
       "1                            0.4\n",
       "2                            0.5\n",
       "3                            0.6\n",
       "4                            0.5\n",
       "5                            0.7"
      ]
     },
     "execution_count": 147,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred.columns=['PredictedProbability']\n",
    "pred.index=range(1,2502)\n",
    "pred.index.name='MoleculeId'\n",
    "pred.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred.to_csv('Bioresponse.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}