class_weight_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ri</th>\n",
       "      <th>na</th>\n",
       "      <th>mg</th>\n",
       "      <th>al</th>\n",
       "      <th>si</th>\n",
       "      <th>k</th>\n",
       "      <th>ca</th>\n",
       "      <th>ba</th>\n",
       "      <th>fe</th>\n",
       "      <th>glass_type</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>1.51966</td>\n",
       "      <td>14.77</td>\n",
       "      <td>3.75</td>\n",
       "      <td>0.29</td>\n",
       "      <td>72.02</td>\n",
       "      <td>0.03</td>\n",
       "      <td>9.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>185</th>\n",
       "      <td>1.51115</td>\n",
       "      <td>17.38</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.34</td>\n",
       "      <td>75.41</td>\n",
       "      <td>0.00</td>\n",
       "      <td>6.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>1.52213</td>\n",
       "      <td>14.21</td>\n",
       "      <td>3.82</td>\n",
       "      <td>0.47</td>\n",
       "      <td>71.77</td>\n",
       "      <td>0.11</td>\n",
       "      <td>9.57</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>1.52213</td>\n",
       "      <td>14.21</td>\n",
       "      <td>3.82</td>\n",
       "      <td>0.47</td>\n",
       "      <td>71.77</td>\n",
       "      <td>0.11</td>\n",
       "      <td>9.57</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51</th>\n",
       "      <td>1.52320</td>\n",
       "      <td>13.72</td>\n",
       "      <td>3.72</td>\n",
       "      <td>0.51</td>\n",
       "      <td>71.75</td>\n",
       "      <td>0.09</td>\n",
       "      <td>10.06</td>\n",
       "      <td>0</td>\n",
       "      <td>0.16</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          ri     na    mg    al     si     k     ca  ba    fe  glass_type\n",
       "id                                                                       \n",
       "22   1.51966  14.77  3.75  0.29  72.02  0.03   9.00   0  0.00           1\n",
       "185  1.51115  17.38  0.00  0.34  75.41  0.00   6.65   0  0.00           6\n",
       "40   1.52213  14.21  3.82  0.47  71.77  0.11   9.57   0  0.00           1\n",
       "39   1.52213  14.21  3.82  0.47  71.77  0.11   9.57   0  0.00           1\n",
       "51   1.52320  13.72  3.72  0.51  71.75  0.09  10.06   0  0.16           1"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/glass/glass.data'\n",
    "col_names = ['id','ri','na','mg','al','si','k','ca','ba','fe','glass_type']\n",
    "glass = pd.read_csv(url, names=col_names, index_col='id')\n",
    "glass.sort_values('al', inplace=True)\n",
    "glass.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "glass['household'] = glass.glass_type.map({1:0, 2:0, 3:0, 5:1, 6:1, 7:1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "glass_normal = glass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "glass_doubled = pd.concat([glass_normal, glass[glass.household == 1]], axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    163\n",
       "1     51\n",
       "Name: household, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "glass_normal.household.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    163\n",
       "1    102\n",
       "Name: household, dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "glass_doubled.household.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 4.18040386]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Run normal regression on normal data\n",
    "\n",
    "logreg = LogisticRegression(C=1e9)\n",
    "feature_cols = ['al']\n",
    "X = glass_normal[feature_cols]\n",
    "y = glass_normal.household\n",
    "logreg.fit(X, y)\n",
    "logreg.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 3.85191349]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Run weighted regression on normal data\n",
    "\n",
    "logreg = LogisticRegression(C=1e9, class_weight={0:1, 1:2})\n",
    "feature_cols = ['al']\n",
    "X = glass_normal[feature_cols]\n",
    "y = glass_normal.household\n",
    "logreg.fit(X, y)\n",
    "logreg.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 3.85191349]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Run normal regression on oversampled data\n",
    "\n",
    "logreg = LogisticRegression(C=1e9)\n",
    "feature_cols = ['al']\n",
    "X = glass_doubled[feature_cols]\n",
    "y = glass_doubled.household\n",
    "logreg.fit(X, y)\n",
    "logreg.coef_"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}