Test Prediction XGBoost.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from pandas.io.parsers import read_csv\n",
    "%matplotlib inline\n",
    "\n",
    "from matplotlib import pyplot as plt\n",
    "import matplotlib as mpl\n",
    "\n",
    "import scipy\n",
    "\n",
    "import xgboost as xgb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "bst = xgb.Booster({'nthread':4})\n",
    "bst.load_model(\"0001.model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "dtest = xgb.DMatrix(\"test.buffer\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "test_sid = np.load(\"test.sid.npy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "test_iid = np.load(\"test.iid.npy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y_pred_xgb_prob = bst.predict(dtest)\n",
    "\n",
    "y_pred_xgb = np.ones_like(y_pred_xgb_prob)\n",
    "y_pred_xgb[:] = y_pred_xgb_prob\n",
    "\n",
    "threshold = 0.047\n",
    "\n",
    "y_pred_xgb[y_pred_xgb >= threshold] = 1\n",
    "y_pred_xgb[y_pred_xgb < threshold] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2724529 0.330174261563\n"
     ]
    }
   ],
   "source": [
    "print np.count_nonzero(y_pred_xgb), 1.0 * np.count_nonzero(y_pred_xgb) / len(test_sid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df = pd.DataFrame(y_pred_xgb, index=test_sid).reset_index()\n",
    "df.columns = ['sid', 'pred_xgb']\n",
    "df['iid'] = test_iid"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sid</th>\n",
       "      <th>pred_xgb</th>\n",
       "      <th>iid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>214530776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>214530776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>214530776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>214820942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>214826810</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sid  pred_xgb        iid\n",
       "0    5         1  214530776\n",
       "1    5         1  214530776\n",
       "2    5         1  214530776\n",
       "3   10         0  214820942\n",
       "4   10         0  214826810"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "guess_df = df[df['pred_xgb'] == 1].groupby('sid')['iid'].apply(lambda group: ','.join(str(k) for k in set(group.values)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "guess_df.reset_index().to_csv(\"xgb_0.1.guess\", sep=\";\", index=False, header=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}