Coupon Purchase Prediction - BTB Script.ipynb

Coupon Purchase Prediction - First Script.ipynb

Flavor of Physics - Classification.ipynb

Flavor of Physics - Mix of models.ipynb

Springleaf - Experiments with Classification.ipynb

Springleaf - Experiments with Random Forest.ipynb

SpringLeaf -Kaggle 18AUG15 (1).ipynb

SpringLeaf -Kaggle 18AUG15.ipynb

Springleaf with xgb.ipynb

Springleaf with xgb1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import sys\n",
    "sys.path.append('C:\\\\Users\\\\Vikrant\\\\xgboost\\\\python-package')\n",
    "import xgboost as xgb\n",
    "from datetime import  datetime"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "train = pd.read_csv('train_Spring.csv')\n",
    "test = pd.read_csv('test_Spring.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def get_data():\n",
    "    features = train.select_dtypes(include=['float']).columns\n",
    "    features = np.setdiff1d(features,['ID','target'])\n",
    "\n",
    "    test_ids = test.ID\n",
    "    y_train = train.target\n",
    "\n",
    "    x_train = train[features]\n",
    "    x_test = test[features]\n",
    "\n",
    "    return x_train, y_train, x_test, test_ids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "ts = datetime.now()\n",
    "x_train, y_train, x_test, test_ids = get_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "xgb_params = {\"objective\": \"binary:logistic\", \"max_depth\": 10, \"silent\": 1}\n",
    "num_rounds = 200"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "dtrain = xgb.DMatrix(x_train, label=y_train)\n",
    "dtest = xgb.DMatrix(x_test)\n",
    "gbdt = xgb.train(xgb_params, dtrain, num_rounds)\n",
    "\n",
    "preds = gbdt.predict(dtest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "elapsed time: 0:11:31.227000\n"
     ]
    }
   ],
   "source": [
    "submission = pd.DataFrame({\"ID\": test_ids, \"target\": preds})\n",
    "submission = submission.set_index('ID')\n",
    "submission.to_csv('Springleaf1.csv')\n",
    "\n",
    "te = datetime.now()\n",
    "print('elapsed time: {0}'.format(te-ts))"
   ]
  },
  {
   "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": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}