xgb_with_count.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(200000, 202)\n"
     ]
    }
   ],
   "source": [
    "import cudf as gd\n",
    "import pandas as pd\n",
    "import time\n",
    "import xgboost as xgb\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "PATH = '../input'\n",
    "cols = ['ID_code', 'target'] + ['var_%d'%i for i in range(200)]\n",
    "dtypes = ['int32', 'int32'] + ['float32' for i in range(200)]\n",
    "train_gd = gd.read_csv('%s/train.csv'%PATH,names=cols,dtype=dtypes,skiprows=1)\n",
    "print(train_gd.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 39 s, sys: 1min 54s, total: 2min 33s\n",
      "Wall time: 3min 40s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "for i in range(200):\n",
    "    col = 'var_%d'%i\n",
    "    var_count = train_gd.groupby(col).agg({col:'count'})\n",
    "    var_count.columns = ['%s_count'%col]\n",
    "    var_count = var_count.reset_index()\n",
    "    train_gd = train_gd.merge(var_count,on=col,how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0]\teval-auc:0.528313\ttrain-auc:0.527316\n",
      "Multiple eval metrics have been passed: 'train-auc' will be used for early stopping.\n",
      "\n",
      "Will train until train-auc hasn't improved in 30 rounds.\n",
      "[1000]\teval-auc:0.887032\ttrain-auc:0.885971\n",
      "[2000]\teval-auc:0.901109\ttrain-auc:0.902143\n",
      "[3000]\teval-auc:0.903539\ttrain-auc:0.907638\n",
      "[4000]\teval-auc:0.904385\ttrain-auc:0.910537\n",
      "[5000]\teval-auc:0.904599\ttrain-auc:0.912562\n",
      "[6000]\teval-auc:0.904142\ttrain-auc:0.914191\n",
      "[7000]\teval-auc:0.904253\ttrain-auc:0.91562\n",
      "[8000]\teval-auc:0.9038\ttrain-auc:0.916824\n",
      "[9000]\teval-auc:0.903308\ttrain-auc:0.917899\n",
      "[9999]\teval-auc:0.903325\ttrain-auc:0.918851\n",
      "CPU times: user 3h 6min 8s, sys: 10min 35s, total: 3h 16min 44s\n",
      "Wall time: 2min 40s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "train,valid = train_gd[:-10000],train_gd[-10000:]\n",
    "x_train = train.drop(['target','ID_code'])\n",
    "y_train = train['target']\n",
    "x_valid = valid.drop(['target','ID_code'])\n",
    "y_valid = valid['target']\n",
    "\n",
    "xgb_params = {\n",
    "            'objective': 'binary:logistic',\n",
    "            'tree_method': 'gpu_hist',\n",
    "            'max_depth': 1, \n",
    "            'eta':0.1,\n",
    "            'silent':1,\n",
    "            'subsample':0.5,\n",
    "            'colsample_bytree': 0.05,  \n",
    "            'eval_metric':'auc',\n",
    "}\n",
    "dtrain = xgb.DMatrix(data=x_train.to_pandas(), label=y_train.to_pandas())\n",
    "dvalid = xgb.DMatrix(data=x_valid.to_pandas(), label=y_valid.to_pandas())\n",
    "watchlist = [(dvalid, 'eval'), (dtrain, 'train')]\n",
    "clf = xgb.train(xgb_params, dtrain=dtrain,\n",
    "                num_boost_round=10000,evals=watchlist,\n",
    "                early_stopping_rounds=30,maximize=True,\n",
    "                verbose_eval=1000)\n",
    "yp = clf.predict(dvalid)"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}