apply_model/java/train_model.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# catboost4j-prediction tutorial"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -q numpy pandas catboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from __future__ import absolute_import, division, print_function, unicode_literals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CatBoost version 0.14.2\n",
      "NumPy version 1.16.3\n",
      "Pandas version 0.24.2\n"
     ]
    }
   ],
   "source": [
    "import catboost as cb\n",
    "import catboost.datasets as cbd\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "# print module versions for reproducibility\n",
    "print('CatBoost version {}'.format(cb.__version__))\n",
    "print('NumPy version {}'.format(np.__version__))\n",
    "print('Pandas version {}'.format(pd.__version__))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "    Download \"Adult Data Set\" [1] from UCI Machine Learning Repository.\n",
      "\n",
      "    Will return two pandas.DataFrame-s, first with train part (adult.data) and second with test part\n",
      "    (adult.test) of the dataset.\n",
      "\n",
      "    [1]: https://archive.ics.uci.edu/ml/datasets/Adult\n",
      "    \n"
     ]
    }
   ],
   "source": [
    "# We are going to use UCI Adult Data Set because it has both numerical and categorical \n",
    "# features and also has missing features.\n",
    "print(cbd.adult.__doc__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_fixed_adult():\n",
    "    train, test = cbd.adult()\n",
    "    \n",
    "    # CatBoost doesn't support pandas.DataFrame missing values for categorical features out \n",
    "    # of the box (seed issue #571 on GitHub or issue MLTOOLS-2785 in internal tracker). So \n",
    "    # we have to replace them with some designated string manually. \n",
    "    for dataset in (train, test, ):\n",
    "        for name in (name for name, dtype in dict(dataset.dtypes).items() if dtype == np.object):\n",
    "            dataset[name].fillna('nan', inplace=True)\n",
    "    \n",
    "    X_train, y_train = train.drop('income', axis=1), train.income\n",
    "    X_test, y_test = test.drop('income', axis=1), test.income\n",
    "    return X_train, y_train, X_test, y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, y_train, _, _ = get_fixed_adult()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>age</th>\n",
       "      <th>workclass</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>education</th>\n",
       "      <th>education-num</th>\n",
       "      <th>marital-status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39.0</td>\n",
       "      <td>State-gov</td>\n",
       "      <td>77516.0</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13.0</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>2174.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50.0</td>\n",
       "      <td>Self-emp-not-inc</td>\n",
       "      <td>83311.0</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13.0</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>38.0</td>\n",
       "      <td>Private</td>\n",
       "      <td>215646.0</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Divorced</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>53.0</td>\n",
       "      <td>Private</td>\n",
       "      <td>234721.0</td>\n",
       "      <td>11th</td>\n",
       "      <td>7.0</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28.0</td>\n",
       "      <td>Private</td>\n",
       "      <td>338409.0</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13.0</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Prof-specialty</td>\n",
       "      <td>Wife</td>\n",
       "      <td>Black</td>\n",
       "      <td>Female</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>Cuba</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age         workclass    fnlwgt  education  education-num  \\\n",
       "0  39.0         State-gov   77516.0  Bachelors           13.0   \n",
       "1  50.0  Self-emp-not-inc   83311.0  Bachelors           13.0   \n",
       "2  38.0           Private  215646.0    HS-grad            9.0   \n",
       "3  53.0           Private  234721.0       11th            7.0   \n",
       "4  28.0           Private  338409.0  Bachelors           13.0   \n",
       "\n",
       "       marital-status         occupation   relationship   race     sex  \\\n",
       "0       Never-married       Adm-clerical  Not-in-family  White    Male   \n",
       "1  Married-civ-spouse    Exec-managerial        Husband  White    Male   \n",
       "2            Divorced  Handlers-cleaners  Not-in-family  White    Male   \n",
       "3  Married-civ-spouse  Handlers-cleaners        Husband  Black    Male   \n",
       "4  Married-civ-spouse     Prof-specialty           Wife  Black  Female   \n",
       "\n",
       "   capital-gain  capital-loss  hours-per-week native-country  \n",
       "0        2174.0           0.0            40.0  United-States  \n",
       "1           0.0           0.0            13.0  United-States  \n",
       "2           0.0           0.0            40.0  United-States  \n",
       "3           0.0           0.0            40.0  United-States  \n",
       "4           0.0           0.0            40.0           Cuba  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning: Custom metrics will not be evaluated because there are no test datasets\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<catboost.core.CatBoostClassifier at 0x7f1f7d037eb8>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# If you want to find out how we found these parameters check \"Simple classification \n",
    "# example with missing feature handling and parameter tuning\" tutorial in `classification`\n",
    "# subdirectory of tutorials\n",
    "model = cb.CatBoostClassifier(\n",
    "    class_names=('<=50K', '>50K'),\n",
    "    loss_function='Logloss',\n",
    "    eval_metric='AUC', \n",
    "    custom_metric=['AUC'],\n",
    "    iterations=100,\n",
    "    random_seed=20181224,\n",
    "    learning_rate=0.4234185321620083, \n",
    "    depth=5, \n",
    "    l2_leaf_reg=9.464266235679002)\n",
    "model.fit(\n",
    "    cb.Pool(X_train, y_train, cat_features=np.where(X_train.dtypes != np.float)[0]),\n",
    "    verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save_model('adult.cbm')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "156K\tadult.cbm\r\n"
     ]
    }
   ],
   "source": [
    "!du -sh adult.cbm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We got the model, now it's time to use it via `catboost4j-prediction` package for Java. Next part of the tutorial\n",
    "will be in a Maven project (seed directory named the same way as this notebook)."
   ]
  }
 ],
 "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
}