Column Transformer Example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "emp_data = pd.read_csv('https://raw.githubusercontent.com/zekelabs/data-science-complete-tutorial/master/Data/HR_comma_sep.csv.txt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>satisfaction_level</th>\n",
       "      <th>last_evaluation</th>\n",
       "      <th>number_project</th>\n",
       "      <th>average_montly_hours</th>\n",
       "      <th>time_spend_company</th>\n",
       "      <th>Work_accident</th>\n",
       "      <th>left</th>\n",
       "      <th>promotion_last_5years</th>\n",
       "      <th>sales</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.38</td>\n",
       "      <td>0.53</td>\n",
       "      <td>2</td>\n",
       "      <td>157</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.80</td>\n",
       "      <td>0.86</td>\n",
       "      <td>5</td>\n",
       "      <td>262</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.11</td>\n",
       "      <td>0.88</td>\n",
       "      <td>7</td>\n",
       "      <td>272</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.72</td>\n",
       "      <td>0.87</td>\n",
       "      <td>5</td>\n",
       "      <td>223</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.37</td>\n",
       "      <td>0.52</td>\n",
       "      <td>2</td>\n",
       "      <td>159</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   satisfaction_level  last_evaluation  number_project  average_montly_hours  \\\n",
       "0                0.38             0.53               2                   157   \n",
       "1                0.80             0.86               5                   262   \n",
       "2                0.11             0.88               7                   272   \n",
       "3                0.72             0.87               5                   223   \n",
       "4                0.37             0.52               2                   159   \n",
       "\n",
       "   time_spend_company  Work_accident  left  promotion_last_5years  sales  \\\n",
       "0                   3              0     1                      0  sales   \n",
       "1                   6              0     1                      0  sales   \n",
       "2                   4              0     1                      0  sales   \n",
       "3                   5              0     1                      0  sales   \n",
       "4                   3              0     1                      0  sales   \n",
       "\n",
       "   salary  \n",
       "0     low  \n",
       "1  medium  \n",
       "2  medium  \n",
       "3     low  \n",
       "4     low  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emp_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 14999 entries, 0 to 14998\n",
      "Data columns (total 10 columns):\n",
      "satisfaction_level       14999 non-null float64\n",
      "last_evaluation          14999 non-null float64\n",
      "number_project           14999 non-null int64\n",
      "average_montly_hours     14999 non-null int64\n",
      "time_spend_company       14999 non-null int64\n",
      "Work_accident            14999 non-null int64\n",
      "left                     14999 non-null int64\n",
      "promotion_last_5years    14999 non-null int64\n",
      "department               14999 non-null object\n",
      "salary                   14999 non-null object\n",
      "dtypes: float64(2), int64(6), object(2)\n",
      "memory usage: 1.1+ MB\n"
     ]
    }
   ],
   "source": [
    "emp_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['sales', 'accounting', 'hr', 'technical', 'support', 'management',\n",
       "       'IT', 'product_mng', 'marketing', 'RandD'], dtype=object)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emp_data.sales.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "emp_data.rename(columns={'sales':'department'}, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>satisfaction_level</th>\n",
       "      <th>last_evaluation</th>\n",
       "      <th>number_project</th>\n",
       "      <th>average_montly_hours</th>\n",
       "      <th>time_spend_company</th>\n",
       "      <th>Work_accident</th>\n",
       "      <th>left</th>\n",
       "      <th>promotion_last_5years</th>\n",
       "      <th>department</th>\n",
       "      <th>salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.38</td>\n",
       "      <td>0.53</td>\n",
       "      <td>2</td>\n",
       "      <td>157</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.80</td>\n",
       "      <td>0.86</td>\n",
       "      <td>5</td>\n",
       "      <td>262</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.11</td>\n",
       "      <td>0.88</td>\n",
       "      <td>7</td>\n",
       "      <td>272</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.72</td>\n",
       "      <td>0.87</td>\n",
       "      <td>5</td>\n",
       "      <td>223</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.37</td>\n",
       "      <td>0.52</td>\n",
       "      <td>2</td>\n",
       "      <td>159</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>sales</td>\n",
       "      <td>low</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   satisfaction_level  last_evaluation  number_project  average_montly_hours  \\\n",
       "0                0.38             0.53               2                   157   \n",
       "1                0.80             0.86               5                   262   \n",
       "2                0.11             0.88               7                   272   \n",
       "3                0.72             0.87               5                   223   \n",
       "4                0.37             0.52               2                   159   \n",
       "\n",
       "   time_spend_company  Work_accident  left  promotion_last_5years department  \\\n",
       "0                   3              0     1                      0      sales   \n",
       "1                   6              0     1                      0      sales   \n",
       "2                   4              0     1                      0      sales   \n",
       "3                   5              0     1                      0      sales   \n",
       "4                   3              0     1                      0      sales   \n",
       "\n",
       "   salary  \n",
       "0     low  \n",
       "1  medium  \n",
       "2  medium  \n",
       "3     low  \n",
       "4     low  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emp_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import OneHotEncoder, StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline_cat = make_pipeline(\n",
    "    OneHotEncoder(handle_unknown='ignore')\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline_num = make_pipeline(\n",
    "    StandardScaler()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import ColumnTransformer, make_column_transformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_cols = ['number_project','average_montly_hours','time_spend_company','Work_accident','promotion_last_5years']\n",
    "cat_cols = ['department','salary']\n",
    "\n",
    "preprocessor = ColumnTransformer(\n",
    "    transformers=[\n",
    "        ('num_proc', pipeline_num, num_cols),\n",
    "        ('cat_proc', pipeline_cat, cat_cols)], \n",
    "    remainder='passthrough')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "pipeline = make_pipeline(preprocessor,DecisionTreeClassifier())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "feature_data = emp_data.drop('left',axis=1)\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "trainX, testX, trainY, testY = train_test_split(feature_data, emp_data.left)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/awantik/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/data.py:625: DataConversionWarning: Data with input dtype int64 were all converted to float64 by StandardScaler.\n",
      "  return self.partial_fit(X, y)\n",
      "/home/awantik/anaconda3/lib/python3.7/site-packages/sklearn/base.py:465: DataConversionWarning: Data with input dtype int64 were all converted to float64 by StandardScaler.\n",
      "  return self.fit(X, y, **fit_params).transform(X)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pipeline(memory=None,\n",
       "     steps=[('columntransformer', ColumnTransformer(n_jobs=None, remainder='passthrough', sparse_threshold=0.3,\n",
       "         transformer_weights=None,\n",
       "         transformers=[('num', Pipeline(memory=None,\n",
       "     steps=[('standardscaler', StandardScaler(copy=True, with_mean=True, with_std=True))]), ['number_proj...      min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best'))])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.fit(trainX, trainY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/awantik/anaconda3/lib/python3.7/site-packages/sklearn/pipeline.py:451: DataConversionWarning: Data with input dtype int64 were all converted to float64 by StandardScaler.\n",
      "  Xt = transform.transform(Xt)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.9818666666666667"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.score(testX,testY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}