examples/DateComponents.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-09-18T08:12:38.232692Z",
     "start_time": "2018-09-18T08:12:38.223700Z"
    }
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append('..')\n",
    "\n",
    "from datefeatures import DateComponents\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from randdate import randdate\n",
    "from datetime import datetime\n",
    "\n",
    "from sklearn.pipeline import Pipeline, FeatureUnion\n",
    "from mlxtend.feature_selection import ColumnSelector"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-09-18T08:12:38.249524Z",
     "start_time": "2018-09-18T08:12:38.237886Z"
    }
   },
   "source": [
    "# Example 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>0_na</th>\n",
       "      <th>0_eoq</th>\n",
       "      <th>0_quarter</th>\n",
       "      <th>0_eom</th>\n",
       "      <th>0_month</th>\n",
       "      <th>1_na</th>\n",
       "      <th>1_eoq</th>\n",
       "      <th>1_quarter</th>\n",
       "      <th>1_eom</th>\n",
       "      <th>1_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0_na  0_eoq  0_quarter  0_eom  0_month   1_na  1_eoq  1_quarter  1_eom  \\\n",
       "0  False      0          2      0        5  False      0          3      0   \n",
       "1  False      0          3      0        9  False      0          2      0   \n",
       "2  False      0          1      0        3  False      0          3      0   \n",
       "3  False      0          3      0        9  False      0          1      0   \n",
       "4  False      0          4      0       12  False      0          1      0   \n",
       "\n",
       "   1_month  \n",
       "0        9  \n",
       "1        5  \n",
       "2        9  \n",
       "3        3  \n",
       "4        1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# generate fake dates\n",
    "X = np.c_[np.array(randdate(10)), np.array(randdate(10))]\n",
    "\n",
    "# transform date variable to fetures\n",
    "cmp = DateComponents(year=False, month=True, day=False, hour=False, minute=False, second=False)\n",
    "cmp.fit(X)\n",
    "Z = cmp.transform(X)\n",
    "\n",
    "Z.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "n_samples = 100000\n",
    "X = np.c_[np.array(randdate(n_samples)), np.array(randdate(n_samples)), np.array(randdate(n_samples))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 222 ms, sys: 11.4 ms, total: 233 ms\n",
      "Wall time: 236 ms\n"
     ]
    }
   ],
   "source": [
    "cmp = DateComponents(year=True, month=False, day=False, hour=False, minute=False, second=False)\n",
    "%time Z = cmp.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 161 ms, sys: 4.64 ms, total: 166 ms\n",
      "Wall time: 165 ms\n"
     ]
    }
   ],
   "source": [
    "cmp = DateComponents(year=False, month=False, day=False, hour=True, minute=True, second=False)\n",
    "%time Z = cmp.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 968 ms, sys: 70.8 ms, total: 1.04 s\n",
      "Wall time: 1.04 s\n"
     ]
    }
   ],
   "source": [
    "cmp = DateComponents(year=True, month=True, day=True, hour=True, minute=True, second=True, microsecond=True)\n",
    "%time Z = cmp.fit_transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "n_samples = 5\n",
    "\n",
    "# generate fake dates\n",
    "X = np.c_[np.array(randdate(n_samples))]\n",
    "\n",
    "# emulate missing value\n",
    "X[1,0] = np.nan"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Example 3a -- without correction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "cmp = DateComponents(missing=False)\n",
    "\n",
    "# What will happen?\n",
    "Z = cmp.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0_eoq           bool\n",
       "0_quarter    float64\n",
       "0_eom           bool\n",
       "0_month      float64\n",
       "0_dy         float64\n",
       "0_dw         float64\n",
       "0_week       float64\n",
       "0_day        float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Z.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>0_eoq</th>\n",
       "      <th>0_quarter</th>\n",
       "      <th>0_eom</th>\n",
       "      <th>0_month</th>\n",
       "      <th>0_dy</th>\n",
       "      <th>0_dw</th>\n",
       "      <th>0_week</th>\n",
       "      <th>0_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>1.0</td>\n",
       "      <td>False</td>\n",
       "      <td>3.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>29.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>3.0</td>\n",
       "      <td>False</td>\n",
       "      <td>8.0</td>\n",
       "      <td>241.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>29.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>2.0</td>\n",
       "      <td>False</td>\n",
       "      <td>4.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>4.0</td>\n",
       "      <td>False</td>\n",
       "      <td>12.0</td>\n",
       "      <td>362.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>28.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0_eoq  0_quarter  0_eom  0_month   0_dy  0_dw  0_week  0_day\n",
       "0  False        1.0  False      3.0   89.0   0.0    14.0   29.0\n",
       "1  False        NaN  False      NaN    NaN   NaN     NaN    NaN\n",
       "2  False        3.0  False      8.0  241.0   1.0    35.0   29.0\n",
       "3  False        2.0  False      4.0   93.0   4.0    14.0    3.0\n",
       "4  False        4.0  False     12.0  362.0   2.0    52.0   28.0"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Z.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Example 3b -- with missing value correction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "cmp = DateComponents(missing=True, year=True)\n",
    "Z = cmp.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0_na          bool\n",
       "0_leap        int8\n",
       "0_year       int16\n",
       "0_eoq         int8\n",
       "0_quarter     int8\n",
       "0_eom         int8\n",
       "0_month       int8\n",
       "0_dy         int16\n",
       "0_dw          int8\n",
       "0_week        int8\n",
       "0_day         int8\n",
       "dtype: object"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Z.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>0_na</th>\n",
       "      <th>0_leap</th>\n",
       "      <th>0_year</th>\n",
       "      <th>0_eoq</th>\n",
       "      <th>0_quarter</th>\n",
       "      <th>0_eom</th>\n",
       "      <th>0_month</th>\n",
       "      <th>0_dy</th>\n",
       "      <th>0_dw</th>\n",
       "      <th>0_week</th>\n",
       "      <th>0_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>1</td>\n",
       "      <td>1976</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>89</td>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>True</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1978</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>241</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1981</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>93</td>\n",
       "      <td>4</td>\n",
       "      <td>14</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1994</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>362</td>\n",
       "      <td>2</td>\n",
       "      <td>52</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0_na  0_leap  0_year  0_eoq  0_quarter  0_eom  0_month  0_dy  0_dw  \\\n",
       "0  False       1    1976      0          1      0        3    89     0   \n",
       "1   True      -1      -1     -1         -1     -1       -1    -1    -1   \n",
       "2  False       0    1978      0          3      0        8   241     1   \n",
       "3  False       0    1981      0          2      0        4    93     4   \n",
       "4  False       0    1994      0          4      0       12   362     2   \n",
       "\n",
       "   0_week  0_day  \n",
       "0      14     29  \n",
       "1      -1     -1  \n",
       "2      35     29  \n",
       "3      14      3  \n",
       "4      52     28  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Z.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>0_na</th>\n",
       "      <th>0_hour</th>\n",
       "      <th>0_min</th>\n",
       "      <th>0_sec</th>\n",
       "      <th>0_ms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>23</td>\n",
       "      <td>59</td>\n",
       "      <td>58</td>\n",
       "      <td>12345</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0_na  0_hour  0_min  0_sec   0_ms\n",
       "0  False      23     59     58  12345"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = np.array(datetime(2016, 1, 1, 23, 59, 58, 12345)).reshape(1, -1)\n",
    "cmp = DateComponents(\n",
    "            year=False, month=False, day=False,\n",
    "            hour=True, minute=True, second=True, microsecond=True)\n",
    "Z = cmp.fit_transform(X)\n",
    "Z"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>0_na</th>\n",
       "      <th>0_eoq</th>\n",
       "      <th>0_quarter</th>\n",
       "      <th>0_eom</th>\n",
       "      <th>0_month</th>\n",
       "      <th>0_dy</th>\n",
       "      <th>0_dw</th>\n",
       "      <th>0_week</th>\n",
       "      <th>0_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>86</td>\n",
       "      <td>4</td>\n",
       "      <td>13</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>165</td>\n",
       "      <td>4</td>\n",
       "      <td>24</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>101</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>357</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0_na  0_eoq  0_quarter  0_eom  0_month  0_dy  0_dw  0_week  0_day\n",
       "0  False      0          1      0        3    86     4      13     27\n",
       "1  False      0          2      0        6   165     4      24     14\n",
       "2  False      0          1      0        2    40     0       7      9\n",
       "3  False      0          2      0        4   101     5      15     11\n",
       "4  False      0          4      0       12   357     0      52     23"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# generate fake dates\n",
    "n_samples = 5\n",
    "X = np.c_[np.array(randdate(n_samples))]\n",
    "\n",
    "# make pipeline\n",
    "pipe = Pipeline(steps=[\n",
    "    ('pre', DateComponents())\n",
    "])\n",
    "\n",
    "Z = pipe.fit_transform(X)\n",
    "Z"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>this_date</th>\n",
       "      <th>some_numbers</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-04-16 14:06:32.745629</td>\n",
       "      <td>-0.387743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1992-11-19 02:56:48.846815</td>\n",
       "      <td>0.723293</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2002-11-21 09:00:36.383417</td>\n",
       "      <td>0.330115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-01-07 14:42:31.335709</td>\n",
       "      <td>-0.466094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2002-02-26 00:57:35.396127</td>\n",
       "      <td>-0.716016</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   this_date  some_numbers\n",
       "0 1985-04-16 14:06:32.745629     -0.387743\n",
       "1 1992-11-19 02:56:48.846815      0.723293\n",
       "2 2002-11-21 09:00:36.383417      0.330115\n",
       "3 2016-01-07 14:42:31.335709     -0.466094\n",
       "4 2002-02-26 00:57:35.396127     -0.716016"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# generate fake dates\n",
    "n_samples = 5\n",
    "X = pd.DataFrame(data=randdate(n_samples), columns=['this_date'])\n",
    "X['some_numbers'] = np.random.randn(n_samples)\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[False, 0, 2, 0, 4, 106, 1, 16, 16, -0.3877432622991901],\n",
       "       [False, 0, 4, 0, 11, 324, 3, 47, 19, 0.7232931454473194],\n",
       "       [False, 0, 4, 0, 11, 325, 3, 47, 21, 0.33011450757540833],\n",
       "       [False, 0, 1, 0, 1, 7, 3, 1, 7, -0.46609446684241734],\n",
       "       [False, 0, 1, 0, 2, 57, 1, 9, 26, -0.7160159716877422]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# make pipeline\n",
    "pipe = Pipeline(steps=[\n",
    "    # process column by column\n",
    "    ('col_by_col', FeatureUnion(transformer_list=[\n",
    "        ('dates', Pipeline(steps=[\n",
    "            ('sel1', ColumnSelector(cols=('this_date'))),\n",
    "            ('pre1', DateComponents())\n",
    "        ])),\n",
    "        ('numbers', ColumnSelector(cols=('some_numbers')))\n",
    "    ]))\n",
    "    # do some other stuff ..\n",
    "])\n",
    "\n",
    "Z = pipe.fit_transform(X)\n",
    "Z"
   ]
  },
  {
   "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": "3.6.2"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}