{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from datetime import timedelta\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "from sklearn.metrics import confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_all_weather = pd.read_csv('2008-2018 Weather Data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "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>STATION</th>\n",
       "      <th>NAME</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>ELEVATION</th>\n",
       "      <th>DATE</th>\n",
       "      <th>AWND</th>\n",
       "      <th>DAPR</th>\n",
       "      <th>FMTM</th>\n",
       "      <th>MDPR</th>\n",
       "      <th>...</th>\n",
       "      <th>WT11</th>\n",
       "      <th>WT13</th>\n",
       "      <th>WT14</th>\n",
       "      <th>WT15</th>\n",
       "      <th>WT16</th>\n",
       "      <th>WT17</th>\n",
       "      <th>WT18</th>\n",
       "      <th>WT19</th>\n",
       "      <th>WT21</th>\n",
       "      <th>WT22</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>US1NYKN0003</td>\n",
       "      <td>BROOKLYN 2.4 SW, NY US</td>\n",
       "      <td>40.6194</td>\n",
       "      <td>-73.9859</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11/18/2008</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>1</th>\n",
       "      <td>US1NYKN0003</td>\n",
       "      <td>BROOKLYN 2.4 SW, NY US</td>\n",
       "      <td>40.6194</td>\n",
       "      <td>-73.9859</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11/19/2008</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>US1NYKN0003</td>\n",
       "      <td>BROOKLYN 2.4 SW, NY US</td>\n",
       "      <td>40.6194</td>\n",
       "      <td>-73.9859</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11/20/2008</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>3</th>\n",
       "      <td>US1NYKN0003</td>\n",
       "      <td>BROOKLYN 2.4 SW, NY US</td>\n",
       "      <td>40.6194</td>\n",
       "      <td>-73.9859</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11/21/2008</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>4</th>\n",
       "      <td>US1NYKN0003</td>\n",
       "      <td>BROOKLYN 2.4 SW, NY US</td>\n",
       "      <td>40.6194</td>\n",
       "      <td>-73.9859</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11/22/2008</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 45 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_all_weather.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_beaches = pd.read_csv('DOHMH_Beach_Water_Quality_Data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "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>Sample ID</th>\n",
       "      <th>Sample Date</th>\n",
       "      <th>Beach Name</th>\n",
       "      <th>Sample Location</th>\n",
       "      <th>Enterococci Results</th>\n",
       "      <th>Units or Notes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>050514CP13</td>\n",
       "      <td>05/05/2014</td>\n",
       "      <td>MIDLAND BEACH</td>\n",
       "      <td>Center</td>\n",
       "      <td>20.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>062011GR04</td>\n",
       "      <td>06/20/2011</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Left</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Result below detection limit</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>072808BH09</td>\n",
       "      <td>07/28/2008</td>\n",
       "      <td>MIDLAND BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>28.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>051214CP36</td>\n",
       "      <td>05/12/2014</td>\n",
       "      <td>SOUTH BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>4.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>081511KB07</td>\n",
       "      <td>08/15/2011</td>\n",
       "      <td>CEDAR GROVE</td>\n",
       "      <td>Left</td>\n",
       "      <td>360.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 5,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_beaches.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_beaches.fillna(0,inplace=True)\n",
    "df_beaches['Sample Date'] = pd.to_datetime(df_beaches['Sample Date'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "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>Sample ID</th>\n",
       "      <th>Sample Date</th>\n",
       "      <th>Beach Name</th>\n",
       "      <th>Sample Location</th>\n",
       "      <th>Enterococci Results</th>\n",
       "      <th>Units or Notes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>050514CP13</td>\n",
       "      <td>2014-05-05</td>\n",
       "      <td>MIDLAND BEACH</td>\n",
       "      <td>Center</td>\n",
       "      <td>20.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>062011GR04</td>\n",
       "      <td>2011-06-20</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Left</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Result below detection limit</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>072808BH09</td>\n",
       "      <td>2008-07-28</td>\n",
       "      <td>MIDLAND BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>28.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>051214CP36</td>\n",
       "      <td>2014-05-12</td>\n",
       "      <td>SOUTH BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>4.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>081511KB07</td>\n",
       "      <td>2011-08-15</td>\n",
       "      <td>CEDAR GROVE</td>\n",
       "      <td>Left</td>\n",
       "      <td>360.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 7,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_beaches.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man = df_beaches[df_beaches['Beach Name'] == 'MANHATTAN BEACH']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "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>Sample ID</th>\n",
       "      <th>Sample Date</th>\n",
       "      <th>Beach Name</th>\n",
       "      <th>Sample Location</th>\n",
       "      <th>Enterococci Results</th>\n",
       "      <th>Units or Notes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>062011GR04</td>\n",
       "      <td>2011-06-20</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Left</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Result below detection limit</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>062909KB01</td>\n",
       "      <td>2009-06-29</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Left</td>\n",
       "      <td>8.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>072015GR06</td>\n",
       "      <td>2015-07-20</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Result below detection limit</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>082112GR05</td>\n",
       "      <td>2012-08-21</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Center</td>\n",
       "      <td>4.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>060914GR06</td>\n",
       "      <td>2014-06-09</td>\n",
       "      <td>MANHATTAN BEACH</td>\n",
       "      <td>Right</td>\n",
       "      <td>8.0</td>\n",
       "      <td>MPN/100 ml</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 9,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_man.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man = df_man[['Sample Date','Enterococci Results']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "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>Sample Date</th>\n",
       "      <th>Enterococci Results</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2011-06-20</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2009-06-29</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2015-07-20</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>2012-08-21</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>2014-06-09</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 11,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_man.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man.columns = ['DATE','Enterococci']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2011-06-20</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2009-06-29</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2015-07-20</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>2012-08-21</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>2014-06-09</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 13,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_man.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man['DATE'] = pd.to_datetime(df_man['DATE'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man.sort_values(by='DATE',inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10187</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5811</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12516</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>20.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4561</th>\n",
       "      <td>2005-05-09</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14220</th>\n",
       "      <td>2005-05-09</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 16,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_man.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_man.index = range(len(df_man.index))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2005-05-02</td>\n",
       "      <td>20.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2005-05-09</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2005-05-09</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 18,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_man.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_jfk = df_all_weather[df_all_weather.NAME == 'JFK INTERNATIONAL AIRPORT, NY US']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "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>STATION</th>\n",
       "      <th>NAME</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>ELEVATION</th>\n",
       "      <th>DATE</th>\n",
       "      <th>AWND</th>\n",
       "      <th>DAPR</th>\n",
       "      <th>FMTM</th>\n",
       "      <th>MDPR</th>\n",
       "      <th>...</th>\n",
       "      <th>WT11</th>\n",
       "      <th>WT13</th>\n",
       "      <th>WT14</th>\n",
       "      <th>WT15</th>\n",
       "      <th>WT16</th>\n",
       "      <th>WT17</th>\n",
       "      <th>WT18</th>\n",
       "      <th>WT19</th>\n",
       "      <th>WT21</th>\n",
       "      <th>WT22</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>49261</th>\n",
       "      <td>USW00094789</td>\n",
       "      <td>JFK INTERNATIONAL AIRPORT, NY US</td>\n",
       "      <td>40.6386</td>\n",
       "      <td>-73.7622</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1/1/2008</td>\n",
       "      <td>15.88</td>\n",
       "      <td>NaN</td>\n",
       "      <td>827.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</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>49262</th>\n",
       "      <td>USW00094789</td>\n",
       "      <td>JFK INTERNATIONAL AIRPORT, NY US</td>\n",
       "      <td>40.6386</td>\n",
       "      <td>-73.7622</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1/2/2008</td>\n",
       "      <td>21.25</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1750.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49263</th>\n",
       "      <td>USW00094789</td>\n",
       "      <td>JFK INTERNATIONAL AIRPORT, NY US</td>\n",
       "      <td>40.6386</td>\n",
       "      <td>-73.7622</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1/3/2008</td>\n",
       "      <td>16.78</td>\n",
       "      <td>NaN</td>\n",
       "      <td>445.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>49264</th>\n",
       "      <td>USW00094789</td>\n",
       "      <td>JFK INTERNATIONAL AIRPORT, NY US</td>\n",
       "      <td>40.6386</td>\n",
       "      <td>-73.7622</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1/4/2008</td>\n",
       "      <td>12.97</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1146.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>49265</th>\n",
       "      <td>USW00094789</td>\n",
       "      <td>JFK INTERNATIONAL AIRPORT, NY US</td>\n",
       "      <td>40.6386</td>\n",
       "      <td>-73.7622</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1/5/2008</td>\n",
       "      <td>6.93</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2203.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 45 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 20,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_jfk.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['STATION', 'NAME', 'LATITUDE', 'LONGITUDE', 'ELEVATION', 'DATE', 'AWND',\n",
       "       'DAPR', 'FMTM', 'MDPR', 'MDSF', 'PGTM', 'PRCP', 'SNOW', 'SNWD', 'TAVG',\n",
       "       'TMAX', 'TMIN', 'TOBS', 'TSUN', 'WDF2', 'WDF5', 'WESD', 'WESF', 'WSF2',\n",
       "       'WSF5', 'WT01', 'WT02', 'WT03', 'WT04', 'WT05', 'WT06', 'WT07', 'WT08',\n",
       "       'WT09', 'WT11', 'WT13', 'WT14', 'WT15', 'WT16', 'WT17', 'WT18', 'WT19',\n",
       "       'WT21', 'WT22'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 21,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_jfk.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_jfk = df_jfk[['DATE','PRCP']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_jfk['DATE'] = pd.to_datetime(df_jfk['DATE'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_jfk.sort_values(by='DATE',inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_merged = pd.merge(df_man, df_jfk, how='inner', on='DATE')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "      <th>PRCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>120.0</td>\n",
       "      <td>1.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.05</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 26,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "      <th>PRCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>120.0</td>\n",
       "      <td>1.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.05</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 27,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "def eWarn(m):\n",
    "    if m > 104:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "df_merged['Warning'] = df_merged.Enterococci.apply(eWarn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "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>DATE</th>\n",
       "      <th>Enterococci</th>\n",
       "      <th>PRCP</th>\n",
       "      <th>Warning</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2008-04-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>120.0</td>\n",
       "      <td>1.05</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2008-04-28</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.05</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 30,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    649\n",
       "1     38\n",
       "Name: Warning, dtype: int64"
      ]
     },
     "execution_count": 31,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.Warning.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5,1,'Warning vs. PRCP')"
      ]
     },
     "execution_count": 32,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "f6a137001a3be7c8d0dcaf9d20d3e763fbf1c799"
     },
     "metadata": {
      "image/png": {
       "height": 277,
       "width": 388
      },
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "df_merged.plot.scatter(x='PRCP',y='Warning',color='black')\n",
    "plt.title('Warning vs. PRCP')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "X = np.array(df_merged.PRCP)\n",
    "y = df_merged.Warning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "logmodel = LogisticRegression(solver='liblinear')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=None, solver='liblinear',\n",
       "          tol=0.0001, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 36,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logmodel.fit(X_train.reshape(-1,1),y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "b0 = logmodel.intercept_\n",
    "b1 = logmodel.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5,1,'Warning vs. PRCP')"
      ]
     },
     "execution_count": 38,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "7d66b157f6a40497688382e2ebfbeb60dbdd53a5"
     },
     "metadata": {
      "image/png": {
       "height": 277,
       "width": 388
      },
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "X2 = sorted(X)\n",
    "df_merged.plot.scatter(x='PRCP',y='Warning',color='black')\n",
    "plt.plot(X2,1/(1+np.exp(-b0-b1*X2)).reshape(-1,1),'r')\n",
    "plt.title('Warning vs. PRCP')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "predictions = logmodel.predict(X_test.reshape(-1,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[213   0]\n",
      " [ 14   0]]\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_test,logmodel.predict(X_test.reshape(-1, 1))))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (Anaconda 5)",
   "language": "python",
   "name": "anaconda5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}