DenguePredictionUsingLSTM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "yBsIRxsJOJyV"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "from sklearn import preprocessing\n",
    "from datetime import datetime\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "CigB6o-IOZUY"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"dengue_features_train.csv\")\n",
    "lables = pd.read_csv(\"dengue_labels_train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "JFVM3bK7Oa-P"
   },
   "outputs": [],
   "source": [
    "data = pd.merge(df, lables, on = ['city', 'year', 'weekofyear'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 226
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 553,
     "status": "ok",
     "timestamp": 1575324613277,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "TTxaiVm0Oc8F",
    "outputId": "6b257e7d-a44d-47d1-90b5-78610f2bb843"
   },
   "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>city</th>\n",
       "      <th>year</th>\n",
       "      <th>weekofyear</th>\n",
       "      <th>week_start_date</th>\n",
       "      <th>ndvi_ne</th>\n",
       "      <th>ndvi_nw</th>\n",
       "      <th>ndvi_se</th>\n",
       "      <th>ndvi_sw</th>\n",
       "      <th>precipitation_amt_mm</th>\n",
       "      <th>reanalysis_air_temp_k</th>\n",
       "      <th>reanalysis_avg_temp_k</th>\n",
       "      <th>reanalysis_dew_point_temp_k</th>\n",
       "      <th>reanalysis_max_air_temp_k</th>\n",
       "      <th>reanalysis_min_air_temp_k</th>\n",
       "      <th>reanalysis_precip_amt_kg_per_m2</th>\n",
       "      <th>reanalysis_relative_humidity_percent</th>\n",
       "      <th>reanalysis_sat_precip_amt_mm</th>\n",
       "      <th>reanalysis_specific_humidity_g_per_kg</th>\n",
       "      <th>reanalysis_tdtr_k</th>\n",
       "      <th>station_avg_temp_c</th>\n",
       "      <th>station_diur_temp_rng_c</th>\n",
       "      <th>station_max_temp_c</th>\n",
       "      <th>station_min_temp_c</th>\n",
       "      <th>station_precip_mm</th>\n",
       "      <th>total_cases</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>sj</td>\n",
       "      <td>1990</td>\n",
       "      <td>18</td>\n",
       "      <td>1990-04-30</td>\n",
       "      <td>0.122600</td>\n",
       "      <td>0.103725</td>\n",
       "      <td>0.198483</td>\n",
       "      <td>0.177617</td>\n",
       "      <td>12.42</td>\n",
       "      <td>297.572857</td>\n",
       "      <td>297.742857</td>\n",
       "      <td>292.414286</td>\n",
       "      <td>299.8</td>\n",
       "      <td>295.9</td>\n",
       "      <td>32.00</td>\n",
       "      <td>73.365714</td>\n",
       "      <td>12.42</td>\n",
       "      <td>14.012857</td>\n",
       "      <td>2.628571</td>\n",
       "      <td>25.442857</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>29.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sj</td>\n",
       "      <td>1990</td>\n",
       "      <td>19</td>\n",
       "      <td>1990-05-07</td>\n",
       "      <td>0.169900</td>\n",
       "      <td>0.142175</td>\n",
       "      <td>0.162357</td>\n",
       "      <td>0.155486</td>\n",
       "      <td>22.82</td>\n",
       "      <td>298.211429</td>\n",
       "      <td>298.442857</td>\n",
       "      <td>293.951429</td>\n",
       "      <td>300.9</td>\n",
       "      <td>296.4</td>\n",
       "      <td>17.94</td>\n",
       "      <td>77.368571</td>\n",
       "      <td>22.82</td>\n",
       "      <td>15.372857</td>\n",
       "      <td>2.371429</td>\n",
       "      <td>26.714286</td>\n",
       "      <td>6.371429</td>\n",
       "      <td>31.7</td>\n",
       "      <td>22.2</td>\n",
       "      <td>8.6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>sj</td>\n",
       "      <td>1990</td>\n",
       "      <td>20</td>\n",
       "      <td>1990-05-14</td>\n",
       "      <td>0.032250</td>\n",
       "      <td>0.172967</td>\n",
       "      <td>0.157200</td>\n",
       "      <td>0.170843</td>\n",
       "      <td>34.54</td>\n",
       "      <td>298.781429</td>\n",
       "      <td>298.878571</td>\n",
       "      <td>295.434286</td>\n",
       "      <td>300.5</td>\n",
       "      <td>297.3</td>\n",
       "      <td>26.10</td>\n",
       "      <td>82.052857</td>\n",
       "      <td>34.54</td>\n",
       "      <td>16.848571</td>\n",
       "      <td>2.300000</td>\n",
       "      <td>26.714286</td>\n",
       "      <td>6.485714</td>\n",
       "      <td>32.2</td>\n",
       "      <td>22.8</td>\n",
       "      <td>41.4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>sj</td>\n",
       "      <td>1990</td>\n",
       "      <td>21</td>\n",
       "      <td>1990-05-21</td>\n",
       "      <td>0.128633</td>\n",
       "      <td>0.245067</td>\n",
       "      <td>0.227557</td>\n",
       "      <td>0.235886</td>\n",
       "      <td>15.36</td>\n",
       "      <td>298.987143</td>\n",
       "      <td>299.228571</td>\n",
       "      <td>295.310000</td>\n",
       "      <td>301.4</td>\n",
       "      <td>297.0</td>\n",
       "      <td>13.90</td>\n",
       "      <td>80.337143</td>\n",
       "      <td>15.36</td>\n",
       "      <td>16.672857</td>\n",
       "      <td>2.428571</td>\n",
       "      <td>27.471429</td>\n",
       "      <td>6.771429</td>\n",
       "      <td>33.3</td>\n",
       "      <td>23.3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>sj</td>\n",
       "      <td>1990</td>\n",
       "      <td>22</td>\n",
       "      <td>1990-05-28</td>\n",
       "      <td>0.196200</td>\n",
       "      <td>0.262200</td>\n",
       "      <td>0.251200</td>\n",
       "      <td>0.247340</td>\n",
       "      <td>7.52</td>\n",
       "      <td>299.518571</td>\n",
       "      <td>299.664286</td>\n",
       "      <td>295.821429</td>\n",
       "      <td>301.9</td>\n",
       "      <td>297.5</td>\n",
       "      <td>12.20</td>\n",
       "      <td>80.460000</td>\n",
       "      <td>7.52</td>\n",
       "      <td>17.210000</td>\n",
       "      <td>3.014286</td>\n",
       "      <td>28.942857</td>\n",
       "      <td>9.371429</td>\n",
       "      <td>35.0</td>\n",
       "      <td>23.9</td>\n",
       "      <td>5.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  city  year  weekofyear  ... station_min_temp_c  station_precip_mm  total_cases\n",
       "0   sj  1990          18  ...               20.0               16.0            4\n",
       "1   sj  1990          19  ...               22.2                8.6            5\n",
       "2   sj  1990          20  ...               22.8               41.4            4\n",
       "3   sj  1990          21  ...               23.3                4.0            3\n",
       "4   sj  1990          22  ...               23.9                5.8            6\n",
       "\n",
       "[5 rows x 25 columns]"
      ]
     },
     "execution_count": 37,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "XMbInQz4OfkG"
   },
   "outputs": [],
   "source": [
    "sj = data[data['city'] == 'sj']\n",
    "sj = sj.drop('city', axis=1)\n",
    "\n",
    "iq = data[data['city'] == 'iq']\n",
    "iq = iq.drop('city', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "iGUdP9gBOmGt"
   },
   "outputs": [],
   "source": [
    "sj['week_start_date'] = pd.to_datetime(sj['week_start_date'])\n",
    "\n",
    "iq['week_start_date'] = pd.to_datetime(iq['week_start_date'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 88
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 633,
     "status": "ok",
     "timestamp": 1575324615871,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "MYDz_6HKPCBB",
    "outputId": "5ab15625-1fa4-45a3-b7c8-0bace0efa442"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Timestamp('2008-04-22 00:00:00'),\n",
       " Timestamp('1990-04-30 00:00:00'),\n",
       " Timestamp('2010-06-25 00:00:00'),\n",
       " Timestamp('2000-07-01 00:00:00'))"
      ]
     },
     "execution_count": 40,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(sj['week_start_date']), min(sj['week_start_date']), max(iq['week_start_date']), min(iq['week_start_date'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "LKk9OaeNN_2V"
   },
   "outputs": [],
   "source": [
    "sj.index = sj['week_start_date']\n",
    "\n",
    "iq.index = iq['week_start_date']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Fd7vDRecPFbx"
   },
   "outputs": [],
   "source": [
    "train_sj = sj.iloc[:800]\n",
    "\n",
    "train_iq = iq.iloc[:400]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8O9ePzO-Poxv"
   },
   "outputs": [],
   "source": [
    "test_sj = sj.iloc[793:]\n",
    "\n",
    "test_iq = iq.iloc[393:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "OemfHJsMPt4Z"
   },
   "outputs": [],
   "source": [
    "train_sj = train_sj.drop('week_start_date', axis=1)\n",
    "test_sj = test_sj.drop('week_start_date', axis=1)\n",
    "\n",
    "train_iq = train_iq.drop('week_start_date', axis=1)\n",
    "test_iq = test_iq.drop('week_start_date', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "vRPgNegPP1tE"
   },
   "outputs": [],
   "source": [
    "train_sj = train_sj.drop(['precipitation_amt_mm', 'reanalysis_air_temp_k', 'reanalysis_avg_temp_k', 'reanalysis_max_air_temp_k', 'reanalysis_min_air_temp_k',\n",
    "                    'reanalysis_precip_amt_kg_per_m2', 'reanalysis_sat_precip_amt_mm', 'ndvi_ne', 'ndvi_nw', 'ndvi_se', 'ndvi_sw', 'reanalysis_tdtr_k'],\n",
    "                     axis=1)\n",
    "test_sj = test_sj.drop(['precipitation_amt_mm', 'reanalysis_air_temp_k', 'reanalysis_avg_temp_k', 'reanalysis_max_air_temp_k', 'reanalysis_min_air_temp_k',\n",
    "                    'reanalysis_precip_amt_kg_per_m2', 'reanalysis_sat_precip_amt_mm', 'ndvi_ne', 'ndvi_nw', 'ndvi_se', 'ndvi_sw', 'reanalysis_tdtr_k'], \n",
    "                    axis=1)\n",
    "\n",
    "train_iq = train_iq.drop(['precipitation_amt_mm', 'reanalysis_air_temp_k', 'reanalysis_avg_temp_k', 'reanalysis_max_air_temp_k', 'reanalysis_min_air_temp_k',\n",
    "                    'reanalysis_precip_amt_kg_per_m2', 'reanalysis_sat_precip_amt_mm', 'ndvi_ne', 'ndvi_nw', 'ndvi_se', 'ndvi_sw', 'reanalysis_tdtr_k'],\n",
    "                     axis=1)\n",
    "test_iq = test_iq.drop(['precipitation_amt_mm', 'reanalysis_air_temp_k', 'reanalysis_avg_temp_k', 'reanalysis_max_air_temp_k', 'reanalysis_min_air_temp_k',\n",
    "                    'reanalysis_precip_amt_kg_per_m2', 'reanalysis_sat_precip_amt_mm', 'ndvi_ne', 'ndvi_nw', 'ndvi_se', 'ndvi_sw', 'reanalysis_tdtr_k'],\n",
    "                     axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "FtfY6_MbP-oO"
   },
   "outputs": [],
   "source": [
    "X_train_sj = train_sj\n",
    "y_train_sj = train_sj['total_cases']\n",
    "\n",
    "X_train_iq = train_iq\n",
    "y_train_iq = train_iq['total_cases']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "4qdWt_ZHQneM"
   },
   "outputs": [],
   "source": [
    "X_test_sj = test_sj\n",
    "y_test_sj = test_sj['total_cases']\n",
    "\n",
    "X_test_iq = test_iq\n",
    "y_test_iq = test_iq['total_cases']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "U9KgWEs4REog"
   },
   "outputs": [],
   "source": [
    "X_train_sj.fillna(0, inplace=True)\n",
    "X_train_iq.fillna(0, inplace=True)\n",
    "\n",
    "X_test_sj.fillna(0, inplace=True)\n",
    "X_test_iq.fillna(0, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 258
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1149,
     "status": "ok",
     "timestamp": 1575324622572,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "jVHyYVe_OJwB",
    "outputId": "f9cb28d1-f916-40f7-843e-b8b7c180e30f"
   },
   "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>year</th>\n",
       "      <th>weekofyear</th>\n",
       "      <th>reanalysis_dew_point_temp_k</th>\n",
       "      <th>reanalysis_relative_humidity_percent</th>\n",
       "      <th>reanalysis_specific_humidity_g_per_kg</th>\n",
       "      <th>station_avg_temp_c</th>\n",
       "      <th>station_diur_temp_rng_c</th>\n",
       "      <th>station_max_temp_c</th>\n",
       "      <th>station_min_temp_c</th>\n",
       "      <th>station_precip_mm</th>\n",
       "      <th>total_cases</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>week_start_date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1990-04-30</th>\n",
       "      <td>1990</td>\n",
       "      <td>18</td>\n",
       "      <td>292.414286</td>\n",
       "      <td>73.365714</td>\n",
       "      <td>14.012857</td>\n",
       "      <td>25.442857</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>29.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-07</th>\n",
       "      <td>1990</td>\n",
       "      <td>19</td>\n",
       "      <td>293.951429</td>\n",
       "      <td>77.368571</td>\n",
       "      <td>15.372857</td>\n",
       "      <td>26.714286</td>\n",
       "      <td>6.371429</td>\n",
       "      <td>31.7</td>\n",
       "      <td>22.2</td>\n",
       "      <td>8.6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-14</th>\n",
       "      <td>1990</td>\n",
       "      <td>20</td>\n",
       "      <td>295.434286</td>\n",
       "      <td>82.052857</td>\n",
       "      <td>16.848571</td>\n",
       "      <td>26.714286</td>\n",
       "      <td>6.485714</td>\n",
       "      <td>32.2</td>\n",
       "      <td>22.8</td>\n",
       "      <td>41.4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-21</th>\n",
       "      <td>1990</td>\n",
       "      <td>21</td>\n",
       "      <td>295.310000</td>\n",
       "      <td>80.337143</td>\n",
       "      <td>16.672857</td>\n",
       "      <td>27.471429</td>\n",
       "      <td>6.771429</td>\n",
       "      <td>33.3</td>\n",
       "      <td>23.3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-28</th>\n",
       "      <td>1990</td>\n",
       "      <td>22</td>\n",
       "      <td>295.821429</td>\n",
       "      <td>80.460000</td>\n",
       "      <td>17.210000</td>\n",
       "      <td>28.942857</td>\n",
       "      <td>9.371429</td>\n",
       "      <td>35.0</td>\n",
       "      <td>23.9</td>\n",
       "      <td>5.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 year  weekofyear  ...  station_precip_mm  total_cases\n",
       "week_start_date                    ...                                \n",
       "1990-04-30       1990          18  ...               16.0            4\n",
       "1990-05-07       1990          19  ...                8.6            5\n",
       "1990-05-14       1990          20  ...               41.4            4\n",
       "1990-05-21       1990          21  ...                4.0            3\n",
       "1990-05-28       1990          22  ...                5.8            6\n",
       "\n",
       "[5 rows x 11 columns]"
      ]
     },
     "execution_count": 49,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_sj.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 792,
     "status": "ok",
     "timestamp": 1575324624667,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "zXvjDkeWL6Sv",
    "outputId": "21419bd2-e94e-4c32-a63b-6171dd3f01bf"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((800, 11), (400, 11))"
      ]
     },
     "execution_count": 50,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_sj.shape, X_train_iq.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Sa7J7o7WROqK"
   },
   "outputs": [],
   "source": [
    "for col in X_train_sj.columns:\n",
    "  X_train_sj[col] = preprocessing.scale(X_train_sj[col].values)\n",
    "  X_test_sj[col] = preprocessing.scale(X_test_sj[col].values)\n",
    "\n",
    "for col in X_train_iq.columns:\n",
    "  X_train_iq[col] = preprocessing.scale(X_train_iq[col].values)\n",
    "  X_test_iq[col] = preprocessing.scale(X_test_iq[col].values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 258
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 719,
     "status": "ok",
     "timestamp": 1575324629675,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "4gqpYSWzSAIO",
    "outputId": "640eb8a8-33f6-49e2-bf8b-ba54f4dbee86"
   },
   "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>year</th>\n",
       "      <th>weekofyear</th>\n",
       "      <th>reanalysis_dew_point_temp_k</th>\n",
       "      <th>reanalysis_relative_humidity_percent</th>\n",
       "      <th>reanalysis_specific_humidity_g_per_kg</th>\n",
       "      <th>station_avg_temp_c</th>\n",
       "      <th>station_diur_temp_rng_c</th>\n",
       "      <th>station_max_temp_c</th>\n",
       "      <th>station_min_temp_c</th>\n",
       "      <th>station_precip_mm</th>\n",
       "      <th>total_cases</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>week_start_date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1990-04-30</th>\n",
       "      <td>-1.687599</td>\n",
       "      <td>-0.574522</td>\n",
       "      <td>-0.019041</td>\n",
       "      <td>-0.651243</td>\n",
       "      <td>-1.148243</td>\n",
       "      <td>-0.510123</td>\n",
       "      <td>0.150730</td>\n",
       "      <td>-0.629886</td>\n",
       "      <td>-0.983822</td>\n",
       "      <td>-0.348505</td>\n",
       "      <td>-0.589953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-07</th>\n",
       "      <td>-1.687599</td>\n",
       "      <td>-0.507307</td>\n",
       "      <td>0.041217</td>\n",
       "      <td>-0.124100</td>\n",
       "      <td>-0.502674</td>\n",
       "      <td>-0.041190</td>\n",
       "      <td>-0.367579</td>\n",
       "      <td>0.089582</td>\n",
       "      <td>-0.091926</td>\n",
       "      <td>-0.604207</td>\n",
       "      <td>-0.571438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-14</th>\n",
       "      <td>-1.687599</td>\n",
       "      <td>-0.440091</td>\n",
       "      <td>0.099347</td>\n",
       "      <td>0.492782</td>\n",
       "      <td>0.197821</td>\n",
       "      <td>-0.041190</td>\n",
       "      <td>-0.255512</td>\n",
       "      <td>0.245988</td>\n",
       "      <td>0.151318</td>\n",
       "      <td>0.529172</td>\n",
       "      <td>-0.589953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-21</th>\n",
       "      <td>-1.687599</td>\n",
       "      <td>-0.372876</td>\n",
       "      <td>0.094475</td>\n",
       "      <td>0.266837</td>\n",
       "      <td>0.114413</td>\n",
       "      <td>0.238062</td>\n",
       "      <td>0.024655</td>\n",
       "      <td>0.590081</td>\n",
       "      <td>0.354022</td>\n",
       "      <td>-0.763156</td>\n",
       "      <td>-0.608467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-05-28</th>\n",
       "      <td>-1.687599</td>\n",
       "      <td>-0.305661</td>\n",
       "      <td>0.114524</td>\n",
       "      <td>0.283016</td>\n",
       "      <td>0.369385</td>\n",
       "      <td>0.780760</td>\n",
       "      <td>2.574175</td>\n",
       "      <td>1.121861</td>\n",
       "      <td>0.597266</td>\n",
       "      <td>-0.700959</td>\n",
       "      <td>-0.552923</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     year  weekofyear  ...  station_precip_mm  total_cases\n",
       "week_start_date                        ...                                \n",
       "1990-04-30      -1.687599   -0.574522  ...          -0.348505    -0.589953\n",
       "1990-05-07      -1.687599   -0.507307  ...          -0.604207    -0.571438\n",
       "1990-05-14      -1.687599   -0.440091  ...           0.529172    -0.589953\n",
       "1990-05-21      -1.687599   -0.372876  ...          -0.763156    -0.608467\n",
       "1990-05-28      -1.687599   -0.305661  ...          -0.700959    -0.552923\n",
       "\n",
       "[5 rows x 11 columns]"
      ]
     },
     "execution_count": 52,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_sj.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "DaJguH0tSO2R"
   },
   "outputs": [],
   "source": [
    "sj_train_dates = X_train_sj.index\n",
    "X_train_sj = X_train_sj.values\n",
    "sj_train_x, sj_train_y = [], []\n",
    "for i in range(7,len(X_train_sj)):\n",
    "    sj_train_x.append(X_train_sj[i-7:i])\n",
    "    sj_train_y.append(y_train_sj[i])\n",
    "sj_train_x, sj_train_y = np.array(sj_train_x), np.array(sj_train_y)\n",
    "\n",
    "iq_train_dates = X_train_iq.index\n",
    "X_train_iq = X_train_iq.values\n",
    "iq_train_x, iq_train_y = [], []\n",
    "for i in range(7,len(X_train_iq)):\n",
    "    iq_train_x.append(X_train_iq[i-7:i])\n",
    "    iq_train_y.append(y_train_iq[i])\n",
    "iq_train_x, iq_train_y = np.array(iq_train_x), np.array(iq_train_y)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 281,
     "status": "ok",
     "timestamp": 1575324633634,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "XLKgsnIfeY_7",
    "outputId": "dce18c00-5f4d-4929-b8d0-ed88d94f0d04"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(793, 7, 11)"
      ]
     },
     "execution_count": 54,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sj_train_x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 571,
     "status": "ok",
     "timestamp": 1575324634405,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "aNAG4lPSTFH5",
    "outputId": "f8e9333e-46c1-4c08-8aea-d827b2336c21"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((793, 7, 11), (793,))"
      ]
     },
     "execution_count": 55,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sj_train_x.shape, sj_train_y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "bYU4nbpSTZRZ"
   },
   "outputs": [],
   "source": [
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, LSTM, Dropout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "lu02kGSoTSMl"
   },
   "outputs": [],
   "source": [
    "model_sj = Sequential()\n",
    "model_sj.add(LSTM(units=50, return_sequences=True, input_shape=(sj_train_x.shape[1], sj_train_x.shape[2])))\n",
    "model_sj.add(LSTM(units=50))\n",
    "model_sj.add(Dense(1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 73
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 629,
     "status": "ok",
     "timestamp": 1575324035357,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "j12ZJ5VuTYT8",
    "outputId": "795a7c5f-c874-4832-dd1a-82a4a8afbe96"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:793: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "model_sj.compile(loss='mean_squared_error', optimizer='adam', metrics = ['mae'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 334441,
     "status": "ok",
     "timestamp": 1575324372556,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "vwF8TgEoTkGB",
    "outputId": "fa73a124-1934-4118-9931-00f915fef68d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_grad.py:1424: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1033: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1020: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3005: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n",
      "\n",
      "Epoch 1/40\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:190: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:197: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:207: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:216: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n",
      "\n",
      "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:223: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n",
      "\n",
      "793/793 [==============================] - 10s 12ms/step - loss: 3386.3073 - mean_absolute_error: 26.4238\n",
      "Epoch 2/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 2805.7584 - mean_absolute_error: 20.7231\n",
      "Epoch 3/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 2484.5719 - mean_absolute_error: 18.2203\n",
      "Epoch 4/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 2253.6248 - mean_absolute_error: 16.4298\n",
      "Epoch 5/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 2066.8197 - mean_absolute_error: 15.1129\n",
      "Epoch 6/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1911.1121 - mean_absolute_error: 14.1665\n",
      "Epoch 7/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1789.6522 - mean_absolute_error: 13.6374\n",
      "Epoch 8/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1674.6376 - mean_absolute_error: 13.0028\n",
      "Epoch 9/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 1568.6616 - mean_absolute_error: 12.4330\n",
      "Epoch 10/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1476.2434 - mean_absolute_error: 12.1028\n",
      "Epoch 11/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 1389.9786 - mean_absolute_error: 11.6550\n",
      "Epoch 12/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1306.2512 - mean_absolute_error: 11.0420\n",
      "Epoch 13/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1236.8501 - mean_absolute_error: 10.8751\n",
      "Epoch 14/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1167.0043 - mean_absolute_error: 10.4982\n",
      "Epoch 15/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 1111.7557 - mean_absolute_error: 10.2308\n",
      "Epoch 16/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 1052.9198 - mean_absolute_error: 9.8152\n",
      "Epoch 17/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 999.3774 - mean_absolute_error: 9.6437\n",
      "Epoch 18/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 944.1546 - mean_absolute_error: 9.1939\n",
      "Epoch 19/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 892.4757 - mean_absolute_error: 8.8979\n",
      "Epoch 20/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 848.7622 - mean_absolute_error: 8.6329\n",
      "Epoch 21/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 799.8703 - mean_absolute_error: 8.3109\n",
      "Epoch 22/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 764.2016 - mean_absolute_error: 8.2067\n",
      "Epoch 23/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 736.6762 - mean_absolute_error: 8.1543\n",
      "Epoch 24/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 695.5154 - mean_absolute_error: 7.8598\n",
      "Epoch 25/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 655.9640 - mean_absolute_error: 7.5873\n",
      "Epoch 26/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 613.2904 - mean_absolute_error: 7.2632\n",
      "Epoch 27/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 584.4919 - mean_absolute_error: 7.0988\n",
      "Epoch 28/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 553.1721 - mean_absolute_error: 6.9241\n",
      "Epoch 29/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 522.6060 - mean_absolute_error: 6.6211\n",
      "Epoch 30/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 495.9998 - mean_absolute_error: 6.6104\n",
      "Epoch 31/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 521.8338 - mean_absolute_error: 6.8488\n",
      "Epoch 32/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 441.7885 - mean_absolute_error: 5.9117\n",
      "Epoch 33/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 408.0091 - mean_absolute_error: 5.3711\n",
      "Epoch 34/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 384.7634 - mean_absolute_error: 5.3245\n",
      "Epoch 35/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 365.4579 - mean_absolute_error: 5.3322\n",
      "Epoch 36/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 345.7571 - mean_absolute_error: 5.2899\n",
      "Epoch 37/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 337.0356 - mean_absolute_error: 5.2779\n",
      "Epoch 38/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 313.1715 - mean_absolute_error: 5.2826\n",
      "Epoch 39/40\n",
      "793/793 [==============================] - 8s 10ms/step - loss: 293.5585 - mean_absolute_error: 5.0240\n",
      "Epoch 40/40\n",
      "793/793 [==============================] - 8s 11ms/step - loss: 287.4852 - mean_absolute_error: 5.2765\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f9bed7e1f60>"
      ]
     },
     "execution_count": 30,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_sj.fit(sj_train_x, sj_train_y, epochs=40, batch_size=1, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8IDBFac4VQZv"
   },
   "outputs": [],
   "source": [
    "sj_test_dates = X_test_sj.index\n",
    "X_test_sj = X_test_sj.values\n",
    "y_test_sj = y_test_sj.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2UZF9CqUTqi3"
   },
   "outputs": [],
   "source": [
    "sj_test_x, sj_test_y = [], []\n",
    "for i in range(7,len(X_test_sj)):\n",
    "    sj_test_x.append(X_test_sj[i-7:i])\n",
    "    sj_test_y.append(y_test_sj[i])\n",
    "sj_test_x, sj_test_y = np.array(sj_test_x), np.array(sj_test_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 321057,
     "status": "ok",
     "timestamp": 1575324372765,
     "user": {
      "displayName": "Smit Anish Kiri",
      "photoUrl": "",
      "userId": "00496750762007332808"
     },
     "user_tz": 300
    },
    "id": "1TTBcTzPVak1",
    "outputId": "e402854f-0d1a-4076-cd65-18f5d68d61d7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(136, 7, 12)"
      ]
     },
     "execution_count": 33,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sj_test_x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "GN7tVGOloY6c"
   },
   "outputs": [],
   "source": [
    "model_sj.evaluate(sj_test_x, )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8kX0VvdbctJo"
   },
   "outputs": [],
   "source": [
    "y_pred_sj = model_sj.predict(sj_test_x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "FfrhQ4i0QFuY"
   },
   "outputs": [],
   "source": [
    "y_pred_sj = [int(round(y,0)) for y in y_pred_sj[:,0]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "s88OXuRm5q8P"
   },
   "outputs": [],
   "source": [
    "y_train_pred_sj = model_sj.predict(sj_train_x)\n",
    "y_train_pred_sj = [int(round(y,0)) for y in y_train_pred_sj[:,0]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 164
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 854,
     "status": "error",
     "timestamp": 1575313961167,
     "user": {
      "displayName": "Fenil Mukesh Shah",
      "photoUrl": "",
      "userId": "16310722189065142470"
     },
     "user_tz": 300
    },
    "id": "QOdo07HaByZ-",
    "outputId": "4d8d4474-dc14-4489-8e84-4c038fce397c"
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "ignored",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-1-03d7eb7d98bd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0my_train_pred_sj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'y_train_pred_sj' is not defined"
     ]
    }
   ],
   "source": [
    "y_train_pred_sj.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 446
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 307016,
     "status": "ok",
     "timestamp": 1574901625914,
     "user": {
      "displayName": "Smit Kiri",
      "photoUrl": "https://lh3.googleusercontent.com/-oC3sDatMc6I/AAAAAAAAAAI/AAAAAAAAFIY/4-X3wk9oODk/s64/photo.jpg",
      "userId": "13362116092602570316"
     },
     "user_tz": 300
    },
    "id": "AKgpTLQTQo0j",
    "outputId": "8bb64e92-f140-4157-8b95-0a46ced46755"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7f94a77b3cc0>"
      ]
     },
     "execution_count": 77,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA6UAAAGbCAYAAAA8zjayAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1152x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(16,7))\n",
    "plt.plot(sj_train_dates, y_train_sj, label = \"Actual train\")\n",
    "plt.plot(sj_train_dates[7:], y_train_pred_sj, label = \"Predicted train\")\n",
    "plt.plot(sj_test_dates[7:], y_test_sj[7:], label = \"Actucal test\")\n",
    "plt.plot(sj_test_dates[7:], y_pred_sj, label = \"Predicted test\")\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_i0sH7MR4_VV"
   },
   "outputs": [],
   "source": [
    "model_iq = Sequential()\n",
    "model_iq.add(LSTM(units=50, return_sequences=True, input_shape=(iq_train_x.shape[1], iq_train_x.shape[2])))\n",
    "model_iq.add(LSTM(units=50))\n",
    "model_iq.add(Dense(1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "lEa1UuJJQuXI"
   },
   "outputs": [],
   "source": [
    "model_iq.compile(loss='mean_squared_error', optimizer='adam')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 928
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 98432,
     "status": "ok",
     "timestamp": 1574905240140,
     "user": {
      "displayName": "Smit Kiri",
      "photoUrl": "https://lh3.googleusercontent.com/-oC3sDatMc6I/AAAAAAAAAAI/AAAAAAAAFIY/4-X3wk9oODk/s64/photo.jpg",
      "userId": "13362116092602570316"
     },
     "user_tz": 300
    },
    "id": "cu_THfIucTuV",
    "outputId": "1c48bbc4-c647-4756-cc99-f95b772787f2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/25\n",
      "393/393 [==============================] - 6s 16ms/step - loss: 107.1259\n",
      "Epoch 2/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 76.2952\n",
      "Epoch 3/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 70.5348\n",
      "Epoch 4/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 62.8535\n",
      "Epoch 5/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 58.8751\n",
      "Epoch 6/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 59.3402\n",
      "Epoch 7/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 54.7960\n",
      "Epoch 8/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 53.3307\n",
      "Epoch 9/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 51.1735\n",
      "Epoch 10/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 49.4883\n",
      "Epoch 11/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 49.1442\n",
      "Epoch 12/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 47.1099\n",
      "Epoch 13/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 45.5191\n",
      "Epoch 14/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 46.4536\n",
      "Epoch 15/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 46.1135\n",
      "Epoch 16/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 46.7288\n",
      "Epoch 17/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 44.1055\n",
      "Epoch 18/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 43.1395\n",
      "Epoch 19/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 41.4309\n",
      "Epoch 20/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 39.3384\n",
      "Epoch 21/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 41.7737\n",
      "Epoch 22/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 38.6248\n",
      "Epoch 23/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 36.0389\n",
      "Epoch 24/25\n",
      "393/393 [==============================] - 4s 10ms/step - loss: 35.0152\n",
      "Epoch 25/25\n",
      "393/393 [==============================] - 4s 9ms/step - loss: 32.7541\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f94a60f9128>"
      ]
     },
     "execution_count": 176,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_iq.fit(iq_train_x, iq_train_y, epochs=25, batch_size=1, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "LyWLg8m8cYkl"
   },
   "outputs": [],
   "source": [
    "iq_test_dates = X_test_iq.index\n",
    "X_test_iq = X_test_iq.values\n",
    "y_test_iq = y_test_iq.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8KhL1TG9cYbT"
   },
   "outputs": [],
   "source": [
    "iq_test_x, iq_test_y = [], []\n",
    "for i in range(7,len(X_test_iq)):\n",
    "    iq_test_x.append(X_test_iq[i-7:i])\n",
    "    iq_test_y.append(y_test_iq[i])\n",
    "iq_test_x, iq_test_y = np.array(iq_test_x), np.array(iq_test_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 539,
     "status": "ok",
     "timestamp": 1574901755408,
     "user": {
      "displayName": "Smit Kiri",
      "photoUrl": "https://lh3.googleusercontent.com/-oC3sDatMc6I/AAAAAAAAAAI/AAAAAAAAFIY/4-X3wk9oODk/s64/photo.jpg",
      "userId": "13362116092602570316"
     },
     "user_tz": 300
    },
    "id": "1O6gQf2wcYTO",
    "outputId": "3cabbb78-4136-4996-80ce-ba53e0a8b699"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 7, 12)"
      ]
     },
     "execution_count": 92,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iq_test_x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "hpmzxd_BcYLS"
   },
   "outputs": [],
   "source": [
    "y_pred_iq = model_iq.predict(iq_test_x)\n",
    "y_pred_iq = [int(round(y,0)) for y in y_pred_iq[:,0]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Gl-M2__2c9Uh"
   },
   "outputs": [],
   "source": [
    "y_train_pred_iq = model_iq.predict(iq_train_x)\n",
    "y_train_pred_iq = [int(round(y,0)) for y in y_train_pred_iq[:,0]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 446
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 667,
     "status": "ok",
     "timestamp": 1574905249277,
     "user": {
      "displayName": "Smit Kiri",
      "photoUrl": "https://lh3.googleusercontent.com/-oC3sDatMc6I/AAAAAAAAAAI/AAAAAAAAFIY/4-X3wk9oODk/s64/photo.jpg",
      "userId": "13362116092602570316"
     },
     "user_tz": 300
    },
    "id": "dYYnIEbGc9DB",
    "outputId": "3a43d0c2-096e-40ea-8a15-adbb28f5b1bd"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7f94a5afab00>"
      ]
     },
     "execution_count": 179,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA6UAAAGbCAYAAAA8zjayAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nVkqVUkoppZRSSvnN/wPlTD0+H71kVgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1152x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(16,7))\n",
    "plt.plot(iq_train_dates, y_train_iq, label = \"Actual train\")\n",
    "plt.plot(iq_train_dates[7:], y_train_pred_iq, label = \"Predicted train\")\n",
    "plt.plot(iq_test_dates[7:], y_test_iq[7:], label = \"Actucal test\")\n",
    "plt.plot(iq_test_dates[7:], y_pred_iq, label = \"Predicted test\")\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "vHErhHhtfvgf"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "DenguePredictionUsingLSTM.ipynb",
   "provenance": []
  },
  "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}