{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "aUcSSVlSOGoA"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 289
    },
    "colab_type": "code",
    "id": "kDn9hp3dPX5G",
    "outputId": "10aaed77-f1b9-4735-89b9-0d2d614a9e98"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         Date  TempHighF  TempAvgF  TempLowF DewPointHighF DewPointAvgF  \\\n",
      "0  2013-12-21         74        60        45            67           49   \n",
      "1  2013-12-22         56        48        39            43           36   \n",
      "2  2013-12-23         58        45        32            31           27   \n",
      "3  2013-12-24         61        46        31            36           28   \n",
      "4  2013-12-25         58        50        41            44           40   \n",
      "\n",
      "  DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent  ...  \\\n",
      "0           43                  93                 75                 57  ...   \n",
      "1           28                  93                 68                 43  ...   \n",
      "2           23                  76                 52                 27  ...   \n",
      "3           21                  89                 56                 22  ...   \n",
      "4           36                  86                 71                 56  ...   \n",
      "\n",
      "  SeaLevelPressureAvgInches SeaLevelPressureLowInches VisibilityHighMiles  \\\n",
      "0                     29.68                     29.59                  10   \n",
      "1                     30.13                     29.87                  10   \n",
      "2                     30.49                     30.41                  10   \n",
      "3                     30.45                      30.3                  10   \n",
      "4                     30.33                     30.27                  10   \n",
      "\n",
      "  VisibilityAvgMiles VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH  \\\n",
      "0                  7                  2          20          4          31   \n",
      "1                 10                  5          16          6          25   \n",
      "2                 10                 10           8          3          12   \n",
      "3                 10                  7          12          4          20   \n",
      "4                 10                  7          10          2          16   \n",
      "\n",
      "  PrecipitationSumInches               Events  \n",
      "0                   0.46  Rain , Thunderstorm  \n",
      "1                      0                       \n",
      "2                      0                       \n",
      "3                      0                       \n",
      "4                      T                       \n",
      "\n",
      "[5 rows x 21 columns]\n",
      "            Date  TempHighF  TempAvgF  TempLowF DewPointHighF DewPointAvgF  \\\n",
      "1314  2017-07-27        103        89        75            71           67   \n",
      "1315  2017-07-28        105        91        76            71           64   \n",
      "1316  2017-07-29        107        92        77            72           64   \n",
      "1317  2017-07-30        106        93        79            70           68   \n",
      "1318  2017-07-31         99        88        77            66           61   \n",
      "\n",
      "     DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent  \\\n",
      "1314           61                  82                 54                 25   \n",
      "1315           55                  87                 54                 20   \n",
      "1316           55                  82                 51                 19   \n",
      "1317           63                  69                 48                 27   \n",
      "1318           54                  64                 43                 22   \n",
      "\n",
      "      ... SeaLevelPressureAvgInches SeaLevelPressureLowInches  \\\n",
      "1314  ...                     29.97                     29.88   \n",
      "1315  ...                      29.9                     29.81   \n",
      "1316  ...                     29.86                     29.79   \n",
      "1317  ...                     29.91                     29.87   \n",
      "1318  ...                     29.97                     29.91   \n",
      "\n",
      "     VisibilityHighMiles VisibilityAvgMiles VisibilityLowMiles WindHighMPH  \\\n",
      "1314                  10                 10                 10          12   \n",
      "1315                  10                 10                 10          14   \n",
      "1316                  10                 10                 10          12   \n",
      "1317                  10                 10                 10          13   \n",
      "1318                  10                 10                 10          12   \n",
      "\n",
      "     WindAvgMPH WindGustMPH PrecipitationSumInches Events  \n",
      "1314          5          21                      0         \n",
      "1315          5          20                      0         \n",
      "1316          4          17                      0         \n",
      "1317          4          20                      0         \n",
      "1318          4          20                      0         \n",
      "\n",
      "[5 rows x 21 columns]\n"
     ]
    }
   ],
   "source": [
    "#\n",
    "# load data and inspect\n",
    "#\n",
    "df = pd.read_csv('../Datasets/austin_weather.csv')\n",
    "#\n",
    "print(df.head())\n",
    "print(df.tail())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "hBtKePSxQDOV",
    "outputId": "11e0290a-73f3-4587-8653-b75303f566ed"
   },
   "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>TempAvgF</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2013-12-21</td>\n",
       "      <td>60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013-12-22</td>\n",
       "      <td>48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2013-12-23</td>\n",
       "      <td>45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2013-12-24</td>\n",
       "      <td>46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2013-12-25</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date  TempAvgF\n",
       "0  2013-12-21        60\n",
       "1  2013-12-22        48\n",
       "2  2013-12-23        45\n",
       "3  2013-12-24        46\n",
       "4  2013-12-25        50"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.loc[:, ['Date', 'TempAvgF']]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "91njYskTbYvc",
    "outputId": "2087cfdd-2acc-4aee-9ec0-cc88b426214e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         Date  TempAvgF  Year  Month  Day\n",
      "0  2013-12-21        60  2013     12   21\n",
      "1  2013-12-22        48  2013     12   22\n",
      "2  2013-12-23        45  2013     12   23\n",
      "3  2013-12-24        46  2013     12   24\n",
      "4  2013-12-25        50  2013     12   25\n",
      "            Date  TempAvgF  Year  Month  Day\n",
      "1314  2017-07-27        89  2017      7   27\n",
      "1315  2017-07-28        91  2017      7   28\n",
      "1316  2017-07-29        92  2017      7   29\n",
      "1317  2017-07-30        93  2017      7   30\n",
      "1318  2017-07-31        88  2017      7   31\n"
     ]
    }
   ],
   "source": [
    "#\n",
    "# add some useful columns\n",
    "#\n",
    "df.loc[:, 'Year'] = df.loc[:, 'Date'].str.slice(0, 4).astype('int')\n",
    "df.loc[:, 'Month'] = df.loc[:, 'Date'].str.slice(5, 7).astype('int')\n",
    "df.loc[:, 'Day'] = df.loc[:, 'Date'].str.slice(8, 10).astype('int')\n",
    "#\n",
    "print(df.head())\n",
    "print(df.tail())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "bb7yHHt-cXt_",
    "outputId": "3b1725b7-b0c6-49d6-f760-018ec5cebf3c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         Date  TempAvgF  Year  Month  Day  20_d_mov_avg\n",
      "0  2013-12-21        60  2013     12   21           NaN\n",
      "1  2013-12-22        48  2013     12   22           NaN\n",
      "2  2013-12-23        45  2013     12   23           NaN\n",
      "3  2013-12-24        46  2013     12   24           NaN\n",
      "4  2013-12-25        50  2013     12   25           NaN\n",
      "            Date  TempAvgF  Year  Month  Day  20_d_mov_avg\n",
      "1314  2017-07-27        89  2017      7   27         88.95\n",
      "1315  2017-07-28        91  2017      7   28         89.10\n",
      "1316  2017-07-29        92  2017      7   29         89.25\n",
      "1317  2017-07-30        93  2017      7   30         89.50\n",
      "1318  2017-07-31        88  2017      7   31         89.45\n"
     ]
    }
   ],
   "source": [
    "#\n",
    "# set a 20 day window then use that to smooth \n",
    "# temperature in a new column\n",
    "window = 20\n",
    "df['20_d_mov_avg'] = df.TempAvgF.rolling(window).mean()\n",
    "print(df.head())\n",
    "print(df.tail())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "qm2_i2KdtLTY",
    "outputId": "589c4383-8ba6-40ce-c06d-b8123f41eda8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   index        Date  TempAvgF  Year  Month  Day  20_d_mov_avg  Day_of_Year\n",
      "0    376  2015-01-01        37  2015      1    1         52.70            1\n",
      "1    377  2015-01-02        41  2015      1    2         51.50            2\n",
      "2    378  2015-01-03        51  2015      1    3         50.65            3\n",
      "3    379  2015-01-04        43  2015      1    4         49.65            4\n",
      "4    380  2015-01-05        41  2015      1    5         48.95            5\n",
      "     index        Date  TempAvgF  Year  Month  Day  20_d_mov_avg  Day_of_Year\n",
      "360    736  2015-12-27        55  2015     12   27         61.10          361\n",
      "361    737  2015-12-28        41  2015     12   28         60.20          362\n",
      "362    738  2015-12-29        43  2015     12   29         59.25          363\n",
      "363    739  2015-12-30        49  2015     12   30         58.45          364\n",
      "364    740  2015-12-31        46  2015     12   31         57.45          365\n"
     ]
    }
   ],
   "source": [
    "#\n",
    "# now let's slice exactly one year on the\n",
    "# calendar start and end dates\n",
    "# we see from the previous output that \n",
    "# 2014 is the first year with complete data, \n",
    "# however it will still have NaN values for \n",
    "# the moving average, so we'll use 2015\n",
    "#\n",
    "df_one_year = df.loc[df.Year == 2015, :].reset_index()\n",
    "df_one_year['Day_of_Year'] = df_one_year.index + 1\n",
    "print(df_one_year.head())\n",
    "print(df_one_year.tail())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 608
    },
    "colab_type": "code",
    "id": "RKtQn57hRMM8",
    "outputId": "7a3cbfe9-9c1c-4f08-c6b6-a231974ec0e6"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(10, 7))\n",
    "ax = fig.add_axes([1, 1, 1, 1]);\n",
    "#\n",
    "# Raw data\n",
    "#\n",
    "ax.scatter(df_one_year.Day_of_Year, \n",
    "           df_one_year.TempAvgF, \n",
    "           label = 'Raw Data', c = 'k')\n",
    "#\n",
    "# Moving averages\n",
    "#\n",
    "ax.plot(df_one_year.Day_of_Year,\n",
    "        df_one_year['20_d_mov_avg'], \n",
    "        c = 'r', \n",
    "        linestyle = '--', \n",
    "        label = f'{window} day moving average')\n",
    "#\n",
    "ax.set_title('Air Temperature Measurements',\n",
    "             fontsize = 16)\n",
    "ax.set_xlabel('Day', \n",
    "              fontsize = 14)\n",
    "ax.set_ylabel('Temperature ($^\\circ$F)', \n",
    "              fontsize = 14)\n",
    "ax.set_xticks(range(df_one_year.Day_of_Year.min(), \n",
    "                    df_one_year.Day_of_Year.max(), \n",
    "                    30))\n",
    "ax.tick_params(labelsize = 12)\n",
    "ax.legend(fontsize = 12)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "UMPUpLhfwWLw",
    "outputId": "2581c42a-8f61-4f24-c935-5d310167f6ab"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "model slope:  [0.04304568]\n",
      "model intercept:  62.23496914044859\n",
      "model r squared:  0.09549593659736466\n"
     ]
    }
   ],
   "source": [
    "#\n",
    "# fit a linear model\n",
    "#\n",
    "linear_model = LinearRegression(fit_intercept = True)\n",
    "linear_model.fit(df_one_year['Day_of_Year'].values.reshape((-1, 1)),\n",
    "                 df_one_year.TempAvgF)\n",
    "print('model slope: ', linear_model.coef_)\n",
    "print('model intercept: ', linear_model.intercept_)\n",
    "print('model r squared: ', \n",
    "      linear_model.score(df_one_year['Day_of_Year'].values.reshape((-1, 1)),\n",
    "                         df_one_year.TempAvgF))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Zh_2jQ1Wz7YW"
   },
   "outputs": [],
   "source": [
    "#\n",
    "# make predictions using the training data\n",
    "#\n",
    "y_pred = linear_model.predict(df_one_year['Day_of_Year'].values.\n",
    "                              reshape((-1, 1)))\n",
    "x_pred = df_one_year.Day_of_Year"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 608
    },
    "colab_type": "code",
    "id": "o7WO0mhUzzx9",
    "outputId": "8b9419b2-70b4-41c0-b8a6-0ef875d1d312"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(10, 7))\n",
    "ax = fig.add_axes([1, 1, 1, 1]);\n",
    "#\n",
    "# Raw data\n",
    "#\n",
    "ax.scatter(df_one_year.Day_of_Year, \n",
    "           df_one_year.TempAvgF, \n",
    "           label = 'Raw Data', c = 'k')\n",
    "#\n",
    "# Moving averages\n",
    "#\n",
    "ax.plot(df_one_year.Day_of_Year,\n",
    "        df_one_year['20_d_mov_avg'], \n",
    "        c = 'r', \n",
    "        linestyle = '--', \n",
    "        label = f'{window} day moving average')\n",
    "#\n",
    "# linear model\n",
    "#\n",
    "ax.plot(x_pred, y_pred,\n",
    "        c = \"blue\",\n",
    "        linestyle = '-.',\n",
    "        label = 'linear model')\n",
    "#\n",
    "ax.set_title('Air Temperature Measurements',\n",
    "             fontsize = 16)\n",
    "ax.set_xlabel('Day', \n",
    "              fontsize = 14)\n",
    "ax.set_ylabel('Temperature ($^\\circ$F)', \n",
    "              fontsize = 14)\n",
    "ax.set_xticks(range(df_one_year.Day_of_Year.min(), \n",
    "                    df_one_year.Day_of_Year.max(), \n",
    "                    30))\n",
    "ax.tick_params(labelsize = 12)\n",
    "ax.legend(fontsize = 12)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Activity 2.02.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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}