Module-05.ipynb

module-05.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Module-05.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "c8JNdbFsg85d",
        "9pKP4AoZ36Zn",
        "nFAEPvsTXVIe",
        "BFMZYwUeXGh1",
        "JUGmxZe4XNsj",
        "mo9URLJe75FU",
        "1bRIrvA2CPwx"
      ],
      "toc_visible": true,
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/727021/76bc0dad8d27f885b6d09b3417ca9c4c/module-05.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "c8JNdbFsg85d"
      },
      "source": [
        "## Data Dictionary"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "52xbrBZF4DDR"
      },
      "source": [
        "- **instant**: record index \n",
        "- **dteday** : date \n",
        "- **season** : season (1:winter, 2:spring, 3:summer, 4:fall) \n",
        "- **hr** : hour (0 to 23) \n",
        "- **holiday** : weather day is holiday or not\n",
        "- **workingday** : if day is neither weekend nor holiday is 1, otherwise is 0. \n",
        "- **weathersit** : \n",
        "  - 1: Clear, Few clouds, Partly cloudy, Partly cloudy \n",
        "  - 2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist \n",
        "  - 3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds \n",
        "  - 4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog \n",
        "- **temp_c** : temperature in Celsius. \n",
        "- **feels_like_c**: \"Feels like\" temperature in Celsius. \n",
        "- **hum**: humidity percentage\n",
        "- **windspeed**: Wind speed.\n",
        "- **casual**: count of casual users \n",
        "- **registered**: count of registered users "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9pKP4AoZ36Zn"
      },
      "source": [
        "## Imports"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L0YQIu7AB-IN",
        "outputId": "0419d1db-db60-4842-fc7c-b442f9e8e230"
      },
      "source": [
        "!pip install -q -U keras-tuner"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\u001b[?25l\r\u001b[K     |██████                          | 10kB 20.6MB/s eta 0:00:01\r\u001b[K     |████████████                    | 20kB 14.5MB/s eta 0:00:01\r\u001b[K     |██████████████████              | 30kB 12.4MB/s eta 0:00:01\r\u001b[K     |████████████████████████        | 40kB 8.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████  | 51kB 4.5MB/s eta 0:00:01\r\u001b[K     |████████████████████████████████| 61kB 3.3MB/s \n",
            "\u001b[?25h  Building wheel for keras-tuner (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Building wheel for terminaltables (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mA0HPVmIBT4C"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers\n",
        "from tensorflow.keras.layers.experimental import preprocessing\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "\n",
        "import IPython\n",
        "import kerastuner as kt\n",
        "\n",
        "plt.style.use('dark_background')\n",
        "sns.set_style('darkgrid')"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nFAEPvsTXVIe"
      },
      "source": [
        "## Bike Data Normalization"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OMi1Np_zxc99"
      },
      "source": [
        "bikes = pd.read_csv('https://raw.githubusercontent.com/byui-cse/cse450-course/master/data/bikes.csv').drop(['Unnamed: 0','instant'], 'columns')"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bhP2-wCeEarp",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 419
        },
        "outputId": "cc56ef76-376f-4a42-b102-f5410f41decf"
      },
      "source": [
        "bikes"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>dteday</th>\n",
              "      <th>season</th>\n",
              "      <th>hr</th>\n",
              "      <th>holiday</th>\n",
              "      <th>workingday</th>\n",
              "      <th>weathersit</th>\n",
              "      <th>hum</th>\n",
              "      <th>windspeed</th>\n",
              "      <th>temp_c</th>\n",
              "      <th>feels_like_c</th>\n",
              "      <th>casual</th>\n",
              "      <th>registered</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1/1/11</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.81</td>\n",
              "      <td>0</td>\n",
              "      <td>3.28</td>\n",
              "      <td>3.0014</td>\n",
              "      <td>3</td>\n",
              "      <td>13</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1/1/11</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.80</td>\n",
              "      <td>0</td>\n",
              "      <td>2.34</td>\n",
              "      <td>1.9982</td>\n",
              "      <td>8</td>\n",
              "      <td>32</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1/1/11</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.80</td>\n",
              "      <td>0</td>\n",
              "      <td>2.34</td>\n",
              "      <td>1.9982</td>\n",
              "      <td>5</td>\n",
              "      <td>27</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1/1/11</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.75</td>\n",
              "      <td>0</td>\n",
              "      <td>3.28</td>\n",
              "      <td>3.0014</td>\n",
              "      <td>3</td>\n",
              "      <td>10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1/1/11</td>\n",
              "      <td>1</td>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.75</td>\n",
              "      <td>0</td>\n",
              "      <td>3.28</td>\n",
              "      <td>3.0014</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17374</th>\n",
              "      <td>12/31/12</td>\n",
              "      <td>1</td>\n",
              "      <td>19</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>0.60</td>\n",
              "      <td>11</td>\n",
              "      <td>4.22</td>\n",
              "      <td>1.0016</td>\n",
              "      <td>11</td>\n",
              "      <td>108</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17375</th>\n",
              "      <td>12/31/12</td>\n",
              "      <td>1</td>\n",
              "      <td>20</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>0.60</td>\n",
              "      <td>11</td>\n",
              "      <td>4.22</td>\n",
              "      <td>1.0016</td>\n",
              "      <td>8</td>\n",
              "      <td>81</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17376</th>\n",
              "      <td>12/31/12</td>\n",
              "      <td>1</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.60</td>\n",
              "      <td>11</td>\n",
              "      <td>4.22</td>\n",
              "      <td>1.0016</td>\n",
              "      <td>7</td>\n",
              "      <td>83</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17377</th>\n",
              "      <td>12/31/12</td>\n",
              "      <td>1</td>\n",
              "      <td>22</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.56</td>\n",
              "      <td>9</td>\n",
              "      <td>4.22</td>\n",
              "      <td>1.9982</td>\n",
              "      <td>13</td>\n",
              "      <td>48</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17378</th>\n",
              "      <td>12/31/12</td>\n",
              "      <td>1</td>\n",
              "      <td>23</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.65</td>\n",
              "      <td>9</td>\n",
              "      <td>4.22</td>\n",
              "      <td>1.9982</td>\n",
              "      <td>12</td>\n",
              "      <td>37</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>17379 rows × 12 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "         dteday  season  hr  holiday  ...  temp_c  feels_like_c  casual  registered\n",
              "0        1/1/11       1   0        0  ...    3.28        3.0014       3          13\n",
              "1        1/1/11       1   1        0  ...    2.34        1.9982       8          32\n",
              "2        1/1/11       1   2        0  ...    2.34        1.9982       5          27\n",
              "3        1/1/11       1   3        0  ...    3.28        3.0014       3          10\n",
              "4        1/1/11       1   4        0  ...    3.28        3.0014       0           1\n",
              "...         ...     ...  ..      ...  ...     ...           ...     ...         ...\n",
              "17374  12/31/12       1  19        0  ...    4.22        1.0016      11         108\n",
              "17375  12/31/12       1  20        0  ...    4.22        1.0016       8          81\n",
              "17376  12/31/12       1  21        0  ...    4.22        1.0016       7          83\n",
              "17377  12/31/12       1  22        0  ...    4.22        1.9982      13          48\n",
              "17378  12/31/12       1  23        0  ...    4.22        1.9982      12          37\n",
              "\n",
              "[17379 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "StiU5QcPPxqQ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "outputId": "52d00e3a-1431-4b89-d3b5-6cc0140712c9"
      },
      "source": [
        "bikes[['temp_c','feels_like_c']].describe()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>temp_c</th>\n",
              "      <th>feels_like_c</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>17379.000000</td>\n",
              "      <td>17379.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>15.358397</td>\n",
              "      <td>15.401157</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>9.050138</td>\n",
              "      <td>11.342114</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>-7.060000</td>\n",
              "      <td>-16.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>7.980000</td>\n",
              "      <td>5.997800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>15.500000</td>\n",
              "      <td>15.996800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>23.020000</td>\n",
              "      <td>24.999200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>39.000000</td>\n",
              "      <td>50.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "             temp_c  feels_like_c\n",
              "count  17379.000000  17379.000000\n",
              "mean      15.358397     15.401157\n",
              "std        9.050138     11.342114\n",
              "min       -7.060000    -16.000000\n",
              "25%        7.980000      5.997800\n",
              "50%       15.500000     15.996800\n",
              "75%       23.020000     24.999200\n",
              "max       39.000000     50.000000"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cDBKDVF5ly-l",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "outputId": "23a5d143-0a0c-4f13-86d9-64e72c738baf"
      },
      "source": [
        "scaler = MinMaxScaler()\n",
        "bikes['temp_scaled'] = scaler.fit_transform(bikes[['temp_c']])\n",
        "bikes['feels_like_scaled'] = scaler.fit_transform(bikes[['feels_like_c']])\n",
        "bikes[['temp_c','temp_scaled','feels_like_c','feels_like_scaled']].describe()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>temp_c</th>\n",
              "      <th>temp_scaled</th>\n",
              "      <th>feels_like_c</th>\n",
              "      <th>feels_like_scaled</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>17379.000000</td>\n",
              "      <td>17379.000000</td>\n",
              "      <td>17379.000000</td>\n",
              "      <td>17379.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>15.358397</td>\n",
              "      <td>0.486722</td>\n",
              "      <td>15.401157</td>\n",
              "      <td>0.475775</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>9.050138</td>\n",
              "      <td>0.196486</td>\n",
              "      <td>11.342114</td>\n",
              "      <td>0.171850</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>-7.060000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>-16.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>7.980000</td>\n",
              "      <td>0.326531</td>\n",
              "      <td>5.997800</td>\n",
              "      <td>0.333300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>15.500000</td>\n",
              "      <td>0.489796</td>\n",
              "      <td>15.996800</td>\n",
              "      <td>0.484800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>23.020000</td>\n",
              "      <td>0.653061</td>\n",
              "      <td>24.999200</td>\n",
              "      <td>0.621200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>39.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>50.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "             temp_c   temp_scaled  feels_like_c  feels_like_scaled\n",
              "count  17379.000000  17379.000000  17379.000000       17379.000000\n",
              "mean      15.358397      0.486722     15.401157           0.475775\n",
              "std        9.050138      0.196486     11.342114           0.171850\n",
              "min       -7.060000      0.000000    -16.000000           0.000000\n",
              "25%        7.980000      0.326531      5.997800           0.333300\n",
              "50%       15.500000      0.489796     15.996800           0.484800\n",
              "75%       23.020000      0.653061     24.999200           0.621200\n",
              "max       39.000000      1.000000     50.000000           1.000000"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NJKm5asBGemA",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "093a8bac-49de-4799-8c1c-48d97cac0015"
      },
      "source": [
        "bikes.columns.array"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<PandasArray>\n",
              "[           'dteday',            'season',                'hr',\n",
              "           'holiday',        'workingday',        'weathersit',\n",
              "               'hum',         'windspeed',            'temp_c',\n",
              "      'feels_like_c',            'casual',        'registered',\n",
              "       'temp_scaled', 'feels_like_scaled']\n",
              "Length: 14, dtype: object"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ALLMN63FPyEQ"
      },
      "source": [
        "from sklearn.preprocessing import MinMaxScaler\n",
        "agg = pd.DataFrame(\n",
        "    [{\n",
        "    'season': bikes[bikes['dteday'] == d]['season'].values[0],\n",
        "    'holiday': bikes[bikes['dteday'] == d]['holiday'].values[0],\n",
        "    'workingday': bikes[bikes['dteday'] == d]['workingday'].values[0],\n",
        "    'weathersit': bikes[bikes['dteday'] == d]['weathersit'].mode().values[0],\n",
        "    'hum': bikes[bikes['dteday'] == d]['hum'].mean(),\n",
        "    'windspeed': bikes[bikes['dteday'] == d]['windspeed'].mean(),\n",
        "    'temp_c': bikes[bikes['dteday'] == d]['temp_c'].median(),\n",
        "    'feels_like_c': bikes[bikes['dteday'] == d]['feels_like_c'].median(),\n",
        "    'total_bikes': bikes[bikes['dteday'] == d]['casual'].sum() + bikes[bikes['dteday'] == d]['registered'].sum()\n",
        "} for d in bikes['dteday'].unique()])\n",
        "\n",
        "scaler = MinMaxScaler()\n",
        "agg['temp_c'] = scaler.fit_transform(agg[['temp_c']])\n",
        "agg['feels_like_c'] = scaler.fit_transform(agg[['feels_like_c']])\n",
        "agg['windspeed'] = scaler.fit_transform(agg[['windspeed']])\n",
        "\n",
        "agg['season'] = agg['season'].map({1: 'winter', 2: 'spring', 3: 'summer', 4: 'fall'})\n",
        "agg['weathersit'] = agg['weathersit'].map({1: 'clear', 2: 'mist_clouds', 3: 'light_rain_snow', 4: 'heavy_rain_snow'})\n",
        "agg = pd.get_dummies(agg, prefix='', prefix_sep='')"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uoR6Vxk2KVJK",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 419
        },
        "outputId": "db4c8c71-62e6-4b55-b772-d38b40d4bcac"
      },
      "source": [
        "agg"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>holiday</th>\n",
              "      <th>workingday</th>\n",
              "      <th>hum</th>\n",
              "      <th>windspeed</th>\n",
              "      <th>temp_c</th>\n",
              "      <th>feels_like_c</th>\n",
              "      <th>total_bikes</th>\n",
              "      <th>fall</th>\n",
              "      <th>spring</th>\n",
              "      <th>summer</th>\n",
              "      <th>winter</th>\n",
              "      <th>clear</th>\n",
              "      <th>light_rain_snow</th>\n",
              "      <th>mist_clouds</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.805833</td>\n",
              "      <td>0.284615</td>\n",
              "      <td>0.4125</td>\n",
              "      <td>0.413430</td>\n",
              "      <td>985</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.696087</td>\n",
              "      <td>0.466221</td>\n",
              "      <td>0.3750</td>\n",
              "      <td>0.346154</td>\n",
              "      <td>801</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.437273</td>\n",
              "      <td>0.465734</td>\n",
              "      <td>0.1750</td>\n",
              "      <td>0.153846</td>\n",
              "      <td>1349</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.590435</td>\n",
              "      <td>0.284281</td>\n",
              "      <td>0.2000</td>\n",
              "      <td>0.192308</td>\n",
              "      <td>1562</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.436957</td>\n",
              "      <td>0.339130</td>\n",
              "      <td>0.2000</td>\n",
              "      <td>0.192308</td>\n",
              "      <td>1600</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>726</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.652917</td>\n",
              "      <td>0.675641</td>\n",
              "      <td>0.2250</td>\n",
              "      <td>0.192308</td>\n",
              "      <td>2114</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>727</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.590000</td>\n",
              "      <td>0.274359</td>\n",
              "      <td>0.2250</td>\n",
              "      <td>0.211475</td>\n",
              "      <td>3095</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>728</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.752917</td>\n",
              "      <td>0.210256</td>\n",
              "      <td>0.2500</td>\n",
              "      <td>0.211475</td>\n",
              "      <td>1341</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>729</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.483333</td>\n",
              "      <td>0.676923</td>\n",
              "      <td>0.2500</td>\n",
              "      <td>0.192308</td>\n",
              "      <td>1796</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>730</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.577500</td>\n",
              "      <td>0.273077</td>\n",
              "      <td>0.2125</td>\n",
              "      <td>0.192308</td>\n",
              "      <td>2729</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>731 rows × 14 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     holiday  workingday       hum  ...  clear  light_rain_snow  mist_clouds\n",
              "0          0           0  0.805833  ...      1                0            0\n",
              "1          0           0  0.696087  ...      0                0            1\n",
              "2          0           1  0.437273  ...      1                0            0\n",
              "3          0           1  0.590435  ...      1                0            0\n",
              "4          0           1  0.436957  ...      1                0            0\n",
              "..       ...         ...       ...  ...    ...              ...          ...\n",
              "726        0           1  0.652917  ...      0                0            1\n",
              "727        0           1  0.590000  ...      0                0            1\n",
              "728        0           0  0.752917  ...      0                0            1\n",
              "729        0           0  0.483333  ...      1                0            0\n",
              "730        0           1  0.577500  ...      1                0            0\n",
              "\n",
              "[731 rows x 14 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BFMZYwUeXGh1"
      },
      "source": [
        "## Keras Image Classification Tutorial"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RnGBwGVZPyyh",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c51e9072-c185-4085-ab75-7b67fd3118f1"
      },
      "source": [
        "fashion_mnist = keras.datasets.fashion_mnist\n",
        "\n",
        "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n",
            "32768/29515 [=================================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n",
            "26427392/26421880 [==============================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n",
            "8192/5148 [===============================================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n",
            "4423680/4422102 [==============================] - 0s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CVSfaqgKPzE2"
      },
      "source": [
        "class_names = ['T-shirt/top','Trouser','Pullover','Dress','Coat','Sandal','Shirt','Sneaker','Bag','Ankle boot']"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NaCwpFfKQ7pr",
        "outputId": "fb7bca77-c447-4273-ed78-a152671f5eff"
      },
      "source": [
        "train_images.shape"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(60000, 28, 28)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yhNOUQVCQ_Wf",
        "outputId": "8237f29f-2227-4dc2-e984-467f354ec122"
      },
      "source": [
        "print (len(train_labels))\n",
        "train_labels"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "60000\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "400xq5IRRMxN",
        "outputId": "a7f234dc-0de9-48dc-eb7c-daec2c11cb26"
      },
      "source": [
        "test_images.shape"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(10000, 28, 28)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YOmeTWweRRjZ",
        "outputId": "df4f51d5-4cda-4f10-b709-ffd2e3304db5"
      },
      "source": [
        "print(len(test_labels))\n",
        "test_labels"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "10000\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([9, 2, 1, ..., 8, 1, 5], dtype=uint8)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 265
        },
        "id": "mZEb_OE6RWQo",
        "outputId": "7a5e70aa-3a82-4ab7-a405-77c7582656bd"
      },
      "source": [
        "plt.figure()\n",
        "plt.imshow(train_images[0])\n",
        "plt.colorbar()\n",
        "plt.grid(False)\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GM9Xuy3vRnAd"
      },
      "source": [
        "train_images = train_images / 255.0\n",
        "test_images = test_images / 255.0"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 589
        },
        "id": "edejv2sFRxPc",
        "outputId": "1237cdc3-782e-4c0b-bea1-336ae1aa4a58"
      },
      "source": [
        "plt.figure(figsize=(10,10))\n",
        "for i in range(25):\n",
        "  plt.subplot(5,5,i+1)\n",
        "  plt.xticks([])\n",
        "  plt.yticks([])\n",
        "  plt.grid(False)\n",
        "  plt.imshow(train_images[i],cmap=plt.cm.binary)\n",
        "  plt.xlabel(class_names[train_labels[i]])\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 25 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sxBGh2t-SRLe"
      },
      "source": [
        "model = keras.Sequential([\n",
        "                          layers.Flatten(input_shape=(28,28)),\n",
        "                          layers.Dense(128, activation='relu'),\n",
        "                          layers.Dense(10)\n",
        "])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-rdX9xR7StT2"
      },
      "source": [
        "model.compile(optimizer='adam',\n",
        "              loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
        "              metrics=['accuracy'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IfHmnLJLTPct",
        "outputId": "0818e7af-856f-4831-8d6e-b2c15559cf69"
      },
      "source": [
        "model.fit(train_images, train_labels, epochs=10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4964 - accuracy: 0.8264\n",
            "Epoch 2/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.3758 - accuracy: 0.8632\n",
            "Epoch 3/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.3374 - accuracy: 0.8771\n",
            "Epoch 4/10\n",
            "1875/1875 [==============================] - 3s 2ms/step - loss: 0.3125 - accuracy: 0.8853\n",
            "Epoch 5/10\n",
            "1875/1875 [==============================] - 3s 2ms/step - loss: 0.2943 - accuracy: 0.8901\n",
            "Epoch 6/10\n",
            "1875/1875 [==============================] - 3s 2ms/step - loss: 0.2796 - accuracy: 0.8964\n",
            "Epoch 7/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2679 - accuracy: 0.9002\n",
            "Epoch 8/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2546 - accuracy: 0.9041\n",
            "Epoch 9/10\n",
            "1875/1875 [==============================] - 5s 3ms/step - loss: 0.2461 - accuracy: 0.9090\n",
            "Epoch 10/10\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2363 - accuracy: 0.9111\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7fc00a8d8828>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eCdk_janTmfr",
        "outputId": "16dd71a4-f4e4-4451-f92a-344737c96158"
      },
      "source": [
        "test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)\n",
        "\n",
        "print('\\nTest accuracy:', test_acc)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "313/313 - 0s - loss: 0.3383 - accuracy: 0.8835\n",
            "\n",
            "Test accuracy: 0.8834999799728394\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "T_8gHjt1T9up",
        "outputId": "0f627eb8-3c9f-4d84-a354-b7f4304ed7e4"
      },
      "source": [
        "probability_model = keras.Sequential([model, layers.Softmax()])\n",
        "predictions = probability_model.predict(test_images)\n",
        "predictions[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([2.67725841e-09, 1.06328314e-10, 2.22532415e-09, 5.89994165e-10,\n",
              "       7.06924352e-10, 4.14969727e-05, 2.91648150e-09, 8.09382880e-04,\n",
              "       9.15227727e-10, 9.99149084e-01], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dIQ9Wf80UkUp"
      },
      "source": [
        "def plot_image(i, predictions_array, true_label, img):\n",
        "  true_label, img = true_label[i], img[i]\n",
        "  plt.grid(False)\n",
        "  plt.xticks([])\n",
        "  plt.yticks([])\n",
        "\n",
        "  plt.imshow(img, cmap=plt.cm.binary)\n",
        "\n",
        "  predicted_label = np.argmax(predictions_array)\n",
        "  color = 'blue' if predicted_label == true_label else 'red'\n",
        "\n",
        "  plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label],\n",
        "                                       100*np.max(predictions_array),\n",
        "                                       class_names[true_label]),\n",
        "             color=color)\n",
        "  \n",
        "def plot_value_array(i, predictions_array, true_label):\n",
        "  true_label = true_label[i]\n",
        "  plt.grid(False)\n",
        "  plt.xticks(range(10))\n",
        "  plt.yticks([])\n",
        "  thisplot = plt.bar(range(10), predictions_array, color='#777777')\n",
        "  plt.ylim([0,1])\n",
        "  predicted_label = np.argmax(predictions_array)\n",
        "\n",
        "  thisplot[predicted_label].set_color('red')\n",
        "  thisplot[true_label].set_color('blue')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 211
        },
        "id": "DN0xDC-dV5q8",
        "outputId": "8c9a0a76-3f4d-4e47-afe6-9a2351287117"
      },
      "source": [
        "i = 12\n",
        "plt.figure(figsize=(6,3))\n",
        "plt.subplot(1,2,1)\n",
        "plot_image(i, predictions[i], test_labels, test_images)\n",
        "plt.subplot(1,2,2)\n",
        "plot_value_array(i, predictions[i], test_labels)\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x216 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JUGmxZe4XNsj"
      },
      "source": [
        "## Keras Regression Tutorial"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "apquqlvPXa-N"
      },
      "source": [
        "url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data'\n",
        "column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight','Acceleration','Model Year','Origin']\n",
        "\n",
        "raw_dataset = pd.read_csv(url, names=column_names, na_values='?', comment='\\t', sep=' ', skipinitialspace=True)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "LfrQ3KB-Ykni",
        "outputId": "f5e2eb7b-bb75-4dd2-fe04-c84bb1acf939"
      },
      "source": [
        "dataset = raw_dataset.copy()\n",
        "dataset.tail()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>MPG</th>\n",
              "      <th>Cylinders</th>\n",
              "      <th>Displacement</th>\n",
              "      <th>Horsepower</th>\n",
              "      <th>Weight</th>\n",
              "      <th>Acceleration</th>\n",
              "      <th>Model Year</th>\n",
              "      <th>Origin</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>393</th>\n",
              "      <td>27.0</td>\n",
              "      <td>4</td>\n",
              "      <td>140.0</td>\n",
              "      <td>86.0</td>\n",
              "      <td>2790.0</td>\n",
              "      <td>15.6</td>\n",
              "      <td>82</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>394</th>\n",
              "      <td>44.0</td>\n",
              "      <td>4</td>\n",
              "      <td>97.0</td>\n",
              "      <td>52.0</td>\n",
              "      <td>2130.0</td>\n",
              "      <td>24.6</td>\n",
              "      <td>82</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>395</th>\n",
              "      <td>32.0</td>\n",
              "      <td>4</td>\n",
              "      <td>135.0</td>\n",
              "      <td>84.0</td>\n",
              "      <td>2295.0</td>\n",
              "      <td>11.6</td>\n",
              "      <td>82</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>396</th>\n",
              "      <td>28.0</td>\n",
              "      <td>4</td>\n",
              "      <td>120.0</td>\n",
              "      <td>79.0</td>\n",
              "      <td>2625.0</td>\n",
              "      <td>18.6</td>\n",
              "      <td>82</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>397</th>\n",
              "      <td>31.0</td>\n",
              "      <td>4</td>\n",
              "      <td>119.0</td>\n",
              "      <td>82.0</td>\n",
              "      <td>2720.0</td>\n",
              "      <td>19.4</td>\n",
              "      <td>82</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      MPG  Cylinders  Displacement  ...  Acceleration  Model Year  Origin\n",
              "393  27.0          4         140.0  ...          15.6          82       1\n",
              "394  44.0          4          97.0  ...          24.6          82       2\n",
              "395  32.0          4         135.0  ...          11.6          82       1\n",
              "396  28.0          4         120.0  ...          18.6          82       1\n",
              "397  31.0          4         119.0  ...          19.4          82       1\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 99
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "z4sgYcLGYqSL",
        "outputId": "11c90156-2674-4580-fde3-f1a42adaa86c"
      },
      "source": [
        "dataset.isna().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "MPG             0\n",
              "Cylinders       0\n",
              "Displacement    0\n",
              "Horsepower      6\n",
              "Weight          0\n",
              "Acceleration    0\n",
              "Model Year      0\n",
              "Origin          0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 100
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9B6AyhTyYtWv"
      },
      "source": [
        "dataset = dataset.dropna()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "rdENk-pXY0zg",
        "outputId": "111d80c2-f691-4dd4-f72c-46af619ab98e"
      },
      "source": [
        "dataset['Origin'] = dataset['Origin'].map({1: 'USA', 2: 'Europe', 3: 'Japan'})\n",
        "dataset = pd.get_dummies(dataset, prefix='', prefix_sep='')\n",
        "dataset.tail()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>MPG</th>\n",
              "      <th>Cylinders</th>\n",
              "      <th>Displacement</th>\n",
              "      <th>Horsepower</th>\n",
              "      <th>Weight</th>\n",
              "      <th>Acceleration</th>\n",
              "      <th>Model Year</th>\n",
              "      <th>Europe</th>\n",
              "      <th>Japan</th>\n",
              "      <th>USA</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>393</th>\n",
              "      <td>27.0</td>\n",
              "      <td>4</td>\n",
              "      <td>140.0</td>\n",
              "      <td>86.0</td>\n",
              "      <td>2790.0</td>\n",
              "      <td>15.6</td>\n",
              "      <td>82</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>394</th>\n",
              "      <td>44.0</td>\n",
              "      <td>4</td>\n",
              "      <td>97.0</td>\n",
              "      <td>52.0</td>\n",
              "      <td>2130.0</td>\n",
              "      <td>24.6</td>\n",
              "      <td>82</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>395</th>\n",
              "      <td>32.0</td>\n",
              "      <td>4</td>\n",
              "      <td>135.0</td>\n",
              "      <td>84.0</td>\n",
              "      <td>2295.0</td>\n",
              "      <td>11.6</td>\n",
              "      <td>82</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>396</th>\n",
              "      <td>28.0</td>\n",
              "      <td>4</td>\n",
              "      <td>120.0</td>\n",
              "      <td>79.0</td>\n",
              "      <td>2625.0</td>\n",
              "      <td>18.6</td>\n",
              "      <td>82</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>397</th>\n",
              "      <td>31.0</td>\n",
              "      <td>4</td>\n",
              "      <td>119.0</td>\n",
              "      <td>82.0</td>\n",
              "      <td>2720.0</td>\n",
              "      <td>19.4</td>\n",
              "      <td>82</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      MPG  Cylinders  Displacement  Horsepower  ...  Model Year  Europe  Japan  USA\n",
              "393  27.0          4         140.0        86.0  ...          82       0      0    1\n",
              "394  44.0          4          97.0        52.0  ...          82       1      0    0\n",
              "395  32.0          4         135.0        84.0  ...          82       0      0    1\n",
              "396  28.0          4         120.0        79.0  ...          82       0      0    1\n",
              "397  31.0          4         119.0        82.0  ...          82       0      0    1\n",
              "\n",
              "[5 rows x 10 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 102
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QDQjpjRVZ62Y"
      },
      "source": [
        "train_dataset = dataset.sample(frac=0.8, random_state=0)\n",
        "test_dataset = dataset.drop(train_dataset.index)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 743
        },
        "id": "B-8T-M4raISi",
        "outputId": "1c6e7c9a-f441-4cce-813f-267ff92d120a"
      },
      "source": [
        "sns.pairplot(train_dataset[['MPG','Cylinders','Displacement','Weight']], diag_kind='kde')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.PairGrid at 0x7fbff7ce9358>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 104
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 20 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 359
        },
        "id": "A_uDME2vacon",
        "outputId": "68d6a9c8-ef4b-4cb7-ca87-9fe49a4a8da1"
      },
      "source": [
        "train_dataset.describe().transpose()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>MPG</th>\n",
              "      <td>314.0</td>\n",
              "      <td>23.310510</td>\n",
              "      <td>7.728652</td>\n",
              "      <td>10.0</td>\n",
              "      <td>17.00</td>\n",
              "      <td>22.0</td>\n",
              "      <td>28.95</td>\n",
              "      <td>46.6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Cylinders</th>\n",
              "      <td>314.0</td>\n",
              "      <td>5.477707</td>\n",
              "      <td>1.699788</td>\n",
              "      <td>3.0</td>\n",
              "      <td>4.00</td>\n",
              "      <td>4.0</td>\n",
              "      <td>8.00</td>\n",
              "      <td>8.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Displacement</th>\n",
              "      <td>314.0</td>\n",
              "      <td>195.318471</td>\n",
              "      <td>104.331589</td>\n",
              "      <td>68.0</td>\n",
              "      <td>105.50</td>\n",
              "      <td>151.0</td>\n",
              "      <td>265.75</td>\n",
              "      <td>455.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Horsepower</th>\n",
              "      <td>314.0</td>\n",
              "      <td>104.869427</td>\n",
              "      <td>38.096214</td>\n",
              "      <td>46.0</td>\n",
              "      <td>76.25</td>\n",
              "      <td>94.5</td>\n",
              "      <td>128.00</td>\n",
              "      <td>225.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Weight</th>\n",
              "      <td>314.0</td>\n",
              "      <td>2990.251592</td>\n",
              "      <td>843.898596</td>\n",
              "      <td>1649.0</td>\n",
              "      <td>2256.50</td>\n",
              "      <td>2822.5</td>\n",
              "      <td>3608.00</td>\n",
              "      <td>5140.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Acceleration</th>\n",
              "      <td>314.0</td>\n",
              "      <td>15.559236</td>\n",
              "      <td>2.789230</td>\n",
              "      <td>8.0</td>\n",
              "      <td>13.80</td>\n",
              "      <td>15.5</td>\n",
              "      <td>17.20</td>\n",
              "      <td>24.8</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Model Year</th>\n",
              "      <td>314.0</td>\n",
              "      <td>75.898089</td>\n",
              "      <td>3.675642</td>\n",
              "      <td>70.0</td>\n",
              "      <td>73.00</td>\n",
              "      <td>76.0</td>\n",
              "      <td>79.00</td>\n",
              "      <td>82.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Europe</th>\n",
              "      <td>314.0</td>\n",
              "      <td>0.178344</td>\n",
              "      <td>0.383413</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Japan</th>\n",
              "      <td>314.0</td>\n",
              "      <td>0.197452</td>\n",
              "      <td>0.398712</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>USA</th>\n",
              "      <td>314.0</td>\n",
              "      <td>0.624204</td>\n",
              "      <td>0.485101</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.00</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "              count         mean         std  ...     50%      75%     max\n",
              "MPG           314.0    23.310510    7.728652  ...    22.0    28.95    46.6\n",
              "Cylinders     314.0     5.477707    1.699788  ...     4.0     8.00     8.0\n",
              "Displacement  314.0   195.318471  104.331589  ...   151.0   265.75   455.0\n",
              "Horsepower    314.0   104.869427   38.096214  ...    94.5   128.00   225.0\n",
              "Weight        314.0  2990.251592  843.898596  ...  2822.5  3608.00  5140.0\n",
              "Acceleration  314.0    15.559236    2.789230  ...    15.5    17.20    24.8\n",
              "Model Year    314.0    75.898089    3.675642  ...    76.0    79.00    82.0\n",
              "Europe        314.0     0.178344    0.383413  ...     0.0     0.00     1.0\n",
              "Japan         314.0     0.197452    0.398712  ...     0.0     0.00     1.0\n",
              "USA           314.0     0.624204    0.485101  ...     1.0     1.00     1.0\n",
              "\n",
              "[10 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 105
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "f9uuiEflalPM"
      },
      "source": [
        "train_features = train_dataset.copy()\n",
        "test_features = test_dataset.copy()\n",
        "\n",
        "train_labels = train_features.pop('MPG')\n",
        "test_labels = test_features.pop('MPG')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 359
        },
        "id": "QHLbfw7obIlD",
        "outputId": "e4efd685-679d-49a6-bf65-8b4138b66a34"
      },
      "source": [
        "train_dataset.describe().transpose()[['mean','std']]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>mean</th>\n",
              "      <th>std</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>MPG</th>\n",
              "      <td>23.310510</td>\n",
              "      <td>7.728652</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Cylinders</th>\n",
              "      <td>5.477707</td>\n",
              "      <td>1.699788</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Displacement</th>\n",
              "      <td>195.318471</td>\n",
              "      <td>104.331589</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Horsepower</th>\n",
              "      <td>104.869427</td>\n",
              "      <td>38.096214</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Weight</th>\n",
              "      <td>2990.251592</td>\n",
              "      <td>843.898596</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Acceleration</th>\n",
              "      <td>15.559236</td>\n",
              "      <td>2.789230</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Model Year</th>\n",
              "      <td>75.898089</td>\n",
              "      <td>3.675642</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Europe</th>\n",
              "      <td>0.178344</td>\n",
              "      <td>0.383413</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Japan</th>\n",
              "      <td>0.197452</td>\n",
              "      <td>0.398712</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>USA</th>\n",
              "      <td>0.624204</td>\n",
              "      <td>0.485101</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                     mean         std\n",
              "MPG             23.310510    7.728652\n",
              "Cylinders        5.477707    1.699788\n",
              "Displacement   195.318471  104.331589\n",
              "Horsepower     104.869427   38.096214\n",
              "Weight        2990.251592  843.898596\n",
              "Acceleration    15.559236    2.789230\n",
              "Model Year      75.898089    3.675642\n",
              "Europe           0.178344    0.383413\n",
              "Japan            0.197452    0.398712\n",
              "USA              0.624204    0.485101"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 107
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H9nAsEdgbTol"
      },
      "source": [
        "normalizer = preprocessing.Normalization()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xoJQeVMwbp3J"
      },
      "source": [
        "normalizer.adapt(np.array(train_features))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UQ2IxH4ibt_L",
        "outputId": "ed55a941-ea96-46a9-e89a-9f9f27d33cb6"
      },
      "source": [
        "print(normalizer.mean.numpy())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[5.4777069e+00 1.9531847e+02 1.0486943e+02 2.9902517e+03 1.5559236e+01\n",
            " 7.5898087e+01 1.7834395e-01 1.9745223e-01 6.2420380e-01]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DJIBO-UWb8O1",
        "outputId": "f7e7884c-18a3-470d-d660-f5c3248392be"
      },
      "source": [
        "first = np.array(train_features[:1])\n",
        "\n",
        "with np.printoptions(precision=2, suppress=True):\n",
        "  print('First example:', first)\n",
        "  print()\n",
        "  print('Normalized:', normalizer(first).numpy())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "First example: [[   4.    90.    75.  2125.    14.5   74.     0.     0.     1. ]]\n",
            "\n",
            "Normalized: [[-0.87 -1.01 -0.79 -1.03 -0.38 -0.52 -0.47 -0.5   0.78]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s5IY30Vic3Qa"
      },
      "source": [
        "horsepower = np.array(train_features['Horsepower'])\n",
        "\n",
        "horsepower_normalizer = preprocessing.Normalization(input_shape=[1,])\n",
        "horsepower_normalizer.adapt(horsepower)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ckCmDqFodXxO",
        "outputId": "d0bbad49-5205-4dc3-bfe8-8ef92459d2c0"
      },
      "source": [
        "horsepower_model = keras.Sequential([\n",
        "                                     horsepower_normalizer,\n",
        "                                     layers.Dense(units=1)\n",
        "])\n",
        "\n",
        "horsepower_model.summary()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential_5\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "normalization_5 (Normalizati (None, 1)                 3         \n",
            "_________________________________________________________________\n",
            "dense_6 (Dense)              (None, 1)                 2         \n",
            "=================================================================\n",
            "Total params: 5\n",
            "Trainable params: 2\n",
            "Non-trainable params: 3\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rMGD4clKdpIS",
        "outputId": "6642087a-fe81-4a91-b4d9-fdfca0022d97"
      },
      "source": [
        "horsepower_model.predict(horsepower[:10])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[-1.2349782],\n",
              "       [-0.6974816],\n",
              "       [ 2.2794225],\n",
              "       [-1.7311288],\n",
              "       [-1.5657452],\n",
              "       [-0.6147898],\n",
              "       [-1.8551663],\n",
              "       [-1.5657452],\n",
              "       [-0.4080604],\n",
              "       [-0.6974816]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 114
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ms2Uxvo1d1yY"
      },
      "source": [
        "horsepower_model.compile(\n",
        "    optimizer=tf.optimizers.Adam(learning_rate=0.1),\n",
        "    loss='mean_absolute_error'\n",
        ")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "F1w6YDSceFu1",
        "outputId": "1c47d10a-9937-4ab4-cb08-207def1882c2"
      },
      "source": [
        "%%time\n",
        "history = horsepower_model.fit(\n",
        "    train_features['Horsepower'],\n",
        "    train_labels,\n",
        "    epochs=100,\n",
        "    verbose=0,\n",
        "    validation_split=0.2\n",
        ")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "CPU times: user 2.85 s, sys: 124 ms, total: 2.98 s\n",
            "Wall time: 2.67 s\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H8PorPcI4uSh"
      },
      "source": [
        "def plot_loss(history):\n",
        "  plt.plot(history.history['loss'], label='loss')\n",
        "  plt.plot(history.history['val_loss'], label='val_loss')\n",
        "  plt.ylim([0,10])\n",
        "  plt.xlabel('Epoch')\n",
        "  plt.ylabel('Error [MPG]')\n",
        "  plt.legend()\n",
        "  plt.grid(True)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        },
        "id": "3mJJyZEL5FOW",
        "outputId": "bd9fcc08-cf3b-4e7d-f494-6eeb1f5fd667"
      },
      "source": [
        "plot_loss(history)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WQy44M5N6pUu"
      },
      "source": [
        "linear_model = keras.Sequential([\n",
        "                                 normalizer,\n",
        "                                 layers.Dense(units=1)\n",
        "])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8gOvPFEu6yXK",
        "outputId": "6b6a845f-abe4-41ba-ce50-64da943130e1"
      },
      "source": [
        "linear_model.predict(train_features[:10])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "WARNING:tensorflow:5 out of the last 317 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7fbffa451400> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[-0.00393232],\n",
              "       [-0.1459277 ],\n",
              "       [ 0.7285248 ],\n",
              "       [ 0.7965479 ],\n",
              "       [-0.08119722],\n",
              "       [ 0.2692903 ],\n",
              "       [-0.25959298],\n",
              "       [-2.2340715 ],\n",
              "       [-0.07960415],\n",
              "       [-1.1002291 ]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 120
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ak-qm7Mn685I",
        "outputId": "d5f3908a-102a-4dc1-cff4-fa5ae1215457"
      },
      "source": [
        "linear_model.layers[1].kernel"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Variable 'dense_7/kernel:0' shape=(9, 1) dtype=float32, numpy=\n",
              "array([[ 0.11204964],\n",
              "       [ 0.39741302],\n",
              "       [-0.30098823],\n",
              "       [ 0.02770174],\n",
              "       [-0.68731296],\n",
              "       [ 0.32002985],\n",
              "       [-0.72629964],\n",
              "       [-0.182738  ],\n",
              "       [-0.30595553]], dtype=float32)>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 121
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lUdgUKpC7Cs_"
      },
      "source": [
        "linear_model.compile(\n",
        "    optimizer=tf.optimizers.Adam(learning_rate=0.1),\n",
        "    loss='mean_absolute_error'\n",
        ")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fnIa7kyR7Mto",
        "outputId": "84fa2704-8cb4-4922-b168-37b73b5e5d0f"
      },
      "source": [
        "%%time\n",
        "history = linear_model.fit(\n",
        "    train_features, train_labels,\n",
        "    epochs=100,\n",
        "    verbose=0,\n",
        "    validation_split=0.2\n",
        ")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "CPU times: user 2.71 s, sys: 144 ms, total: 2.86 s\n",
            "Wall time: 2.56 s\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        },
        "id": "ANMzhmmg7X6b",
        "outputId": "e9915ca9-66f3-4f48-b282-0d4bc81f2efc"
      },
      "source": [
        "plot_loss(history)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "mo9URLJe75FU"
      },
      "source": [
        "## Bike Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5Sg-MM1I74U3",
        "outputId": "2e226d81-b94c-41d6-e8ce-f6be3ad9b464"
      },
      "source": [
        "agg.columns.array.to_numpy().tolist()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['holiday',\n",
              " 'workingday',\n",
              " 'hum',\n",
              " 'windspeed',\n",
              " 'temp_c',\n",
              " 'feels_like_c',\n",
              " 'total_bikes',\n",
              " 'fall',\n",
              " 'spring',\n",
              " 'summer',\n",
              " 'winter',\n",
              " 'clear',\n",
              " 'light_rain_snow',\n",
              " 'mist_clouds']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7qEhvGqS8GTL"
      },
      "source": [
        "bike_train = agg.sample(frac=0.8, random_state=0)\n",
        "bike_test = agg.drop(bike_train.index)"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 483
        },
        "id": "5xdDqWwa8niK",
        "outputId": "a706fce1-1080-411b-ac17-0d72ce2c80a3"
      },
      "source": [
        "bike_train.describe().transpose()"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>holiday</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.027350</td>\n",
              "      <td>0.163242</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>workingday</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.680342</td>\n",
              "      <td>0.466743</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hum</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.628929</td>\n",
              "      <td>0.142203</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.522500</td>\n",
              "      <td>0.629167</td>\n",
              "      <td>0.733750</td>\n",
              "      <td>0.970417</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>windspeed</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.347288</td>\n",
              "      <td>0.160988</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.232051</td>\n",
              "      <td>0.328205</td>\n",
              "      <td>0.436789</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>temp_c</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.543953</td>\n",
              "      <td>0.224826</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.350000</td>\n",
              "      <td>0.550000</td>\n",
              "      <td>0.725000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>feels_like_c</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.509204</td>\n",
              "      <td>0.207204</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.326860</td>\n",
              "      <td>0.519167</td>\n",
              "      <td>0.692308</td>\n",
              "      <td>0.961538</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>total_bikes</th>\n",
              "      <td>585.0</td>\n",
              "      <td>4517.779487</td>\n",
              "      <td>1959.251530</td>\n",
              "      <td>22.0</td>\n",
              "      <td>3204.000000</td>\n",
              "      <td>4553.000000</td>\n",
              "      <td>6031.000000</td>\n",
              "      <td>8714.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>fall</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.239316</td>\n",
              "      <td>0.427031</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>spring</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.258120</td>\n",
              "      <td>0.437975</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>summer</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.252991</td>\n",
              "      <td>0.435098</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>winter</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.249573</td>\n",
              "      <td>0.433136</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>clear</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.745299</td>\n",
              "      <td>0.436066</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>light_rain_snow</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.042735</td>\n",
              "      <td>0.202432</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mist_clouds</th>\n",
              "      <td>585.0</td>\n",
              "      <td>0.211966</td>\n",
              "      <td>0.409051</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                 count         mean  ...          75%          max\n",
              "holiday          585.0     0.027350  ...     0.000000     1.000000\n",
              "workingday       585.0     0.680342  ...     1.000000     1.000000\n",
              "hum              585.0     0.628929  ...     0.733750     0.970417\n",
              "windspeed        585.0     0.347288  ...     0.436789     1.000000\n",
              "temp_c           585.0     0.543953  ...     0.725000     1.000000\n",
              "feels_like_c     585.0     0.509204  ...     0.692308     0.961538\n",
              "total_bikes      585.0  4517.779487  ...  6031.000000  8714.000000\n",
              "fall             585.0     0.239316  ...     0.000000     1.000000\n",
              "spring           585.0     0.258120  ...     1.000000     1.000000\n",
              "summer           585.0     0.252991  ...     1.000000     1.000000\n",
              "winter           585.0     0.249573  ...     0.000000     1.000000\n",
              "clear            585.0     0.745299  ...     1.000000     1.000000\n",
              "light_rain_snow  585.0     0.042735  ...     0.000000     1.000000\n",
              "mist_clouds      585.0     0.211966  ...     0.000000     1.000000\n",
              "\n",
              "[14 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "v2_r-XSS8wE1"
      },
      "source": [
        "bike_train_X = bike_train.copy()\n",
        "bike_test_X = bike_test.copy()\n",
        "\n",
        "bike_train_y = bike_train_X.pop('total_bikes')\n",
        "bike_test_y = bike_test_X.pop('total_bikes')"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "I7GE3rtT9ndI"
      },
      "source": [
        "bike_model = keras.Sequential([\n",
        "                               layers.Input(shape=(len(bike_train_X.columns),)),\n",
        "                               layers.Dense(64, activation='relu'),\n",
        "                               layers.Dense(64, activation='relu'),\n",
        "                               layers.Dense(1)\n",
        "])"
      ],
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "p1kcsZbo-aXR"
      },
      "source": [
        "bike_model.compile(\n",
        "    loss='mean_absolute_error',\n",
        "    optimizer=keras.optimizers.Adam(0.001)\n",
        ")"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JJMLiRiA-v4q",
        "outputId": "947c59c2-f26e-4b89-e889-0250df8b9410"
      },
      "source": [
        "bike_model.summary()"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "dense (Dense)                (None, 64)                896       \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 64)                4160      \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 1)                 65        \n",
            "=================================================================\n",
            "Total params: 5,121\n",
            "Trainable params: 5,121\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cx2pd4yC-2WJ",
        "outputId": "140c8e89-794b-4666-ffd6-8e9aa9039683"
      },
      "source": [
        "%%time\n",
        "bike_history = bike_model.fit(\n",
        "    bike_train_X, bike_train_y,\n",
        "    validation_split=0.2,\n",
        "    verbose=0,\n",
        "    epochs=1000\n",
        ")"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "CPU times: user 34.5 s, sys: 2.76 s, total: 37.2 s\n",
            "Wall time: 30.3 s\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 623
        },
        "id": "s-vkeoaL_Gk2",
        "outputId": "c1db0657-b521-4834-fb6e-5786f65a678f"
      },
      "source": [
        "plt.figure(figsize=(10,10))\n",
        "plt.plot(bike_history.history['loss'], label='loss')\n",
        "plt.plot(bike_history.history['val_loss'], label='val_loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Error [total_bikes]')\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "\n",
        "bike_history.history['loss'][-1]"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1054.3192138671875"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G7Aja9W7AB5a",
        "outputId": "e1559541-4612-4140-c0ae-b6c9601428d7"
      },
      "source": [
        "bike_model.evaluate(bike_test_X, bike_test_y, verbose=0)"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1135.6805419921875"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1bRIrvA2CPwx"
      },
      "source": [
        "## Keras Tuner"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CAUQrRzoCRwk"
      },
      "source": [
        "def model_builder(hp):\n",
        "  model = keras.Sequential()\n",
        "  model.add(layers.Input(shape=(len(bike_train_X.columns),)))\n",
        "  hp_units_1 = hp.Int('units', min_value=32, max_value=512, step=32)\n",
        "  model.add(layers.Dense(units=hp_units_1, activation='relu'))\n",
        "  model.add(layers.Dense(1))\n",
        "\n",
        "  hp_learning_rate = hp.Choice('learning_rate', values=[1e-2,1e-3,1e-4])\n",
        "\n",
        "  model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate),\n",
        "                loss='mean_absolute_error',\n",
        "                metrics=['accuracy'])\n",
        "  \n",
        "  return model"
      ],
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dn0U4zkqDnk-"
      },
      "source": [
        "tuner = kt.Hyperband(model_builder,\n",
        "                     objective='val_accuracy',\n",
        "                     max_epochs=300,\n",
        "                     factor=3,\n",
        "                     directory='cse450',\n",
        "                     project_name='module_5')"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Rnzz9jzyD9RB"
      },
      "source": [
        "class ClearTrainingOutput(keras.callbacks.Callback):\n",
        "  def on_train_end(*args, **kwargs):\n",
        "    IPython.display.clear_output(wait=True)"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pwbVcH7yEKZ6",
        "outputId": "10d277de-f9ab-45f9-f490-8f24ae86b955"
      },
      "source": [
        "tuner.search(bike_train_X, bike_train_y, epochs=2000, validation_data=(bike_test_X, bike_test_y), callbacks=[ClearTrainingOutput()])\n",
        "\n",
        "best_hps = tuner.get_best_hyperparameters(num_trials=1)[0]\n",
        "\n",
        "print(f\"The hyperparameter search is complete. The optimal number of units in the first densely-connected layer is {best_hps.get('units')}.\")\n",
        "print(f\"The optimal learning rate for the optimizer is {best_hps.get('learning_rate')}.\")"
      ],
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Oracle triggered exit\n",
            "The hyperparameter search is complete. The optimal number of units in the first densely-connected layer is 192.\n",
            "The optimal learning rate for the optimizer is 0.0001.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AVbm7qrkFA1n",
        "outputId": "148c7a67-9c32-4df5-b894-82e66529af72"
      },
      "source": [
        "%%time\n",
        "model = tuner.hypermodel.build(best_hps)\n",
        "history = model.fit(bike_train_X, bike_train_y, epochs=2000, validation_data=(bike_train_X, bike_train_y), verbose=0)"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "CPU times: user 1min 46s, sys: 7.54 s, total: 1min 54s\n",
            "Wall time: 1min 27s\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 606
        },
        "id": "Lu9kUiAsGarD",
        "outputId": "6df4c22b-8fcd-4568-a778-27fd9ae418d3"
      },
      "source": [
        "plt.figure(figsize=(10,10))\n",
        "plt.plot(history.history['loss'], label='loss')\n",
        "plt.plot(history.history['val_loss'], label='val_loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Error [total_bikes]')\n",
        "plt.legend()\n",
        "plt.grid(True)"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eEbhP9eeobZV",
        "outputId": "547c94f6-417f-489f-9b8a-2a5aa0a87722",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "model.evaluate(bike_test_X,bike_test_y)"
      ],
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "5/5 [==============================] - 0s 2ms/step - loss: 1249.4923 - accuracy: 0.0000e+00\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1249.4923095703125, 0.0]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WoRArAFkKMH0"
      },
      "source": [
        "## New Bike Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KuBRAYCBKOND"
      },
      "source": [
        "new_model = keras.Sequential([\n",
        "                              layers.Input(shape=(len(bike_train_X.columns),)),\n",
        "                              layers.Dense(192, activation='relu'),\n",
        "                              layers.Dense(192, activation='relu'),\n",
        "                              layers.Dense(1, activation='linear')\n",
        "])\n",
        "new_model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.0001),\n",
        "                  loss='mean_absolute_error',\n",
        "                  metrics=['accuracy'])"
      ],
      "execution_count": 54,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iFsI4bLnLES9",
        "outputId": "dc0000ff-612f-4456-9838-18e2c3602b4c"
      },
      "source": [
        "%%time\n",
        "history = new_model.fit(bike_train_X,bike_train_y,epochs=2000,verbose=0,validation_data=(bike_test_X,bike_test_y))"
      ],
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "CPU times: user 1min 48s, sys: 6.75 s, total: 1min 55s\n",
            "Wall time: 1min 23s\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "btqTE-zzLeqQ",
        "outputId": "c073e6a9-1a72-4f86-fbce-34a9e15dc813"
      },
      "source": [
        "new_model.evaluate(bike_test_X,bike_test_y)"
      ],
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "5/5 [==============================] - 0s 3ms/step - loss: 1139.9543 - accuracy: 0.0000e+00\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1139.954345703125, 0.0]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 57
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 606
        },
        "id": "5cLcztLrLZ_3",
        "outputId": "a21dbf06-0608-4ab0-d7b0-1da4c1785c04"
      },
      "source": [
        "plt.figure(figsize=(10,10))\n",
        "plt.plot(history.history['loss'], label='loss')\n",
        "plt.plot(history.history['val_loss'], label='val_loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Error [total_bikes]')\n",
        "plt.legend()\n",
        "plt.grid(True)"
      ],
      "execution_count": 56,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}