regression_tutorial_keras_deep_learning_library_python.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "regression-tutorial-keras-deep-learning-library-python.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyODo9oRTaKtPYXEw0aUDlcr",
      "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/github/ademaldemir/deeplearning/blob/master/regression_tutorial_keras_deep_learning_library_python.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wNh4jQ4l8r4X",
        "colab_type": "text"
      },
      "source": [
        "# Regression Tutorial with the Keras Deep Learning Library in Python\n",
        "👨🏻‍💻 https://machinelearningmastery.com/regression-tutorial-keras-deep-learning-library-python/"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5SYmfPlfe5lc",
        "colab_type": "text"
      },
      "source": [
        "# Develop a Baseline Neural Network Model\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2kpj9s6e8nRc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import pandas as pd\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "from keras.wrappers.scikit_learn import KerasRegressor\n",
        "from sklearn.model_selection import cross_val_score\n",
        "from sklearn.model_selection import KFold\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.pipeline import Pipeline"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AKkPRkbffooz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# load dataset\n",
        "dataframe = pd.read_csv(\"https://raw.githubusercontent.com/jbrownlee/Datasets/master/housing.data\", \n",
        "                        delim_whitespace=True, header=None)\n",
        "dataset = dataframe.values"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AM0cbwoSgFw-",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        },
        "outputId": "14616475-cbc2-4344-e87b-4370beb68f0b"
      },
      "source": [
        "dataset"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[6.3200e-03, 1.8000e+01, 2.3100e+00, ..., 3.9690e+02, 4.9800e+00,\n",
              "        2.4000e+01],\n",
              "       [2.7310e-02, 0.0000e+00, 7.0700e+00, ..., 3.9690e+02, 9.1400e+00,\n",
              "        2.1600e+01],\n",
              "       [2.7290e-02, 0.0000e+00, 7.0700e+00, ..., 3.9283e+02, 4.0300e+00,\n",
              "        3.4700e+01],\n",
              "       ...,\n",
              "       [6.0760e-02, 0.0000e+00, 1.1930e+01, ..., 3.9690e+02, 5.6400e+00,\n",
              "        2.3900e+01],\n",
              "       [1.0959e-01, 0.0000e+00, 1.1930e+01, ..., 3.9345e+02, 6.4800e+00,\n",
              "        2.2000e+01],\n",
              "       [4.7410e-02, 0.0000e+00, 1.1930e+01, ..., 3.9690e+02, 7.8800e+00,\n",
              "        1.1900e+01]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U8V63LWVgTz1",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "a4d6257e-a4cc-47da-9a3b-ef768f3e564a"
      },
      "source": [
        "dataframe.head()"
      ],
      "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>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "      <th>5</th>\n",
              "      <th>6</th>\n",
              "      <th>7</th>\n",
              "      <th>8</th>\n",
              "      <th>9</th>\n",
              "      <th>10</th>\n",
              "      <th>11</th>\n",
              "      <th>12</th>\n",
              "      <th>13</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.00632</td>\n",
              "      <td>18.0</td>\n",
              "      <td>2.31</td>\n",
              "      <td>0</td>\n",
              "      <td>0.538</td>\n",
              "      <td>6.575</td>\n",
              "      <td>65.2</td>\n",
              "      <td>4.0900</td>\n",
              "      <td>1</td>\n",
              "      <td>296.0</td>\n",
              "      <td>15.3</td>\n",
              "      <td>396.90</td>\n",
              "      <td>4.98</td>\n",
              "      <td>24.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.02731</td>\n",
              "      <td>0.0</td>\n",
              "      <td>7.07</td>\n",
              "      <td>0</td>\n",
              "      <td>0.469</td>\n",
              "      <td>6.421</td>\n",
              "      <td>78.9</td>\n",
              "      <td>4.9671</td>\n",
              "      <td>2</td>\n",
              "      <td>242.0</td>\n",
              "      <td>17.8</td>\n",
              "      <td>396.90</td>\n",
              "      <td>9.14</td>\n",
              "      <td>21.6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.02729</td>\n",
              "      <td>0.0</td>\n",
              "      <td>7.07</td>\n",
              "      <td>0</td>\n",
              "      <td>0.469</td>\n",
              "      <td>7.185</td>\n",
              "      <td>61.1</td>\n",
              "      <td>4.9671</td>\n",
              "      <td>2</td>\n",
              "      <td>242.0</td>\n",
              "      <td>17.8</td>\n",
              "      <td>392.83</td>\n",
              "      <td>4.03</td>\n",
              "      <td>34.7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.03237</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.18</td>\n",
              "      <td>0</td>\n",
              "      <td>0.458</td>\n",
              "      <td>6.998</td>\n",
              "      <td>45.8</td>\n",
              "      <td>6.0622</td>\n",
              "      <td>3</td>\n",
              "      <td>222.0</td>\n",
              "      <td>18.7</td>\n",
              "      <td>394.63</td>\n",
              "      <td>2.94</td>\n",
              "      <td>33.4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.06905</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.18</td>\n",
              "      <td>0</td>\n",
              "      <td>0.458</td>\n",
              "      <td>7.147</td>\n",
              "      <td>54.2</td>\n",
              "      <td>6.0622</td>\n",
              "      <td>3</td>\n",
              "      <td>222.0</td>\n",
              "      <td>18.7</td>\n",
              "      <td>396.90</td>\n",
              "      <td>5.33</td>\n",
              "      <td>36.2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        0     1     2   3      4      5   ...  8      9     10      11    12    13\n",
              "0  0.00632  18.0  2.31   0  0.538  6.575  ...   1  296.0  15.3  396.90  4.98  24.0\n",
              "1  0.02731   0.0  7.07   0  0.469  6.421  ...   2  242.0  17.8  396.90  9.14  21.6\n",
              "2  0.02729   0.0  7.07   0  0.469  7.185  ...   2  242.0  17.8  392.83  4.03  34.7\n",
              "3  0.03237   0.0  2.18   0  0.458  6.998  ...   3  222.0  18.7  394.63  2.94  33.4\n",
              "4  0.06905   0.0  2.18   0  0.458  7.147  ...   3  222.0  18.7  396.90  5.33  36.2\n",
              "\n",
              "[5 rows x 14 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZEbx5OXZgaPI",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# split into input (X) and output (Y) variables\n",
        "X = dataset[:, 0:13]\n",
        "y = dataset[:, 13]"
      ],
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "E5yZy9hkg2qM",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# define base model\n",
        "def baseline_model():\n",
        "    #create model\n",
        "    model = Sequential()\n",
        "    model.add(Dense(13, input_dim=13, kernel_initializer='normal', activation='relu'))\n",
        "    model.add(Dense(1, kernel_initializer='normal'))\n",
        "    #compile model\n",
        "    model.compile(loss='mean_squared_error', optimizer='adam')\n",
        "    return model"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TuEMySX3iQ9C",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 85
        },
        "outputId": "8ec2b1cf-ffc0-4c78-d456-e6764032b4f1"
      },
      "source": [
        "for i in range(0,4):\n",
        "    kfold = KFold(n_splits=10)\n",
        "    estimator = KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=0)\n",
        "    results = cross_val_score(estimator, X, y, cv=kfold)\n",
        "    print(\"Results: {:.2f} {:.2f} MSE\".format(results.mean(), results.std()))\n",
        "    print(\"\\n\")"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Results: -32.75 21.68 MSE\n",
            "Results: -29.18 16.53 MSE\n",
            "Results: -32.79 21.58 MSE\n",
            "Results: -27.68 23.42 MSE\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "P9Y41c4blgwb",
        "colab_type": "text"
      },
      "source": [
        "# Modeling The Standardized Dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6XON-H8hkIfl",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "fe2b28a2-6e9c-4cc7-a325-38709ab945e0"
      },
      "source": [
        "# evaluate the model with standardized dataset\n",
        "estimators = []\n",
        "estimators.append(('standardize', StandardScaler()))\n",
        "estimators.append(('mlp', KerasRegressor(build_fn=baseline_model, epochs=50, batch_size=5, verbose=0)))\n",
        "pipeline = Pipeline(estimators)\n",
        "kfold = KFold(n_splits=10)\n",
        "results = cross_val_score(pipeline, X, y, cv=kfold)\n",
        "print(\"Standardized: {:.2f} ({:.2f}) MSE\".format(results.mean(), results.std()))"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Standardized: -29.26 (26.12) MSE\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ivlNBZV7OliE",
        "colab_type": "text"
      },
      "source": [
        "# Tune The Neural Network Topology\n",
        "One way to improve the performance a neural network is to add more layers. This might allow the model to extract and recombine higher order features embedded in the data."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "f2CPwS9gO74D",
        "colab_type": "text"
      },
      "source": [
        "\n",
        "\n",
        "---"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fYl6kznqmaHK",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#define the model\n",
        "def larger_model():\n",
        "    #create model\n",
        "    model = Sequential()\n",
        "    model.add(Dense(13, input_dim=13, kernel_initializer='normal', activation='relu'))\n",
        "    model.add(Dense(6, kernel_initializer='normal', activation='relu'))\n",
        "    model.add(Dense(1, kernel_initializer='normal'))\n",
        "    # compile mdel\n",
        "    model.compile(loss='mean_squared_error', optimizer='adam')\n",
        "    return model"
      ],
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5kAkKu2DPjNh",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "552cdea9-3797-47a4-b9d7-23e115248ea1"
      },
      "source": [
        "estimators = []\n",
        "estimators.append(('standardize', StandardScaler()))\n",
        "estimators.append(('mlp', KerasRegressor(build_fn=larger_model, epochs=50, batch_size=5, verbose=0)))\n",
        "pipeline = Pipeline(estimators)\n",
        "kfold = KFold(n_splits=10)\n",
        "results = cross_val_score(pipeline, X, y, cv=kfold)\n",
        "print(\"Larger: %.2f (%.2f) MSE\" % (results.mean(), results.std()))"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Larger: -24.55 (30.25) MSE\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nqQEG3kzSFoz",
        "colab_type": "text"
      },
      "source": [
        "## Evaluate a Wider Network Topology\n",
        "Another approach to increasing the representational capability of the model is to create a wider network.\n",
        "\n",
        "In this section we evaluate the effect of keeping a shallow network architecture and nearly doubling the number of neurons in the one hidden layer."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TDtKUWULQhRg",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# define wider model\n",
        "def wider_model():\n",
        "    #create model\n",
        "    model = Sequential()\n",
        "    model.add(Dense(20, input_dim=13, kernel_initializer='normal', activation='relu'))\n",
        "    model.add(Dense(1, kernel_initializer='normal'))\n",
        "    # compile model\n",
        "    model.compile(loss='mean_squared_error', optimizer='adam')\n",
        "    return model"
      ],
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bRao0pJbSm7A",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "51e7afe2-9f06-481c-d7e9-5b78f36cc100"
      },
      "source": [
        "estimators = []\n",
        "estimators.append(('standardize', StandardScaler()))\n",
        "estimators.append(('mlp', KerasRegressor(build_fn=wider_model, epochs=50, batch_size=5, verbose=0)))\n",
        "pipeline = Pipeline(estimators)\n",
        "kfold = KFold(n_splits=10)\n",
        "results = cross_val_score(pipeline, X, y, cv=kfold)\n",
        "print('Wider: {:.2f} ({:.2f})'.format(results.mean(), results.std()))"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Wider: -25.26 (23.92)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E8PBawE0T9qN",
        "colab_type": "text"
      },
      "source": [
        "It would have been hard to guess that a wider network would outperform a deeper network on this problem. The results demonstrate the importance of empirical testing when it comes to developing neural network models."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mK32nypoTVjK",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}