BaseballANN-DRAminus.ipynb

baseballann-draminus.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "BaseballANN-DRAminus.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.5"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/daveklotz/a798c85edb64352d104921a1521c3238/baseballann-draminus.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lP6JLo1tGNBg"
      },
      "source": [
        "# DRA- Based Artificial Neural Network"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": true,
        "id": "MxkJoQBkUIHC"
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import tensorflow as tf\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import KFold\n"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": true,
        "id": "SyEfdFFEAOMb"
      },
      "source": [
        "np.set_printoptions(suppress=True)\n",
        "tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": true,
        "id": "MXUkhkMfU4wq"
      },
      "source": [
        "#dataset = pd.read_csv('mlb odds 2019-DRAm-random-games.csv')\n",
        "dataset = pd.read_csv('ann_input_example.csv')\n",
        "\n",
        "# 1 - Game ID, / 0\n",
        "# 4 - FEATURE: Visitor or Home as 0 or 1, / 1\n",
        "# 48 - FEATURE: Win % diff (team - opponent), / 2\n",
        "# 60 - FEATURE: Starter DRA- diff  /  3\n",
        "\n",
        "X = dataset.iloc[:, [1, 4, 48, 60]].values\n",
        "y = dataset.iloc[:, 54].values"
      ],
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": true,
        "id": "-M1KboxFb6OO"
      },
      "source": [
        "sc = StandardScaler()\n",
        "X_scaled = X\n",
        "X_scaled[:, [1, 2, 3]] = sc.fit_transform(X[:, [1, 2, 3]])\n"
      ],
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": true,
        "id": "3hMEObuEAOMp"
      },
      "source": [
        "units = 10\n",
        "\n",
        "ann = tf.keras.models.Sequential()\n",
        "#ann.add(tf.keras.layers.Dense(units=units, activation='relu'))\n",
        "#ann.add(tf.keras.layers.Dense(units=units, activation='relu'))\n",
        "#ann.add(tf.keras.layers.Dense(units=units, activation='relu'))\n",
        "ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid'))\n",
        "ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid'))\n",
        "ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid'))\n",
        "\n",
        "\n",
        "ann.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))\n",
        "ann.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])\n",
        "\n",
        "\n",
        "X_for_training = X_scaled\n",
        "X_for_training = X_for_training[:, [1,2,3]]\n",
        "#print(X_for_training)\n",
        "\n",
        "\n",
        "\n"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0uZiMAtnAOMr"
      },
      "source": [
        "history = ann.fit(X_for_training, y, batch_size = 8, epochs = 100, verbose=1)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "I1h0Sy2BAOMs",
        "outputId": "83e8cb3c-77dc-44aa-a2ab-781dc481a0af"
      },
      "source": [
        "prediction = ann.predict( sc.transform([[0, 0, 0]]) )\n",
        "print(prediction[0][0])\n",
        "\n",
        "prediction = ann.predict( sc.transform([[1, 0, 0]]) )\n",
        "print(prediction[0][0])"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.49958766\n",
            "0.5308103\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": true,
        "id": "1bTwDJoVAOMt"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}