Regression_With_Tensorflow_2.0.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Deep_Neural_Network.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RGxe5H9TNCM7",
        "colab_type": "text"
      },
      "source": [
        "## Regression With Tensorflow 2.0"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sX3FalwWNU2N",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "9a021702-8258-4123-d0a2-8bd7f36be4c9"
      },
      "source": [
        "#Imports Tensorflow 2.0 in Google Colab\n",
        "try:\n",
        "  %tensorflow_version 2.x \n",
        "except Exception:\n",
        "  pass\n",
        "\n",
        "import tensorflow as tf"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "TensorFlow 2.x selected.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jMlc5th0JQXi",
        "colab_type": "text"
      },
      "source": [
        "X_train : An array consisting of the independent variables from the training set.\n",
        "\n",
        "y_train : An array consisting of the dependent variable / Target from the training set.\n",
        "\n",
        "X_test : An array consisting of the independent variables from the test set.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BK1u6YRBY1B5",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "\n",
        "#Initializing The Neural Network\n",
        "model = keras.Sequential([\n",
        "    keras.layers.InputLayer(input_shape = 'number_of_independent_variables'),\n",
        "    keras.layers.Dense(500, activation = \"relu\", kernel_initializer = 'uniform'),\n",
        "    keras.layers.Dense(1)\n",
        "])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RpgxGwiMJ1pM",
        "colab_type": "text"
      },
      "source": [
        "The above code block initializes a neural network with :\n",
        "\n",
        "* An input layer consisting of n number of nodes where n is the number of independent variables.\n",
        "\n",
        "* A hidden layer with 500 nodes , activated by relu activation function and uniform initializaton of weights.\n",
        "\n",
        "* An output layer of a single node.\n",
        "\n",
        "---\n",
        "\n",
        "Click [here](https://www.tensorflow.org/api_docs/python/tf/keras/activations) for complete list of available **activation functions**.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "W0V6N-DdbENO",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#Compiling The Neural Network With an optimizer,a loss and metrics\n",
        "model.compile(\n",
        "    optimizer='sgd',\n",
        "    loss='mean_squared_logarithmic_error',\n",
        "    metrics= ['RootMeanSquaredError']\n",
        "   )"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Fa0o8q35K7fU",
        "colab_type": "text"
      },
      "source": [
        "Click [here](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers) for complete list of available **optimizers**.\n",
        "\n",
        "Click [here](https://www.tensorflow.org/api_docs/python/tf/keras/losses) for complete list of available **loss functions**.\n",
        "\n",
        "Click [here](https://www.tensorflow.org/api_docs/python/tf/keras/metrics) for complete list of available **metrics**.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0n_p-xwCcEVU",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#Training The Network With Training Data And Validating On A Fraction It\n",
        "model.fit(X_train, y_train,epochs=20,validation_split = 0.2, shuffle=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9pv0X3GIL6Ie",
        "colab_type": "text"
      },
      "source": [
        "* The above code block trains the neural network using the training data (X_train and y_train) for 20 cycles specified by the epochs. One epoch is one complete cycle of training with the training data.\n",
        "\n",
        "* validation_split specifies the fraction of training samples to be used for validating or testing during the training process.\n",
        "\n",
        "* shuffle when set to true shuffles the training sample at each epoch.\n",
        "\n",
        "---\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b2VMgEeWfA8h",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#Predicting Using The Trained Network\n",
        "predictions = model.predict(X_test)"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}