Regression_with_neural_network.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNj6ASvX5rcNg5l5GyOOdKD",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/thayyilakul/Tensorflow-ML/blob/main/Regression_with_neural_network.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LGuJKb51Ybm-",
        "outputId": "c5e733dd-3fc8-49d3-cb20-4ebb73fb7218"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "2.17.1\n"
          ]
        }
      ],
      "source": [
        "import tensorflow as tf\n",
        "print(tf.__version__)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "X = tf.constant([-7.0,-4.0,-1.0,2.0,5.0,8.0,11.0,14.0])\n",
        "y = tf.constant([3.0,6.0,9.0,12.0,15.0,18.0,21.0,24.0])\n",
        "\n",
        "plt.scatter(X, y)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 452
        },
        "id": "X-DGInoTYiVD",
        "outputId": "d6a54926-fa89-4c9b-83dd-63259fd5080d"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.collections.PathCollection at 0x7b52134e00d0>"
            ]
          },
          "metadata": {},
          "execution_count": 2
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X.shape, y.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bjCnt9QuZEEE",
        "outputId": "7e6c82bb-0c07-41a4-dfa9-515ed0d00f2c"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(TensorShape([8]), TensorShape([8]))"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.random.set_seed(42)\n",
        "\n",
        "model_0 = tf.keras.Sequential([\n",
        "    tf.keras.layers.Dense(1)\n",
        "])\n",
        "\n",
        "model_0.compile(loss = tf.keras.losses.mae,\n",
        "                optimizer = tf.keras.optimizers.SGD(),\n",
        "                metrics = ['mae'])\n",
        "\n",
        "model_0.fit(tf.expand_dims(X, axis = -1), y, epochs = 5)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FJ5cywlAZG3K",
        "outputId": "42880fc5-99d5-475d-c1ff-4ea934c4ef6d"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 918ms/step - loss: 18.1381 - mae: 18.1381\n",
            "Epoch 2/5\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 17.8569 - mae: 17.8569\n",
            "Epoch 3/5\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 17.5756 - mae: 17.5756\n",
            "Epoch 4/5\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 127ms/step - loss: 17.2944 - mae: 17.2944\n",
            "Epoch 5/5\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 17.0131 - mae: 17.0131\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x7b5209e169b0>"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "number = tf.constant([17.0])\n",
        "model_0.predict(number)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Jt3QvufQZ8rO",
        "outputId": "53f74d07-88fc-467c-8885-afb0e8ecbc90"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[-12.947309]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.random.set_seed(42)\n",
        "\n",
        "model_1 = tf.keras.Sequential([\n",
        "    tf.keras.layers.Dense(1)\n",
        "])\n",
        "\n",
        "model_1.compile(loss = tf.keras.losses.mae,\n",
        "                optimizer = tf.keras.optimizers.SGD(),\n",
        "                metrics = ['mae'])\n",
        "\n",
        "model_1.fit(tf.expand_dims(X, axis = -1), y, epochs = 100)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "K7uUPvKdae-5",
        "outputId": "92964dbf-587a-43f9-d349-7f51d67b9f74"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 718ms/step - loss: 16.0519 - mae: 16.0519\n",
            "Epoch 2/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 15.7707 - mae: 15.7707\n",
            "Epoch 3/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 15.4894 - mae: 15.4894\n",
            "Epoch 4/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 15.2082 - mae: 15.2082\n",
            "Epoch 5/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 14.9363 - mae: 14.9363\n",
            "Epoch 6/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 133ms/step - loss: 14.8038 - mae: 14.8038\n",
            "Epoch 7/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 14.6713 - mae: 14.6713\n",
            "Epoch 8/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 14.5388 - mae: 14.5388\n",
            "Epoch 9/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 14.4063 - mae: 14.4063\n",
            "Epoch 10/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 14.2738 - mae: 14.2738\n",
            "Epoch 11/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 14.1413 - mae: 14.1413\n",
            "Epoch 12/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 14.0088 - mae: 14.0088\n",
            "Epoch 13/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 13.8763 - mae: 13.8763\n",
            "Epoch 14/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 13.7438 - mae: 13.7438\n",
            "Epoch 15/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 13.6113 - mae: 13.6113\n",
            "Epoch 16/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 13.4788 - mae: 13.4788\n",
            "Epoch 17/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 13.3463 - mae: 13.3463\n",
            "Epoch 18/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 13.2138 - mae: 13.2138\n",
            "Epoch 19/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step - loss: 13.0813 - mae: 13.0813\n",
            "Epoch 20/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 12.9488 - mae: 12.9488\n",
            "Epoch 21/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 12.8163 - mae: 12.8163\n",
            "Epoch 22/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 12.6838 - mae: 12.6838\n",
            "Epoch 23/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 12.5513 - mae: 12.5513\n",
            "Epoch 24/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 12.4188 - mae: 12.4188\n",
            "Epoch 25/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 12.2863 - mae: 12.2863\n",
            "Epoch 26/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 12.1538 - mae: 12.1538\n",
            "Epoch 27/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 12.0213 - mae: 12.0213\n",
            "Epoch 28/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 11.8888 - mae: 11.8888\n",
            "Epoch 29/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 11.7563 - mae: 11.7563\n",
            "Epoch 30/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 11.6238 - mae: 11.6238\n",
            "Epoch 31/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 11.4913 - mae: 11.4913\n",
            "Epoch 32/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 11.3588 - mae: 11.3588\n",
            "Epoch 33/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 11.2263 - mae: 11.2263\n",
            "Epoch 34/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 11.0938 - mae: 11.0938\n",
            "Epoch 35/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 10.9613 - mae: 10.9613\n",
            "Epoch 36/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 10.8288 - mae: 10.8288\n",
            "Epoch 37/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 128ms/step - loss: 10.6963 - mae: 10.6963\n",
            "Epoch 38/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 10.5638 - mae: 10.5638\n",
            "Epoch 39/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 10.4313 - mae: 10.4313\n",
            "Epoch 40/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 10.2988 - mae: 10.2988\n",
            "Epoch 41/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 10.1663 - mae: 10.1663\n",
            "Epoch 42/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 10.0338 - mae: 10.0338\n",
            "Epoch 43/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 9.9013 - mae: 9.9013\n",
            "Epoch 44/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 9.7688 - mae: 9.7688\n",
            "Epoch 45/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 9.6363 - mae: 9.6363\n",
            "Epoch 46/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 9.5038 - mae: 9.5038\n",
            "Epoch 47/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 9.3713 - mae: 9.3713\n",
            "Epoch 48/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 9.2388 - mae: 9.2388\n",
            "Epoch 49/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 9.1063 - mae: 9.1063\n",
            "Epoch 50/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 8.9738 - mae: 8.9738\n",
            "Epoch 51/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 8.8413 - mae: 8.8413\n",
            "Epoch 52/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 8.7088 - mae: 8.7088\n",
            "Epoch 53/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 8.5763 - mae: 8.5763\n",
            "Epoch 54/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 8.4438 - mae: 8.4438\n",
            "Epoch 55/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 8.3113 - mae: 8.3113\n",
            "Epoch 56/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 8.1788 - mae: 8.1788\n",
            "Epoch 57/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 136ms/step - loss: 8.0463 - mae: 8.0463\n",
            "Epoch 58/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 7.9138 - mae: 7.9138\n",
            "Epoch 59/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 7.7813 - mae: 7.7813\n",
            "Epoch 60/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 7.6488 - mae: 7.6488\n",
            "Epoch 61/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 7.5163 - mae: 7.5163\n",
            "Epoch 62/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 7.3838 - mae: 7.3838\n",
            "Epoch 63/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 7.2513 - mae: 7.2513\n",
            "Epoch 64/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 7.1188 - mae: 7.1188\n",
            "Epoch 65/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 7.0275 - mae: 7.0275\n",
            "Epoch 66/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 7.0219 - mae: 7.0219\n",
            "Epoch 67/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 7.0163 - mae: 7.0163\n",
            "Epoch 68/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 7.0106 - mae: 7.0106\n",
            "Epoch 69/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 7.0050 - mae: 7.0050\n",
            "Epoch 70/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 6.9994 - mae: 6.9994\n",
            "Epoch 71/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 6.9938 - mae: 6.9938\n",
            "Epoch 72/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 6.9881 - mae: 6.9881\n",
            "Epoch 73/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 6.9825 - mae: 6.9825\n",
            "Epoch 74/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 6.9769 - mae: 6.9769\n",
            "Epoch 75/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 6.9713 - mae: 6.9713\n",
            "Epoch 76/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 6.9656 - mae: 6.9656\n",
            "Epoch 77/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 6.9600 - mae: 6.9600\n",
            "Epoch 78/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 6.9544 - mae: 6.9544\n",
            "Epoch 79/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 6.9488 - mae: 6.9488\n",
            "Epoch 80/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 6.9431 - mae: 6.9431\n",
            "Epoch 81/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 6.9375 - mae: 6.9375\n",
            "Epoch 82/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 6.9319 - mae: 6.9319\n",
            "Epoch 83/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 6.9263 - mae: 6.9263\n",
            "Epoch 84/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 6.9206 - mae: 6.9206\n",
            "Epoch 85/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 6.9150 - mae: 6.9150\n",
            "Epoch 86/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 6.9094 - mae: 6.9094\n",
            "Epoch 87/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 6.9038 - mae: 6.9038\n",
            "Epoch 88/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 6.8981 - mae: 6.8981\n",
            "Epoch 89/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 6.8925 - mae: 6.8925\n",
            "Epoch 90/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 6.8869 - mae: 6.8869\n",
            "Epoch 91/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 6.8812 - mae: 6.8812\n",
            "Epoch 92/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 6.8756 - mae: 6.8756\n",
            "Epoch 93/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 6.8700 - mae: 6.8700\n",
            "Epoch 94/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 6.8644 - mae: 6.8644\n",
            "Epoch 95/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 6.8588 - mae: 6.8588\n",
            "Epoch 96/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 137ms/step - loss: 6.8531 - mae: 6.8531\n",
            "Epoch 97/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 6.8475 - mae: 6.8475\n",
            "Epoch 98/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 6.8419 - mae: 6.8419\n",
            "Epoch 99/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 6.8363 - mae: 6.8363\n",
            "Epoch 100/100\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 6.8306 - mae: 6.8306\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x7b5212a54220>"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_1.predict(tf.constant([17.0]))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BN3AhzHUbVeA",
        "outputId": "1f9a0be3-7e0e-48e3-8d24-17e9e1043e23"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[29.4781]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X = np.arange(-100, 100, 4)\n",
        "X"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "POOw9lWTcPuV",
        "outputId": "f310530a-3310-44e3-9cb1-3e77da890b6f"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([-100,  -96,  -92,  -88,  -84,  -80,  -76,  -72,  -68,  -64,  -60,\n",
              "        -56,  -52,  -48,  -44,  -40,  -36,  -32,  -28,  -24,  -20,  -16,\n",
              "        -12,   -8,   -4,    0,    4,    8,   12,   16,   20,   24,   28,\n",
              "         32,   36,   40,   44,   48,   52,   56,   60,   64,   68,   72,\n",
              "         76,   80,   84,   88,   92,   96])"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y = np.arange(-90, 110, 4)\n",
        "y"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zPYyEhdfcaCh",
        "outputId": "f0083f01-b109-41e0-eabb-6f56b34c39f9"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([-90, -86, -82, -78, -74, -70, -66, -62, -58, -54, -50, -46, -42,\n",
              "       -38, -34, -30, -26, -22, -18, -14, -10,  -6,  -2,   2,   6,  10,\n",
              "        14,  18,  22,  26,  30,  34,  38,  42,  46,  50,  54,  58,  62,\n",
              "        66,  70,  74,  78,  82,  86,  90,  94,  98, 102, 106])"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X.shape, y.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6lQqRMUTcgSL",
        "outputId": "42be759b-83f4-4a96-fe20-bf669e8cda97"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((50,), (50,))"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_train = X[:40]\n",
        "y_train = y[:40]\n",
        "\n",
        "X_test = X[40:]\n",
        "y_test = y[40:]\n",
        "\n",
        "len(X_train), len(y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fGY3FGVkci_V",
        "outputId": "0bddfd3f-e17a-409a-dbb1-af14f4f09991"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(40, 40)"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(X_train, y_train, c = 'b', label = 'Training Data')\n",
        "plt.scatter(X_test, y_test, c = 'g', label = 'Testing Data')\n",
        "plt.legend();"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "srg7jE8ic3pB",
        "outputId": "e189ba05-3947-4c39-e63c-edc31950aac7"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.random.set_seed(42)\n",
        "\n",
        "model_2 = tf.keras.Sequential([\n",
        "    tf.keras.layers.Dense(1)\n",
        "])\n",
        "\n",
        "model_2.compile(loss = tf.keras.losses.mae,\n",
        "                optimizer = tf.keras.optimizers.SGD(),\n",
        "                metrics = ['mae'])\n",
        "\n",
        "model_2.fit(tf.expand_dims(X_train, axis = -1), y_train, epochs = 100, verbose = 0)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "m6vedoMgc-84",
        "outputId": "ba57bfd6-da7b-4a36-a7c6-e07836981f2b"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x7b51fe05e740>"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_2.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 177
        },
        "id": "Vy02HfQmeSSc",
        "outputId": "62379281-433d-4376-e512-bcab49076edf"
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential_8\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_8\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                        \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape               \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m        Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ dense_8 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)                   │               \u001b[38;5;34m2\u001b[0m │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                         </span>┃<span style=\"font-weight: bold\"> Output Shape                </span>┃<span style=\"font-weight: bold\">         Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ dense_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)                   │               <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4\u001b[0m (20.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4</span> (20.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m2\u001b[0m (8.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> (8.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> (12.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_preds = model_2.predict(X_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VTEpM_jqechy",
        "outputId": "04be443b-e657-4175-ebbe-03cdb5755da8"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 489ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_preds"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nUuWrOlJe3fG",
        "outputId": "e133fe33-6ced-4fdd-dc1d-b99436d9892a"
      },
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ 63.153954],\n",
              "       [ 67.272804],\n",
              "       [ 71.391655],\n",
              "       [ 75.5105  ],\n",
              "       [ 79.62934 ],\n",
              "       [ 83.74819 ],\n",
              "       [ 87.86704 ],\n",
              "       [ 91.985886],\n",
              "       [ 96.10473 ],\n",
              "       [100.22358 ]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(X_train, y_train, c = 'b', label = 'Training Data')\n",
        "plt.scatter(X_test, y_test, c = 'g', label = 'Testing Data')\n",
        "plt.scatter(X_test, y_preds, c = 'r', label = 'Prediction Data')\n",
        "plt.legend();"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "8rUS3izFe4he",
        "outputId": "94489c09-758b-4080-82c4-9d22c9c4ad04"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_2.evaluate(X_test, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IjFs1Wp7fTPC",
        "outputId": "f7211f95-c949-400e-b1c4-f30c89cb5677"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 239ms/step - loss: 6.3112 - mae: 6.3112\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[6.311232089996338, 6.311232089996338]"
            ]
          },
          "metadata": {},
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.metrics.mae(y_test, tf.squeeze(y_preds))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "E0cIlp93f8Qq",
        "outputId": "bd4c8242-11b2-49b5-f424-53fa2937d6ca"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(), dtype=float32, numpy=6.311232>"
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.metrics.mse(y_test, tf.squeeze(y_preds))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8RUR28fYgQhI",
        "outputId": "7fff1311-6705-48e8-a686-51938acf6068"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(), dtype=float32, numpy=39.948174>"
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    }
  ]
}