Lecture_10_Fashion_MNIST_with_Artificial_Neural_Network.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "name": "Lecture_10_Fashion_MNIST_with Artificial Neural Network.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true,
      "authorship_tag": "ABX9TyP1LiQ16HTAdiJta1I/1Rv9",
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "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/ashishpatel26/Ganpat-University-Data-Science/blob/main/Lecture_10_Fashion_MNIST_with_Artificial_Neural_Network.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fnFyKRtrQoCr"
      },
      "source": [
        "### 1.Load Libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iSHBSF0ENd9G"
      },
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "%matplotlib inline\n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')"
      ],
      "execution_count": 62,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d6QKwe9qkNbZ",
        "outputId": "22c3464a-3631-44e3-ba7c-79ed8d8536b5"
      },
      "source": [
        "print(tf.__version__)"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "2.4.1\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-6AYYw5moMNq"
      },
      "source": [
        "### 2.Load Dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KULqHiJLuKMv",
        "outputId": "b80a12fb-26ed-45a4-cab4-131cd115e423"
      },
      "source": [
        "!nvidia-smi -L"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "GPU 0: Tesla T4 (UUID: GPU-11ab71ab-ddce-8f92-f886-8d833fabf27a)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5PqTfn1XkXPo"
      },
      "source": [
        "fashion_mnist = tf.keras.datasets.fashion_mnist"
      ],
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "S0OcIE6JoNzc"
      },
      "source": [
        "### 3.Extract train and test data from fashionMNIST"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vbc8cleokwkT",
        "outputId": "dd3293cd-28d8-4368-b052-f56c841b09a2"
      },
      "source": [
        "(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()\n",
        "\n",
        "for i in [x_train, y_train, x_test, y_test]:\n",
        "  print(f\"{i.shape}\")"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(60000, 28, 28)\n",
            "(60000,)\n",
            "(10000, 28, 28)\n",
            "(10000,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Mae81Yk-oSwX"
      },
      "source": [
        "### 4.Define the class as per target variable"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K129lmi5lXqe"
      },
      "source": [
        "class_names  = ['T-shirt/top','Trouser','Pullover','Dress','Coat','Sandal','Shirt','Sneaker','Bag','Ankle boot']"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "O29JDBcDoW-g"
      },
      "source": [
        "### 5.Data Visualization"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 309
        },
        "id": "EAMkj4oylqkR",
        "outputId": "22eb6a3a-2ede-45d0-b641-46f0f1fa6538"
      },
      "source": [
        "plt.figure(figsize=(5,5))\n",
        "plt.imshow(x_train[0])\n",
        "plt.colorbar()\n",
        "plt.grid(False)\n",
        "plt.show()"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 589
        },
        "id": "gXmY1CiJm1IK",
        "outputId": "d28ec1e1-27a1-4597-8006-93a5d2e076ab"
      },
      "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(x_train[i], cmap=plt.cm.binary)\n",
        "  plt.xlabel(class_names[y_train[i]])\n",
        "plt.show()"
      ],
      "execution_count": 20,
      "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": "markdown",
      "metadata": {
        "id": "qcDbnm0Ooa8n"
      },
      "source": [
        "### 6. Define the Neural Network"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ivsFwRyym1qy"
      },
      "source": [
        "model = tf.keras.Sequential()\n",
        "# Input Layer\n",
        "model.add(tf.keras.layers.Flatten(input_shape = x_train[0].shape))\n",
        "# Hidden Layer\n",
        "model.add(tf.keras.layers.Dense(128, activation='relu'))\n",
        "# Output Layer\n",
        "model.add(tf.keras.layers.Dense(len(class_names), activation='softmax'))"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lpiuYxUV0UAN"
      },
      "source": [
        "### 7. Model BackPropagation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uPb2VSWypQzh"
      },
      "source": [
        "# backward propagation\n",
        "model.compile(optimizer='adam', # optimiser\n",
        "              loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), # cost function\n",
        "              metrics = ['accuracy']\n",
        "              )"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "74CNDJIi0Y-j"
      },
      "source": [
        "### 8.Model Summary"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zDaO_88LrwGr",
        "outputId": "3bf11be3-8ef6-4bd0-cb78-d10c4325868e"
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "flatten_1 (Flatten)          (None, 784)               0         \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 128)               100480    \n",
            "_________________________________________________________________\n",
            "dense_3 (Dense)              (None, 10)                1290      \n",
            "=================================================================\n",
            "Total params: 101,770\n",
            "Trainable params: 101,770\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M31D6Wpw0ccL"
      },
      "source": [
        "### 9.Model Training"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "myws_DZRsViz",
        "outputId": "31924e02-7c19-40cb-bce7-7a2a27e9b3f9"
      },
      "source": [
        "model.fit(x = x_train,\n",
        "          y = y_train,\n",
        "          batch_size = 32,\n",
        "          epochs = 30,\n",
        "          validation_data = (x_test, y_test),\n",
        "          verbose=1)"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/30\n",
            "1875/1875 [==============================] - 7s 2ms/step - loss: 9.6490 - accuracy: 0.6818 - val_loss: 0.7861 - val_accuracy: 0.7075\n",
            "Epoch 2/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.7003 - accuracy: 0.7309 - val_loss: 0.7666 - val_accuracy: 0.7434\n",
            "Epoch 3/30\n",
            "1875/1875 [==============================] - 3s 2ms/step - loss: 0.6320 - accuracy: 0.7638 - val_loss: 0.6238 - val_accuracy: 0.7814\n",
            "Epoch 4/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.5887 - accuracy: 0.7794 - val_loss: 0.6234 - val_accuracy: 0.7708\n",
            "Epoch 5/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.5576 - accuracy: 0.7955 - val_loss: 0.5508 - val_accuracy: 0.8102\n",
            "Epoch 6/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.5204 - accuracy: 0.8171 - val_loss: 0.6191 - val_accuracy: 0.7698\n",
            "Epoch 7/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.5047 - accuracy: 0.8257 - val_loss: 0.5551 - val_accuracy: 0.8136\n",
            "Epoch 8/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4924 - accuracy: 0.8287 - val_loss: 0.5627 - val_accuracy: 0.8287\n",
            "Epoch 9/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4960 - accuracy: 0.8294 - val_loss: 0.5345 - val_accuracy: 0.8220\n",
            "Epoch 10/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4814 - accuracy: 0.8325 - val_loss: 0.5449 - val_accuracy: 0.8229\n",
            "Epoch 11/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4800 - accuracy: 0.8337 - val_loss: 0.5341 - val_accuracy: 0.8260\n",
            "Epoch 12/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4690 - accuracy: 0.8391 - val_loss: 0.5477 - val_accuracy: 0.8171\n",
            "Epoch 13/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4795 - accuracy: 0.8368 - val_loss: 0.5493 - val_accuracy: 0.8339\n",
            "Epoch 14/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4740 - accuracy: 0.8402 - val_loss: 0.5475 - val_accuracy: 0.8256\n",
            "Epoch 15/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4602 - accuracy: 0.8422 - val_loss: 0.5617 - val_accuracy: 0.8303\n",
            "Epoch 16/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4664 - accuracy: 0.8396 - val_loss: 0.5453 - val_accuracy: 0.8155\n",
            "Epoch 17/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4651 - accuracy: 0.8424 - val_loss: 0.5872 - val_accuracy: 0.8209\n",
            "Epoch 18/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4666 - accuracy: 0.8434 - val_loss: 0.5883 - val_accuracy: 0.8256\n",
            "Epoch 19/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4624 - accuracy: 0.8425 - val_loss: 0.6286 - val_accuracy: 0.8049\n",
            "Epoch 20/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4527 - accuracy: 0.8442 - val_loss: 0.5297 - val_accuracy: 0.8370\n",
            "Epoch 21/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4477 - accuracy: 0.8472 - val_loss: 0.6051 - val_accuracy: 0.8302\n",
            "Epoch 22/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4509 - accuracy: 0.8451 - val_loss: 0.5945 - val_accuracy: 0.8112\n",
            "Epoch 23/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4641 - accuracy: 0.8451 - val_loss: 0.5833 - val_accuracy: 0.8226\n",
            "Epoch 24/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4523 - accuracy: 0.8438 - val_loss: 0.6161 - val_accuracy: 0.7866\n",
            "Epoch 25/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4438 - accuracy: 0.8476 - val_loss: 0.6222 - val_accuracy: 0.7992\n",
            "Epoch 26/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4530 - accuracy: 0.8480 - val_loss: 0.5769 - val_accuracy: 0.8203\n",
            "Epoch 27/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4474 - accuracy: 0.8489 - val_loss: 0.5560 - val_accuracy: 0.8351\n",
            "Epoch 28/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4366 - accuracy: 0.8540 - val_loss: 0.5691 - val_accuracy: 0.8232\n",
            "Epoch 29/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4527 - accuracy: 0.8492 - val_loss: 0.5620 - val_accuracy: 0.8306\n",
            "Epoch 30/30\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4495 - accuracy: 0.8474 - val_loss: 0.5553 - val_accuracy: 0.8355\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7fab0e199410>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J6kczRTe0fK6"
      },
      "source": [
        "### 10.Training Result Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 935
        },
        "id": "LgGoD0XavhF-",
        "outputId": "7847d992-897e-422a-b65d-0b44834f0b4f"
      },
      "source": [
        "import pandas as pd\n",
        "pd.DataFrame(model.history.history)"
      ],
      "execution_count": 25,
      "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>loss</th>\n",
              "      <th>accuracy</th>\n",
              "      <th>val_loss</th>\n",
              "      <th>val_accuracy</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>3.492824</td>\n",
              "      <td>0.696833</td>\n",
              "      <td>0.786073</td>\n",
              "      <td>0.7075</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.675246</td>\n",
              "      <td>0.739733</td>\n",
              "      <td>0.766582</td>\n",
              "      <td>0.7434</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.627480</td>\n",
              "      <td>0.767717</td>\n",
              "      <td>0.623835</td>\n",
              "      <td>0.7814</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.585166</td>\n",
              "      <td>0.783117</td>\n",
              "      <td>0.623419</td>\n",
              "      <td>0.7708</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.555110</td>\n",
              "      <td>0.802567</td>\n",
              "      <td>0.550765</td>\n",
              "      <td>0.8102</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.520853</td>\n",
              "      <td>0.819767</td>\n",
              "      <td>0.619057</td>\n",
              "      <td>0.7698</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.508791</td>\n",
              "      <td>0.824850</td>\n",
              "      <td>0.555051</td>\n",
              "      <td>0.8136</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.499049</td>\n",
              "      <td>0.826817</td>\n",
              "      <td>0.562730</td>\n",
              "      <td>0.8287</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0.495507</td>\n",
              "      <td>0.830183</td>\n",
              "      <td>0.534465</td>\n",
              "      <td>0.8220</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.488957</td>\n",
              "      <td>0.832450</td>\n",
              "      <td>0.544936</td>\n",
              "      <td>0.8229</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>0.485003</td>\n",
              "      <td>0.834417</td>\n",
              "      <td>0.534107</td>\n",
              "      <td>0.8260</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>0.478502</td>\n",
              "      <td>0.836383</td>\n",
              "      <td>0.547736</td>\n",
              "      <td>0.8171</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>0.480412</td>\n",
              "      <td>0.837250</td>\n",
              "      <td>0.549328</td>\n",
              "      <td>0.8339</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>13</th>\n",
              "      <td>0.477072</td>\n",
              "      <td>0.839333</td>\n",
              "      <td>0.547527</td>\n",
              "      <td>0.8256</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>14</th>\n",
              "      <td>0.465390</td>\n",
              "      <td>0.841617</td>\n",
              "      <td>0.561724</td>\n",
              "      <td>0.8303</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15</th>\n",
              "      <td>0.466336</td>\n",
              "      <td>0.841200</td>\n",
              "      <td>0.545276</td>\n",
              "      <td>0.8155</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16</th>\n",
              "      <td>0.466470</td>\n",
              "      <td>0.843250</td>\n",
              "      <td>0.587182</td>\n",
              "      <td>0.8209</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17</th>\n",
              "      <td>0.466780</td>\n",
              "      <td>0.842517</td>\n",
              "      <td>0.588301</td>\n",
              "      <td>0.8256</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>18</th>\n",
              "      <td>0.465046</td>\n",
              "      <td>0.842417</td>\n",
              "      <td>0.628564</td>\n",
              "      <td>0.8049</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19</th>\n",
              "      <td>0.459574</td>\n",
              "      <td>0.843950</td>\n",
              "      <td>0.529716</td>\n",
              "      <td>0.8370</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>20</th>\n",
              "      <td>0.458771</td>\n",
              "      <td>0.843883</td>\n",
              "      <td>0.605062</td>\n",
              "      <td>0.8302</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>21</th>\n",
              "      <td>0.455161</td>\n",
              "      <td>0.844217</td>\n",
              "      <td>0.594483</td>\n",
              "      <td>0.8112</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>22</th>\n",
              "      <td>0.465119</td>\n",
              "      <td>0.844700</td>\n",
              "      <td>0.583254</td>\n",
              "      <td>0.8226</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>23</th>\n",
              "      <td>0.459542</td>\n",
              "      <td>0.844017</td>\n",
              "      <td>0.616117</td>\n",
              "      <td>0.7866</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>24</th>\n",
              "      <td>0.450645</td>\n",
              "      <td>0.846867</td>\n",
              "      <td>0.622232</td>\n",
              "      <td>0.7992</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25</th>\n",
              "      <td>0.458393</td>\n",
              "      <td>0.846450</td>\n",
              "      <td>0.576934</td>\n",
              "      <td>0.8203</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26</th>\n",
              "      <td>0.452312</td>\n",
              "      <td>0.846767</td>\n",
              "      <td>0.556013</td>\n",
              "      <td>0.8351</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>27</th>\n",
              "      <td>0.457107</td>\n",
              "      <td>0.847617</td>\n",
              "      <td>0.569131</td>\n",
              "      <td>0.8232</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28</th>\n",
              "      <td>0.450732</td>\n",
              "      <td>0.849317</td>\n",
              "      <td>0.562011</td>\n",
              "      <td>0.8306</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29</th>\n",
              "      <td>0.449447</td>\n",
              "      <td>0.849783</td>\n",
              "      <td>0.555303</td>\n",
              "      <td>0.8355</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        loss  accuracy  val_loss  val_accuracy\n",
              "0   3.492824  0.696833  0.786073        0.7075\n",
              "1   0.675246  0.739733  0.766582        0.7434\n",
              "2   0.627480  0.767717  0.623835        0.7814\n",
              "3   0.585166  0.783117  0.623419        0.7708\n",
              "4   0.555110  0.802567  0.550765        0.8102\n",
              "5   0.520853  0.819767  0.619057        0.7698\n",
              "6   0.508791  0.824850  0.555051        0.8136\n",
              "7   0.499049  0.826817  0.562730        0.8287\n",
              "8   0.495507  0.830183  0.534465        0.8220\n",
              "9   0.488957  0.832450  0.544936        0.8229\n",
              "10  0.485003  0.834417  0.534107        0.8260\n",
              "11  0.478502  0.836383  0.547736        0.8171\n",
              "12  0.480412  0.837250  0.549328        0.8339\n",
              "13  0.477072  0.839333  0.547527        0.8256\n",
              "14  0.465390  0.841617  0.561724        0.8303\n",
              "15  0.466336  0.841200  0.545276        0.8155\n",
              "16  0.466470  0.843250  0.587182        0.8209\n",
              "17  0.466780  0.842517  0.588301        0.8256\n",
              "18  0.465046  0.842417  0.628564        0.8049\n",
              "19  0.459574  0.843950  0.529716        0.8370\n",
              "20  0.458771  0.843883  0.605062        0.8302\n",
              "21  0.455161  0.844217  0.594483        0.8112\n",
              "22  0.465119  0.844700  0.583254        0.8226\n",
              "23  0.459542  0.844017  0.616117        0.7866\n",
              "24  0.450645  0.846867  0.622232        0.7992\n",
              "25  0.458393  0.846450  0.576934        0.8203\n",
              "26  0.452312  0.846767  0.556013        0.8351\n",
              "27  0.457107  0.847617  0.569131        0.8232\n",
              "28  0.450732  0.849317  0.562011        0.8306\n",
              "29  0.449447  0.849783  0.555303        0.8355"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SiJyrZQu0jog"
      },
      "source": [
        "### 11. Accuracy and Loss Curve"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zRYTfgTDtlJC",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 573
        },
        "outputId": "ca4bce8f-f7cc-4118-ec63-a557126370d6"
      },
      "source": [
        "#  \"Accuracy\"\n",
        "plt.plot(model.history.history['accuracy'])\n",
        "plt.plot(model.history.history['val_accuracy'],color='red')\n",
        "plt.title('model accuracy')\n",
        "plt.ylabel('accuracy')\n",
        "plt.xlabel('epoch')\n",
        "plt.legend(['train', 'validation'], loc='upper left')\n",
        "plt.show()\n",
        "# \"Loss\"\n",
        "plt.plot(model.history.history['loss'])\n",
        "plt.plot(model.history.history['val_loss'],color='red')\n",
        "plt.title('model loss')\n",
        "plt.ylabel('loss')\n",
        "plt.xlabel('epoch')\n",
        "plt.legend(['train', 'validation'], loc='upper left')\n",
        "plt.show()"
      ],
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FaZmebV80nvZ"
      },
      "source": [
        "### 12.Model Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j_a16E7pvpx9",
        "outputId": "b93477b0-5d6c-4532-b9b8-c15b93a839a8"
      },
      "source": [
        "model.evaluate(x_test, y_test)"
      ],
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "313/313 [==============================] - 1s 2ms/step - loss: 0.5553 - accuracy: 0.8355\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.5553030371665955, 0.8355000019073486]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KhtcMN1m0pnB"
      },
      "source": [
        "### 13.Model Prediction"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3FUQTIh9wjbV"
      },
      "source": [
        "y_pred = model.predict(x_test)\n",
        "y_pred_per = model.predict(x_test)"
      ],
      "execution_count": 88,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Sw3LBR__wqUv"
      },
      "source": [
        "y_pred = np.argmax(y_pred, axis=1)"
      ],
      "execution_count": 52,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-v2ScTykw3GI"
      },
      "source": [
        "from sklearn.metrics import *"
      ],
      "execution_count": 53,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ke1mRoZrxqVb",
        "outputId": "9022927a-7003-48f1-8e1b-7ab878675695"
      },
      "source": [
        "y_test, y_pred"
      ],
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(array([9, 2, 1, ..., 8, 1, 5], dtype=uint8), array([9, 4, 1, ..., 8, 1, 5]))"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Ui8C-F9p0r1D"
      },
      "source": [
        "### 14.Model Performance"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TL1yHoelxf22",
        "outputId": "c785bf9b-afe3-400c-fa88-e9f4b4748815"
      },
      "source": [
        "print(\"Classification Report : \\n\",classification_report(y_test, y_pred))\n",
        "print(\"Accuracy :\", accuracy_score(y_test, y_pred) * 100)\n",
        "print(\"Cohen Kappa :\", cohen_kappa_score(y_test, y_pred))"
      ],
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Classification Report : \n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.75      0.85      0.80      1000\n",
            "           1       0.97      0.95      0.96      1000\n",
            "           2       0.64      0.72      0.68      1000\n",
            "           3       0.86      0.80      0.82      1000\n",
            "           4       0.64      0.87      0.74      1000\n",
            "           5       0.96      0.94      0.95      1000\n",
            "           6       0.75      0.41      0.53      1000\n",
            "           7       0.92      0.95      0.94      1000\n",
            "           8       0.96      0.93      0.95      1000\n",
            "           9       0.96      0.94      0.95      1000\n",
            "\n",
            "    accuracy                           0.84     10000\n",
            "   macro avg       0.84      0.84      0.83     10000\n",
            "weighted avg       0.84      0.84      0.83     10000\n",
            "\n",
            "Accuracy : 83.55\n",
            "Cohen Kappa : 0.8172222222222223\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Yuv-W0SgyG9w"
      },
      "source": [
        "?confusion_matrix"
      ],
      "execution_count": 58,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 797
        },
        "id": "WM0QEdnkxlNa",
        "outputId": "4ef67a55-6e72-4d9c-c6c9-17a1d40ec730"
      },
      "source": [
        "cm = confusion_matrix(y_test, y_pred)\n",
        "print(cm)\n",
        "plt.figure(figsize=(10,10))\n",
        "sns.heatmap(cm, annot = True, cmap=\"YlGnBu\")\n",
        "plt.xlabel(\"Predicte\")\n",
        "plt.xlabel(\"True\")\n",
        "plt.title(\"Confusion Matrix\")\n",
        "plt.show()"
      ],
      "execution_count": 65,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[851   2  47  44   2   0  45   0   9   0]\n",
            " [  9 951   7  22   7   0   2   0   2   0]\n",
            " [ 17   2 718   8 237   0  17   0   1   0]\n",
            " [ 52  20  36 795  67   0  26   0   4   0]\n",
            " [  0   1  82  16 870   0  29   0   2   0]\n",
            " [  0   0   5   0   0 945   0  31   5  14]\n",
            " [198   1 181  40 163   0 405   0  12   0]\n",
            " [  0   0   0   0   0  21   0 950   1  28]\n",
            " [  1   0  38   3   7   3  16   1 931   0]\n",
            " [  0   0   1   0   0  12   0  48   0 939]]\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BI-FfnofyktS",
        "outputId": "4882090d-fdd3-46a9-bf20-1c192cb85e60"
      },
      "source": [
        "!pip install pycm"
      ],
      "execution_count": 66,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting pycm\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/76/c4/a05b90819dcf7e50bdddb030238a771bf87b0695e6c47a247f66ab7ed5d0/pycm-3.1-py2.py3-none-any.whl (63kB)\n",
            "\r\u001b[K     |█████▏                          | 10kB 21.8MB/s eta 0:00:01\r\u001b[K     |██████████▎                     | 20kB 16.1MB/s eta 0:00:01\r\u001b[K     |███████████████▍                | 30kB 14.2MB/s eta 0:00:01\r\u001b[K     |████████████████████▌           | 40kB 13.2MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▊      | 51kB 7.7MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▉ | 61kB 7.4MB/s eta 0:00:01\r\u001b[K     |████████████████████████████████| 71kB 5.1MB/s \n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.9.0 in /usr/local/lib/python3.7/dist-packages (from pycm) (1.19.5)\n",
            "Collecting art>=1.8\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/a1/74/55552eaad673dc81546d1386161e6cd8f7edf951690de82df822fe46541d/art-5.2-py2.py3-none-any.whl (571kB)\n",
            "\u001b[K     |████████████████████████████████| 573kB 10.6MB/s \n",
            "\u001b[?25hInstalling collected packages: art, pycm\n",
            "Successfully installed art-5.2 pycm-3.1\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mba72g1YymEf"
      },
      "source": [
        "from pycm import *"
      ],
      "execution_count": 67,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "044gpHU2ywZV"
      },
      "source": [
        "cm = ConfusionMatrix(actual_vector=y_test, predict_vector=y_pred)"
      ],
      "execution_count": 69,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J6gFD7bmyzXJ",
        "outputId": "831ae3b7-9243-4109-a544-1efe6372d84a"
      },
      "source": [
        "cm.classes"
      ],
      "execution_count": 70,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Fg2oH9byy2z4",
        "outputId": "87fdf21f-0588-4d7d-b1eb-e45d587cf3e3"
      },
      "source": [
        "print(cm)"
      ],
      "execution_count": 71,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predict   0         1         2         3         4         5         6         7         8         9         \n",
            "Actual\n",
            "0         851       2         47        44        2         0         45        0         9         0         \n",
            "\n",
            "1         9         951       7         22        7         0         2         0         2         0         \n",
            "\n",
            "2         17        2         718       8         237       0         17        0         1         0         \n",
            "\n",
            "3         52        20        36        795       67        0         26        0         4         0         \n",
            "\n",
            "4         0         1         82        16        870       0         29        0         2         0         \n",
            "\n",
            "5         0         0         5         0         0         945       0         31        5         14        \n",
            "\n",
            "6         198       1         181       40        163       0         405       0         12        0         \n",
            "\n",
            "7         0         0         0         0         0         21        0         950       1         28        \n",
            "\n",
            "8         1         0         38        3         7         3         16        1         931       0         \n",
            "\n",
            "9         0         0         1         0         0         12        0         48        0         939       \n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "Overall Statistics : \n",
            "\n",
            "95% CI                                                            (0.82823,0.84277)\n",
            "ACC Macro                                                         0.9671\n",
            "ARI                                                               0.69831\n",
            "AUNP                                                              0.90861\n",
            "AUNU                                                              0.90861\n",
            "Bangdiwala B                                                      0.72411\n",
            "Bennett S                                                         0.81722\n",
            "CBA                                                               0.79297\n",
            "CSI                                                               0.67821\n",
            "Chi-Squared                                                       63156.62714\n",
            "Chi-Squared DF                                                    81\n",
            "Conditional Entropy                                               0.80969\n",
            "Cramer V                                                          0.8377\n",
            "Cross Entropy                                                     3.35438\n",
            "F1 Macro                                                          0.83156\n",
            "F1 Micro                                                          0.8355\n",
            "FNR Macro                                                         0.1645\n",
            "FNR Micro                                                         0.1645\n",
            "FPR Macro                                                         0.01828\n",
            "FPR Micro                                                         0.01828\n",
            "Gwet AC1                                                          0.81724\n",
            "Hamming Loss                                                      0.1645\n",
            "Joint Entropy                                                     4.13162\n",
            "KL Divergence                                                     0.03245\n",
            "Kappa                                                             0.81722\n",
            "Kappa 95% CI                                                      (0.80915,0.8253)\n",
            "Kappa No Prevalence                                               0.671\n",
            "Kappa Standard Error                                              0.00412\n",
            "Kappa Unbiased                                                    0.81703\n",
            "Krippendorff Alpha                                                0.81704\n",
            "Lambda A                                                          0.81722\n",
            "Lambda B                                                          0.80976\n",
            "Mutual Information                                                2.48312\n",
            "NIR                                                               0.1\n",
            "Overall ACC                                                       0.8355\n",
            "Overall CEN                                                       0.18722\n",
            "Overall J                                                         (7.34401,0.7344)\n",
            "Overall MCC                                                       0.81893\n",
            "Overall MCEN                                                      0.27673\n",
            "Overall RACC                                                      0.1\n",
            "Overall RACCU                                                     0.10094\n",
            "P-Value                                                           None\n",
            "PPV Macro                                                         0.84271\n",
            "PPV Micro                                                         0.8355\n",
            "Pearson C                                                         0.92914\n",
            "Phi-Squared                                                       6.31566\n",
            "RCI                                                               0.74749\n",
            "RR                                                                1000.0\n",
            "Reference Entropy                                                 3.32193\n",
            "Response Entropy                                                  3.29281\n",
            "SOA1(Landis & Koch)                                               Almost Perfect\n",
            "SOA2(Fleiss)                                                      Excellent\n",
            "SOA3(Altman)                                                      Very Good\n",
            "SOA4(Cicchetti)                                                   Excellent\n",
            "SOA5(Cramer)                                                      Very Strong\n",
            "SOA6(Matthews)                                                    Strong\n",
            "Scott PI                                                          0.81703\n",
            "Standard Error                                                    0.00371\n",
            "TNR Macro                                                         0.98172\n",
            "TNR Micro                                                         0.98172\n",
            "TPR Macro                                                         0.8355\n",
            "TPR Micro                                                         0.8355\n",
            "Zero-one Loss                                                     1645\n",
            "\n",
            "Class Statistics :\n",
            "\n",
            "Classes                                                           0             1             2             3             4             5             6             7             8             9             \n",
            "ACC(Accuracy)                                                     0.9574        0.9925        0.9321        0.9662        0.9387        0.9909        0.927         0.987         0.9895        0.9897        \n",
            "AGF(Adjusted F-score)                                             0.90193       0.97503       0.8233        0.88862       0.89103       0.97119       0.64968       0.96873       0.96473       0.96778       \n",
            "AGM(Adjusted geometric mean)                                      0.9371        0.98483       0.88882       0.93248       0.92582       0.9824        0.799         0.98018       0.97861       0.98029       \n",
            "AM(Difference between automatic and manual classification)        128           -23           115           -72           353           -19           -460          30            -33           -19           \n",
            "AUC(Area under the ROC curve)                                     0.91011       0.97406       0.83694       0.89011       0.90817       0.9705        0.695         0.97056       0.9635        0.96717       \n",
            "AUCI(AUC value interpretation)                                    Excellent     Excellent     Very Good     Very Good     Excellent     Excellent     Fair          Excellent     Excellent     Excellent     \n",
            "AUPR(Area under the PR curve)                                     0.80272       0.96219       0.68097       0.82584       0.75651       0.95415       0.5775        0.93617       0.94689       0.94809       \n",
            "BCD(Bray-Curtis dissimilarity)                                    0.0064        0.00115       0.00575       0.0036        0.01765       0.00095       0.023         0.0015        0.00165       0.00095       \n",
            "BM(Informedness or bookmaker informedness)                        0.82022       0.94811       0.67389       0.78022       0.81633       0.941         0.39          0.94111       0.927         0.93433       \n",
            "CEN(Confusion entropy)                                            0.22804       0.06803       0.32987       0.24118       0.26727       0.07584       0.43014       0.09213       0.0928        0.07615       \n",
            "DOR(Diagnostic odds ratio)                                        179.85785     6698.8022     55.17404      258.5463      118.00908     4278.27273    44.69748      2118.5        3359.69565    3283.20141    \n",
            "DP(Discriminant power)                                            1.24321       2.10938       0.96027       1.3301        1.14231       2.00202       0.90985       1.83374       1.94415       1.93864       \n",
            "DPI(Discriminant power interpretation)                            Limited       Fair          Poor          Limited       Limited       Fair          Poor          Limited       Limited       Limited       \n",
            "ERR(Error rate)                                                   0.0426        0.0075        0.0679        0.0338        0.0613        0.0091        0.073         0.013         0.0105        0.0103        \n",
            "F0.5(F0.5 score)                                                  0.77195       0.96883       0.65751       0.84359       0.67842       0.95959       0.64082       0.92773       0.95624       0.95349       \n",
            "F1(F1 score - harmonic mean of precision and sensitivity)         0.79981       0.96206       0.67896       0.82469       0.73948       0.95406       0.52597       0.93596       0.94662       0.94801       \n",
            "F2(F2 score)                                                      0.82976       0.95539       0.70186       0.80662       0.81263       0.9486        0.44604       0.94433       0.93719       0.94258       \n",
            "FDR(False discovery rate)                                         0.24557       0.02661       0.35605       0.14332       0.35698       0.0367        0.25          0.07767       0.03723       0.04281       \n",
            "FN(False negative/miss/type 2 error)                              149           49            282           205           130           55            595           50            69            61            \n",
            "FNR(Miss rate or false negative rate)                             0.149         0.049         0.282         0.205         0.13          0.055         0.595         0.05          0.069         0.061         \n",
            "FOR(False omission rate)                                          0.01679       0.00543       0.03174       0.0226        0.01503       0.0061        0.0629        0.00557       0.00764       0.00676       \n",
            "FP(False positive/type 1 error/false alarm)                       277           26            397           133           483           36            135           80            36            42            \n",
            "FPR(Fall-out or false positive rate)                              0.03078       0.00289       0.04411       0.01478       0.05367       0.004         0.015         0.00889       0.004         0.00467       \n",
            "G(G-measure geometric mean of precision and sensitivity)          0.80126       0.96213       0.67997       0.82526       0.74795       0.95411       0.55114       0.93606       0.94675       0.94805       \n",
            "GI(Gini index)                                                    0.82022       0.94811       0.67389       0.78022       0.81633       0.941         0.39          0.94111       0.927         0.93433       \n",
            "GM(G-mean geometric mean of specificity and sensitivity)          0.90819       0.97378       0.82845       0.88502       0.90736       0.97016       0.63161       0.97034       0.96295       0.96676       \n",
            "IBA(Index of balanced accuracy)                                   0.7273        0.90453       0.52306       0.63426       0.76046       0.89322       0.16755       0.90285       0.867         0.88197       \n",
            "ICSI(Individual classification success index)                     0.60543       0.92439       0.36195       0.65168       0.51302       0.9083        0.155         0.87233       0.89377       0.89619       \n",
            "IS(Information score)                                             2.91539       3.28301       2.68694       3.09876       2.68485       3.26799       2.90689       3.20528       3.26719       3.2588        \n",
            "J(Jaccard index)                                                  0.66641       0.9269        0.51396       0.70168       0.58665       0.91216       0.35683       0.87963       0.89865       0.90115       \n",
            "LS(Lift score)                                                    7.54433       9.73388       6.43946       8.56681       6.43016       9.63303       7.5           9.2233        9.62771       9.57187       \n",
            "MCC(Matthews correlation coefficient)                             0.77783       0.95798       0.64231       0.8067        0.71599       0.94907       0.51766       0.92885       0.94096       0.94234       \n",
            "MCCI(Matthews correlation coefficient interpretation)             Strong        Very Strong   Moderate      Strong        Strong        Very Strong   Moderate      Very Strong   Very Strong   Very Strong   \n",
            "MCEN(Modified confusion entropy)                                  0.32107       0.11449       0.42967       0.35554       0.35804       0.12533       0.51572       0.14688       0.15371       0.1228        \n",
            "MK(Markedness)                                                    0.73764       0.96796       0.61221       0.83408       0.62798       0.9572        0.6871        0.91676       0.95513       0.95042       \n",
            "N(Condition negative)                                             9000          9000          9000          9000          9000          9000          9000          9000          9000          9000          \n",
            "NLR(Negative likelihood ratio)                                    0.15373       0.04914       0.29501       0.20807       0.13737       0.05522       0.60406       0.05045       0.06928       0.06129       \n",
            "NLRI(Negative likelihood ratio interpretation)                    Fair          Good          Poor          Poor          Fair          Good          Negligible    Good          Good          Good          \n",
            "NPV(Negative predictive value)                                    0.98321       0.99457       0.96826       0.9774        0.98497       0.9939        0.9371        0.99443       0.99236       0.99324       \n",
            "OC(Overlap coefficient)                                           0.851         0.97339       0.718         0.85668       0.87          0.9633        0.75          0.95          0.96277       0.95719       \n",
            "OOC(Otsuka-Ochiai coefficient)                                    0.80126       0.96213       0.67997       0.82526       0.74795       0.95411       0.55114       0.93606       0.94675       0.94805       \n",
            "OP(Optimized precision)                                           0.89245       0.96883       0.78998       0.85935       0.89667       0.96462       0.50973       0.96582       0.95577       0.96058       \n",
            "P(Condition positive or support)                                  1000          1000          1000          1000          1000          1000          1000          1000          1000          1000          \n",
            "PLR(Positive likelihood ratio)                                    27.64982      329.19231     16.27708      53.79699      16.21118      236.25        27.0          106.875       232.75        201.21429     \n",
            "PLRI(Positive likelihood ratio interpretation)                    Good          Good          Good          Good          Good          Good          Good          Good          Good          Good          \n",
            "POP(Population)                                                   10000         10000         10000         10000         10000         10000         10000         10000         10000         10000         \n",
            "PPV(Precision or positive predictive value)                       0.75443       0.97339       0.64395       0.85668       0.64302       0.9633        0.75          0.92233       0.96277       0.95719       \n",
            "PRE(Prevalence)                                                   0.1           0.1           0.1           0.1           0.1           0.1           0.1           0.1           0.1           0.1           \n",
            "Q(Yule Q - coefficient of colligation)                            0.98894       0.9997        0.9644        0.99229       0.98319       0.99953       0.95623       0.99906       0.9994        0.99939       \n",
            "QI(Yule Q interpretation)                                         Strong        Strong        Strong        Strong        Strong        Strong        Strong        Strong        Strong        Strong        \n",
            "RACC(Random accuracy)                                             0.01128       0.00977       0.01115       0.00928       0.01353       0.00981       0.0054        0.0103        0.00967       0.00981       \n",
            "RACCU(Random accuracy unbiased)                                   0.01132       0.00977       0.01118       0.00929       0.01384       0.00981       0.00593       0.0103        0.00967       0.00981       \n",
            "TN(True negative/correct rejection)                               8723          8974          8603          8867          8517          8964          8865          8920          8964          8958          \n",
            "TNR(Specificity or true negative rate)                            0.96922       0.99711       0.95589       0.98522       0.94633       0.996         0.985         0.99111       0.996         0.99533       \n",
            "TON(Test outcome negative)                                        8872          9023          8885          9072          8647          9019          9460          8970          9033          9019          \n",
            "TOP(Test outcome positive)                                        1128          977           1115          928           1353          981           540           1030          967           981           \n",
            "TP(True positive/hit)                                             851           951           718           795           870           945           405           950           931           939           \n",
            "TPR(Sensitivity, recall, hit rate, or true positive rate)         0.851         0.951         0.718         0.795         0.87          0.945         0.405         0.95          0.931         0.939         \n",
            "Y(Youden index)                                                   0.82022       0.94811       0.67389       0.78022       0.81633       0.941         0.39          0.94111       0.927         0.93433       \n",
            "dInd(Distance index)                                              0.15215       0.04909       0.28543       0.20553       0.14064       0.05515       0.59519       0.05078       0.06912       0.06118       \n",
            "sInd(Similarity index)                                            0.89242       0.96529       0.79817       0.85467       0.90055       0.96101       0.57914       0.96409       0.95113       0.95674       \n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vyfWw8xp5cOB"
      },
      "source": [
        "### 15.Result Visualization"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KvXwPfvI3sZm"
      },
      "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",
        "    \n",
        "    if predicted_label == true_label:\n",
        "      color = 'blue'\n",
        "    else:\n",
        "      color = 'red'\n",
        "\n",
        "    plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label], 100*np.max(predictions_array), class_names[true_label]), 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": 80,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZKcFlcQx4xlS",
        "outputId": "34947c6b-9ac6-4137-9df0-b1d227712b89"
      },
      "source": [
        "y_pred_per[0]"
      ],
      "execution_count": 89,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([2.8523831e-27, 1.8574791e-24, 0.0000000e+00, 3.7751789e-26,\n",
              "       0.0000000e+00, 3.2811020e-02, 0.0000000e+00, 3.7132062e-02,\n",
              "       1.4221133e-20, 9.3005699e-01], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 89
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 211
        },
        "id": "H4HhsV913vrE",
        "outputId": "b19dd664-6939-443b-e5d6-84366eba202b"
      },
      "source": [
        "i = 12\n",
        "plt.figure(figsize=(6,3))\n",
        "plt.subplot(1,2,1)\n",
        "plot_image(i, y_pred_per[i], y_test, x_test)\n",
        "plt.subplot(1,2,2)\n",
        "plot_value_array(i, y_pred_per[i],  y_test)\n",
        "plt.show()"
      ],
      "execution_count": 90,
      "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": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 729
        },
        "id": "VUfgXNVn3x5m",
        "outputId": "b3554de6-d0ad-4f45-e070-d24f52c6955a"
      },
      "source": [
        "num_rows = 5\n",
        "num_cols = 3\n",
        "num_images = num_rows*num_cols\n",
        "plt.figure(figsize=(2*2*num_cols, 2*num_rows))\n",
        "for i in range(num_images):\n",
        "  plt.subplot(num_rows, 2*num_cols, 2*i+1)\n",
        "  plot_image(i, y_pred_per[i], y_test, x_test)\n",
        "  plt.subplot(num_rows, 2*num_cols, 2*i+2)\n",
        "  plot_value_array(i, y_pred_per[i], y_test)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "execution_count": 92,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x720 with 30 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_OxbqIRH5hdd"
      },
      "source": [
        "### 16.Result for Single Image"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "u1e9WFRD5hCN",
        "outputId": "53a5ea5c-175f-450a-be9d-580fe5957840"
      },
      "source": [
        "img = np.expand_dims(x_test[0], 0)\n",
        "img_pred = class_names[np.argmax(model.predict(img))]\n",
        "img_actual = class_names[y_test[0]]\n",
        "\n",
        "plt.figure(figsize=(5,5))\n",
        "plt.imshow(x_test[0])\n",
        "plt.xticks([])\n",
        "plt.yticks([])\n",
        "plt.xlabel(f\"Actual : {img_actual}\\nPrediction : {img_pred}\", fontsize=14)\n",
        "plt.grid(False)\n",
        "plt.show()"
      ],
      "execution_count": 104,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}