{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "068d30b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.11.0'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Import dependencies and packages needed; Tensorflow and Keras\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "# Check Keras version\n",
    "keras.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8a514eb5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.11.0'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check Tensorflow version\n",
    "tf.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b833279d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Assign a variable for the dataset and download\n",
    "fashion_mnist = keras.datasets.fashion_mnist\n",
    "(X_train_full, y_train_full), (X_test, y_test) = fashion_mnist.load_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7ed65c35",
   "metadata": {},
   "source": [
    "<h2>MNIST Fashion Dataset</h2>\n",
    "\n",
    "<p>Fashion-MNIST is a dataset of Zalando's article images</p>\n",
    "<p>It consists of a training set of 60,000 examples and a test set of 10,000 examples</p>\n",
    "<p>Each example is a 28x28 grayscale image</p>\n",
    "<p>Each image is associated with a label from 10 classes</p>\n",
    "<p> All details on the Keras TF dataset is at this address:</p>\n",
    "<p>https://www.tensorflow.org/datasets/catalog/fashion_mnist</p>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2b68046",
   "metadata": {},
   "source": [
    "<img>https://production-media.paperswithcode.com/datasets/Fashion-MNIST-0000000040-4a13281a_m8bp4wm.jpg</img>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "673772f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(60000, 28, 28)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the structure of the train dataset - 60,000 datapoints of images 28 x 28 pixels\n",
    "X_train_full.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "07be93f1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('uint8')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the type as well\n",
    "X_train_full.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6a7e6c6c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot an individual image from the dataset\n",
    "import matplotlib.pyplot as plt\n",
    "plt.figure()\n",
    "plt.imshow(X_train_full[11])\n",
    "plt.colorbar()\n",
    "plt.grid(False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "01b4c9b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Assign names to the classification labels\n",
    "class_names = ['T-shirt/top', 'Trousers', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']\n",
    "class_names[y_train_full[0]]\n",
    "# Check that label matches the picture\n",
    "y_train_full[11]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a109ae95",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAEMAAABBCAYAAACKAhl4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAL6klEQVR4nO2aXWxc1XbHf3vOnPkej0eeIbId48EOoSHGCpGFEkjBRICIBBIloPTjFkWtKvF0eWofryh9qNQWqOCqFZWqRpXapwj6cCta0URxlHITxcEmhDi2mTjNeBLH9iTzPXM+dx8y59wxscnHTJy08l8azdaevc9Z+z9rrb3W2ltIKdnATXgetAAPEzbIaMIGGU3YIKMJG2Q0wdvK5EQiIVOpVFsE0TSNarWKaZp4PB48Hg9+vx+fz4fXe3dinjlzZllKmbxbGVoiI5VKMT4+3sojANB1nffff5+zZ8+Sy+UQQiClJBQKsWnTJp5//nmy2SyapuHxeNiyZQuvv/46iUQCRVGQUiKEcJ8nhPife5GjJTJaQfMCbNvm5MmTpNNp8vk8lmVhmia2bRMOhykWi1y6dIlarYbX62Xr1q309fXx1FNP0dPTg2VZKIqygpB7wUNBhpSSfD6Px+MhHA5jWRaqqlKtVtF1nSNHjlCv1xFCoCgKMzMzRKNR9u/fz/79+13T+j9NhvOt6zpXrlzBMAwURcGyLKrVKqqqEo1G6ejoIJPJIKVEURRs2+btt99m9+7dAAghWiYCHuBuYts2UkqKxSIzMzNUKhVs217xm5QS27YxDAPLsrAsC9u26e3txe/3Y5ompVLprh3sWnggmtFsIqVSidnZWaSU7i7iLFxRFEzTpFarYZomUkoCgQADAwPUajVyuRxSSqLRqEteKxryQMgQQrj/Zj6f58KFC8TjcVRVxbIsFhcXEUKgqqrrT6SU+P1+4vE4o6OjzM3NUavVGBwcpK+vr2Ui4AH6DAfXr1/n9OnTWJZFPB4nHA7z6KOPks1mkVJimiY3btzg8ccfp1AoUCqV0HWdZ599lv7+fhKJBAAeT+sWv+5kOOrsCF+r1bh69SqGYbC0tESpVCISibjOVFVVUqkUiqKQTCZJJpO89NJLDAwMEIvF8Pv9bZPtgfkMuBlslctllpeXsW2bfD4PQDAYRFEUvF4vkUiE3t5eMpkM3d3dDA8Ps3fv3vsi17qT4cQKANPT00xNTZHP53niiSeoVqtUq1VXO6rVKoVCgUQiQTabRVVVarXafZPtgSZqp06d4ptvvsG2bWzbJhgM0tnZSTKZJBqNEg6HiUQi+P1+hBAMDAwwNDTERx99xNLSUtvlWVcyflxiTKfTzM/P4/f7qVQqlEolisWi29Z1HdM00TQNKSV9fX3s2LEDwzAYGxvj3LlzbZVvXc3EIUMIgWVZzM3NsbCwQDgcplAooGnaihhDCEEgEKBarSKlJB6PMzg4yLVr1/j888/Zs2cPQ0NDbZNvXTXDiQMsy2Jqaoq5uTmuX7+OqqrYto2qqkQiEfr7+zFNk1AoRGdnp7vzfPbZZxw4cIBdu3Zx9uxZpqam2irfupMhhMAwDMbHx6lUKni9Xnw+H6qquoGYE3EGg0Gi0Sj1eh2Px0OlUiGdTnPo0CFyuRzj4+N8+umnt5jfvWLdyGhOzDRN4+TJk67TrNfrmKbppu2maWJZFn6/n1AohKZp7txyucyRI0cwTZNcLseJEyfIZrPout6yjOtOhmmaFAoFvvzyS1RVJRaLuZFlrVZD13U3YQsEAi5ZlmW5mjM2NobX60XTNL7//ntOnz7NjRs33Hn3inVzoI7dT05OcvjwYTKZDIqiEA6H6e7uJp1Oo+s6lmURCARumeuQqSgKgUDA3Y4Nw+Do0aMsLS0xPDzMrl277lnGdSGjOYnKZDKMjY0RDoepVCqYponX62Xz5s3k83l0XadardLV1YWiKBiGgaqqKwpBzpa7adMmnnzySQ4ePEhnZyednZ0tybmuW2s+nyeTyZBOp/F6vdTrdXRdd7PRjo4Od3t1tMOyLHw+n0uGEALbtvH5fKRSKUZHR9m5c2dbijvrQoYj6OTkJOfPn2d5eZnOzk63aFMul9E0jb6+Prfsl8lksCwLgFAohMfjWVHnTCaTvPDCC7z77rttk3NdNePQoUNMTEyQSqVIpVIsLy9TqVQwDINsNkuxWCQcDtPT04MQgrm5Obf26dQ4HYJ0XccwjLbKd1/JcHyFaZpks1lmZmZYWFhAURS3XuGYSCQSQdM0DMNgcXERr9dLLBYjFotx9epVgBWa4ff7UVW1rfKuy9aq6zoTExMsLCxQKpXc2kW5XHYr280JmhNzOBFoIBBwdxOnNBgIBPD5fG2Vs62a4RRwgRWl+0KhwCeffEI+n0dVVXcx+XyexcVFbNvG7/fT09NDR0cHjz32GIuLi5TLZVRVZcuWLVy8eBHALQeGw+FbtuBW0RYybNt2zzqcWoWDM2fO8NVXXzExMcHWrVsplUpks1k8Hg/BYNCNGQzDoFQquZmraZq88cYb7Nixg9nZWdLpNLZt4/V6MQyDWCxGMBhsh/gu2kJGc8EGbkaZ5XKZyclJjh49yvHjx4nH4wCug1xcXHSdoeMgnUBK13XefPNNXnvtNXp6epienl6hcVJKgsFgW0t+0EbNqNfrLC8vu/WHxcVFvvjiC44fP86FCxcYGhrCMAz8fj/JZJJCoUC5XMa2bdcxSilRVZXu7m7eeecdRkZG3APp5nFwM1R3yGhHZRzaREYul+PYsWO89957FAoFbNt2kyvH0c3MzLBt2zbq9Trz8/P09/czNzdHuVx2TaxcLrNt2zY++OAD9u3bh8/n4+LFi7fkHEIIurq6iEajwENERqlU4rvvvuPjjz9G0zS3mOuYgAPTNJmeniYej9Pb27vibKRcLlOr1di+fTt79+7lxRdfdLdNZ4zTdnKccDi8QjPagZbJuHLlCrOzs1y6dGmFDTuEOEeCQgjq9Trlchm/34+UkmQyiaZp2LZNsVjkueee45VXXqGjo8PVBocMx1fYto3H4yEUCq3YTR6KQ6SFhQXm5+fRNI14PI5pmm5twTCMW85JSqUS9XrdPQMxDINarYbH4+HVV19l3759AG4CJ4RwC8LN5EYiEZeMh0Yzdu/ejc/n4+uvv+aHH35wAyknoXJU24ktnH/38uXL5HI5t5hz+PBhRkZGfiNYgwhHM5wjSa/Xi23bK4Iux7m2ipbJUFWV7du38+GHHzI/P8+3337L+fPnOXfunJtb/Pifc7ZQTdMYHh7mwIEDPPPMM8RisVWf39vbi6IorgZ1d3fT399PV1cX0J6jRWgDGUIIOjo6ePrpp0mlUjzyyCMMDAwwODjI/Pw8xWKRWq3mXjzxeDyoquqekQwNDfHyyy/T1dW1qs2HQiF27tzJ6Ogo9XqdUChEIpGgr6+PUCgE0JaLKgCiFXsbGRmRt7vTlcvluHbtGpcvX6ZYLLoXUPr7+9m8efOaUaRjYs4iT506hcfjoaOjg1gsRiKRWPNehhDijJRyZNUffwItkSGEWALu6TLZfUb/vdz2a4mM/2/YuBTbhA0ymrBBRhPuiAwhxO8IIaQQ4rfucPwlIURilf7y3Qh3t+N/4jkHhRA9txt3p5rxe8AJ4HdbkurB4SBwWzLc3GGtDxABssBW4EJT/yhwDDgMXAD+hd/sTpeABBAE/gP4k0Z/uWn+nwKngbPAn6/x7jLwIfANcARINvp3ACcbc78A4mv1A281njMNTALBNdd6B2T8DPjHRvtrYGcTGQVgMzc17NfAniYyUsB/Ae80L67x/QrwD4BozP0V8Pwq75bAHzTavwB+2WifBV5otD8A/vY2/ceAkduu9Q7I+Hfg5Ub758BfN5HxVdO4vwd+1kTGt85CViHjbxpjJhufH4A/XuXdFuBttAcaY2PA5aYxgw3NWbX/bsj4ydxECNEF7AWGhBASUAAphPizxhCtabjFylznv4F9Qoh/lbdGdgL4SynlZz/1/lVwXyPE2znQt4B/llL2SylTUso+YA7YcwfP/gWQA/5uld/+E/gjIUQEQAjRK4R4ZA353mq0fx84IaUsADeEEL/d6P9DYGyt/ka7BERvK/FtTOQY8OqP+n7OTZMYBX7V1P9L4OCPHKgA/gn4q1Uc6HvAd43Pr4HBNRzoXwBngKOs7kD/jdUdaHP/fu7AgW7kJk3YiECbsEFGEzbIaMIGGU3YIKMJG2Q0YYOMJvwv+iJGQHbqkbAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Alternatively plot 25 images and labels to compare\n",
    "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_full[i], cmap = plt.cm.binary)\n",
    "    plt.xlabel(class_names[y_train_full[i]])\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6c389a9a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split the train features to give 5000 validation datapoints and 55000 train datapoints\n",
    "# Normalise data to range 0 to 1.0\n",
    "X_valid = X_train_full[:5000]/255.0\n",
    "X_train = X_train_full[5000:]/255.0\n",
    "# Split the train labels to give 5000 validation datapoints and 55000 train datapoints\n",
    "y_valid = y_train_full[:5000]\n",
    "y_train = y_train_full[5000:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "427b37cb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a variable to store the model, using sequential NN model\n",
    "model = tf.keras.Sequential()\n",
    "# Add layers to the model to build an artificial neural network\n",
    "model.add(keras.layers.Flatten(input_shape = (28, 28))) # A flatten layer to transform a \n",
    "model.add(keras.layers.Dense(300, activation = 'relu'))\n",
    "model.add(keras.layers.Dense(100, activation = 'relu'))\n",
    "model.add(keras.layers.Dense(10, activation = 'softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4fef14a6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " flatten (Flatten)           (None, 784)               0         \n",
      "                                                                 \n",
      " dense (Dense)               (None, 300)               235500    \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 100)               30100     \n",
      "                                                                 \n",
      " dense_2 (Dense)             (None, 10)                1010      \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 266,610\n",
      "Trainable params: 266,610\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "# Show summary of layers and parameters (weights and biases)\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "14b79b61",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compile the model using Stochastic Gradient Descent optimisation and Sparse Categorical Crossentropy Loss Function\n",
    "model.compile(loss = 'sparse_categorical_crossentropy', optimizer = 'sgd', metrics = [\"accuracy\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7e185b5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n",
      "1719/1719 [==============================] - 4s 2ms/step - loss: 0.7276 - accuracy: 0.7613 - val_loss: 0.5680 - val_accuracy: 0.7940\n",
      "Epoch 2/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.4860 - accuracy: 0.8307 - val_loss: 0.4385 - val_accuracy: 0.8536\n",
      "Epoch 3/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.4395 - accuracy: 0.8466 - val_loss: 0.4166 - val_accuracy: 0.8600\n",
      "Epoch 4/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.4121 - accuracy: 0.8557 - val_loss: 0.3871 - val_accuracy: 0.8666\n",
      "Epoch 5/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3911 - accuracy: 0.8632 - val_loss: 0.3896 - val_accuracy: 0.8652\n",
      "Epoch 6/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3753 - accuracy: 0.8663 - val_loss: 0.3851 - val_accuracy: 0.8646\n",
      "Epoch 7/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3615 - accuracy: 0.8721 - val_loss: 0.3607 - val_accuracy: 0.8780\n",
      "Epoch 8/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3504 - accuracy: 0.8750 - val_loss: 0.3768 - val_accuracy: 0.8700\n",
      "Epoch 9/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3410 - accuracy: 0.8783 - val_loss: 0.3591 - val_accuracy: 0.8758\n",
      "Epoch 10/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3316 - accuracy: 0.8828 - val_loss: 0.3466 - val_accuracy: 0.8790\n",
      "Epoch 11/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3231 - accuracy: 0.8845 - val_loss: 0.3628 - val_accuracy: 0.8730\n",
      "Epoch 12/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3161 - accuracy: 0.8868 - val_loss: 0.3323 - val_accuracy: 0.8854\n",
      "Epoch 13/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3083 - accuracy: 0.8902 - val_loss: 0.3302 - val_accuracy: 0.8834\n",
      "Epoch 14/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.3021 - accuracy: 0.8924 - val_loss: 0.3250 - val_accuracy: 0.8842\n",
      "Epoch 15/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2964 - accuracy: 0.8930 - val_loss: 0.3373 - val_accuracy: 0.8822\n",
      "Epoch 16/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2915 - accuracy: 0.8967 - val_loss: 0.3193 - val_accuracy: 0.8852\n",
      "Epoch 17/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2850 - accuracy: 0.8977 - val_loss: 0.3304 - val_accuracy: 0.8832\n",
      "Epoch 18/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2789 - accuracy: 0.9003 - val_loss: 0.3485 - val_accuracy: 0.8776\n",
      "Epoch 19/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2751 - accuracy: 0.9006 - val_loss: 0.3086 - val_accuracy: 0.8914\n",
      "Epoch 20/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2690 - accuracy: 0.9035 - val_loss: 0.3167 - val_accuracy: 0.8914\n",
      "Epoch 21/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2649 - accuracy: 0.9037 - val_loss: 0.3340 - val_accuracy: 0.8802\n",
      "Epoch 22/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2605 - accuracy: 0.9070 - val_loss: 0.3113 - val_accuracy: 0.8874\n",
      "Epoch 23/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2561 - accuracy: 0.9082 - val_loss: 0.3018 - val_accuracy: 0.8944\n",
      "Epoch 24/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2513 - accuracy: 0.9094 - val_loss: 0.3056 - val_accuracy: 0.8894\n",
      "Epoch 25/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2482 - accuracy: 0.9108 - val_loss: 0.3239 - val_accuracy: 0.8806\n",
      "Epoch 26/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2426 - accuracy: 0.9135 - val_loss: 0.2952 - val_accuracy: 0.8926\n",
      "Epoch 27/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2395 - accuracy: 0.9144 - val_loss: 0.3213 - val_accuracy: 0.8886\n",
      "Epoch 28/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2352 - accuracy: 0.9160 - val_loss: 0.2954 - val_accuracy: 0.8982\n",
      "Epoch 29/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2307 - accuracy: 0.9170 - val_loss: 0.3216 - val_accuracy: 0.8828\n",
      "Epoch 30/30\n",
      "1719/1719 [==============================] - 3s 2ms/step - loss: 0.2277 - accuracy: 0.9183 - val_loss: 0.3219 - val_accuracy: 0.8864\n"
     ]
    }
   ],
   "source": [
    "# Train and validate the model on 30 iterations (epochs) - Take note of training accuracy vs validation accuracy\n",
    "history = model.fit(X_train, y_train, epochs = 30, validation_data = (X_valid, y_valid))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bb1da588",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "313/313 [==============================] - 0s 988us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 0., 1.],\n",
       "       [0., 0., 1., ..., 0., 0., 0.],\n",
       "       [0., 1., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 1., 0.],\n",
       "       [0., 1., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]], dtype=float32)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Predict on the test set to evaluate metrics\n",
    "X_new = X_test[:]\n",
    "X_test.shape\n",
    "y_prob = model.predict(X_new)\n",
    "y_prob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7ae5d4e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use Argmax for highest probability\n",
    "y_pred = tf.argmax(y_prob, axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "93c47d51",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tf.Tensor([9 2 1 ... 8 1 5], shape=(10000,), dtype=int64)\n"
     ]
    }
   ],
   "source": [
    "# Show the predicted classifications in Tensor form\n",
    "print(y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "0cb01dc7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[831  13  13  28  14   0  75   0  26   0]\n",
      " [  0 985   0   9   3   0   1   0   2   0]\n",
      " [ 13  11 604  11 318   0  32   0  11   0]\n",
      " [ 14  40  11 845  73   0   9   0   8   0]\n",
      " [  0   1  24  17 946   0   8   0   4   0]\n",
      " [  0   1   0   0   0 939   0  20   7  33]\n",
      " [132  11  62  32 265   0 470   0  28   0]\n",
      " [  0   0   0   0   0  19   0 937   0  44]\n",
      " [  4   1   0   3   6   1   1   4 980   0]\n",
      " [  1   0   0   0   0   2   0  28   0 969]]\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0      0.835     0.831     0.833      1000\n",
      "           1      0.927     0.985     0.955      1000\n",
      "           2      0.846     0.604     0.705      1000\n",
      "           3      0.894     0.845     0.869      1000\n",
      "           4      0.582     0.946     0.721      1000\n",
      "           5      0.977     0.939     0.958      1000\n",
      "           6      0.789     0.470     0.589      1000\n",
      "           7      0.947     0.937     0.942      1000\n",
      "           8      0.919     0.980     0.949      1000\n",
      "           9      0.926     0.969     0.947      1000\n",
      "\n",
      "    accuracy                          0.851     10000\n",
      "   macro avg      0.864     0.851     0.847     10000\n",
      "weighted avg      0.864     0.851     0.847     10000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print confusion matrix and metric report - Notice the mistakes in predictions... Why could this be?\n",
    "from sklearn import metrics\n",
    "print(metrics.confusion_matrix(y_test, y_pred))\n",
    "print()\n",
    "print(metrics.classification_report(y_test, y_pred, digits = 3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ebcd5b59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_history(history):\n",
    "    acc = history.history[\"accuracy\"]\n",
    "    loss = history.history[\"loss\"]\n",
    "    val_loss = history.history[\"val_loss\"]\n",
    "    val_accuracy = history.history[\"val_accuracy\"]\n",
    "    \n",
    "    x = range(1, len(acc) + 1)\n",
    "    \n",
    "    plt.figure(figsize=(12,5))\n",
    "    plt.subplot(1, 2, 1)\n",
    "    plt.plot(x, acc, \"b\", label=\"traning_acc\")\n",
    "    plt.plot(x, val_accuracy, \"r\", label=\"traning_acc\")\n",
    "    plt.title(\"Accuracy\")\n",
    "    \n",
    "    plt.subplot(1, 2, 2)\n",
    "    plt.plot(x, loss, \"b\", label=\"traning_acc\")\n",
    "    plt.plot(x, val_loss, \"r\", label=\"traning_acc\")\n",
    "    plt.title(\"Loss\")\n",
    "    \n",
    "    \n",
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5a722448",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}