single input digit prediction using neural network

Author: N0-man

Unit03/Neural_Networks.ipynb

@@ -265,7 +265,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### **3) Backpropagation**"
+    "## **3) Backpropagation**"
    ]
   },
   {
@@ -527,7 +527,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### 4) Improvements or Optimization (Gradient Descent)"
+    "## **4) Improvements or Optimization (Gradient Descent)**"
    ]
   },
   {
@@ -571,12 +571,14 @@
    "source": [
     "<hr>\n",
     "\n",
-    "## Lets build a Neural Network"
+    "## Lets build a Neural Network\n",
+    "\n",
+    "A simple neural network with one hidden layer."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -746,7 +748,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -833,14 +835,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 94.17%\n"
+      "Accuracy: 93.06%\n"
      ]
     },
     {
@@ -909,6 +911,95 @@
     "print(f\"Accuracy: {accuracy:.2%}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Predict Single Digit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Input Single Digit 8x8 image vector : \n",
+      "+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+\n",
+      "|    Pix1    |    Pix2    |    Pix3    |    Pix4    |    Pix5    |    Pix6    |    Pix7    |    Pix8    |\n",
+      "+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+\n",
+      "|    0.00    |    0.00    |    0.12    |    0.81    |    0.50    |    0.00    |    0.00    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.38    |    1.00    |    1.00    |    0.38    |    0.00    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.31    |    0.94    |    0.81    |    0.69    |    0.00    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.00    |    0.44    |    1.00    |    0.94    |    0.00    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.00    |    0.00    |    0.00    |    0.88    |    0.21    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.00    |    0.00    |    0.00    |    0.44    |    0.69    |    0.00    |\n",
+      "|    0.00    |    0.00    |    0.00    |    0.19    |    0.25    |    0.25    |    1.00    |    0.15    |\n",
+      "|    0.00    |    0.00    |    0.12    |    0.94    |    0.81    |    0.88    |    0.81    |    0.12    |\n",
+      "+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+::::::::::::+\n",
+      "Predicted Value :  9\n",
+      "Actual Digit Image with Label :\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from dataclasses import dataclass\n",
+    "import pandas as pd\n",
+    "from tabulate import tabulate\n",
+    "from prettytable import PrettyTable\n",
+    "\n",
+    "def show_input_vector(vector):\n",
+    "    reshaped_X = vector.reshape(8, 8)\n",
+    "    df = pd.DataFrame(reshaped_X)\n",
+    "    fixed_width_df = df.map(lambda x: f\"{x:5.2f}\")\n",
+    "\n",
+    "    t = PrettyTable(\n",
+    "        ['Pix1', 'Pix2', 'Pix3', 'Pix4', 'Pix5', 'Pix6', 'Pix7', 'Pix8'], \n",
+    "        align='c', \n",
+    "        horizontal_char=':',\n",
+    "        max_width=10, \n",
+    "        min_width=10\n",
+    "    )   \n",
+    "    t.add_rows(fixed_width_df.values.tolist())\n",
+    "    print(t)\n",
+    "\n",
+    "@dataclass\n",
+    "class SingleDigit:\n",
+    "   images: np.array\n",
+    "   target: np.array\n",
+    "\n",
+    "test_idx = 31\n",
+    "X_single_input = X[test_idx]\n",
+    "y_single_label = y[test_idx]\n",
+    "singleDigit = SingleDigit(\n",
+    "    # Shape of digits.images is (samples_n, 8, 8) where 8x8 are pixels\n",
+    "    images = np.array([digits.images[test_idx]]),\n",
+    "    target = np.array([digits.target[test_idx]])\n",
+    ")\n",
+    "    \n",
+    "predict = np.argmax(nn.forward(X_single_input), axis=1)\n",
+    "\n",
+    "print(f\"Input Single Digit 8x8 image vector : \")\n",
+    "show_input_vector(X_single_input)\n",
+    "print(f\"Predicted Value : \", predict[0])\n",
+    "print(f\"Actual Digit Image with Label :\")\n",
+    "show_digits(singleDigit, 1)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

poetry.lock

@@ -32,6 +32,8 @@ plotly = "^5.23.0"
 plotly-express = "^0.4.1"
 spacy = "^3.7.6"
 nltk = "^3.9.1"
+tabulate = "^0.9.0"
+prettytable = "^3.11.0"
 
 [tool.poetry.group.dev.dependencies]
 notebook = "^7.2.1"