{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "64df0af5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cf28cb0a",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('Fashion.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "eaebe840",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data.iloc[:, :-1].values  # Assuming the last column is the label\n",
    "y = data.iloc[:, -1].values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2e4133a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unique labels before cleaning: [  0   1   2   3   4   5   6   9  11  23  35  37  42  48  50  51  60  62\n",
      "  77 107]\n"
     ]
    }
   ],
   "source": [
    "print(\"Unique labels before cleaning:\", np.unique(y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2cc325f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "label_mapping = {11: 1, 23: 3, 35: 5, 37: 7, 42: 2, 48: 8, 50: 0, 51: 1, 60: 6, 62: 2, 77: 7, 107: 7}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "57b7c196",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = np.array([label_mapping.get(label, label) for label in y])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0d406abc",
   "metadata": {},
   "outputs": [],
   "source": [
    "valid_indices = np.where((y >= 0) & (y <= 9))  # Filter out any invalid labels\n",
    "X = X[valid_indices]\n",
    "y = y[valid_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "c4ecdf34",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unique labels after cleaning: [0 1 2 3 4 5 6 7 8 9]\n"
     ]
    }
   ],
   "source": [
    "print(\"Unique labels after cleaning:\", np.unique(y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e65dfb05",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X.reshape(-1, 28, 28, 1)  # Reshape for CNN input\n",
    "\n",
    "# Normalize images\n",
    "X = X / 255.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ee675c84",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_cat = tf.keras.utils.to_categorical(y, 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a9431ca1",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(X, y_cat, test_size=0.2, random_state=42)\n",
    "\n",
    "# Class names (adjust as needed for your dataset)\n",
    "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "77c670ce",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\backend.py:1398: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
      "\n",
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\normalization\\batch_normalization.py:979: The name tf.nn.fused_batch_norm is deprecated. Please use tf.compat.v1.nn.fused_batch_norm instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Input(shape=(28, 28, 1)),\n",
    "    tf.keras.layers.Conv2D(32, kernel_size=(3, 3), padding='same', activation='relu'),\n",
    "    tf.keras.layers.AvgPool2D(pool_size=(2, 2)),\n",
    "    tf.keras.layers.Conv2D(16, kernel_size=(3, 3), padding='same', activation='relu'),\n",
    "    tf.keras.layers.AvgPool2D(pool_size=(2, 2)),\n",
    "    tf.keras.layers.Conv2D(8, kernel_size=(3, 3), padding='same', activation='relu'),\n",
    "    tf.keras.layers.AvgPool2D(pool_size=(2, 2)),\n",
    "    tf.keras.layers.BatchNormalization(),\n",
    "    tf.keras.layers.Flatten(),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dense(10, activation=\"softmax\")\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3f8715b8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\optimizers\\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
      "\n",
      "Epoch 1/10\n",
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
      "\n",
      "WARNING:tensorflow:From C:\\Users\\Work\\anaconda3\\Lib\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
      "\n",
      "250/250 [==============================] - 5s 13ms/step - loss: 0.0769 - accuracy: 0.9893 - val_loss: 0.1436 - val_accuracy: 0.9960\n",
      "Epoch 2/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0241 - accuracy: 0.9966 - val_loss: 0.0375 - val_accuracy: 0.9960\n",
      "Epoch 3/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0215 - accuracy: 0.9966 - val_loss: 0.0303 - val_accuracy: 0.9960\n",
      "Epoch 4/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0206 - accuracy: 0.9966 - val_loss: 0.0287 - val_accuracy: 0.9960\n",
      "Epoch 5/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0189 - accuracy: 0.9965 - val_loss: 0.0284 - val_accuracy: 0.9960\n",
      "Epoch 6/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0187 - accuracy: 0.9966 - val_loss: 0.0306 - val_accuracy: 0.9960\n",
      "Epoch 7/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0170 - accuracy: 0.9966 - val_loss: 0.0306 - val_accuracy: 0.9960\n",
      "Epoch 8/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0159 - accuracy: 0.9965 - val_loss: 0.0299 - val_accuracy: 0.9960\n",
      "Epoch 9/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0151 - accuracy: 0.9966 - val_loss: 0.0327 - val_accuracy: 0.9960\n",
      "Epoch 10/10\n",
      "250/250 [==============================] - 3s 11ms/step - loss: 0.0135 - accuracy: 0.9966 - val_loss: 0.0364 - val_accuracy: 0.9960\n"
     ]
    }
   ],
   "source": [
    "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n",
    "\n",
    "# Train the model\n",
    "history = model.fit(x_train, y_train, epochs=10, validation_data=(x_test, y_test))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c8d6d596",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame(history.history).plot(figsize=(10,7))\n",
    "plt.title(\"Metrics Graph\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4abe010c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63/63 [==============================] - 0s 5ms/step - loss: 0.0364 - accuracy: 0.9960\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.03638689965009689, 0.9959999918937683]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(x_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "33590a11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63/63 [==============================] - 1s 5ms/step\n"
     ]
    }
   ],
   "source": [
    "predictions = model.predict(x_test)\n",
    "predictions = tf.argmax(predictions, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "35530d57",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test = tf.argmax(y_test, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "4270fafb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00      1992\n",
      "           1       0.00      0.00      0.00         2\n",
      "           2       0.00      0.00      0.00         1\n",
      "           3       0.00      0.00      0.00         1\n",
      "           4       0.00      0.00      0.00         0\n",
      "           5       0.00      0.00      0.00         1\n",
      "           6       0.00      0.00      0.00         2\n",
      "           7       0.00      0.00      0.00         1\n",
      "\n",
      "    accuracy                           1.00      2000\n",
      "   macro avg       0.12      0.12      0.12      2000\n",
      "weighted avg       0.99      1.00      0.99      2000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, predictions, zero_division=0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "96b6c8ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, predictions)\n",
    "sns.heatmap(cm, cmap='crest', annot=True, fmt=\".0f\", xticklabels=class_names, yticklabels=class_names)\n",
    "plt.title(\"Confusion Matrix\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "2fc29cbb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "images = []\n",
    "labels = []\n",
    "random_indices = random.sample(range(len(x_test)), 10)\n",
    "for idx in random_indices:\n",
    "    images.append(x_test[idx])\n",
    "    labels.append(y_test[idx])\n",
    "images = np.array(images)\n",
    "labels = np.array(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "660cbffa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 158ms/step\n",
      "1/1 [==============================] - 0s 42ms/step\n",
      "1/1 [==============================] - 0s 36ms/step\n",
      "1/1 [==============================] - 0s 39ms/step\n",
      "1/1 [==============================] - 0s 46ms/step\n",
      "1/1 [==============================] - 0s 41ms/step\n",
      "1/1 [==============================] - 0s 37ms/step\n",
      "1/1 [==============================] - 0s 48ms/step\n",
      "1/1 [==============================] - 0s 53ms/step\n",
      "1/1 [==============================] - 0s 40ms/step\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x800 with 10 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(20, 8))\n",
    "rows = 2\n",
    "cols = 5\n",
    "x = 1\n",
    "for image, label in zip(images, labels):\n",
    "    fig.add_subplot(rows, cols, x)\n",
    "    prediction = model.predict(tf.expand_dims(image, axis=0))\n",
    "    prediction = class_names[tf.argmax(prediction.flatten())]\n",
    "    label = class_names[label]\n",
    "    plt.title(f\"Label: {label}, Prediction: {prediction}\")\n",
    "    plt.imshow(image/255.)\n",
    "    plt.axis(\"off\")\n",
    "    x += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d6f2ea13",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}