{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "64df0af5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Manmath\\anacoda5\\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\\Manmath\\anacoda5\\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\\Manmath\\anacoda5\\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\\Manmath\\anacoda5\\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\\Manmath\\anacoda5\\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\\Manmath\\anacoda5\\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 [==============================] - 7s 16ms/step - loss: 0.0959 - accuracy: 0.9846 - val_loss: 0.0874 - val_accuracy: 0.9960\n",
      "Epoch 2/10\n",
      "250/250 [==============================] - 4s 15ms/step - loss: 0.0232 - accuracy: 0.9966 - val_loss: 0.0288 - val_accuracy: 0.9960\n",
      "Epoch 3/10\n",
      "250/250 [==============================] - 4s 15ms/step - loss: 0.0207 - accuracy: 0.9966 - val_loss: 0.0300 - val_accuracy: 0.9960\n",
      "Epoch 4/10\n",
      "250/250 [==============================] - 3s 14ms/step - loss: 0.0203 - accuracy: 0.9966 - val_loss: 0.0285 - val_accuracy: 0.9960\n",
      "Epoch 5/10\n",
      "250/250 [==============================] - 3s 13ms/step - loss: 0.0194 - accuracy: 0.9966 - val_loss: 0.0296 - val_accuracy: 0.9960\n",
      "Epoch 6/10\n",
      "250/250 [==============================] - 4s 14ms/step - loss: 0.0174 - accuracy: 0.9965 - val_loss: 0.0297 - val_accuracy: 0.9960\n",
      "Epoch 7/10\n",
      "250/250 [==============================] - 3s 13ms/step - loss: 0.0170 - accuracy: 0.9966 - val_loss: 0.0301 - val_accuracy: 0.9960\n",
      "Epoch 8/10\n",
      "250/250 [==============================] - 3s 14ms/step - loss: 0.0164 - accuracy: 0.9966 - val_loss: 0.0292 - val_accuracy: 0.9960\n",
      "Epoch 9/10\n",
      "250/250 [==============================] - 3s 13ms/step - loss: 0.0146 - accuracy: 0.9969 - val_loss: 0.0300 - val_accuracy: 0.9960\n",
      "Epoch 10/10\n",
      "250/250 [==============================] - 3s 14ms/step - loss: 0.0147 - accuracy: 0.9965 - val_loss: 0.0336 - 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": 19,
   "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": 20,
   "id": "4abe010c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63/63 [==============================] - 0s 5ms/step - loss: 0.0327 - accuracy: 0.9960\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.032689135521650314, 0.9959999918937683]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(x_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "33590a11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63/63 [==============================] - 1s 6ms/step\n"
     ]
    }
   ],
   "source": [
    "predictions = model.predict(x_test)\n",
    "predictions = tf.argmax(predictions, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "35530d57",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test = tf.argmax(y_test, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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",
      "           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       0.14      0.14      0.14      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": 20,
   "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": 21,
   "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": 22,
   "id": "660cbffa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 48ms/step\n",
      "1/1 [==============================] - 0s 31ms/step\n",
      "1/1 [==============================] - 0s 31ms/step\n",
      "1/1 [==============================] - 0s 47ms/step\n",
      "1/1 [==============================] - 0s 31ms/step\n",
      "1/1 [==============================] - 0s 30ms/step\n",
      "1/1 [==============================] - 0s 50ms/step\n",
      "1/1 [==============================] - 0s 55ms/step\n",
      "1/1 [==============================] - 0s 42ms/step\n",
      "1/1 [==============================] - 0s 37ms/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
}