{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dd93c4f2-d64a-4148-9673-cd749392b11d",
   "metadata": {},
   "source": [
    "# Practical-2b (Classification using Deep Neural Network - IMDB Dataset)\n",
    "\n",
    "---\n",
    "\n",
    "Problem Statement: Binary classification using Deep Neural Networks Example: Classify movie reviews into positive\" reviews and \"negative\" reviews, just based on the text content of the reviews. Use IMDB dataset\n",
    "\n",
    "- Dataset link: https://www.kaggle.com/datasets/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews\n",
    "- Dataset available in [Datasets](https://git.kska.io/sppu-be-comp-content/DeepLearning/src/branch/main/Datasets/) directory.\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0a8eeb31-1a70-45b4-93f1-2611c5d612d3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "I0000 00:00:1777813310.532586   61345 cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.\n",
      "I0000 00:00:1777813310.578090   61345 cpu_feature_guard.cc:227] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "I0000 00:00:1777813312.920697   61345 cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.\n"
     ]
    }
   ],
   "source": [
    "# 1. Import Libraries\n",
    "import re\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.metrics import confusion_matrix, classification_report\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense, Embedding, GlobalAveragePooling1D\n",
    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
    "from tensorflow.keras.preprocessing.sequence import pad_sequences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2cec2b8a-0371-4884-b17b-cd909a4b1b72",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                              review sentiment\n",
      "0  One of the other reviewers has mentioned that ...  positive\n",
      "1  A wonderful little production. <br /><br />The...  positive\n",
      "2  I thought this was a wonderful way to spend ti...  positive\n",
      "3  Basically there's a family where a little boy ...  negative\n",
      "4  Petter Mattei's \"Love in the Time of Money\" is...  positive\n"
     ]
    }
   ],
   "source": [
    "# 2. Load Dataset\n",
    "data = pd.read_csv('IMDB Dataset.csv')\n",
    "print(data.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "dfed9c66",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (50000, 2)\n",
      "\n",
      "Missing Values:\n",
      " review       0\n",
      "sentiment    0\n",
      "dtype: int64\n",
      "\n",
      "Class Distribution:\n",
      " sentiment\n",
      "positive    25000\n",
      "negative    25000\n",
      "Name: count, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Sample positive review:\n",
      " One of the other reviewers has mentioned that after watching just 1 Oz episode you'll be hooked. They are right, as this is exactly what happened with me.<br /><br />The first thing that struck me about Oz was its brutality and unflinching scenes of violence, which set in right from the word GO. Tru\n",
      "\n",
      "Sample negative review:\n",
      " Basically there's a family where a little boy (Jake) thinks there's a zombie in his closet & his parents are fighting all the time.<br /><br />This movie is slower than a soap opera... and suddenly, Jake decides to become Rambo and kill the zombie.<br /><br />OK, first of all when you're going to ma\n"
     ]
    }
   ],
   "source": [
    "# 3. Exploratory Data Analysis (EDA)\n",
    "print(\"Shape:\", data.shape)\n",
    "print(\"\\nMissing Values:\\n\", data.isnull().sum())\n",
    "print(\"\\nClass Distribution:\\n\", data['sentiment'].value_counts())\n",
    "\n",
    "# Visualize class distribution\n",
    "sns.countplot(x='sentiment', data=data)\n",
    "plt.title('Sentiment Class Distribution')\n",
    "plt.show()\n",
    "\n",
    "# Sample reviews\n",
    "print(\"\\nSample positive review:\\n\", data[data['sentiment'] == 'positive']['review'].iloc[0][:300])\n",
    "print(\"\\nSample negative review:\\n\", data[data['sentiment'] == 'negative']['review'].iloc[0][:300])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4ae3e31b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sample cleaned review:\n",
      " one of the other reviewers has mentioned that after watching just 1 oz episode you'll be hooked. they are right, as this is exactly what happened with me.the first thing that struck me about oz was its brutality and unflinching scenes of violence, which set in right from the word go. trust me, this \n"
     ]
    }
   ],
   "source": [
    "# 4. Data Cleaning - Strip HTML Tags\n",
    "def clean_text(text):\n",
    "    text = re.sub(r'<.*?>', '', text)   # remove HTML tags like <br />\n",
    "    text = text.lower().strip()         # lowercase and trim whitespace\n",
    "    return text\n",
    "\n",
    "data['review'] = data['review'].apply(clean_text)\n",
    "print(\"Sample cleaned review:\\n\", data['review'].iloc[0][:300])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9e041a03-e7a7-42ab-a691-f47ba275053e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 5. Encode Labels and Separate Features\n",
    "label_encoder = LabelEncoder()\n",
    "data['sentiment'] = label_encoder.fit_transform(data['sentiment'])  # positive=1, negative=0\n",
    "\n",
    "X = data['review'].values    # input: review text\n",
    "y = data['sentiment'].values # output: 0 or 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "05290c03-55b1-4110-a43d-4a80d85afba8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 6. Tokenize and Pad Text Sequences\n",
    "vocab_size = 10000   # keep only top 10,000 most frequent words\n",
    "max_length = 200     # truncate/pad all reviews to 200 words\n",
    "\n",
    "tokenizer = Tokenizer(num_words=vocab_size, oov_token='<OOV>')  # <OOV> handles unknown words\n",
    "tokenizer.fit_on_texts(X)                        # build word index from training text\n",
    "\n",
    "sequences = tokenizer.texts_to_sequences(X)      # convert each word to its integer index\n",
    "padded_sequences = pad_sequences(sequences, maxlen=max_length,\n",
    "                                 padding='post', truncating='post')  # pad/truncate to fixed length"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "bb7a6674-014b-4794-b379-1dcd86fa4372",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 7. Split into Training and Testing Sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(padded_sequences, y, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b17621cf-a2de-4547-ba38-abd75b0ac971",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ embedding (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>)           │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling1d        │ ?                      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling1D</span>)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ embedding (\u001b[38;5;33mEmbedding\u001b[0m)           │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling1d        │ ?                      │             \u001b[38;5;34m0\u001b[0m │\n",
       "│ (\u001b[38;5;33mGlobalAveragePooling1D\u001b[0m)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 8. Build the Neural Network Model\n",
    "model = Sequential()\n",
    "model.add(Embedding(vocab_size, 16))        # maps each word index to a 16-dim vector\n",
    "model.add(GlobalAveragePooling1D())          # averages all word vectors into one vector\n",
    "model.add(Dense(24, activation='relu'))      # hidden layer: 24 neurons\n",
    "model.add(Dense(1, activation='sigmoid'))    # output: probability between 0 and 1 (binary)\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "66306231-6f10-4f8f-a7b9-eaee2755d0e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 9. Compile the Model\n",
    "# binary_crossentropy: standard loss for binary classification; sigmoid output\n",
    "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "18ddd713-c2fc-4514-82ee-adc9efd5586d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9491 - loss: 0.1434 - val_accuracy: 0.8649 - val_loss: 0.3963\n",
      "Epoch 2/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9538 - loss: 0.1357 - val_accuracy: 0.8525 - val_loss: 0.4348\n",
      "Epoch 3/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9557 - loss: 0.1311 - val_accuracy: 0.8566 - val_loss: 0.4351\n",
      "Epoch 4/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9588 - loss: 0.1232 - val_accuracy: 0.8304 - val_loss: 0.4906\n",
      "Epoch 5/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9587 - loss: 0.1214 - val_accuracy: 0.8580 - val_loss: 0.4798\n",
      "Epoch 6/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9625 - loss: 0.1131 - val_accuracy: 0.8553 - val_loss: 0.5034\n",
      "Epoch 7/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9643 - loss: 0.1104 - val_accuracy: 0.8559 - val_loss: 0.5165\n",
      "Epoch 8/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9676 - loss: 0.1022 - val_accuracy: 0.8465 - val_loss: 0.5404\n",
      "Epoch 9/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9701 - loss: 0.0982 - val_accuracy: 0.8549 - val_loss: 0.5504\n",
      "Epoch 10/10\n",
      "\u001b[1m1000/1000\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3ms/step - accuracy: 0.9699 - loss: 0.0954 - val_accuracy: 0.8445 - val_loss: 0.6037\n"
     ]
    }
   ],
   "source": [
    "# 10. Train the Model\n",
    "history = model.fit(X_train, y_train, epochs=10, batch_size=32, validation_split=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "9bd99de0-c460-4da1-8e15-62f20ec22c5c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8494 - loss: 0.5875\n",
      "Test Loss: 0.5875\n",
      "Test Accuracy: 84.94%\n"
     ]
    }
   ],
   "source": [
    "# 11. Evaluate the Model on Test Data\n",
    "loss, accuracy = model.evaluate(X_test, y_test)\n",
    "print(f\"Test Loss: {loss:.4f}\")\n",
    "print(f\"Test Accuracy: {accuracy*100:.2f}%\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f34119f9-0b0c-4c92-8777-f170ceb3aa77",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 12. Plot Training vs Validation Accuracy\n",
    "plt.plot(history.history['accuracy'], label='Training Accuracy')\n",
    "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
    "plt.title('Model Accuracy Over Epochs')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.xlabel('Epoch')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()\n",
    "\n",
    "# 13. Plot Training vs Validation Loss\n",
    "plt.plot(history.history['loss'], label='Training Loss')\n",
    "plt.plot(history.history['val_loss'], label='Validation Loss')\n",
    "plt.title('Model Loss Over Epochs')\n",
    "plt.ylabel('Loss')\n",
    "plt.xlabel('Epoch')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "353c4724-fc92-4a86-8d88-dc9f4f95cd47",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1ms/step\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "    Negative       0.84      0.86      0.85      4961\n",
      "    Positive       0.86      0.84      0.85      5039\n",
      "\n",
      "    accuracy                           0.85     10000\n",
      "   macro avg       0.85      0.85      0.85     10000\n",
      "weighted avg       0.85      0.85      0.85     10000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# 14. Confusion Matrix and Classification Report\n",
    "y_pred = (model.predict(X_test) > 0.5).astype(int)  # threshold 0.5: prob > 0.5 = positive\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
    "            xticklabels=['Negative', 'Positive'],\n",
    "            yticklabels=['Negative', 'Positive'])\n",
    "plt.title('Confusion Matrix')\n",
    "plt.ylabel('Actual')\n",
    "plt.xlabel('Predicted')\n",
    "plt.show()\n",
    "\n",
    "print(\"\\nClassification Report:\\n\", classification_report(y_test, y_pred, target_names=['Negative', 'Positive']))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a09416f-2a29-4769-9b8e-bbb6d6f29e67",
   "metadata": {},
   "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": "3.12.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}