{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import re\n",
        "import nltk\n",
        "from nltk.corpus import stopwords\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import accuracy_score, f1_score, classification_report\n",
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.text import Tokenizer\n",
        "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, LSTM, Dense, Dropout\n",
        "from tensorflow.keras.layers import SpatialDropout1D, MaxPooling1D, Bidirectional, BatchNormalization\n",
        "from tensorflow.keras.regularizers import l2\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau"
      ],
      "metadata": {
        "id": "sRGxb_uPDjvI"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Download the dataset directly to Colab (very fast)\n",
        "!wget http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz\n",
        "\n",
        "#  Extract the new file\n",
        "!tar -xf aclImdb_v1.tar.gz"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DN0rTQ2gDlS7",
        "outputId": "21292565-ce05-4262-e0a7-c8ea459af25f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2026-03-29 22:38:22--  http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz\n",
            "Resolving ai.stanford.edu (ai.stanford.edu)... 171.64.68.10\n",
            "Connecting to ai.stanford.edu (ai.stanford.edu)|171.64.68.10|:80... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 84125825 (80M) [application/x-gzip]\n",
            "Saving to: ‘aclImdb_v1.tar.gz’\n",
            "\n",
            "aclImdb_v1.tar.gz   100%[===================>]  80.23M  19.0MB/s    in 7.6s    \n",
            "\n",
            "2026-03-29 22:38:30 (10.5 MB/s) - ‘aclImdb_v1.tar.gz’ saved [84125825/84125825]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "def load_imdb_from_folders(base_path):\n",
        "    data = []\n",
        "    # Loop through 'train' and 'test' folders\n",
        "    for split in ['train', 'test']:\n",
        "        # Loop through 'pos' and 'neg' subfolders\n",
        "        for sentiment in ['pos', 'neg']:\n",
        "            folder_path = os.path.join(base_path, split, sentiment)\n",
        "            label = 1 if sentiment == 'pos' else 0\n",
        "\n",
        "            # Read each .txt file in the folder\n",
        "            for filename in os.listdir(folder_path):\n",
        "                if filename.endswith(\".txt\"):\n",
        "                    with open(os.path.join(folder_path, filename), 'r', encoding='utf-8') as f:\n",
        "                        review = f.read()\n",
        "                        data.append([review, label])\n",
        "\n",
        "    return pd.DataFrame(data, columns=['review', 'sentiment'])\n",
        "\n",
        "# Set the path to your main folder (the one containing train/ and test/)\n",
        "# Example: base_path = 'aclImdb'\n",
        "df = load_imdb_from_folders('/content/aclImdb')"
      ],
      "metadata": {
        "id": "uOcbxMVovye9"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(df.shape)\n",
        "print(df['sentiment'].value_counts())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ahvc2Ltkvz2h",
        "outputId": "b9b27fe3-0568-4b36-d5af-d6a030808c19"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(50000, 2)\n",
            "sentiment\n",
            "1    25000\n",
            "0    25000\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "nltk.download('stopwords')\n",
        "stop_words = set(stopwords.words('english'))\n",
        "\n",
        "def clean_text(text):\n",
        "    text = re.sub(r'<.*?>', '', text) # Remove HTML\n",
        "    text = re.sub(r'[^a-zA-Z\\s]', '', text) # Remove non-alpha\n",
        "    text = text.lower().strip()\n",
        "    text = \" \".join([word for word in text.split() if word not in stop_words])\n",
        "    return text\n",
        "\n",
        "df['review'] = df['review'].apply(clean_text)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EUxHsyfUx1df",
        "outputId": "4ebef0e3-2911-446e-d2f0-772613e214dc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Unzipping corpora/stopwords.zip.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "# This line creates the X_train, X_test, y_train, and y_test variables\n",
        "# It takes the 'X' and 'y' we created during the padding step\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
        "\n",
        "print(\"Data split successfully!\")\n",
        "print(f\"Training samples: {len(X_train)}\")\n",
        "print(f\"Testing samples: {len(X_test)}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZdV-tiTh0viw",
        "outputId": "0ee49cc0-4096-468b-dd8b-d6e1f7bb29ba"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Data split successfully!\n",
            "Training samples: 40000\n",
            "Testing samples: 10000\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "\n",
        "vocab_size = 10000\n",
        "max_length = 250\n",
        "\n",
        "tokenizer = Tokenizer(num_words=vocab_size, oov_token=\"<OOV>\")\n",
        "tokenizer.fit_on_texts(df['review'])\n",
        "\n",
        "X = pad_sequences(tokenizer.texts_to_sequences(df['review']), maxlen=max_length)\n",
        "y = df['sentiment'].values"
      ],
      "metadata": {
        "id": "r5ArbaSXx6MM"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Improved Hybrid Model Design\n",
        "model = Sequential([\n",
        "    Embedding(vocab_size, 128, input_length=max_length),\n",
        "    SpatialDropout1D(0.3),\n",
        "\n",
        "    # CNN Layer for local feature extraction\n",
        "    Conv1D(64, kernel_size=3, padding='same', activation='relu'),\n",
        "    BatchNormalization(),\n",
        "\n",
        "    # Use MaxPooling1D to reduce size while keeping the sequence for the LSTM\n",
        "    MaxPooling1D(pool_size=2),\n",
        "\n",
        "    # Bidirectional LSTM for context\n",
        "    # return_sequences=False ensures the output is rank 2 (batch, units)\n",
        "    Bidirectional(LSTM(64, dropout=0.2, recurrent_dropout=0.2, return_sequences=False)),\n",
        "    BatchNormalization(),\n",
        "\n",
        "    Dense(64, activation='relu', kernel_regularizer=l2(0.001)),\n",
        "    Dropout(0.5),\n",
        "    Dense(1, activation='sigmoid') # Output will now be rank 2 (batch, 1)\n",
        "])"
      ],
      "metadata": {
        "id": "YeM3tcBXx9bW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Callbacks for Fine-Tuning\n",
        "callbacks = [\n",
        "    EarlyStopping(monitor='val_loss', patience=2, restore_best_weights=True),\n",
        "    ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=1, min_lr=1e-7)\n",
        "]\n",
        "\n",
        "model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
        "\n",
        "# --- TRAINING ---\n",
        "# Ensure X_train, y_train, X_test, y_test are defined from the previous split\n",
        "history=model.fit(X_train, y_train,\n",
        "          epochs=30,\n",
        "          batch_size=32,\n",
        "          validation_data=(X_test, y_test),\n",
        "          callbacks=callbacks)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TZCQYZiv1G7G",
        "outputId": "4b9c1777-53df-4774-ce59-a1f8ba4a82ea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/30\n",
            "\u001b[1m1250/1250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m428s\u001b[0m 334ms/step - accuracy: 0.8969 - loss: 0.2825 - val_accuracy: 0.8908 - val_loss: 0.2768 - learning_rate: 0.0010\n",
            "Epoch 2/30\n",
            "\u001b[1m1250/1250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m418s\u001b[0m 334ms/step - accuracy: 0.9275 - loss: 0.2040 - val_accuracy: 0.8845 - val_loss: 0.2940 - learning_rate: 0.0010\n",
            "Epoch 3/30\n",
            "\u001b[1m1250/1250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m440s\u001b[0m 332ms/step - accuracy: 0.9632 - loss: 0.1155 - val_accuracy: 0.8884 - val_loss: 0.3802 - learning_rate: 2.0000e-04\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x78df948abfe0>"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class ManualHistory:\n",
        "    def __init__(self):\n",
        "        self.history = {\n",
        "            'accuracy': [0.8969, 0.9275, 0.9632],\n",
        "            'loss': [0.2825, 0.2040, 0.1155],\n",
        "            'val_accuracy': [0.8908, 0.8845, 0.8884],\n",
        "            'val_loss': [0.2768, 0.2940, 0.3802]\n",
        "        }\n",
        "\n",
        "# Define the variable manually so the plotting code can find it\n",
        "history = ManualHistory()"
      ],
      "metadata": {
        "id": "r4TuTavcCOVg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "acc = history.history['accuracy']\n",
        "val_acc = history.history['val_accuracy']\n",
        "loss = history.history['loss']\n",
        "val_loss = history.history['val_loss']\n",
        "epochs = range(1, len(acc) + 1)\n",
        "\n",
        "plt.figure(figsize=(14, 5))\n",
        "\n",
        "# Accuracy Plot\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(epochs, acc, 'b-o', label='Training Accuracy')\n",
        "plt.plot(epochs, val_acc, 'r-o', label='Validation Accuracy')\n",
        "plt.title('Training and Validation Accuracy')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "\n",
        "# Loss Plot\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(epochs, loss, 'b-o', label='Training Loss')\n",
        "plt.plot(epochs, val_loss, 'r-o', label='Validation Loss')\n",
        "plt.title('Training and Validation Loss')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 376
        },
        "id": "gRG58FqIDbEr",
        "outputId": "bcb877b5-6f5f-4ec3-ee4b-1c3c1cf5f009"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "A734FQqNDdk0"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}