{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "0f7e912d", "metadata": {}, "outputs": [ { "ename": "ModuleNotFoundError", "evalue": "No module named 'keras'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[1], line 6\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodel_selection\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m train_test_split\n\u001b[0;32m 5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpreprocessing\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m LabelEncoder\n\u001b[1;32m----> 6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpreprocessing\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtext\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Tokenizer\n\u001b[0;32m 7\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpreprocessing\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msequence\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pad_sequences\n\u001b[0;32m 8\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Sequential\n", "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'keras'" ] } ], "source": [ "import pandas as pd\n", "import re\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import LabelEncoder\n", "from keras.preprocessing.text import Tokenizer\n", "from keras.preprocessing.sequence import pad_sequences\n", "from keras.models import Sequential\n", "from keras.layers import Embedding, LSTM, Dense, Dropout, SpatialDropout1D\n", "from keras.utils import to_categorical\n", "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n", "\n", "# Step 1: Load the Dataset\n", "df = pd.read_csv('Twitter_Data.csv')\n", "\n", "# Step 2: Data Preprocessing\n", "def preprocess_text(text):\n", " text = re.sub(r\"http\\S+|www\\S+|https\\S+\", '', text, flags=re.MULTILINE) # Remove URLs\n", " text = re.sub(r'\\@\\w+|\\#', '', text) # Remove @mentions and hashtags\n", " text = re.sub(r'[^A-Za-z0-9 ]+', '', text) # Remove special characters\n", " text = text.lower() # Convert to lowercase\n", " return text\n", "\n", "df['text'] = df['text'].apply(preprocess_text)\n", "\n", "# Step 3: Convert Text to Sequences\n", "# Tokenization and padding\n", "tokenizer = Tokenizer(num_words=10000)\n", "tokenizer.fit_on_texts(df['text'])\n", "X = tokenizer.texts_to_sequences(df['text'])\n", "X = pad_sequences(X, maxlen=200)\n", "\n", "# Step 4: Prepare Target Variable\n", "# Encode labels\n", "le = LabelEncoder()\n", "y = le.fit_transform(df['sentiment'])\n", "y = to_categorical(y)\n", "\n", "# Step 5: Split the Dataset\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Step 6: Build the RNN Model\n", "model = Sequential()\n", "model.add(Embedding(input_dim=10000, output_dim=128, input_length=200))\n", "model.add(SpatialDropout1D(0.2)) # Adds spatial dropout to prevent overfitting\n", "model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2, return_sequences=True))\n", "model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))\n", "model.add(Dense(64, activation='relu'))\n", "model.add(Dropout(0.5)) # Additional dropout layer\n", "model.add(Dense(y.shape[1], activation='softmax'))\n", "\n", "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n", "\n", "# Step 7: Train the Model\n", "model.fit(X_train, y_train, epochs=10, batch_size=64, validation_split=0.2)\n", "\n", "# Step 8: Make Predictions\n", "y_pred = model.predict(X_test)\n", "y_pred_classes = np.argmax(y_pred, axis=1)\n", "y_test_classes = np.argmax(y_test, axis=1)\n", "\n", "# Evaluate the Model\n", "accuracy = accuracy_score(y_test_classes, y_pred_classes)\n", "print(f\"Accuracy: {accuracy}\")\n", "\n", "# Classification Report\n", "report = classification_report(y_test_classes, y_pred_classes, target_names=le.classes_)\n", "print(f\"Classification Report:\\n{report}\")\n", "\n", "# Confusion Matrix\n", "cm = confusion_matrix(y_test_classes, y_pred_classes)\n", "print(f\"Confusion Matrix:\\n{cm}\")\n", "\n", "# Step 9: Make Predictions on New Data\n", "new_tweets = [\"I love this!\", \"This is the worst.\"]\n", "new_tweets_processed = [preprocess_text(tweet) for tweet in new_tweets]\n", "new_tweets_sequences = tokenizer.texts_to_sequences(new_tweets_processed)\n", "new_tweets_padded = pad_sequences(new_tweets_sequences, maxlen=200)\n", "\n", "predictions = model.predict(new_tweets_padded)\n", "predicted_classes = le.inverse_transform(np.argmax(predictions, axis=1))\n", "print(f\"Predictions for new tweets: {predicted_classes}\")\n" ] } ], "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": "3.12.0" } }, "nbformat": 4, "nbformat_minor": 5 }