Upload bert.py

bert.py

@@ -0,0 +1,64 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from transformers import BertTokenizer, TFBertForSequenceClassification
+import tensorflow as tf
+
+# Load preprocessed data
+def load_data(file_path="preprocessed_reviews.csv"):
+    return pd.read_csv("preprocessed_reviews.csv")
+
+# Tokenize text using BERT tokenizer
+
+def tokenize_text(tokenizer, texts, max_length):
+    encodings = tokenizer(texts.tolist(), padding=True, truncation=True, max_length=max_length, return_tensors="tf")
+    # Convert BatchEncoding to dictionary
+    encodings_dict = {key: value.numpy() for key, value in encodings.items()}
+    return encodings_dict
+
+
+if __name__ == "__main__":
+    # Load preprocessed data
+    data = load_data("preprocessed_reviews.csv")
+
+    # Check if 'sentiment' column exists
+    if 'sentiment' in data.columns:
+        # Split data into train and validation sets
+        train_data, val_data = train_test_split(data, test_size=0.2, random_state=42)
+
+        # Tokenize text using BERT tokenizer
+        max_length = 128
+        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+        train_inputs = tokenize_text(tokenizer, train_data['clean_text'], max_length)
+        val_inputs = tokenize_text(tokenizer, val_data['clean_text'], max_length)
+
+        # Convert 'sentiment' column to numerical format
+        num_labels = len(data['sentiment'].unique())
+        train_labels = train_data['sentiment'].astype('category').cat.codes.values
+        val_labels = val_data['sentiment'].astype('category').cat.codes.values
+
+        # Fine-tuning BERT model for sequence classification
+        model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=num_labels)
+        optimizer = tf.keras.optimizers.Adam(learning_rate=2e-5)
+        loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
+        metrics = ['accuracy']
+        model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
+
+        # Train the model
+        history = model.fit(
+            train_inputs,
+            train_labels,
+            validation_data=(val_inputs, val_labels),
+            epochs=3,
+            batch_size=32,
+            verbose=1
+        )
+
+        # Evaluate the model
+        loss, accuracy = model.evaluate(val_inputs, val_labels)
+        print(f'Validation loss: {loss}, Validation accuracy: {accuracy}')
+
+        # Save the trained model
+        model.save_pretrained('fine_tuned_bert_model')
+
+    else:
+        raise ValueError("The 'sentiment' column is not found in the DataFrame.")