Update tr.py

tr.py

@@ -1,33 +1,49 @@
-import tensorflow as tf
-from tensorflow.keras.layers import Dense, Embedding, GlobalAveragePooling1D
+import numpy as np
 from tensorflow.keras.models import Sequential
-from transformers import AutoTokenizer, TFAutoModelForSequenceClassification, pipeline
+from tensorflow.keras.layers import Dense, Embedding, GlobalAveragePooling1D
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from sklearn.model_selection import train_test_split
 
 # Sample data for sentiment analysis
 texts = ["I love deep learning!", "I hate Mondays.", "This movie is fantastic.", "The weather is terrible."]
+labels = np.array([1, 0, 1, 0])  # 1 for positive sentiment, 0 for negative sentiment
 
-labels = [1, 0, 1, 0]  # 1 for positive sentiment, 0 for negative sentiment
+# Tokenize the texts
+tokenizer = Tokenizer(num_words=1000, oov_token='<OOV>')
+tokenizer.fit_on_texts(texts)
+sequences = tokenizer.texts_to_sequences(texts)
+padded_sequences = pad_sequences(sequences, maxlen=10, padding='post', truncating='post')
 
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
-model = TFAutoModelForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(padded_sequences, labels, test_size=0.2, random_state=42)
 
-# Tokenize the texts
-inputs = tokenizer(texts, padding=True, truncation=True, return_tensors='tf')
+# Build the model
+model = Sequential([
+    Embedding(input_dim=1000, output_dim=16, input_length=10),
+    GlobalAveragePooling1D(),
+    Dense(16, activation='relu'),
+    Dense(1, activation='sigmoid')
+])
 
-# Compile the model
-model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
 
 # Train the model
-model.fit(inputs, labels, epochs=3, batch_size=2)
+model.fit(X_train, y_train, epochs=5, batch_size=2)
+
+# Evaluate the model
+loss, accuracy = model.evaluate(X_test, y_test)
+print(f'Accuracy: {accuracy * 100:.2f}%')
 
-# Save the model to Hugging Face Model Hub
-model.save_pretrained("./my-text-classifier")
+# Save the model
+model.save('my_custom_text_classifier')
 
-# Load the saved model from disk
-loaded_model = TFAutoModelForSequenceClassification.from_pretrained("./my-text-classifier")
+# Later, load the model and make predictions
+loaded_model = tf.keras.models.load_model('my_custom_text_classifier')
 
-# Use the loaded model for prediction
-classifier = pipeline('text-classification', model=loaded_model, tokenizer=tokenizer)
-result = classifier("I'm feeling great!")
-print(result)
+# Example prediction
+new_texts = ["I'm feeling great!", "This book is boring."]
+sequences = tokenizer.texts_to_sequences(new_texts)
+padded_sequences = pad_sequences(sequences, maxlen=10, padding='post', truncating='post')
+predictions = loaded_model.predict(padded_sequences)
+print(predictions)