tr.py

import os
import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
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
from huggingface_hub import push_to_hub_keras

# Environment variable for Hugging Face token
sac = os.getenv('accesstoken')

# 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

# 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')

# 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)

# Build the model
model = Sequential([
    Embedding(input_dim=1000, output_dim=16),
    GlobalAveragePooling1D(),
    Dense(16, activation='relu'),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train the model
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 with the correct filepath extension
model.save('my_custom_text_classifier.keras')
# tf.saved_model.save(model, "my_custom_text_classifier")

# Later, load the model and make predictions
loaded_model = tf.keras.models.load_model('my_custom_text_classifier.keras')
# loaded_model =tf.keras.layers.TFSMLayer("my_custom_text_classifier", call_endpoint="serving_default")


# 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 = model.predict(padded_sequences)
print(predictions)

push_to_hub_keras(
    model,
    repo_id="okeowo1014/kerascatanddog",
    commit_message="Initial commit",
    token=sac
)