app.py

import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.preprocessing import LabelEncoder
import gradio as gr
import pickle
import os

# Load model and tokenizer
model = tf.keras.models.load_model('sentiment_rnn.h5')

# Load tokenizer
with open('tokenizer.pkl', 'rb') as f:
    tokenizer = pickle.load(f)

# Initialize label encoder
label_encoder = LabelEncoder()
label_encoder.fit(["Happy", "Sad", "Neutral"])

def predict_sentiment(text):
    """
    Predict sentiment for a given text
    """
    # Preprocess the text
    sequence = tokenizer.texts_to_sequences([text])
    padded = pad_sequences(sequence, maxlen=50)
    
    # Make prediction
    prediction = model.predict(padded, verbose=0)[0]
    predicted_class = np.argmax(prediction)
    sentiment = label_encoder.inverse_transform([predicted_class])[0]
    confidence = float(prediction[predicted_class])
    
    # Create confidence dictionary for all classes
    confidences = {
        "Happy": float(prediction[0]),
        "Sad": float(prediction[1]),
        "Neutral": float(prediction[2])
    }
    
    return sentiment, confidences

# Create Gradio interface
with gr.Blocks(title="Sentiment Analysis with RNN") as demo:
    gr.Markdown("# Sentiment Analysis with RNN")
    gr.Markdown("Enter text to analyze its sentiment (Happy, Sad, or Neutral)")
    
    with gr.Row():
        text_input = gr.Textbox(label="Input Text", placeholder="Type your text here...")
        sentiment_output = gr.Label(label="Predicted Sentiment")
        confidence_output = gr.Label(label="Confidence Scores")
    
    submit_btn = gr.Button("Analyze Sentiment")
    
    examples = gr.Examples(
        examples=[
            ["I'm feeling great today!"],
            ["My dog passed away..."],
            ["The office is closed tomorrow."],
            ["This is the best day ever!"],
            ["I feel miserable."],
            ["There are 12 books on the shelf."]
        ],
        inputs=text_input
    )
    
    def analyze_text(text):
        sentiment, confidences = predict_sentiment(text)
        return sentiment, confidences
    
    submit_btn.click(
        fn=analyze_text,
        inputs=text_input,
        outputs=[sentiment_output, confidence_output]
    )
    
    text_input.submit(
        fn=analyze_text,
        inputs=text_input,
        outputs=[sentiment_output, confidence_output]
    )

# Launch the app
if __name__ == "__main__":
    demo.launch()