app.py

import gradio as gr
import tensorflow as tf
import numpy as np

# Define a function to preprocess the text input
def preprocess(text):
    tokenizer = tf.keras.preprocessing.text.Tokenizer()
    tokenizer.fit_on_texts([text])
    text = tokenizer.texts_to_sequences([text])
    text = tf.keras.preprocessing.sequence.pad_sequences(text, maxlen=500, padding='post', truncating='post')
    return text

# Load the pre-trained model
model = tf.keras.models.load_model('sentimentality.h5')

# Define a function to make a prediction on the input text
def predict_sentiment(text):
    # Preprocess the text
    text = preprocess(text)
    # Make a prediction using the loaded model
    proba = model.predict(text)[0]
    # Normalize the probabilities
    proba /= proba.sum()
    # Get the predicted sentiment label
    sentiment_label = ['Positive', 'Negative', 'Neutral'][np.argmax(proba)]
    # Determine the color based on the sentiment label
    if sentiment_label == 'Positive':
        color = '#2a9d8f'
    elif sentiment_label == 'Negative':
        color = '#e76f51'
    else:
        color = '#264653'
    # Return the sentiment label and color
    return {'label': sentiment_label, 'color': color}

# Define the Gradio interface
iface = gr.Interface(
    fn=predict_sentiment,
    inputs=gr.inputs.Textbox(label='Enter text here'),
    outputs=gr.outputs.Label(label='Sentiment', value='Neutral', 
                             font_size=30, font_family='Arial', 
                             background_color='#f8f8f8', 
                             color='black'),
    title='SENTIMENT ANALYSIS'
)

# Launch the interface
iface.launch()