import gradio as gr
import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import imdb

word_to_index = imdb.get_word_index()

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

# Define a function to make predictions
def predict_sentiment(user_input, number_of_words, words_per_view):
    # Encode the input text
    words = user_input.split()
    encoded_word = np.zeros(words_per_view).astype(int)
    encoded_word[words_per_view - len(words) - 1] = 1
    for i, word in enumerate(words):
        index = words_per_view - len(words) + i
        encoded_word[index] = word_to_index.get(word, 0) + 3
    encoded_word = np.expand_dims(encoded_word, axis=0)
    
    # Make the prediction
    prediction = loaded_model.predict(encoded_word)[0][0]
    
    # Return the sentiment label
    if prediction > 0.5:
        return "Positive"
    else:
        return "Negative"

# Create the Gradio interface
iface = gr.Interface(
    fn=predict_sentiment,
    inputs=["textbox", gr.inputs.NumberRange(minimum=1, maximum=10000, default=3000, label="Number of words"), gr.inputs.NumberRange(minimum=1, maximum=100, default=30, label="Words per view")],
    outputs="text",
    title="Sentiment Analysis",
    description="Enter a text and get the sentiment prediction"
)

# Launch the interface
iface.launch()