import tensorflow as tf
from tensorflow.keras.layers import TextVectorization,LSTM
import gradio as gr
import pandas as pd
import os

df = pd.read_csv('train.csv')

MAX_FEATURES = 200000 

vectorizer = TextVectorization(max_tokens=MAX_FEATURES,
                               output_sequence_length=1800,
                               output_mode='int')

# Adapt the vectorizer to the training data
vectorizer.adapt(df['comment_text'].values)

model = tf.keras.models.load_model('toxicity.keras')

def score_comment(comment):
    vectorized_comment = vectorizer([comment])
    results = model.predict(vectorized_comment)
    
    text = ''
    for idx, col in enumerate(df.columns[2:]):
        text += '{}: {}\n'.format(col, results[0][idx]>0.5)

    return text

interface = gr.Interface(fn=score_comment, 
                         inputs=gr.Textbox(lines=2, placeholder='Comment to score'),
                        outputs='text')

interface.launch(share=True)