app.py

import gradio as gr
import tensorflow as tf
import pandas as pd

from tensorflow.keras.layers import TextVectorization

MAX_WORDS = 200000

df = pd.read_csv(os.path.join('.', 'dataset', 'train.csv'))
X = df['comment_text']

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

vectorizer.adapt(X.values)

model = tf.keras.models.load_model('toxicity.h5')

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()