toxic1.py

# toxic.py
import streamlit as st
import numpy as np
import pandas as pd
import time
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Ensure your model and tokenizer paths are correct and accessible by the Streamlit app.
# Since you're importing this into another file, relative or absolute paths might need to be updated accordingly.
model_t_checkpoint = 'cointegrated/rubert-tiny-toxicity'
tokenizer_t = AutoTokenizer.from_pretrained(model_t_checkpoint)
model_t = AutoModelForSequenceClassification.from_pretrained(model_t_checkpoint)

def text2toxicity(text, aggregate=True):
    with torch.no_grad():
        inputs = tokenizer_t(text, return_tensors='pt', truncation=True, padding=True).to('cpu')
        proba = torch.sigmoid(model_t(**inputs).logits).cpu().numpy()
    if isinstance(text, str):
        proba = proba[0]
    if aggregate:
        return 1 - proba.T[0] * (1 - proba.T[-1])
    return proba

def toxicity_page():
    st.title("""
    Определим токсичный комментарий или нет
    """)

    user_text_input = st.text_area('Введите ваш отзыв здесь:')

    if st.button('Предсказать'):
        start_time = time.time()
        proba = text2toxicity(user_text_input, True)
        end_time = time.time()
        prediction_time = end_time - start_time

        if proba >= 0.5:
            st.write(f'Степень токсичности комментария: {round(proba, 2)} – комментарий токсичный.')
        else:
            st.write(f'Степень токсичности комментария: {round(proba, 2)} – комментарий не токсичный.')
        st.write(f'Время предсказания: {prediction_time:.4f} секунд')