app.py

import nltk 
import re
import pandas as pd
import numpy as np
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from nltk.tokenize import word_tokenize
from sklearn.feature_extraction.text import TfidfVectorizer
import gradio as gr
import joblib
from joblib import dump, load
import os

nltk.download('punkt')
nltk.download('punkt_tab')
nltk.download('stopwords')
nltk.download('wordnet')

def preprocess_text(text):
    text = text.lower()
    text = re.sub(r'[^a-zA-Z\s]', '', text)
    tokens = word_tokenize(text, language='english')
    stop_words = set(stopwords.words('english'))
    tokens = [word for word in tokens if word not in stop_words]
    lemmatizer = WordNetLemmatizer()
    tokens = [lemmatizer.lemmatize(word) for word in tokens]
    return ' '.join(tokens)

def custom_tokenizer(text):
    return text.split()

# Загрузка модели и векторайзера
loaded_model_nb = load('best_nb_model.joblib')
loaded_vectorizer = load('tfidf_vectorizer.joblib')

def predict_sentiment(text):
    # Предобработка текста
    processed_text = preprocess_text(text)
    # Векторизация
    X = loaded_vectorizer.transform([processed_text])
    # Предсказание
    prediction = loaded_model_nb.predict(X)[0]
    return "Положительный" if prediction == 1 else "Отрицательный"

iface = gr.Interface(
    fn=predict_sentiment,
    inputs=gr.Textbox(lines=3, placeholder="Введите отзыв на английском..."),
    outputs="label",
    title="Анализатор отзывов о ресторанах",
    # examples=["The food was amazing!", "Service was terrible."]  ← закомментировать
)
iface.launch(ssr_mode=False)