strim_nlp.py

import streamlit as st
import pandas as pd
import catboost
from catboost import CatBoostClassifier
import re
import string
from nltk.corpus import stopwords
from pymystem3 import Mystem
from joblib import load  
import nltk

def data_preprocessing(text):
    stop_words = set(stopwords.words('russian'))
    text = text.lower()
    text = re.sub("<.*?>", "", text)
    text = re.sub(r'http\S+', " ", text)
    text = re.sub(r'@\w+', ' ', text)
    text = re.sub(r'#\w+', ' ', text)
    text = re.sub(r'\d+', ' ', text)
    text = "".join([c for c in text if c not in string.punctuation])
    return " ".join([word for word in text.split() if word not in stop_words])

def lemmatize_text(text):
    mystem = Mystem()
    lemmas = mystem.lemmatize(text)
    return ' '.join(lemmas)

model = CatBoostClassifier()
model.load_model('cat_model4.cbm')

tfidf_vectorizer = load('tfidf_vectorizer.joblib')

def classic_ml_page():
    st.title("Классификация отзывов о медицинских учреждениях")
    user_review = st.text_area("Введите ваш отзыв здесь:")

    if st.button("Классифицировать"):
        if user_review:
            preprocessed_review = data_preprocessing(user_review)
            lemmatized_review = lemmatize_text(preprocessed_review)
            vectorized_review = tfidf_vectorizer.transform([lemmatized_review])
            prediction = model.predict(vectorized_review)
            
            if prediction[0] == 1:
                st.write("Позитивный отзыв 😀")
            else:
                st.write("Негативный отзыв 😟")
        else:
            st.write("Пожалуйста, введите отзыв для классификации.")