preprocessing.py

import re
import string
import numpy as np
import torch
import unicodedata
import nltk

# Ensure NLTK stopwords are downloaded
nltk.download('stopwords')
from nltk.corpus import stopwords
stop_words = set(stopwords.words('russian', 'english'))

def data_preprocessing(text: str) -> str:

    text = text.lower()
    text = text.replace('-', ' ').replace('\n', ' ')

    text = re.sub('<.*?>', '', text)
    text = ''.join([c for c in text if unicodedata.category(c).startswith(('L', 'N', 'Z')) or c == "'"])
    text = ' '.join([word for word in text.split() if word.lower() not in stop_words])
    text = ' '.join([word for word in text.split() if not word.isdigit()])
    return text


def get_words_by_freq(sorted_words: list, n: int = 10) -> list:
    return list(filter(lambda x: x[1] > n, sorted_words))

def padding(review_int: list, seq_len: int) -> np.array: # type: ignore

    features = np.zeros((len(review_int), seq_len), dtype = int)
    for i, review in enumerate(review_int):
        if len(review) <= seq_len:
            zeros = list(np.zeros(seq_len - len(review)))
            new = zeros + review
        else:
            new = review[: seq_len]
        features[i, :] = np.array(new)
            
    return features

def preprocess_single_string(
    input_string: str, 
    seq_len: int, 
    vocab_to_int: dict,
    verbose : bool = False
    ) -> torch.tensor:


    preprocessed_string = data_preprocessing(input_string)
    result_list = []
    for word in preprocessed_string.split():
        try: 
            result_list.append(vocab_to_int[word])
        except KeyError as e:
            if verbose:
                print(f'{e}: not in dictionary!')
            pass
    result_padded = padding([result_list], seq_len)[0]

    return torch.tensor(result_padded)