stop_words.py

import pandas as pd


def load_stopwords(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        stopwords = f.read().splitlines()  # Her satır bir stopword olacak şekilde yükle
    return set(stopwords)


stop_words = load_stopwords('stopwords.txt')


df = pd.read_csv('veriler_cleaned.csv')


def remove_stopwords_without_nltk(text):
    if isinstance(text, str):  
        words = text.split()  
        filtered_words = [word for word in words if word.lower() not in stop_words]  
        return ' '.join(filtered_words)  
    else:
        return ""  


df['stopwords_text'] = df['cleaned_text'].apply(remove_stopwords_without_nltk)


print(df[['cleaned_text', 'stopwords_text']].head())


df.to_csv('temizlenmis_veri.csv', index=False)




"""
import pandas as pd
import nltk
from nltk.tokenize import word_tokenize

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


from nltk.corpus import stopwords
stop_words = set(stopwords.words('turkish'))

def load_custom_stopwords(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        custom_stopwords = f.read().splitlines()
    return set(custom_stopwords)


custom_stopwords = load_custom_stopwords('stopwords.txt')
stop_words.update(custom_stopwords)


df = pd.read_csv('veriler_cleaned.csv')


def remove_stopwords(text):
    if isinstance(text, str): 
        words = word_tokenize(text)  
        filtered_words = [word for word in words if word.lower() not in stop_words]  # Stopwords'leri çıkar
        return ' '.join(filtered_words)  
    else:
        return ""  


df['stopwords_text'] = df['cleaned_text'].apply(remove_stopwords)


print(df[['cleaned_text', 'stopwords_text']].head())


df.to_csv('temizlenmis_veri.csv', index=False)
"""