full process for cleaning tweets

clean_tweet2.py

tweets_df = pd.read_csv("split-data/X_train.csv")
target_df = pd.read_csv("split-data/y_train.csv")
# PREPROCESS
# drop the info we're not going to use 
# id, date, flag 
tweets_df.drop(columns=['ids', 'date', 'flag'], inplace=True)
# start the cleaning process 
# lower text 
tweets_df.loc[:,'lower_text'] = tweets_df['text'].str.lower() 
# remove stopwords 
tweets_df.loc[:,'clean_text1'] = tweets_df['lower_text'].apply(remove_stopwords)
# remove puncts 
tweets_df.loc[:,'clean_text2'] = tweets_df['clean_text1'].apply(remove_specific_chars)
# remove chars 
tweets_df.loc[:,'clean_text3'] = tweets_df['clean_text2'].apply(remove_punctuation)