Cleaning tweets

clean_tweet.py

import pandas as pd
import nltk 
nltk.download("stopwords")
from nltk.corpus import stopwords 
import string 
import re
# vectorizer
from sklearn.feature_extraction.text import CountVectorizer  

STOPWORDS = stopwords.words("english")

# HELPER FUNCTIONS 
def remove_stopwords(text):
    r""" Function to remove stopwords from tweets
    Parameters
    ----------
    text: str, input tweet 
    
    Return 
    ------
    str, cleared tweet
    """
    tweet_no_punct = [word for word in text.split() if not word in STOPWORDS]
    return ' '.join(tweet_no_punct)

def remove_punctuation(text):
    r""" Function to remove punctuation
    Parameters
    ----------
    text: str, input tweet 
    
    Return 
    ------
    str, cleared tweet"""
    outline = text.translate(str.maketrans('', '', string.punctuation))
    return outline

def remove_specific_chars(text):
    r""" Custom function to remove \n, \s+ or \' 
    Parameters
    ----------
    text: str, input tweet 
    
    Return 
    ------
    str, cleared tweet
    """
    # remove words after @
    outline = re.sub("@\S+ ", "", text) 
    # remove single quote
    outline = re.sub("\'", '', outline) 
    # remove new line
    outline = re.sub('\\n', '', outline)   
    return outline