Python Forum

I am a newbie to regular expressions. In google colaboratory, while doing an assignment on bag of words based on twitter dataset, I gave my code like this to modify the twitter tweets from the given dataset.

#Replacing 2 or more repetitions of character with the character itself
def replaceTwoOrMore(s):
    pattern = re.compile(r"(.)\1{1,}", re.DOTALL)
    return pattern.sub(r"\1\1", s)

def tweets_reconstruction(tweet):
  #Removing numbers
  tweet = re.sub('[0-9]', '', tweet)
  #Convert to lower case
  tweet = tweet.lower()
  tweet = tweet.translate(str.maketrans('', '', string.punctuation))
  #Replacing short URLs with ""
  tweet = re.sub(r"[\b(http)]+", "", tweet)
  #Replacing "@username" with "AT_USER"
  tweet = re.sub(r"[\b(@)]+", "AT_USER", tweet)
  #Replacing "#word" with "word"
  tweet = re.sub(r'#([^\s]+)', r'\1', tweet)
  #Replacing multiple whitespaces with single whitespace
  tweet = re.sub(r"[\s]+", " ", tweet)
  tweet = replaceTwoOrMore(tweet)
  return tweet

processedTweets = []
for tweet in tweets:
  processedTweets.append(tweets_reconstruction(tweet))

vectorizer = CountVectorizer()
featurevector = vectorizer.fit_transform(processedTweets)
featurevector.todense()

While running, it is showing "Session crashed after using all available RAM"
Please help me out.

Bhavika