sarcasm preprocessing.py

sno = nltk.stem.SnowballStemmer('english')    # Initializing stemmer
wordcloud = [[], []]
all_sentences = []    # All cleaned sentences


for x in range(len(df['headline'].values)):
    headline = df['headline'].values[x]
    sarcasm = df['is_sarcastic'].values[x]

    cleaned_sentence = []
    sentence = removeURL(headline) 
    sentence = removeHTML(sentence)
    sentence = onlyAlphabets(sentence)
    sentence = sentence.lower()   

    for word in sentence.split():
        #if word not in stop:
            stemmed = sno.stem(word)
            cleaned_sentence.append(stemmed)
            
            wordcloud[sarcasm].append(word)
            

    all_sentences.append(' '.join(cleaned_sentence))

# add as column in dataframe
X = all_sentences
y = df['is_sarcastic']