question_cleaning_text.py

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


for x in range(len(df['Questions'].values)):
    question = df['Questions'].values[x]
    classname = df['Category0'].values[x]

    cleaned_sentence = []
    sentence = removeURL(question) 
    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[class_names.index(classname)].append(word)
            

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

# add as column in dataframe
X = all_sentences