Text_Processing.py

def text_processing(input_text):
    tokens = tokenizer.tokenize(input_text)
    lemmatizer = WordNetLemmatizer()
    tokens = [lemmatizer.lemmatize(i) for i in tokens]
    stops = set(stopwords.words('english'))
    values = [i for i in tokens if i not in stops]
    weird = ["wa", "u"]
    values = [i for i in values if i not in weird]
    return(values)
values = text_processing(text)
print("The number of unique words is: " + str(len(set(values))))