INNER CODE UNIT · Python

main

NishkarshRaj/100DaysofMLCode · 8_Natural_Language_Processing/natural_language_processing.py:16

def main():
    # Importing the dataset
    dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter='\t', quoting=3)

    # Cleaning the texts

    nltk.download('stopwords')
    corpus = []
    for i in range(0, 1000):
        review = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])
        review = review.lower()
        review = review.split()
        ps = PorterStemmer()
        review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
        review = ' '.join(review)
        corpus.append(review)

    # Creating the Bag of Words model

View source record →