CountVectorizer.py

#Save corpus for use in deployment
file_name = "corpus.pkl"
pickle.dump(corpus, open(file_name, 'wb'))

#Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features=2500)
X = cv.fit_transform(corpus).toarray()

#Extracting dependent variable from the dataset
y = pd.get_dummies(sms['label'])
y = y.iloc[:, 1].values