Sentiment Analysis - Vectorization

vectorization.py

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split

#vectorization
cv = CountVectorizer(lowercase= False) 
text_vector = cv.fit_transform(df.text.values)

x = text_vector
y = df.iloc[:,-1].values

# train validation test split
x_train, xtest, y_train, ytest = train_test_split(x, y, stratify = y, 
                                                  test_size=0.20, random_state=42)

x_val, x_test, y_val, y_test = train_test_split(xtest, ytest,stratify = ytest, 
                                                test_size=0.5, random_state=42)