ngram_vectorizer.py

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split

ngram_vectorizer = CountVectorizer(binary=True, ngram_range=(1, 2))
ngram_vectorizer.fit(reviews_train_clean)
X = ngram_vectorizer.transform(reviews_train_clean)
X_test = ngram_vectorizer.transform(reviews_test_clean)

X_train, X_val, y_train, y_val = train_test_split(
    X, target, train_size = 0.75
)

for c in [0.01, 0.05, 0.25, 0.5, 1]:
    
    lr = LogisticRegression(C=c)
    lr.fit(X_train, y_train)
    print ("Accuracy for C=%s: %s" 
           % (c, accuracy_score(y_val, lr.predict(X_val))))
    
# Accuracy for C=0.01: 0.88416
# Accuracy for C=0.05: 0.892
# Accuracy for C=0.25: 0.89424
# Accuracy for C=0.5: 0.89456
# Accuracy for C=1: 0.8944
    
final_ngram = LogisticRegression(C=0.5)
final_ngram.fit(X, target)
print ("Final Accuracy: %s" 
       % accuracy_score(target, final_ngram.predict(X_test)))

# Final Accuracy: 0.898