Last active
October 13, 2018 16:09
-
-
Save aaronkub/9c76024bb61bd744032ff0e7839e3636 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.linear_model import LogisticRegression | |
from sklearn.metrics import accuracy_score | |
from sklearn.model_selection import train_test_split | |
wc_vectorizer = CountVectorizer(binary=False) | |
wc_vectorizer.fit(reviews_train_clean) | |
X = wc_vectorizer.transform(reviews_train_clean) | |
X_test = wc_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: 0.87456 | |
# Accuracy for C=0.05: 0.88016 | |
# Accuracy for C=0.25: 0.87936 | |
# Accuracy for C=0.5: 0.87936 | |
# Accuracy for C=1: 0.87696 | |
final_wc = LogisticRegression(C=0.05) | |
final_wc.fit(X, target) | |
print ("Final Accuracy: %s" | |
% accuracy_score(target, final_wc.predict(X_test))) | |
# Final Accuracy: 0.88184 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment