Created
December 15, 2011 10:15
-
-
Save fannix/1480609 to your computer and use it in GitHub Desktop.
Naive Bayes with sparse matrix with Stratified KFold cross validation
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.datasets import load_svmlight_file | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.cross_validation import StratifiedKFold | |
from sklearn import metrics | |
X, y = load_svmlight_file("mpqa_en.vec") | |
kf = StratifiedKFold(y, k = 10, indices=True) | |
clf = MultinomialNB() | |
for train_index, test_index in kf: | |
X_train, X_test = X[train_index], X[test_index] | |
y_train, y_test = y[train_index], y[test_index] | |
clf.fit(X_train, y_train) | |
y_predicted = clf.predict(X_test) | |
print metrics.confusion_matrix(y_test, y_predicted) | |
print metrics.classification_report(y_test, y_predicted) | |
print sum(-1 == y_test) / float(len(y_test)) | |
print sum(y_predicted == y_test) / float(len(y_test)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment