cross validation

cross_validation.py

from sklearn.datasets import load_svmlight_file
from sklearn.naive_bayes import MultinomialNB
from sklearn.svm.sparse import LinearSVC
from sklearn.cross_validation import StratifiedKFold
from sklearn import metrics
import numpy as np

X, y = load_svmlight_file("fr.vec")
y[y == -1] = 0
kf = StratifiedKFold(y, k = 10, indices=True)
#clf = MultinomialNB()
clf = LinearSVC()
mean_li = []
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)
    mean_li.append(sum(y_predicted == y_test) / float(len(y_test)))

print np.mean(mean_li)