Semi-supervised Naive Bayes

emnb.py

from sklearn.naive_bayes import EMNB, MultinomialNB, BernoulliNB
from sklearn.cross_validation import KFold
from sklearn.datasets import load_svmlight_file
from scipy.sparse import vstack
import numpy as np

X, y = load_svmlight_file("mpqa_en.vec")
y = np.asarray(y, np.int32)
n_labeled = int(0.8 * X.shape[0])
X_labeled = X[:n_labeled]
y_labeled = y[:n_labeled]
y_labeled[y_labeled == -1] = 0
X_unlabeled = X[n_labeled:]
y_unlabeled = y[n_labeled:]
y_unlabeled[:] = -1
kf = KFold(n_labeled, k = 10, indices=True)
clf1 = MultinomialNB()
clf = EMNB(MultinomialNB(alpha=1), verbose=False, n_iter=100)
i = 0
li_super = []

#supervised
for train_index, test_index in kf:
    X_train, X_test = X_labeled[train_index], X_labeled[test_index]
    y_train, y_test = y_labeled[train_index], y_labeled[test_index]
    clf1.fit(X_train, y_train.flatten())
    y_predicted = clf1.predict(X_test)
    li_super.append(sum(y_predicted == y_test) / float(len(y_predicted)))

print np.mean(li_super)

kf = KFold(n_labeled, k = 10, indices=True)
li_semi = []
#semi-supervised
for train_index, test_index in kf:
    X_train, X_test = X_labeled[train_index], X_labeled[test_index]
    y_train, y_test = y_labeled[train_index], y_labeled[test_index]
    X_ = vstack((X_train, X_unlabeled), format="csr")
    y_ = np.vstack((y_train[:, np.newaxis], y_unlabeled[:, np.newaxis]))
    clf.fit(X_, y_.flatten())
    y_predicted = clf.predict(X_test)
    li_semi.append(sum(y_predicted == y_test) / float(len(y_predicted)))

print np.mean(li_semi)