# Split the data into test and train data
test_pcnt = 0.15
X_train = X[:int(len(X) * (1 - test_pcnt)), :]
X_test = X[int(len(X) * (1 - test_pcnt)):, :]
y_train = y[:int(len(X) * (1 - test_pcnt))]
y_test = y[int(len(X) * (1 - test_pcnt)):]
ytrue = y_train
print X_train.shape, y_train.shape
# Just supervised score
basemodel = WQDA() # weighted Quadratic Discriminant Analysis
#basemodel = SGDClassifier(loss='log', penalty='l1') # scikit logistic regression
basemodel.fit(X_train, ytrue)
print "full labeled wqda score", basemodel.score(X_test, y_test)
print "standard error of wqda", 1.96 * np.sqrt(
basemodel.score(X_test, y_test) *
(1 - basemodel.score(X_test, y_test)) / X_test.shape[0])
# Just supervised score
#basemodel = WQDA() # weighted Quadratic Discriminant Analysis
basemodel = SGDClassifier(loss='log',
penalty='l1') # scikit logistic regression
basemodel.fit(X_train, ytrue)
print "full labeled log.reg. score", basemodel.score(X_test, y_test)
print "standard error of log reg", 1.96 * np.sqrt(
basemodel.score(X_test, y_test) *
(1 - basemodel.score(X_test, y_test)) / X_test.shape[0])
super_acc = np.zeros(num_trials)
