def CPLELearningWrapper(X_train, y_train, X_test):
from frameworks.CPLELearning import CPLELearningModel
#clf = RandomForestClassifier()
from sklearn.linear_model.stochastic_gradient import SGDClassifier
clf = SGDClassifier(loss='log', penalty='l1')
ssmodel = CPLELearningModel(clf)
newlabels = np.concatenate((np.array(y_train), -np.ones(len(X_test))))
ssmodel.fit(np.concatenate((X_train, X_test)), newlabels)
return ssmodel.predict(X_test)
lbl = "S3VM (Gieseke et al. 2012):"
model = scikitTSVM.SKTSVM(kernel=kernel)
elif i == 2:
lbl = "CPLE(pessimistic) SVM:"
model = CPLELearningModel(sklearn.svm.SVC(kernel=kernel, probability=True))
elif i == 3:
lbl = "CPLE(optimistic) SVM:"
CPLELearningModel.pessimistic = False
model = CPLELearningModel(sklearn.svm.SVC(kernel=kernel, probability=True))
model.fit(Xs, ys.astype(int))
print ""
print lbl
print "Model training time: ", round(time.time()-t1, 3)
# predict, and evaluate
pred = model.predict(Xs)
acc = np.mean(pred==ytrue)
print "accuracy:", round(acc, 3)
# plot probabilities
[minx, maxx] = [np.min(Xs[:, 0]), np.max(Xs[:, 0])]
[miny, maxy] = [np.min(Xs[:, 1]), np.max(Xs[:, 1])]
gridsize = 100
xx = np.linspace(minx, maxx, gridsize)
yy = np.linspace(miny, maxy, gridsize).T
xx, yy = np.meshgrid(xx, yy)
Xfull = np.c_[xx.ravel(), yy.ravel()]
probas = model.predict_proba(Xfull)
plt.imshow(probas[:, 1].reshape((gridsize, gridsize)), extent=(minx, maxx, miny, maxy), origin='lower')
print 'No. of training data:', len_train
#Final Traning labels
train_labels = np.concatenate((y_labelled, y_minusone), axis = 0)
len_labels = len(train_labels)
print 'No. of training labels:', len_labels
##Print the number of test data
print 'No. of test data:', len(y_extra)
################################################################################
################################################################################
lbl = "CPLE(pessimistic) SVM:"
print lbl
model = CPLELearningModel(svm.SVC(kernel="rbf", probability=True), predict_from_probabilities=True, max_iter = 5000 )
model.fit(train_data, train_labels)
y_predict = model.predict(X_extra)
accuracy = accuracy_score(y_extra, y_predict)
print accuracy
error_rate_svm[i] = 1 - accuracy
logLik_svm[i] = -np.sum( stats.norm.logpdf(y_extra, loc=y_predict, scale=sd) )
print 'CPLE Error Rate:', error_rate_svm[i], logLik_svm[i]
###############################################################################
################################################################################
#Create the semi supervised KNN classifier
lbl = "Label Propagation(KNN):"
print lbl
knn_model = label_propagation.LabelSpreading(kernel='knn', alpha=0.0001, max_iter=3000)
knn_model.fit(train_data, train_labels)
y_predict = knn_model.predict(X_extra)
