ys = np.array([-1] * len(ytrue)) # -1 denotes unlabeled point
random_labeled_points = random.sample(np.where(ytrue == 0)[0], labeled_N/2)+\
random.sample(np.where(ytrue == 1)[0], labeled_N/2)
ys[random_labeled_points] = ytrue[random_labeled_points]
# supervised score
#basemodel = WQDA() # weighted Quadratic Discriminant Analysis
basemodel = SGDClassifier(loss='log',
penalty='l1') # scikit logistic regression
basemodel.fit(X[random_labeled_points, :], ys[random_labeled_points])
print("supervised log.reg. score", basemodel.score(X, ytrue))
# fast (but naive, unsafe) self learning framework
ssmodel = SelfLearningModel(basemodel)
ssmodel.fit(X, ys)
print("self-learning log.reg. score", ssmodel.score(X, ytrue))
# semi-supervised score (base model has to be able to take weighted samples)
ssmodel = CPLELearningModel(basemodel)
ssmodel.fit(X, ys)
print("CPLE semi-supervised log.reg. score", ssmodel.score(X, ytrue))
# semi-supervised score, WQDA model
ssmodel = CPLELearningModel(WQDA(), predict_from_probabilities=True
) # weighted Quadratic Discriminant Analysis
ssmodel.fit(X, ys)
print("CPLE semi-supervised WQDA score", ssmodel.score(X, ytrue))
# semi-supervised score, RBF SVM model
ssmodel = CPLELearningModel(sklearn.svm.SVC(kernel="rbf", probability=True),
predict_from_probabilities=True) # RBF SVM
ys = np.array([-1] * len(ytrue)) # -1 denotes unlabeled point
random_labeled_points = random.sample(np.where(ytrue == 0)[0], labeled_N / 2) + random.sample(
np.where(ytrue == 1)[0], labeled_N / 2
)
ys[random_labeled_points] = ytrue[random_labeled_points]
# supervised score
# basemodel = WQDA() # weighted Quadratic Discriminant Analysis
basemodel = SGDClassifier(loss="log", penalty="l1") # scikit logistic regression
basemodel.fit(X[random_labeled_points, :], ys[random_labeled_points])
print "supervised log.reg. score", basemodel.score(X, ytrue)
# fast (but naive, unsafe) self learning framework
ssmodel = SelfLearningModel(basemodel)
ssmodel.fit(X, ys)
print "self-learning log.reg. score", ssmodel.score(X, ytrue)
# semi-supervised score (base model has to be able to take weighted samples)
ssmodel = CPLELearningModel(basemodel)
ssmodel.fit(X, ys)
print "CPLE semi-supervised log.reg. score", ssmodel.score(X, ytrue)
# semi-supervised score, WQDA model
ssmodel = CPLELearningModel(WQDA(), predict_from_probabilities=True) # weighted Quadratic Discriminant Analysis
ssmodel.fit(X, ys)
print "CPLE semi-supervised WQDA score", ssmodel.score(X, ytrue)
# semi-supervised score, RBF SVM model
ssmodel = CPLELearningModel(sklearn.svm.SVC(kernel="rbf", probability=True), predict_from_probabilities=True) # RBF SVM
ssmodel.fit(X, ys)
print "CPLE semi-supervised RBF SVM score", ssmodel.score(X, ytrue)
ysupervised = ys[ys!=-1]
lbl = "Base model SVM(kernel=rbf):"
print (lbl)
basemodel = sklearn.svm.SVC(kernel=kernel, probability=True)
basemodel.fit(Xsupervised, ysupervised)
evaluate(basemodel, X, ys, ytrue, lbl)
# basemodel = SGDClassifier(loss='hinge', penalty='l1', tol=1e-3, max_iter=1000) # scikit logistic regression
# basemodel.fit(X[random_labeled_points, :], ys[random_labeled_points])
# print ("supervised log.reg. score", basemodel.score(X, ytrue))
#
# fast (but naive, unsafe) self learning framework
ssmodel = SelfLearningModel(basemodel)
ssmodel.fit(X, ys)
print ("self-learning log.reg. score", ssmodel.score(X, ytrue))
kernel = "rbf"
Xsupervised = X[ys!=-1, :]
ysupervised = ys[ys!=-1]
lbl = "Purely supervised SVM:"
print (lbl)
model = sklearn.svm.SVC(kernel=kernel, probability=True)
model.fit(Xsupervised, ysupervised)
evaluate(model, X, ys, ytrue, lbl)
lbl = "S3VM (Gieseke et al. 2012):"
print (lbl)
model = scikitTSVM.SKTSVM(kernel=kernel)
# supervised score
basemodel = SGDClassifier(loss='hinge',
penalty='l1',
tol=1e-3,
max_iter=1000) # scikit logistic regression
basemodel.fit(X[random_labeled_points, :], ys[random_labeled_points])
acc = basemodel.score(X, ytrue)
if acc:
sgd_active.append(acc)
kernel = "rbf"
svm_model = sklearn.svm.SVC(kernel=kernel, probability=True)
ssmodel = SelfLearningModel(svm_model)
ssmodel.fit(X, ys)
acc = ssmodel.score(X, ytrue)
if acc:
self_learning_active.append(acc)
Xsupervised = X[ys != -1, :]
ysupervised = ys[ys != -1]
lbl = "Purely supervised SVM:"
model = sklearn.svm.SVC(kernel=kernel, probability=True)
model.fit(Xsupervised, ysupervised)
acc = evaluate(model, X, ys, ytrue, lbl)
print("SVM Accuracy:{}".format(acc))
if acc:
svm_active.append(acc)
lbl = "S3VM (Gieseke et al. 2012):"
sum_super += basemodel.score(X_test, y_test)
super_acc[i] = basemodel.score(X_test, y_test)
sum_super_err += 1.96 * np.sqrt(super_acc[i] *
(1 - super_acc[i]) / X_test.shape[0])
# fast (but naive, unsafe) self learning framework
ssmodel = SelfLearningModel(basemodel)
ssmodel.fit(X_model, ys)
#print "self-learning log.reg. score", ssmodel.score(X_test, y_test)
#if j == 2:
#Plot the ssmodel
# evaluate_and_plot(ssmodel, X_model, ys, ytrue, "Self-Learning", subplot = 2, block=True)
#Calculate accuracy
sum_semi += ssmodel.score(X_test, y_test)
semi_acc[i] = ssmodel.score(X_test, y_test)
sum_semi_err += 1.96 * np.sqrt(semi_acc[i] *
(1 - semi_acc[i]) / X_test.shape[0])
#if j==2:
#Save the figure
# plt.savefig(('comparisons_' + str(j) + '_' + str(i) + '.png'))
print "average supervised accuracy: ", sum_super / num_trials
sup_accs[cnt] = sum_super / num_trials
#print "standard deviation of supervised accuracy: ", np.std(super_acc, ddof=1)
print "standard error of supervised: ", sum_super_err / num_trials
print "average semi-supervised accuracy: ", sum_semi / num_trials
semi_accs[cnt] = sum_semi / num_trials
# supervised score
basemodel = SGDClassifier(loss='hinge',
penalty='l1',
tol=1e-3,
max_iter=1000) # scikit logistic regression
basemodel.fit(X[random_labeled_points, :], ys[random_labeled_points])
sgd_active.append(basemodel.score(X, ytrue))
kernel = "rbf"
svm_model = sklearn.svm.SVC(kernel=kernel, probability=True)
ssmodel = SelfLearningModel(svm_model)
ssmodel.fit(X, ys)
self_learning_active.append(ssmodel.score(X, ytrue))
Xsupervised = X[ys != -1, :]
ysupervised = ys[ys != -1]
lbl = "Purely supervised SVM:"
model = sklearn.svm.SVC(kernel=kernel, probability=True)
model.fit(Xsupervised, ysupervised)
acc = evaluate(model, X, ys, ytrue, lbl)
svm_active.append(acc)
lbl = "S3VM (Gieseke et al. 2012):"
model = scikitTSVM.SKTSVM(kernel=kernel)
model.fit(X, ys)
acc = evaluate(model, X, ys, ytrue, lbl)
s3vm_active.append(acc)