def test_linear_svm(self): """ Train linear SVM on dataset 0, which is linearly separable. Then try on dataset 3, which is not separable, but close to linearly separable. """ i = 0 params = {'kernel': 'linear', 'C': 1.0} lin_svm_model = kernel_svm_train(self.train_data[i], self.train_labels[i], params) predictions, _ = kernel_svm_predict(self.test_data[i], lin_svm_model) test_accuracy = np.mean(predictions == self.test_labels[i]) print("Linear SVM had test accuracy %2.3f (should be around 0.98)" % test_accuracy) assert test_accuracy > 0.95, "Accuracy was below 0.95." i = 3 params = {'kernel': 'linear', 'C': 1.0} lin_svm_model = kernel_svm_train(self.train_data[i], self.train_labels[i], params) predictions, _ = kernel_svm_predict(self.test_data[i], lin_svm_model) test_accuracy = np.mean(predictions == self.test_labels[i]) print("Linear SVM had test accuracy %2.3f (should be around 0.93)" % test_accuracy) assert test_accuracy > 0.9, "Accuracy was below 0.9."
def test_rbf_svm(self): """ Train RBF SVM on dataset 1, which is not linearly separable. """ i = 1 params = {'kernel': 'rbf', 'C': 1.0, 'sigma': 1.0} rbf_svm_model = kernel_svm_train(self.train_data[i], self.train_labels[i], params) predictions, _ = kernel_svm_predict(self.test_data[i], rbf_svm_model) test_accuracy = np.mean(predictions == self.test_labels[i]) print("RBF SVM had test accuracy %2.3f (should be around 0.92)" % test_accuracy) assert test_accuracy > 0.9, "Accuracy was below 0.9."
def test_poly_svm(self): """ Train quadratic polynomial SVM on dataset 1, which is not linearly separable. """ i = 1 params = {'kernel': 'polynomial', 'C': 1.0, 'order': 2} poly_svm_model = kernel_svm_train(self.train_data[i], self.train_labels[i], params) predictions, _ = kernel_svm_predict(self.test_data[i], poly_svm_model) test_accuracy = np.mean(predictions == self.test_labels[i]) print( "Polynomial SVM had test accuracy %2.3f (should be around 0.94)" % test_accuracy) assert test_accuracy > 0.9, "Accuracy was below 0.9."
def test_rbf_svm(self): """ Train RBF SVM on datasets 0 to 9. """ threshold_accuracy = [0.95,0.9,0.875,0.95,0.9,0.9,0.95,0.9,0.875,0.875] # threshold accuracy values to beat for every dataset pass_vec = np.zeros(10, dtype =bool) # stores whether test passed on a dataset or not for i in range(10): params = {'kernel': 'rbf', 'C': 1.0, 'sigma': 0.5} svm_model = kernel_svm_train(self.train_data[i], self.train_labels[i], params) predictions, _ = kernel_svm_predict(self.test_data[i], svm_model) test_accuracy = np.mean(predictions == self.test_labels[i]) print("On dataset %d, Kernel SVM had test accuracy %2.3f (should be greater than %2.3f)" % (i, test_accuracy,threshold_accuracy[i])) pass_vec = test_accuracy - threshold_accuracy[i] < 0 assert np.sum(pass_vec) == 0, "Kernel SVM accuracy was less than threshold for one of the datasets."