def test_rectangular_tsvm_hepatitis(self):
"""
It tests TSVM with rectangular on hepatitis dataset
"""
clf = TSVM('RBF', 0.75, 0.5, 2, 0.1)
clf.fit(X, y)
pred = clf.predict(X)
assert_greater(np.mean(y == pred), 0.95)
def test_linear_tsvm_hepatitis(self):
"""
It tests linear TSVM estimator on hepatits dataset
"""
clf = TSVM('linear', 1, 0.5, 0.5)
clf.fit(X, y)
pred = clf.predict(X)
assert_greater(np.mean(y == pred), 0.78)
def test_rbf_tsvm_hepatitis(self):
"""
It tests non-linear TSVM estimator on hepatitis dataset
"""
clf = TSVM('RBF', 1, 0.5, 0.5, 0.1)
clf.fit(X, y)
pred = clf.predict(X)
assert_greater(np.mean(y == pred), 0.95)
data_path = '/home/mir/mir-projects/NDC'
# Specify the dataset's filename
dataset = DataReader(join(data_path, 'NDC-train-1l.csv'), ',', False)
dataset.load_data(False, False)
X, y, _ = dataset.get_data()
print("Loaded the dataset...")
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.3)
print(X_train.shape)
print("Split train/test sets...")
# A TSVM-based estimator
tsvm_model = TSVM()
train_t = time.time()
tsvm_model.fit(X_train, y_train)
print("Train time: %.5f" % (time.time() - train_t))
test_t = time.time()
pred = tsvm_model.predict(X_test)
print("Test time: %.5f" % (time.time() - test_t))
acc = accuracy_score(y_test, pred)
print("Acc: %.2f" % (acc * 100))