def test_fit_one_hot(self,):
x = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# keys as label array
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
labels = ht.array(keys, split=0)
# keys as one_hot
keys = []
for i in range(50):
keys.append([1, 0, 0])
for i in range(50, 100):
keys.append([0, 1, 0])
for i in range(100, 150):
keys.append([0, 0, 1])
y = ht.array(keys)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x, y)
result = knn.predict(x)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, labels.shape)
def test_split_none(self):
x = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
y = ht.array(keys)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x, y)
result = knn.predict(x)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, y.shape)
def test_split_none(self):
X = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# Generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
Y = ht.array(keys)
knn = KNN(X, Y, 5)
result = knn.predict(X)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, Y.shape)
def test_classifier(self):
gnb = ht.naive_bayes.GaussianNB()
self.assertTrue(ht.is_estimator(gnb))
self.assertTrue(ht.is_classifier(gnb))