def test_kprotoypes_cao_stocks(self):
kproto_cao = kprototypes.KPrototypes(n_clusters=4, init='Cao',
verbose=2, random_state=42)
result = kproto_cao.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 3, 3, 3, 3, 0, 0, 0, 0, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kprotoypes_cao_stocks_ng(self):
np.random.seed(42)
kproto_cao = kprototypes.KPrototypes(n_clusters=4, init='Cao', verbose=2, cat_dissim=ng_dissim)
result = kproto_cao.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 3, 3, 3, 3, 0, 0, 0, 0, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint8))
def test_kprotoypes_cao_stocks(self):
kproto_cao = kprototypes.KPrototypes(n_clusters=4, init='Cao',
verbose=2, random_state=42)
result = kproto_cao.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 3, 3, 3, 3, 0, 0, 0, 0, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kprotoypes_init_stocks(self):
# Wrong order
init_vals = [
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]]),
np.array([[356.975],
[275.35],
[738.5],
[197.667]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=2, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
# Wrong number of clusters
init_vals = [
np.array([356.975, 275.35, 738.5, 197.667, 0.]),
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
# Wrong number of attributes
init_vals = [
np.array([356.975, 275.35, 738.5, 197.667]),
np.array([3, 0, 3, 2])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
init_vals = [
np.array([[356.975],
[275.35],
[738.5],
[197.667]]),
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2, random_state=42)
result = kproto_init.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 0, 0, 0, 0, 1, 1, 1, 1, 3, 3, 3])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kprotoypes_init_stocks(self):
# Wrong order
init_vals = [
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]]),
np.array([[356.975],
[275.35],
[738.5],
[197.667]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=2, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
# Wrong number of clusters
init_vals = [
np.array([356.975, 275.35, 738.5, 197.667, 0.]),
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
# Wrong number of attributes
init_vals = [
np.array([356.975, 275.35, 738.5, 197.667]),
np.array([3, 0, 3, 2])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2)
with self.assertRaises(AssertionError):
kproto_init.fit_predict(STOCKS, categorical=[1, 2])
init_vals = [
np.array([[356.975],
[275.35],
[738.5],
[197.667]]),
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals,
verbose=2, random_state=42)
result = kproto_init.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 0, 0, 0, 0, 1, 1, 1, 1, 3, 3, 3])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kprotoypes_predict_stocks(self):
np.random.seed(42)
kproto_cao = kprototypes.KPrototypes(n_clusters=4,
init='Cao',
verbose=2)
kproto_cao = kproto_cao.fit(STOCKS, categorical=[1, 2])
result = kproto_cao.predict(STOCKS2, categorical=[1, 2])
expected = np.array([1, 1, 3, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint8))
def test_kprotoypes_huang_stocks(self):
np.random.seed(42)
kproto_huang = kprototypes.KPrototypes(n_clusters=4, n_init=1, init='Huang', verbose=2)
# Untrained model
with self.assertRaises(AssertionError):
kproto_huang.predict(STOCKS, categorical=[1, 2])
result = kproto_huang.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([0, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint8))
def test_kprotoypes_huang_stocks_parallel(self):
kproto_huang = kprototypes.KPrototypes(n_clusters=4, n_init=4,
init='Huang', verbose=2,
random_state=42, n_jobs=4)
# Untrained model
with self.assertRaises(AssertionError):
kproto_huang.predict(STOCKS, categorical=[1, 2])
result = kproto_huang.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([0, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kprotoypes_init_stocks_ng(self):
init_vals = [
np.array([[356.975], [275.35], [738.5], [197.667]]),
np.array([[3, 2], [0, 2], [3, 2], [2, 2]])
]
kproto_init = kprototypes.KPrototypes(n_clusters=4,
init=init_vals,
verbose=2,
cat_dissim=ng_dissim,
random_state=42)
result = kproto_init.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 0, 0, 0, 0, 1, 1, 1, 1, 3, 3, 3])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint16))
def test_kmodes_fit_predict_equality(self):
"""Test whether fit_predict interface works the same as fit and predict."""
kproto = kprototypes.KPrototypes(n_clusters=3,
init='Cao',
random_state=42)
sample_weight = [0.5] * STOCKS.shape[0]
model1 = kproto.fit(STOCKS,
categorical=[1, 2],
sample_weight=sample_weight)
data1 = model1.predict(STOCKS, categorical=[1, 2])
data2 = kproto.fit_predict(STOCKS,
categorical=[1, 2],
sample_weight=sample_weight)
assert_cluster_splits_equal(data1, data2)
def test_kprotoypes_huang_stocks_ng(self):
np.random.seed(42)
kproto_huang = kprototypes.KPrototypes(n_clusters=4,
n_init=1,
init='Huang',
verbose=2,
cat_dissim=ng_dissim)
# Untrained model
with self.assertRaises(AssertionError):
kproto_huang.predict(STOCKS, categorical=[1, 2])
result = kproto_huang.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([0, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint8))
def test_kprotoypes_init_stocks_ng(self):
init_vals = [
np.array([[356.975],
[275.35],
[738.5],
[197.667]]),
np.array([[3, 2],
[0, 2],
[3, 2],
[2, 2]])
]
np.random.seed(42)
kproto_init = kprototypes.KPrototypes(n_clusters=4, init=init_vals, verbose=2, cat_dissim=ng_dissim)
result = kproto_init.fit_predict(STOCKS, categorical=[1, 2])
expected = np.array([2, 0, 0, 0, 0, 1, 1, 1, 1, 3, 3, 3])
assert_cluster_splits_equal(result, expected)
self.assertTrue(result.dtype == np.dtype(np.uint8))