def test_hoeffding_tree():
stream = RegressionGenerator(n_samples=500,
n_features=20,
n_informative=15,
random_state=1)
stream.prepare_for_use()
learner = HoeffdingAdaptiveTreeRegressor(leaf_prediction='mean',
random_state=1)
cnt = 0
max_samples = 500
y_pred = array('d')
y_true = array('d')
wait_samples = 10
while cnt < max_samples:
X, y = stream.next_sample()
# Test every n samples
if (cnt % wait_samples == 0) and (cnt != 0):
y_pred.append(learner.predict(X)[0])
y_true.append(y[0])
learner.partial_fit(X, y)
cnt += 1
expected_predictions = array('d', [
102.38946041769101, 55.6584574987656, 5.746076599168373,
17.11797209372667, 2.566888222752787, 9.188247802192826,
17.87894804676911, 15.940629626883966, 8.981172175448485,
13.152624115190092, 11.106058099429399, 6.473195313058236,
4.723621479590173, 13.825568609556493, 8.698873073880696,
1.6452441811010252, 5.123496188584294, 6.34387187194982,
5.9977733790395105, 6.874251577667707, 4.605348088338317,
8.20112636572672, 9.032631648758098, 4.428189978974459,
4.249801041367518, 9.983272668044492, 12.859518508979734,
11.741395774380285, 11.230028410261868, 9.126921979081521,
9.132146661688296, 7.750655625124709, 6.445145118245414,
5.760928671876355, 4.041291302080659, 3.591837600560529,
0.7640424010500604, 0.1738639840537784, 2.2068337802212286,
-81.05302946841077, 96.17757415335177, -77.35894903819677,
95.85568683733698, 99.1981674250886, 99.89327888035015,
101.66673013734784, -79.1904234513751, -80.42952143783687,
100.63954789983896
])
assert np.allclose(y_pred, expected_predictions)
error = mean_absolute_error(y_true, y_pred)
expected_error = 143.11351404083086
assert np.isclose(error, expected_error)
expected_info = "HoeffdingAdaptiveTreeRegressor(binary_split=False, grace_period=200, leaf_prediction='mean', " \
"learning_ratio_const=True, learning_ratio_decay=0.001, learning_ratio_perceptron=0.02, " \
"max_byte_size=33554432, memory_estimate_period=1000000, nb_threshold=0, no_preprune=False, " \
"nominal_attributes=None, random_state=1, remove_poor_atts=False, split_confidence=1e-07, " \
"stop_mem_management=False, tie_threshold=0.05)"
info = " ".join([line.strip() for line in learner.get_info().split()])
assert info == expected_info
assert isinstance(learner.get_model_description(), type(''))
assert type(learner.predict(X)) == np.ndarray
def test_hoeffding_adaptive_tree_regressor_perceptron():
stream = RegressionGenerator(n_samples=500, n_features=20, n_informative=15, random_state=1)
learner = HoeffdingAdaptiveTreeRegressor(leaf_prediction='perceptron', random_state=1)
cnt = 0
max_samples = 500
y_pred = array('d')
y_true = array('d')
wait_samples = 10
while cnt < max_samples:
X, y = stream.next_sample()
# Test every n samples
if (cnt % wait_samples == 0) and (cnt != 0):
y_pred.append(learner.predict(X)[0])
y_true.append(y[0])
learner.partial_fit(X, y)
cnt += 1
expected_predictions = array('d', [207.20901655684412, 106.30316877540555, 101.46950096324191,
114.38162776688861, 48.40271620592212, -79.94375846313639,
-76.69182794940929, 88.38425569670662, -13.92372162581644,
3.0549887923350507, 55.36276732455883, 32.0512081208464,
17.54953203218902, -1.7305966738232161, 43.54548690756897,
8.502241407478213, -61.14739038895263, 50.528736810827745,
9.679668917948607, 89.93098085572623, 85.1994809437223,
1.8721866382932664, -7.1972581323107825, -45.86230662663542,
3.111671172363243, 57.921908276916646, 61.43400576850072,
-16.61695641848216, -6.0769944259948065, 19.929266442289546,
-60.972801351912224, -0.3342549973033524,
-50.53334350658139, -14.885488543743078,
-13.255920225124637, 28.909916365484275,
-103.03499425386107, -36.44921969674884, -15.40018796932204,
-84.98471039676006, 38.270205984888065, -62.97228157481581,
-48.095864628804044, 95.5028130171316, 73.62390886812497,
152.7135140597221, -120.4662342226783, -77.68182541723442,
66.82059046110074])
assert np.allclose(y_pred, expected_predictions)
error = mean_absolute_error(y_true, y_pred)
expected_error = 126.11208652969131
assert np.isclose(error, expected_error)
expected_info = "HoeffdingAdaptiveTreeRegressor(binary_split=False, grace_period=200, " \
"leaf_prediction='perceptron', learning_ratio_const=True, learning_ratio_decay=0.001, " \
"learning_ratio_perceptron=0.02, max_byte_size=33554432, memory_estimate_period=1000000, " \
"no_preprune=False, nominal_attributes=None, random_state=1, " \
"remove_poor_atts=False, split_confidence=1e-07, stop_mem_management=False, tie_threshold=0.05)"
info = " ".join([line.strip() for line in learner.get_info().split()])
assert info == expected_info
assert isinstance(learner.get_model_description(), type(''))
assert type(learner.predict(X)) == np.ndarray
assert learner._estimator_type == 'regressor'
def test_hoeffding_tree_perceptron():
stream = RegressionGenerator(n_samples=500,
n_features=20,
n_informative=15,
random_state=1)
stream.prepare_for_use()
learner = HoeffdingAdaptiveTreeRegressor(leaf_prediction='perceptron',
random_state=1)
cnt = 0
max_samples = 500
y_pred = array('d')
y_true = array('d')
wait_samples = 10
while cnt < max_samples:
X, y = stream.next_sample()
# Test every n samples
if (cnt % wait_samples == 0) and (cnt != 0):
y_pred.append(learner.predict(X)[0])
y_true.append(y[0])
learner.partial_fit(X, y)
cnt += 1
expected_predictions = array('d', [
1198.4326121743168, 456.36607750881586, 927.9912160545144,
1160.4797981899128, 506.50541829176535, -687.8187227095925,
-677.8120094065415, 231.14888704761225, -284.46324039942937,
-255.69195985557175, 47.58787439365423, -135.22494016284043,
-10.351457437330152, 164.95903200643997, 360.72854984472383,
193.30633911830088, -64.23638301570358, 587.9771578214296,
649.8395655757931, 481.01214222804026, 305.4402728117724,
266.2096493865043, -445.11447171009775, -567.5748694154349,
-68.70070048021438, -446.79910655850153, -115.892348067663,
-98.26862866231015, 71.04707905920286, -10.239274802165584,
18.748731569441812, 4.971217265129857, 172.2223575990573,
-655.2864976783711, -129.69921313686626, -114.01187375876822,
-405.66166686550963, -215.1264381928009, -345.91020370426247,
-80.49330468453074, 108.78958382083302, 134.95267043280126,
-398.5273538477553, -157.1784910649728, 219.72541225645654,
-100.91598162899217, 80.9768574308987, -296.8856956382453,
251.9332271253148
])
assert np.allclose(y_pred, expected_predictions)
error = mean_absolute_error(y_true, y_pred)
expected_error = 362.98595964244623
assert np.isclose(error, expected_error)
expected_info = "HoeffdingAdaptiveTreeRegressor(binary_split=False, grace_period=200, " \
"leaf_prediction='perceptron', learning_ratio_const=True, learning_ratio_decay=0.001, " \
"learning_ratio_perceptron=0.02, max_byte_size=33554432, memory_estimate_period=1000000, " \
"nb_threshold=0, no_preprune=False, nominal_attributes=None, random_state=1, " \
"remove_poor_atts=False, split_confidence=1e-07, stop_mem_management=False, tie_threshold=0.05)"
info = " ".join([line.strip() for line in learner.get_info().split()])
assert info == expected_info
assert isinstance(learner.get_model_description(), type(''))
assert type(learner.predict(X)) == np.ndarray
assert learner._estimator_type == 'regressor'
def test_hoeffding_adaptive_tree_regressor_perceptron():
stream = RegressionGenerator(n_samples=500,
n_features=20,
n_informative=15,
random_state=1)
learner = HoeffdingAdaptiveTreeRegressor(leaf_prediction='perceptron',
random_state=1)
cnt = 0
max_samples = 500
y_pred = array('d')
y_true = array('d')
wait_samples = 10
while cnt < max_samples:
X, y = stream.next_sample()
# Test every n samples
if (cnt % wait_samples == 0) and (cnt != 0):
y_pred.append(learner.predict(X)[0])
y_true.append(y[0])
learner.partial_fit(X, y)
cnt += 1
expected_predictions = array('d', [
-106.84237763060068, -10.965517384802226, -180.90711470797237,
-218.20896751607663, -96.4271589961865, 110.51551963099622,
108.34616947202511, 30.1720109214627, 57.92205878998479,
77.82418885914053, 49.972060923364765, 68.56117081695875,
15.996949915551697, -34.22744443808294, -19.762696110319702,
-28.447329394752995, -50.62864370485592, -47.37357781048561,
-99.82613515424342, 13.985531117918336, 41.41709671929987,
-34.679807275938174, 62.75626094547859, 30.925078688018893,
12.130320819235365, 119.3648998377624, 82.96422756064737,
-6.920397563039609, -12.701774870569059, 24.883730398016034,
-74.22855883237567, -0.8012436194087567, -83.03683748750394,
46.737839617687854, 0.537404558240671, 48.53591837633138,
-86.2259777783834, -24.985514024179967, 6.396035456152859,
-90.19454995571908, 32.05821807667601, -83.08553684151566,
-28.32223999320023, 113.28916673506842, 68.10498750807977,
173.9146410394573, -150.2067507947196, -74.10346402222962,
54.39153137687993
])
assert np.allclose(y_pred, expected_predictions)
error = mean_absolute_error(y_true, y_pred)
expected_error = 115.78916175164417
assert np.isclose(error, expected_error)
expected_info = "HoeffdingAdaptiveTreeRegressor(binary_split=False, grace_period=200, " \
"leaf_prediction='perceptron', learning_ratio_const=True, learning_ratio_decay=0.001, " \
"learning_ratio_perceptron=0.02, max_byte_size=33554432, memory_estimate_period=1000000, " \
"no_preprune=False, nominal_attributes=None, random_state=1, " \
"remove_poor_atts=False, split_confidence=1e-07, stop_mem_management=False, tie_threshold=0.05)"
info = " ".join([line.strip() for line in learner.get_info().split()])
assert info == expected_info
assert isinstance(learner.get_model_description(), type(''))
assert type(learner.predict(X)) == np.ndarray
assert learner._estimator_type == 'regressor'