def test_default_configuration(self):
for i in range(10):
predictions, targets = \
_test_regressor(KNearestNeighborsRegressor)
self.assertAlmostEqual(0.068600456340847438,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = \
_test_regressor(AdaboostRegressor, sparse=True, dataset='boston')
self.assertAlmostEqual(0.2039634989252479,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_boston(self):
for i in range(2):
predictions, targets, n_calls = \
_test_regressor(dataset="boston",
Regressor=self.module)
if "default_boston_le_ge" in self.res:
# Special treatment for Gaussian Process Regression
self.assertLessEqual(
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions),
self.res["default_boston_le_ge"][0])
self.assertGreaterEqual(
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions),
self.res["default_boston_le_ge"][1])
else:
score = sklearn.metrics.r2_score(targets, predictions)
fixture = self.res["default_boston"]
if score < -1e10:
score = np.log(-score)
fixture = np.log(-fixture)
self.assertAlmostEqual(
fixture,
score,
places=self.res.get("default_boston_places", 7),
)
if self.res.get("boston_n_calls"):
self.assertEqual(self.res["boston_n_calls"], n_calls)
def test_default_configuration(self):
for i in range(10):
predictions, targets = \
_test_regressor(ARDRegression, dataset='boston')
self.assertAlmostEqual(0.70316694175513961,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration_sparse_data(self):
for i in range(10):
predictions, targets = \
_test_regressor(KNearestNeighborsRegressor, sparse=True)
self.assertAlmostEqual(-0.16321841460809972,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(LibLinear_SVR,
dataset='boston')
self.assertAlmostEqual(0.54372712745256768,
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions))
def test_default_configuration(self):
configuration_space = RidgeRegression.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
configuration_space_preproc = RandomKitchenSinks.get_hyperparameter_search_space()
default_preproc = configuration_space_preproc.get_default_configuration()
for i in range(10):
# This should be a bad results
predictions, targets = _test_regressor(RidgeRegression,)
self.assertAlmostEqual(0.32614416980439365,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
# This should be much more better
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes',
make_sparse=False)
preprocessor = RandomKitchenSinks(
random_state=1,
**{hp_name: default_preproc[hp_name] for hp_name in
default_preproc if default_preproc[hp_name] is not None})
transformer = preprocessor.fit(X_train, Y_train)
X_train_transformed = transformer.transform(X_train)
X_test_transformed = transformer.transform(X_test)
regressor = RidgeRegression(
random_state=1,
**{hp_name: default[hp_name] for hp_name in
default if default[hp_name] is not None})
predictor = regressor.fit(X_train_transformed, Y_train)
predictions = predictor.predict(X_test_transformed)
self.assertAlmostEqual(0.37183512452087852,
sklearn.metrics.r2_score(y_true=Y_test, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = \
_test_regressor(AdaboostRegressor, dataset='boston')
self.assertAlmostEqual(0.59461560848921158,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration(self):
for i in range(10):
# Float32 leads to numeric instabilities
predictions, targets = _test_regressor(GaussianProcess,
dataset='boston')
self.assertAlmostEqual(0.83362335184173442,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions),
places=2)
def test_default_configuration(self):
# Only twice to reduce the number of warning printed to the command line
for i in range(2):
# Float32 leads to numeric instabilities
predictions, targets = _test_regressor(GaussianProcess,
dataset='boston')
self.assertAlmostEqual(0.83362335184173442,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions),
places=2)
def test_default_configuration(self):
for i in range(10):
# Float32 leads to numeric instabilities
predictions, targets = _test_regressor(GaussianProcess,
dataset='boston')
self.assertAlmostEqual(0.83362335184173442,
sklearn.metrics.r2_score(
y_true=targets, y_pred=predictions),
places=2)
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(LibLinear_SVR,
dataset='boston')
# Lenient test because of travis-ci which gets quite different
# results here!
self.assertAlmostEqual(0.68,
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions),
places=2)
def test_default_diabetes(self):
for i in range(2):
predictions, targets = \
_test_regressor(dataset="diabetes",
Regressor=self.module)
self.assertAlmostEqual(
self.res["default_diabetes"],
sklearn.metrics.r2_score(targets, predictions),
places=self.res.get("default_diabetes_places", 7))
def test_default_configuration(self):
for i in range(2):
predictions, targets = _test_regressor(LibLinear_SVR,
dataset='boston')
# Lenient test because of travis-ci which gets quite different
# results here!
self.assertAlmostEqual(0.68,
sklearn.metrics.r2_score(
y_true=targets, y_pred=predictions),
places=2)
def test_default_configuration(self):
# Only twice to reduce the number of warning printed to the command line
for i in range(2):
# Float32 leads to numeric instabilities
predictions, targets = _test_regressor(GaussianProcess,
dataset='boston')
self.assertAlmostEqual(0.83362335184173442,
sklearn.metrics.r2_score(
y_true=targets, y_pred=predictions),
places=2)
def test_default_boston_sparse(self):
if SPARSE not in self.module.get_properties()["input"]:
return
for i in range(2):
predictions, targets, _ = \
_test_regressor(dataset="boston",
Regressor=self.module,
sparse=True)
self.assertAlmostEqual(
self.res["default_boston_sparse"],
sklearn.metrics.r2_score(targets, predictions),
places=self.res.get("default_boston_sparse_places", 7))
def test_default_configuration(self):
# Only twice to reduce the number of warning printed to the command line
for i in range(2):
# Float32 leads to numeric instabilities
predictions, targets = _test_regressor(GaussianProcess,
dataset='boston')
# My machine: 0.574913739659292
# travis-ci: 0.49562471963524557
self.assertLessEqual(
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions),
0.6)
self.assertGreaterEqual(
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions),
0.4)
def test_default_boston_sparse(self):
if SPARSE not in self.module.get_properties()["input"]:
return
for i in range(2):
predictions, targets, _ = \
_test_regressor(dataset="boston",
Regressor=self.module,
sparse=True)
self.assertAlmostEqual(self.res["default_boston_sparse"],
sklearn.metrics.r2_score(targets,
predictions),
places=self.res.get(
"default_boston_sparse_places", 7))
def test_default_diabetes(self):
for i in range(2):
predictions, targets, n_calls = \
_test_regressor(dataset="diabetes",
Regressor=self.module)
self.assertAlmostEqual(self.res["default_diabetes"],
sklearn.metrics.r2_score(targets,
predictions),
places=self.res.get(
"default_diabetes_places", 7))
if self.res.get("diabetes_n_calls"):
self.assertEqual(self.res["diabetes_n_calls"], n_calls)
def test_default_diabetes(self):
if self.__class__ == BaseRegressionComponentTest:
return
for i in range(2):
predictions, targets, n_calls = \
_test_regressor(dataset="diabetes",
Regressor=self.module)
self.assertAlmostEqual(
self.res["default_diabetes"],
sklearn.metrics.r2_score(targets, predictions),
places=self.res.get("default_diabetes_places", 7))
if self.res.get("diabetes_n_calls"):
self.assertEqual(self.res["diabetes_n_calls"], n_calls)
def test_default_configuration(self):
configuration_space = RidgeRegression.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
configuration_space_preproc = RandomKitchenSinks.get_hyperparameter_search_space(
)
default_preproc = configuration_space_preproc.get_default_configuration(
)
for i in range(2):
# This should be a bad results
predictions, targets = _test_regressor(RidgeRegression, )
self.assertAlmostEqual(
0.32614416980439365,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
# This should be much more better
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes',
make_sparse=False)
preprocessor = RandomKitchenSinks(
random_state=1,
**{
hp_name: default_preproc[hp_name]
for hp_name in default_preproc
if default_preproc[hp_name] is not None
})
transformer = preprocessor.fit(X_train, Y_train)
X_train_transformed = transformer.transform(X_train)
X_test_transformed = transformer.transform(X_test)
regressor = RidgeRegression(random_state=1,
**{
hp_name: default[hp_name]
for hp_name in default
if default[hp_name] is not None
})
predictor = regressor.fit(X_train_transformed, Y_train)
predictions = predictor.predict(X_test_transformed)
self.assertAlmostEqual(
0.37183512452087852,
sklearn.metrics.r2_score(y_true=Y_test, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(2):
predictions, targets = _test_regressor(XGradientBoostingRegressor,
sparse=True)
self.assertAlmostEqual(0.20743694821393754,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
#def test_default_configuration_iterative_fit(self):
# for i in range(10):
# predictions, targets = \
# _test_regressor_iterative_fit(XGradientBoostingRegressor)
# self.assertAlmostEqual(0.40965687834764064,
# sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
#def test_default_configuration_iterative_fit_sparse(self):
# for i in range(10):
# predictions, targets = \
# _test_regressor_iterative_fit(XGradientBoostingRegressor,
# sparse=True)
# self.assertAlmostEqual(0.40965687834764064,
# sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(XGradientBoostingRegressor,
sparse=True)
self.assertAlmostEqual(0.20743694821393754,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
#def test_default_configuration_iterative_fit(self):
# for i in range(10):
# predictions, targets = \
# _test_regressor_iterative_fit(XGradientBoostingRegressor)
# self.assertAlmostEqual(0.40965687834764064,
# sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
#def test_default_configuration_iterative_fit_sparse(self):
# for i in range(10):
# predictions, targets = \
# _test_regressor_iterative_fit(XGradientBoostingRegressor,
# sparse=True)
# self.assertAlmostEqual(0.40965687834764064,
# sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_boston(self):
for i in range(2):
predictions, targets = \
_test_regressor(dataset="boston",
Regressor=self.module)
if "default_boston_le_ge" in self.res:
# Special treatment for Gaussian Process Regression
self.assertLessEqual(
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions),
self.res["default_boston_le_ge"][0])
self.assertGreaterEqual(
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions),
self.res["default_boston_le_ge"][1])
else:
self.assertAlmostEqual(
self.res["default_boston"],
sklearn.metrics.r2_score(targets, predictions),
places=self.res.get("default_boston_places", 7))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree)
self.assertAlmostEqual(0.14886750572325669, sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(SGD)
self.assertAlmostEqual(0.078043497701660636,
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree, sparse=True)
self.assertAlmostEqual(0.021778487309118133, sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets =_test_regressor(LinReg)
R2score = sklearn.metrics.r2_score(y_true=targets, y_pred=predictions)
print(R2score)
self.assertAlmostEqual(0.1212, R2score, places=1)
def test_default_configuration_iterative_fit(self):
for i in range(10):
predictions, targets = _test_regressor(GradientBoosting)
self.assertAlmostEqual(
0.35273007696557712,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree, sparse=True)
self.assertAlmostEqual(-0.020818312539637507,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(LibSVM_SVR)
self.assertAlmostEqual(0.12849591861430087,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree, sparse=True)
self.assertAlmostEqual(
0.021778487309118133,
sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree,)
self.assertAlmostEqual(0.1564592449511697,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(RandomForest, sparse=True)
self.assertAlmostEqual(0.24225685933770469,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(SGD)
self.assertAlmostEqual(0.066576586105546731,
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions))
def test_default_configuration(self):
for i in range(2):
predictions, targets = _test_regressor(XGradientBoostingRegressor)
self.assertAlmostEqual(0.34009199992306871,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(SGD)
self.assertAlmostEqual(0.092460881802630235,
sklearn.metrics.r2_score(y_true=targets,
y_pred=predictions))
def test_default_configuration(self):
for i in range(2):
predictions, targets = _test_regressor(DecisionTree,)
self.assertAlmostEqual(0.1564592449511697,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(RegDeepNet)
R2score = sklearn.metrics.r2_score(y_true=targets, y_pred=predictions)
print(R2score)
self.assertAlmostEqual(0.43, R2score)
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(XGradientBoostingRegressor)
self.assertAlmostEqual(0.34009199992306871,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(ExtraTreesRegressor)
self.assertAlmostEqual(0.4269923975466271, sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(ExtraTreesRegressor, sparse=True)
self.assertAlmostEqual(0.26287621251507987, sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(RandomForest)
self.assertAlmostEqual(0.41795829411621988,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(LibSVM_SVR,
sparse=True)
self.assertAlmostEqual(0.0098877566961463881,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_sparse(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree, sparse=True)
self.assertAlmostEqual(
-0.020818312539637507,
sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(GradientBoosting)
self.assertAlmostEqual(0.35273007696557712,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(DecisionTree, )
self.assertAlmostEqual(
0.14886750572325669,
sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(SGD)
self.assertAlmostEqual(
0.092460881802630235,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))