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(KNearestNeighborsRegressor)
self.assertAlmostEqual(
0.068600456340847438,
sklearn.metrics.r2_score(targets, predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = \
_test_regressor(AdaboostRegressor, dataset='boston')
self.assertAlmostEqual(
0.11053868761882502,
sklearn.metrics.r2_score(targets, 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(RandomForest)
self.assertAlmostEqual(
0.41224692924630502,
sklearn.metrics.r2_score(y_true=targets, y_pred=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):
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(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(-0.077540100211211049,
sklearn.metrics.r2_score(targets,
predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = \
_test_regressor(AdaboostRegressor, dataset='boston')
self.assertAlmostEqual(0.11053868761882502,
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_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(ExtraTreesRegressor)
self.assertAlmostEqual(0.4269923975466271,
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_sparse(self):
for i in range(10):
predictions, targets = \
_test_regressor(AdaboostRegressor, sparse=True, dataset='boston')
self.assertAlmostEqual(
-0.077540100211211049,
sklearn.metrics.r2_score(targets, 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):
# 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):
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_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_digits(self):
for i in range(10):
predictions, targets = _test_regressor(SGD, dataset='boston')
self.assertAlmostEqual(-2.9165866511775519e+31,
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_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(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(RandomForest, sparse=True)
self.assertAlmostEqual(
0.24117530425422551,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration_digits(self):
for i in range(10):
predictions, targets = _test_regressor(SGD, dataset='boston')
self.assertAlmostEqual(
-2.9165866511775519e+31,
sklearn.metrics.r2_score(y_true=targets, y_pred=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(SGD)
self.assertAlmostEqual(
0.092460881802630235,
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(RandomForest, sparse=True)
self.assertAlmostEqual(0.24117530425422551,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))
def test_default_configuration(self):
for i in range(10):
predictions, targets = _test_regressor(RandomForest)
self.assertAlmostEqual(0.41224692924630502,
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(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(LibSVM_SVR, sparse=True)
self.assertAlmostEqual(
0.0098877566961463881,
sklearn.metrics.r2_score(y_true=targets, y_pred=predictions))