def get_hyperparameter_search_space(dataset_properties=None):
n_neighbors = UniformIntegerHyperparameter(name="n_neighbors",
lower=1,
upper=100,
default=1)
weights = CategoricalHyperparameter(name="weights",
choices=["uniform", "distance"],
default="uniform")
metric = UnParametrizedHyperparameter(name="metric", value="minkowski")
algorithm = Constant(name='algorithm', value="auto")
p = CategoricalHyperparameter(name="p", choices=[1, 2, 5], default=2)
leaf_size = Constant(name="leaf_size", value=30)
# Unparametrized
# TODO: If we further parametrize 'metric' we need more metric params
metric = UnParametrizedHyperparameter(name="metric", value="minkowski")
cs = ConfigurationSpace()
cs.add_hyperparameter(n_neighbors)
cs.add_hyperparameter(weights)
cs.add_hyperparameter(metric)
cs.add_hyperparameter(algorithm)
cs.add_hyperparameter(p)
cs.add_hyperparameter(leaf_size)
# Conditions
metric_p = EqualsCondition(parent=metric, child=p, value="minkowski")
cs.add_condition(metric_p)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
N = UniformIntegerHyperparameter("N", 5, 20, default=10)
precond = UniformFloatHyperparameter("precond", 0, 0.5, default=0.1)
cs = ConfigurationSpace()
cs.add_hyperparameter(N)
cs.add_hyperparameter(precond)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
C = cs.add_hyperparameter(UniformFloatHyperparameter(
"C", 0.03125, 32768, log=True, default=1.0))
loss = cs.add_hyperparameter(CategoricalHyperparameter(
"loss", ["epsilon_insensitive", "squared_epsilon_insensitive"],
default="squared_epsilon_insensitive"))
# Random Guess
epsilon = cs.add_hyperparameter(UniformFloatHyperparameter(
name="epsilon", lower=0.001, upper=1, default=0.1, log=True))
dual = cs.add_hyperparameter(Constant("dual", "False"))
# These are set ad-hoc
tol = cs.add_hyperparameter(UniformFloatHyperparameter(
"tol", 1e-5, 1e-1, default=1e-4, log=True))
fit_intercept = cs.add_hyperparameter(Constant("fit_intercept", "True"))
intercept_scaling = cs.add_hyperparameter(Constant(
"intercept_scaling", 1))
dual_and_loss = ForbiddenAndConjunction(
ForbiddenEqualsClause(dual, "False"),
ForbiddenEqualsClause(loss, "epsilon_insensitive")
)
cs.add_forbidden_clause(dual_and_loss)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
n_estimators = cs.add_hyperparameter(Constant("n_estimators", 100))
criterion = cs.add_hyperparameter(
CategoricalHyperparameter("criterion", ["gini", "entropy"],
default="gini"))
max_features = cs.add_hyperparameter(
UniformFloatHyperparameter("max_features", 0.5, 5, default=1))
max_depth = cs.add_hyperparameter(
UnParametrizedHyperparameter(name="max_depth", value="None"))
min_samples_split = cs.add_hyperparameter(
UniformIntegerHyperparameter("min_samples_split", 2, 20,
default=2))
min_samples_leaf = cs.add_hyperparameter(
UniformIntegerHyperparameter("min_samples_leaf", 1, 20, default=1))
min_weight_fraction_leaf = cs.add_hyperparameter(
Constant('min_weight_fraction_leaf', 0.))
bootstrap = cs.add_hyperparameter(
CategoricalHyperparameter("bootstrap", ["True", "False"],
default="False"))
return cs
def get_hyperparameter_search_space(dataset_properties=None):
loss = CategoricalHyperparameter(
"loss",
["hinge", "log", "modified_huber", "squared_hinge", "perceptron"],
default="hinge")
penalty = CategoricalHyperparameter("penalty",
["l1", "l2", "elasticnet"],
default="l2")
alpha = UniformFloatHyperparameter("alpha",
10**-7,
10**-1,
log=True,
default=0.0001)
l1_ratio = UniformFloatHyperparameter("l1_ratio", 0, 1, default=0.15)
fit_intercept = UnParametrizedHyperparameter("fit_intercept", "True")
n_iter = UniformIntegerHyperparameter("n_iter", 5, 1000, default=20)
epsilon = UniformFloatHyperparameter("epsilon",
1e-5,
1e-1,
default=1e-4,
log=True)
learning_rate = CategoricalHyperparameter(
"learning_rate", ["optimal", "invscaling", "constant"],
default="optimal")
eta0 = UniformFloatHyperparameter("eta0", 10**-7, 0.1, default=0.01)
power_t = UniformFloatHyperparameter("power_t", 1e-5, 1, default=0.5)
# This does not allow for other resampling methods!
class_weight = CategoricalHyperparameter("class_weight",
["None", "auto"],
default="None")
cs = ConfigurationSpace()
cs.add_hyperparameter(loss)
cs.add_hyperparameter(penalty)
cs.add_hyperparameter(alpha)
cs.add_hyperparameter(l1_ratio)
cs.add_hyperparameter(fit_intercept)
cs.add_hyperparameter(n_iter)
cs.add_hyperparameter(epsilon)
cs.add_hyperparameter(learning_rate)
cs.add_hyperparameter(eta0)
cs.add_hyperparameter(power_t)
cs.add_hyperparameter(class_weight)
# TODO add passive/aggressive here, although not properly documented?
elasticnet = EqualsCondition(l1_ratio, penalty, "elasticnet")
epsilon_condition = EqualsCondition(epsilon, loss, "modified_huber")
# eta0 seems to be always active according to the source code; when
# learning_rate is set to optimial, eta0 is the starting value:
# https://github.com/scikit-learn/scikit-learn/blob/0.15.X/sklearn/linear_model/sgd_fast.pyx
#eta0_and_inv = EqualsCondition(eta0, learning_rate, "invscaling")
#eta0_and_constant = EqualsCondition(eta0, learning_rate, "constant")
#eta0_condition = OrConjunction(eta0_and_inv, eta0_and_constant)
power_t_condition = EqualsCondition(power_t, learning_rate,
"invscaling")
cs.add_condition(elasticnet)
cs.add_condition(epsilon_condition)
cs.add_condition(power_t_condition)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
# base_estimator = Constant(name="base_estimator", value="None")
n_estimators = cs.add_hyperparameter(
UniformIntegerHyperparameter(name="n_estimators",
lower=50,
upper=500,
default=50,
log=False))
learning_rate = cs.add_hyperparameter(
UniformFloatHyperparameter(name="learning_rate",
lower=0.0001,
upper=2,
default=0.1,
log=True))
algorithm = cs.add_hyperparameter(
CategoricalHyperparameter(name="algorithm",
choices=["SAMME.R", "SAMME"],
default="SAMME.R"))
max_depth = cs.add_hyperparameter(
UniformIntegerHyperparameter(name="max_depth",
lower=1,
upper=10,
default=1,
log=False))
return cs
def get_hyperparameter_search_space(dataset_properties=None):
n_components = UniformIntegerHyperparameter("n_components",
10,
2000,
default=100)
kernel = CategoricalHyperparameter(
'kernel', ['poly', 'rbf', 'sigmoid', 'cosine'], 'rbf')
degree = UniformIntegerHyperparameter('degree', 2, 5, 3)
gamma = UniformFloatHyperparameter("gamma",
3.0517578125e-05,
8,
log=True,
default=1.0)
coef0 = UniformFloatHyperparameter("coef0", -1, 1, default=0)
cs = ConfigurationSpace()
cs.add_hyperparameter(n_components)
cs.add_hyperparameter(kernel)
cs.add_hyperparameter(degree)
cs.add_hyperparameter(gamma)
cs.add_hyperparameter(coef0)
degree_depends_on_poly = EqualsCondition(degree, kernel, "poly")
coef0_condition = InCondition(coef0, kernel, ["poly", "sigmoid"])
gamma_condition = InCondition(gamma, kernel, ["poly", "rbf"])
cs.add_condition(degree_depends_on_poly)
cs.add_condition(coef0_condition)
cs.add_condition(gamma_condition)
return cs
def test_add_forbidden(self):
m = numpy.ones([2, 3])
preprocessors_list = ['pa', 'pb']
classifier_list = ['ca', 'cb', 'cc']
cs = ConfigurationSpace()
preprocessor = CategoricalHyperparameter(name='preprocessor',
choices=preprocessors_list)
classifier = CategoricalHyperparameter(name='classifier',
choices=classifier_list)
cs.add_hyperparameter(preprocessor)
cs.add_hyperparameter(classifier)
new_cs = autosklearn.pipeline.create_searchspace_util.add_forbidden(
conf_space=cs,
node_0_list=preprocessors_list,
node_1_list=classifier_list,
matches=m,
node_0_name='preprocessor',
node_1_name="classifier")
self.assertEqual(len(new_cs.forbidden_clauses), 0)
self.assertIsInstance(new_cs, ConfigurationSpace)
m[1, 1] = 0
new_cs = autosklearn.pipeline.create_searchspace_util.add_forbidden(
conf_space=cs,
node_0_list=preprocessors_list,
node_1_list=classifier_list,
matches=m,
node_0_name='preprocessor',
node_1_name="classifier")
self.assertEqual(len(new_cs.forbidden_clauses), 1)
self.assertEqual(new_cs.forbidden_clauses[0].components[0].value, 'cb')
self.assertEqual(new_cs.forbidden_clauses[0].components[1].value, 'pb')
self.assertIsInstance(new_cs, ConfigurationSpace)
def get_hyperparameter_search_space(dataset_properties=None):
# TODO add replace by zero!
strategy = CategoricalHyperparameter("strategy", ["none", "weighting"],
default="none")
cs = ConfigurationSpace()
cs.add_hyperparameter(strategy)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
target_dim = UniformIntegerHyperparameter("target_dim",
10,
256,
default=128)
cs = ConfigurationSpace()
cs.add_hyperparameter(target_dim)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
max_epochs = UniformIntegerHyperparameter("max_epochs",
1,
20,
default=2)
cs = ConfigurationSpace()
cs.add_hyperparameter(max_epochs)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
reg_param = UniformFloatHyperparameter('reg_param',
0.0,
10.0,
default=0.5)
cs = ConfigurationSpace()
cs.add_hyperparameter(reg_param)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
keep_variance = UniformFloatHyperparameter(
"keep_variance", 0.5, 0.9999, default=0.9999)
whiten = CategoricalHyperparameter(
"whiten", ["False", "True"], default="False")
cs = ConfigurationSpace()
cs.add_hyperparameter(keep_variance)
cs.add_hyperparameter(whiten)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
gamma = UniformFloatHyperparameter(
"gamma", 0.3, 2., default=1.0)
n_components = UniformIntegerHyperparameter(
"n_components", 50, 10000, default=100, log=True)
cs = ConfigurationSpace()
cs.add_hyperparameter(gamma)
cs.add_hyperparameter(n_components)
return cs
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
alpha = cs.add_hyperparameter(UniformFloatHyperparameter(
"alpha", 10 ** -5, 10., log=True, default=1.))
fit_intercept = cs.add_hyperparameter(UnParametrizedHyperparameter(
"fit_intercept", "True"))
tol = cs.add_hyperparameter(UniformFloatHyperparameter(
"tol", 1e-5, 1e-1, default=1e-4, log=True))
return cs
def test_hyperparameters_with_valid_condition(self):
cs = ConfigurationSpace()
hp1 = CategoricalHyperparameter("parent", [0, 1])
cs.add_hyperparameter(hp1)
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cs.add_hyperparameter(hp2)
cond = EqualsCondition(hp2, hp1, 0)
cs.add_condition(cond)
self.assertEqual(len(cs._hyperparameters), 2)
def test_condition_without_added_hyperparameters(self):
cs = ConfigurationSpace()
hp1 = CategoricalHyperparameter("parent", [0, 1])
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cond = EqualsCondition(hp2, hp1, 0)
self.assertRaisesRegexp(
ValueError, "Child hyperparameter 'child' not "
"in configuration space.", cs.add_condition, cond)
cs.add_hyperparameter(hp1)
self.assertRaisesRegexp(
ValueError, "Child hyperparameter 'child' not "
"in configuration space.", cs.add_condition, cond)
# Test also the parent hyperparameter
cs2 = ConfigurationSpace()
cs2.add_hyperparameter(hp2)
self.assertRaisesRegexp(
ValueError, "Parent hyperparameter 'parent' "
"not in configuration space.", cs2.add_condition, cond)
def test_get_conditions(self):
cs = ConfigurationSpace()
hp1 = CategoricalHyperparameter("parent", [0, 1])
cs.add_hyperparameter(hp1)
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cs.add_hyperparameter(hp2)
self.assertEqual([], cs.get_conditions())
cond1 = EqualsCondition(hp2, hp1, 0)
cs.add_condition(cond1)
self.assertEqual([cond1], cs.get_conditions())
def get_hyperparameter_search_space(dataset_properties=None):
alpha = UniformFloatHyperparameter(name="alpha",
lower=0.0001,
upper=10,
default=1.0,
log=True)
cs = ConfigurationSpace()
cs.add_hyperparameter(alpha)
return cs
def test_add_configuration_space(self):
cs = ConfigurationSpace()
hp1 = cs.add_hyperparameter(CategoricalHyperparameter(
"input1", [0, 1]))
forb1 = cs.add_forbidden_clause(ForbiddenEqualsClause(hp1, 1))
hp2 = cs.add_hyperparameter(
UniformIntegerHyperparameter("child", 0, 10))
cond = cs.add_condition(EqualsCondition(hp2, hp1, 0))
cs2 = ConfigurationSpace()
cs2.add_configuration_space('prefix', cs, delimiter='__')
self.assertEqual(
str(cs2), '''Configuration space object:
Hyperparameters:
prefix__child, Type: UniformInteger, Range: [0, 10], Default: 5
prefix__input1, Type: Categorical, Choices: {0, 1}, Default: 0
Conditions:
prefix__child | prefix__input1 == 0
Forbidden Clauses:
Forbidden: prefix__input1 == 1
''')
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
n_neighbors = cs.add_hyperparameter(UniformIntegerHyperparameter(
name="n_neighbors", lower=1, upper=100, log=True, default=1))
weights = cs.add_hyperparameter(CategoricalHyperparameter(
name="weights", choices=["uniform", "distance"], default="uniform"))
p = cs.add_hyperparameter(CategoricalHyperparameter(
name="p", choices=[1, 2], default=2))
return cs
def get_hyperparameter_search_space(dataset_properties=None):
percentile = UniformFloatHyperparameter(
"percentile", lower=1, upper=99, default=50)
score_func = UnParametrizedHyperparameter(
name="score_func", value="f_regression")
cs = ConfigurationSpace()
cs.add_hyperparameter(percentile)
cs.add_hyperparameter(score_func)
return cs
def test_get_hyperparameter(self):
cs = ConfigurationSpace()
hp1 = CategoricalHyperparameter("parent", [0, 1])
cs.add_hyperparameter(hp1)
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cs.add_hyperparameter(hp2)
retval = cs.get_hyperparameter("parent")
self.assertEqual(hp1, retval)
retval = cs.get_hyperparameter("child")
self.assertEqual(hp2, retval)
self.assertRaises(KeyError, cs.get_hyperparameter, "grandfather")
def get_hyperparameter_search_space(dataset_properties=None):
loss = CategoricalHyperparameter("loss", ["hinge", "squared_hinge"],
default="hinge")
fit_intercept = UnParametrizedHyperparameter("fit_intercept", "True")
n_iter = UniformIntegerHyperparameter("n_iter", 5, 1000, default=20)
C = UniformFloatHyperparameter("C", 1e-5, 10, 1, log=True)
cs = ConfigurationSpace()
cs.add_hyperparameter(loss)
cs.add_hyperparameter(fit_intercept)
cs.add_hyperparameter(n_iter)
cs.add_hyperparameter(C)
return cs
def test_check_forbidden_with_sampled_vector_configuration(self):
cs = ConfigurationSpace()
metric = CategoricalHyperparameter("metric", ["minkowski", "other"])
cs.add_hyperparameter(metric)
forbidden = ForbiddenEqualsClause(metric, "other")
cs.add_forbidden_clause(forbidden)
configuration = Configuration(cs,
vector=np.ones(1,
dtype=[('metric', int)]))
self.assertRaisesRegexp(ValueError, "violates forbidden clause",
cs._check_forbidden, configuration)
def get_hyperparameter_search_space(dataset_properties=None):
nugget = UniformFloatHyperparameter(
name="nugget", lower=0.0001, upper=10, default=0.1, log=True)
thetaL = UniformFloatHyperparameter(
name="thetaL", lower=1e-6, upper=1e-3, default=1e-4, log=True)
thetaU = UniformFloatHyperparameter(
name="thetaU", lower=0.2, upper=10, default=1.0, log=True)
cs = ConfigurationSpace()
cs.add_hyperparameter(nugget)
cs.add_hyperparameter(thetaL)
cs.add_hyperparameter(thetaU)
return cs
def test_get_hyperparameters(self):
cs = ConfigurationSpace()
self.assertEqual(0, len(cs.get_hyperparameters()))
hp1 = CategoricalHyperparameter("parent", [0, 1])
cs.add_hyperparameter(hp1)
self.assertEqual([hp1], cs.get_hyperparameters())
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cs.add_hyperparameter(hp2)
cond1 = EqualsCondition(hp2, hp1, 1)
cs.add_condition(cond1)
self.assertEqual([hp1, hp2], cs.get_hyperparameters())
# TODO: I need more tests for the topological sort!
self.assertEqual([hp1, hp2], cs.get_hyperparameters())
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
shrinkage = cs.add_hyperparameter(CategoricalHyperparameter(
"shrinkage", ["None", "auto", "manual"], default="None"))
shrinkage_factor = cs.add_hyperparameter(UniformFloatHyperparameter(
"shrinkage_factor", 0., 1., 0.5))
n_components = cs.add_hyperparameter(UniformIntegerHyperparameter(
'n_components', 1, 250, default=10))
tol = cs.add_hyperparameter(UniformFloatHyperparameter(
"tol", 1e-5, 1e-1, default=1e-4, log=True))
cs.add_condition(EqualsCondition(shrinkage_factor, shrinkage, "manual"))
return cs
def test_condition_with_cycles(self):
cs = ConfigurationSpace()
hp1 = CategoricalHyperparameter("parent", [0, 1])
cs.add_hyperparameter(hp1)
hp2 = UniformIntegerHyperparameter("child", 0, 10)
cs.add_hyperparameter(hp2)
cond1 = EqualsCondition(hp2, hp1, 0)
cs.add_condition(cond1)
cond2 = EqualsCondition(hp1, hp2, 0)
self.assertRaisesRegexp(
ValueError, "Hyperparameter configuration "
"contains a cycle \[\['child', 'parent'\]\]", cs.add_condition,
cond2)
def get_hyperparameter_search_space(dataset_properties=None):
cs = ConfigurationSpace()
loss = cs.add_hyperparameter(
CategoricalHyperparameter("loss",
["ls", "lad", "huber", "quantile"],
default="ls"))
learning_rate = cs.add_hyperparameter(
UniformFloatHyperparameter(name="learning_rate",
lower=0.0001,
upper=1,
default=0.1,
log=True))
n_estimators = cs.add_hyperparameter(Constant("n_estimators", 100))
max_depth = cs.add_hyperparameter(
UniformIntegerHyperparameter(name="max_depth",
lower=1,
upper=10,
default=3))
min_samples_split = cs.add_hyperparameter(
UniformIntegerHyperparameter(name="min_samples_split",
lower=2,
upper=20,
default=2,
log=False))
min_samples_leaf = cs.add_hyperparameter(
UniformIntegerHyperparameter(name="min_samples_leaf",
lower=1,
upper=20,
default=1,
log=False))
min_weight_fraction_leaf = cs.add_hyperparameter(
UnParametrizedHyperparameter("min_weight_fraction_leaf", 0.))
subsample = cs.add_hyperparameter(
UniformFloatHyperparameter(name="subsample",
lower=0.01,
upper=1.0,
default=1.0,
log=False))
max_features = cs.add_hyperparameter(
UniformFloatHyperparameter("max_features", 0.5, 5, default=1))
max_leaf_nodes = cs.add_hyperparameter(
UnParametrizedHyperparameter(name="max_leaf_nodes", value="None"))
alpha = cs.add_hyperparameter(
UniformFloatHyperparameter("alpha",
lower=0.75,
upper=0.99,
default=0.9))
cs.add_condition(InCondition(alpha, loss, ['huber', 'quantile']))
return cs
