def test_bool_enum(self):
from lale.lib.sklearn import SVR
from lale.schemas import AnyOf, Bool, Null
SVR = SVR.customize_schema(shrinking=AnyOf(
types=[Bool(), Null()],
default=None,
desc="Whether to use the shrinking heuristic.",
))
ranges, dists = SVR.get_param_ranges()
expected_ranges = {
"kernel": ["poly", "rbf", "sigmoid", "linear"],
"degree": (2, 5, 3),
"gamma": (3.0517578125e-05, 8, None),
"tol": (0.0, 0.01, 0.001),
"C": (0.03125, 32768, 1.0),
"shrinking": [False, True, None],
}
self.maxDiff = None
self.assertEqual(ranges, expected_ranges)
if sklearn.__version__ >= "0.22":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.svm.SVC.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.svm.SVC.html
from lale.schemas import AnyOf, Bool, Enum, Float
SVC = SVC.customize_schema(
gamma=AnyOf(
types=[
Enum(["scale", "auto"]),
Float(
minimum=0.0,
exclusiveMinimum=True,
minimumForOptimizer=3.0517578125e-05,
maximumForOptimizer=8,
distribution="loguniform",
),
],
desc="Kernel coefficient for 'rbf', 'poly' and 'sigmoid'.",
default="scale",
),
break_ties=Bool(
desc="If true, decision_function_shape='ovr', and number of classes > 2, predict will break ties according to the confidence values of decision_function; otherwise the first class among the tied classes is returned.",
default=False,
),
set_as_available=True,
)
lale.docstrings.set_docstrings(SVC)
"post": []
},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
FunctionTransformer: lale.operators.IndividualOp
FunctionTransformer = lale.operators.make_operator(FunctionTransformerImpl,
_combined_schemas)
if sklearn.__version__ >= "0.22":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.preprocessing.FunctionTransformer.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.preprocessing.FunctionTransformer.html
from lale.schemas import Bool
FunctionTransformer = FunctionTransformer.customize_schema(
validate=Bool(
desc=
"Indicate that the input X array should be checked before calling ``func``.",
default=False,
),
pass_y=None,
)
lale.docstrings.set_docstrings(FunctionTransformerImpl,
FunctionTransformer._schemas)
},
}
GradientBoostingRegressor: lale.operators.PlannedIndividualOp
GradientBoostingRegressor = lale.operators.make_operator(
sklearn.ensemble.GradientBoostingRegressor, _combined_schemas
)
if sklearn.__version__ >= "0.22":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
# new: https://scikit-learn.org/0.22/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
from lale.schemas import AnyOf, Bool, Enum, Float
GradientBoostingRegressor = GradientBoostingRegressor.customize_schema(
presort=AnyOf(
types=[Bool(), Enum(["deprecated", "auto"])],
desc="This parameter is deprecated and will be removed in v0.24.",
default="deprecated",
),
ccp_alpha=Float(
desc="Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ccp_alpha will be chosen. By default, no pruning is performed.",
default=0.0,
forOptimizer=False,
min=0.0,
maxForOptimizer=0.1,
),
)
if sklearn.__version__ >= "0.24":
# old: https://scikit-learn.org/0.22/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
# new: https://scikit-learn.org/0.24/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
"post": []
},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
RobustScaler: lale.operators.PlannedIndividualOp
RobustScaler = lale.operators.make_operator(sklearn.preprocessing.RobustScaler,
_combined_schemas)
if sklearn.__version__ >= "0.24":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.preprocessing.RobustScaler.html
# new: https://scikit-learn.org/0.24/modules/generated/sklearn.preprocessing.RobustScaler.html
from lale.schemas import Bool
RobustScaler = RobustScaler.customize_schema(
unit_variance=Bool(
desc=
"If True, scale data so that normally distributed features have a variance of 1. In general, if the difference between the x-values of q_max and q_min for a standard normal distribution is greater than 1, the dataset will be scaled down. If less than 1, the dataset will be scaled up.",
default=False,
forOptimizer=True,
),
set_as_available=True,
)
lale.docstrings.set_docstrings(RobustScaler)
}
RidgeClassifier = lale.operators.make_operator(
sklearn.linear_model.RidgeClassifier, _combined_schemas)
if sklearn.__version__ >= "1.0":
# old: https://scikit-learn.org/0.24/modules/generated/sklearn.linear_model.RidgeClassifier.html
# new: https://scikit-learn.org/1.0/modules/generated/sklearn.linear_model.RidgeClassifier.html
from lale.schemas import Bool
RidgeClassifier = RidgeClassifier.customize_schema(
relevantToOptimizer=[
"alpha",
"fit_intercept",
"copy_X",
"max_iter",
"tol",
"solver",
],
normalize=Bool(
desc="""This parameter is ignored when fit_intercept is set to False.
If True, the regressors X will be normalized before regression by subtracting the mean and dividing by the l2-norm.
If you wish to standardize, please use StandardScaler before calling fit on an estimator with normalize=False.""",
default=False,
forOptimizer=False,
),
set_as_available=True,
)
lale.docstrings.set_docstrings(RidgeClassifier)
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_predict": _input_predict_schema,
"output_predict": _output_predict_schema,
"input_predict_proba": _input_predict_proba_schema,
"output_predict_proba": _output_predict_proba_schema,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
Pipeline = lale.operators.make_operator(_PipelineImpl, _combined_schemas)
if sklearn.__version__ >= "0.21":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.pipeline.Pipeline.html
# new: https://scikit-learn.org/0.21/modules/generated/sklearn.pipeline.Pipeline.html
Pipeline = typing.cast(
lale.operators.PlannedIndividualOp,
Pipeline.customize_schema(
verbose=Bool(
desc="If True, the time elapsed while fitting each step will be printed as it is completed.",
default=False,
),
set_as_available=True,
),
)
lale.docstrings.set_docstrings(Pipeline)
"tags": {
"pre": [],
"op": ["transformer"],
"post": []
},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
ColumnTransformer = lale.operators.make_operator(ColumnTransformerImpl,
_combined_schemas)
if sklearn.__version__ >= "0.21":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.compose.ColumnTransformer.html
# new: https://scikit-learn.org/0.21/modules/generated/sklearn.compose.ColumnTransformer.html
ColumnTransformer = typing.cast(
lale.operators.PlannedIndividualOp,
ColumnTransformer.customize_schema(verbose=Bool(
desc=
"If True, the time elapsed while fitting each transformer will be printed as it is completed.",
default=False,
), ),
)
lale.docstrings.set_docstrings(ColumnTransformerImpl,
ColumnTransformer._schemas)
'hyperparams': _hyperparams_schema,
'input_fit': _input_fit_schema,
'input_predict': _input_predict_schema,
'output_predict': _output_predict_schema
}
}
GradientBoostingRegressor: lale.operators.IndividualOp
GradientBoostingRegressor = lale.operators.make_operator(
GradientBoostingRegressorImpl, _combined_schemas)
if sklearn.__version__ >= '0.22':
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
from lale.schemas import AnyOf, Bool, Enum, Float
GradientBoostingRegressor = GradientBoostingRegressor.customize_schema(
presort=AnyOf(
types=[Bool(), Enum(['deprecated', 'auto'])],
desc='This parameter is deprecated and will be removed in v0.24.',
default='deprecated'),
ccp_alpha=Float(
desc=
'Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ccp_alpha will be chosen. By default, no pruning is performed.',
default=0.0,
forOptimizer=True,
min=0.0,
maxForOptimizer=0.1))
lale.docstrings.set_docstrings(GradientBoostingRegressorImpl,
GradientBoostingRegressor._schemas)
"op": ["estimator", "transformer"],
"post": []
},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_predict": _input_predict_schema,
"output_predict": _output_predict_schema,
"input_predict_proba": _input_predict_proba_schema,
"output_predict_proba": _output_predict_proba_schema,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
Pipeline = lale.operators.make_operator(PipelineImpl, _combined_schemas)
if sklearn.__version__ >= "0.21":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.pipeline.Pipeline.html
# new: https://scikit-learn.org/0.21/modules/generated/sklearn.pipeline.Pipeline.html
Pipeline = typing.cast(
lale.operators.PlannedIndividualOp,
Pipeline.customize_schema(verbose=Bool(
desc=
"If True, the time elapsed while fitting each step will be printed as it is completed.",
default=False,
), ),
)
lale.docstrings.set_docstrings(PipelineImpl, Pipeline._schemas)
"type": "object",
"tags": {"pre": [], "op": ["estimator", "classifier"], "post": []},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_fit_schema,
"input_predict": _input_predict_schema,
"output_predict": _output_predict_schema,
"input_predict_proba": _input_predict_proba_schema,
"output_predict_proba": _output_predict_proba_schema,
},
}
SnapRandomForestClassifier = lale.operators.make_operator(
_SnapRandomForestClassifierImpl, _combined_schemas
)
if snapml_installed and snapml.__version__ > "1.7.8": # type: ignore # noqa
from lale.schemas import Bool
SnapRandomForestClassifier = SnapRandomForestClassifier.customize_schema(
compress_trees=Bool(
desc="""Compress trees after training for fast inference.""",
default=False,
forOptimizer=False,
),
set_as_available=True,
)
lale.docstrings.set_docstrings(SnapRandomForestClassifier)
"output_predict": _output_predict_schema,
},
}
LinearRegression: lale.operators.PlannedIndividualOp
LinearRegression = lale.operators.make_operator(LinearRegressionImpl,
_combined_schemas)
if sklearn.__version__ >= "0.24":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.linear_model.LinearRegression.html
# new: https://scikit-learn.org/0.24/modules/generated/sklearn.linear_model.LinearRegression.html
from lale.schemas import JSON, Bool
LinearRegression = LinearRegression.customize_schema(positive=Bool(
desc="When set to True, forces the coefficients to be positive.",
default=False,
forOptimizer=False,
))
LinearRegression = LinearRegression.customize_schema(constraint=JSON({
"description":
"Setting positive=True is only supported for dense arrays.",
"anyOf": [
{
"type": "object",
"properties": {
"positive": {
"enum": [False]
}
}
},
{
"tags": {
"pre": ["~categoricals"],
"op": ["transformer", "interpretable"],
"post": [],
},
"properties": {
"hyperparams": _hyperparams_schema,
"input_fit": _input_schema_fit,
"input_transform": _input_transform_schema,
"output_transform": _output_transform_schema,
},
}
MinMaxScaler: lale.operators.PlannedIndividualOp
MinMaxScaler = lale.operators.make_operator(MinMaxScalerImpl,
_combined_schemas)
if sklearn.__version__ >= "0.24":
# old: https://scikit-learn.org/0.22/modules/generated/sklearn.preprocessing.MinMaxScaler.html
# new: https://scikit-learn.org/0.24/modules/generated/sklearn.preprocessing.MinMaxScaler.html
from lale.schemas import Bool
MinMaxScaler = MinMaxScaler.customize_schema(clip=Bool(
desc=
"Set to True to clip transformed values of held-out data to provided feature range.",
default=False,
forOptimizer=False,
), )
lale.docstrings.set_docstrings(MinMaxScalerImpl, MinMaxScaler._schemas)
constraint=AnyOf(
[Object(n_clusters=Null()),
Object(distance_threshold=Null())],
desc="n_clusters must be None if distance_threshold is not None.",
),
)
FeatureAgglomeration = FeatureAgglomeration.customize_schema(
constraint=AnyOf(
[
Object(compute_full_tree=Enum(["True"])),
Object(distance_threshold=Null()),
],
desc=
"compute_full_tree must be True if distance_threshold is not None.",
))
if sklearn.__version__ >= "0.24":
# old: https://scikit-learn.org/0.21/modules/generated/sklearn.cluster.FeatureAgglomeration.html
# new: https://scikit-learn.org/0.24/modules/generated/sklearn.cluster.FeatureAgglomeration.html
from lale.schemas import Bool
FeatureAgglomeration = FeatureAgglomeration.customize_schema(
compute_distances=Bool(
desc=
"Computes distances between clusters even if distance_threshold is not used. This can be used to make dendrogram visualization, but introduces a computational and memory overhead.",
default=False,
forOptimizer=False,
), )
lale.docstrings.set_docstrings(FeatureAgglomeration)
'hyperparams': _hyperparams_schema,
'input_fit': _input_fit_schema,
'input_predict': _input_predict_schema,
'output_predict': _output_predict_schema
}
}
GradientBoostingRegressor: lale.operators.IndividualOp
GradientBoostingRegressor = lale.operators.make_operator(
GradientBoostingRegressorImpl, _combined_schemas)
if sklearn.__version__ >= '0.22':
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
from lale.schemas import AnyOf, Bool, Enum, Float
GradientBoostingRegressor = GradientBoostingRegressor.customize_schema(
presort=AnyOf(
types=[Bool(), Enum(['deprecated'])],
desc='This parameter is deprecated and will be removed in v0.24.',
default='deprecated'),
ccp_alpha=Float(
desc=
'Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ccp_alpha will be chosen. By default, no pruning is performed.',
default=0.0,
forOptimizer=True,
min=0.0,
maxForOptimizer=0.1))
lale.docstrings.set_docstrings(GradientBoostingRegressorImpl,
GradientBoostingRegressor._schemas)
def predict_proba(self, X):
return self._wrapped_model.predict_proba(X)
DecisionTreeClassifier: lale.operators.IndividualOp
DecisionTreeClassifier = lale.operators.make_operator(
DecisionTreeClassifierImpl, _combined_schemas)
if sklearn.__version__ >= "0.22":
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.tree.DecisionTreeClassifier.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.tree.DecisionTreeClassifier.html
from lale.schemas import AnyOf, Bool, Enum, Float
DecisionTreeClassifier = DecisionTreeClassifier.customize_schema(
presort=AnyOf(
types=[Bool(), Enum(["deprecated"])],
desc="This parameter is deprecated and will be removed in v0.24.",
default="deprecated",
),
ccp_alpha=Float(
desc=
"Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ccp_alpha will be chosen. By default, no pruning is performed.",
default=0.0,
forOptimizer=True,
min=0.0,
maxForOptimizer=0.1,
),
)
lale.docstrings.set_docstrings(DecisionTreeClassifierImpl,
DecisionTreeClassifier._schemas)
'type': 'object',
'tags': {
'pre': [],
'op': ['transformer'],
'post': []
},
'properties': {
'hyperparams': _hyperparams_schema,
'input_fit': _input_fit_schema,
'input_transform': _input_transform_schema,
'output_transform': _output_transform_schema
}
}
FunctionTransformer: lale.operators.IndividualOp
FunctionTransformer = lale.operators.make_operator(FunctionTransformerImpl,
_combined_schemas)
if sklearn.__version__ >= '0.22':
# old: https://scikit-learn.org/0.20/modules/generated/sklearn.preprocessing.FunctionTransformer.html
# new: https://scikit-learn.org/0.23/modules/generated/sklearn.preprocessing.FunctionTransformer.html
from lale.schemas import Bool
FunctionTransformer = FunctionTransformer.customize_schema(validate=Bool(
desc=
'Indicate that the input X array should be checked before calling ``func``.',
default=False),
pass_y=None)
lale.docstrings.set_docstrings(FunctionTransformerImpl,
FunctionTransformer._schemas)