class GroupUpHyperparameter(hyperparams.Hyperparams):
verbose = UniformBool(default=False,
semantic_types=['http://schema.org/Boolean',
'https://metadata.datadrivendiscovery.org/types/ControlParameter'])
use_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to force primitive to operate on. If any specified column cannot be parsed, it is skipped.",
)
# exclude_columns = hyperparams.Set(
# elements=hyperparams.Hyperparameter[int](-1),
# default=(),
# semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
# description="A set of column indices to not operate on. Applicable only if \"use_columns\" is not provided.",
# )
return_result = hyperparams.Enumeration(
values=['append', 'replace', 'new'],
default='replace',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Should parsed columns be appended, should they replace original columns, or should only parsed columns be returned? This hyperparam is ignored if use_semantic_types is set to false.",
)
# use_semantic_types = hyperparams.UniformBool(
# default=False,
# semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
# description="Controls whether semantic_types metadata will be used for filtering columns in input dataframe. Setting this to false makes the code ignore return_result and will produce only the output dataframe"
# )
add_index_columns = hyperparams.UniformBool(
default=True,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Also include primary index columns if input data has them. Applicable only if \"return_result\" is set to \"new\".",
)
class MiceHyperparameter(Hyperparams):
verbose = UniformBool(
default=False,
semantic_types=[
'http://schema.org/Boolean',
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
])
class EncHyperparameter(hyperparams.Hyperparams):
text2int = UniformBool(
default=False,
description=
'Whether to convert everything to numerical. For text columns, each row may get converted into a column',
semantic_types=[
'http://schema.org/Boolean',
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
])
n_limit = UniformInt(
lower=5,
upper=100,
default=12,
description='Limits the maximum number of columns to generate',
semantic_types=[
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
categorical_features = Enumeration(
values=['95in10'],
default='95in10',
description='rule to declare categorical',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
])
class KnnHyperparameter(Hyperparams):
# A reasonable upper bound would the size of the input. For now using 100.
k = UniformInt(lower=1, upper=100, default=5,
description='Number of neighbors',
semantic_types=['http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/TuningParameter'])
verbose = UniformBool(default=False,
semantic_types=['http://schema.org/Boolean',
'https://metadata.datadrivendiscovery.org/types/ControlParameter'])
class EchoRegressor_Hyperparams(hyperparams.Hyperparams):
# regularization strength
alpha = Uniform(
lower=0,
upper=10,
default=1,
q=.1,
description='regularization strength',
semantic_types=[
"http://schema.org/Float",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
#
diagonal = UniformBool(
default=False,
description=
'assume diagonal covariance, leading to sparsity in data basis (instead of covariance eigenbasis)',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
class EchoIB_Hyperparams(hyperparams.Hyperparams):
n_hidden = UniformInt(
lower=1,
upper=401,
default=200,
description='number of hidden factors learned',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
beta = Uniform(
lower=0,
upper=1000,
default=.1,
q=.01,
description=
'Lagrange multiplier for beta (applied to regularizer I(X:Z)): defining tradeoff btwn label relevance : compression.',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
epochs = UniformInt(
lower=1,
upper=10000,
default=100,
description='number of epochs to train',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
batch = UniformInt(
lower=10,
upper=1000,
default=50,
description='batch_size',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
lr = LogUniform(
lower=0.00001,
upper=0.101,
default=0.001,
description='learning rate for Adam optimization',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
activation = Enumeration(
values=['relu', 'tanh', 'elu'],
default='tanh',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="activation to use for intermediate activations")
convolutional = UniformBool(
default=False,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="whether to use a convolutional architecture")
task = Enumeration(
values=['CLASSIFICATION', 'REGRESSION'],
default='CLASSIFICATION',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description='task type')
use_as_modeling = UniformBool(
default=False,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"whether to return constructed features AND predictions (else, used for modeling i.e. only predictions"
)
units = UniformInt(
lower=10,
upper=401,
default=200,
description='# neurons in FC intermediate layers',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
layers = UniformInt(
lower=1,
upper=8,
default=2,
description='# of layers',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
error_on_no_input = hyperparams.UniformBool(
default=True,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"Throw an exception if no input column is selected/provided. Defaults to true to behave like sklearn. To prevent pipelines from breaking set this to False."
)
gpus = Uniform(
lower=0,
upper=5,
q=1,
default=1,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ResourcesUseParameter'
],
description='GPUs to Use')
class SDNE_Hyperparams(hyperparams.Hyperparams):
dimension = UniformInt(
lower=10,
upper=200,
default=10,
#q = 5,
description='dimension of latent embedding',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
epochs = UniformInt(
lower=1,
upper=500,
default=50,
#q = 5e-8,
description='number of epochs to train',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
beta = UniformInt(
lower=1,
upper=20,
default=5,
#q = 1,
description=
'seen edge reconstruction weight (to account for sparsity in links for reconstructing adjacency. matrix B in Wang et al 2016',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
alpha = Uniform(
lower=1e-8,
upper=1,
default=1e-5,
#q = 5e-8,
description='first order proximity weight',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
lr = Uniform(
lower=1e-5,
upper=1e-2,
default=5e-4,
#q = 5e-8,
description='learning rate (constant across training)',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
depth = UniformInt(
lower=1,
upper=10,
default=3,
#q = 5,
description='number of hidden layers',
semantic_types=[
"http://schema.org/Integer",
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
])
return_list = UniformBool(
default=False,
description='for testing',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])