class Hyperparams(hyperparams.Hyperparams):
n_neighbors = hyperparams.UniformInt(
lower=0,
upper=sys.maxsize,
default=5,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"number of neighbors on which to make classification decision",
)
distance_metric = hyperparams.Enumeration(
default="euclidean",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
values=["euclidean", "dtw"],
description=
"whether to use euclidean or dynamic time warping distance metric in KNN computation",
)
sample_weighting = hyperparams.Enumeration(
default="uniform",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
values=["uniform", "inverse_distance"],
description=
"whether to weight points uniformly or by the inverse of their distance",
)
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default="HDBSCAN",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
values=["DBSCAN", "HDBSCAN"],
description="type of clustering algorithm to use",
)
eps = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=0.5,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"maximum distance between two samples for them to be considered as in \
the same neigborhood, used in DBSCAN algorithm",
)
min_cluster_size = hyperparams.UniformInt(
lower=2,
upper=sys.maxsize,
default=5,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="the minimum size of clusters",
)
min_samples = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=5,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"The number of samples in a neighbourhood for a point to be considered a core point.",
)
cluster_selection_method = hyperparams.Enumeration(
default="eom",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
values=["leaf", "eom"],
description=
"Determines how clusters are selected from the cluster hierarchy tree for HDBSCAN",
)
required_output = hyperparams.Enumeration(
default="feature",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
values=["prediction", "feature"],
description=
"Determines whether the output is a dataframe with just predictions,\
or an additional feature added to the input dataframe.",
)
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='HDBSCAN',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['DBSCAN', 'HDBSCAN'],
description='type of clustering algorithm to use')
eps = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=0.5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'maximum distance between two samples for them to be considered as in the same neigborhood, \
used in DBSCAN algorithm')
min_cluster_size = hyperparams.UniformInt(
lower=2,
upper=sys.maxsize,
default=5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='the minimum size of clusters')
min_samples = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'The number of samples in a neighbourhood for a point to be considered a core point.'
)
cluster_selection_method = hyperparams.Enumeration(
default='eom',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
values=['leaf', 'eom'],
description=
'Determines how clusters are selected from the cluster hierarchy tree for HDBSCAN'
)
required_output = hyperparams.Enumeration(
default='feature',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['prediction', 'feature'],
description=
'Determines whether the output is a dataframe with just predictions,\
or an additional feature added to the input dataframe.')
pass
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='HDBSCAN',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['DBSCAN', 'HDBSCAN'],
description='type of clustering algorithm to use')
eps = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=0.5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'maximum distance between two samples for them to be considered as in the same neigborhood, \
used in DBSCAN algorithm')
min_cluster_size = hyperparams.UniformInt(
lower=2,
upper=sys.maxsize,
default=5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='the minimum size of clusters')
min_samples = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'The number of samples in a neighbourhood for a point to be considered a core point.'
)
long_format = hyperparams.UniformBool(
default=False,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"whether the input dataset is already formatted in long format or not")
cluster_selection_method = hyperparams.Enumeration(
default='eom',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
values=['leaf', 'eom'],
description=
'Determines how clusters are selected from the cluster hierarchy tree for HDBSCAN'
)
pass
class Hyperparams(hyperparams.Hyperparams):
n_clusters = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=8,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='The dimension of the projection space')
n_init = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=10,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'Number of times the k-means algorithm will be run with different centroid seeds'
)
n_neighbors = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=10,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'Number of neighbors when constructing the affintiy matrix using n-neighbors, ignored for affinity="rbf"'
)
affinity = hyperparams.Enumeration(
default='rbf',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
values=['rbf', 'nearest_neighbors'],
description='method to construct affinity matrix')
task_type = hyperparams.Enumeration(
default='classification',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['clustering', 'classification'],
description=
'Determines whether the output is a dataframe with just predictions,\
or an additional feature added to the input dataframe.')
pass
class Hyperparams(hyperparams.Hyperparams):
# Added by Guanchu
with_mean = hyperparams.UniformBool(
default=True,
description='If True, center the data before scaling. This does not work (and will raise an exception) when attempted on sparse matrices, because centering them entails building a dense matrix which in common use cases is likely to be too large to fit in memory.',
semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
)
with_std = hyperparams.UniformBool(
default=True,
description='If True, scale the data to unit variance (or equivalently, unit standard deviation).',
semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
)
# copy = hyperparams.UniformBool(
# default=True,
# description='If False, try to avoid a copy and do inplace scaling instead. This is not guaranteed to always work inplace; e.g. if the data is not a NumPy array or scipy.sparse CSR matrix, a copy may still be returned.',
# semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
# )
# Keep previous
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='new',
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=False,
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\".",
)
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.",
)
return_semantic_type = hyperparams.Enumeration[str](
values=['https://metadata.datadrivendiscovery.org/types/Attribute',
'https://metadata.datadrivendiscovery.org/types/ConstructedAttribute'],
default='https://metadata.datadrivendiscovery.org/types/Attribute',
description='Decides what semantic type to attach to generated attributes',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter']
)
class Hyperparams(hyperparams.Hyperparams):
reduce_method = hyperparams.Enumeration(
default = 'pca',
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
values = ['pca', 'svd'],
description = 'dimensionality reduction method that is applied to feature vectors'
)
reduce_dimension = hyperparams.UniformInt(
lower=0,
upper=1024,
default=128,
upper_inclusive=True,
semantic_types=["https://metadata.datadrivendiscovery.org/types/ControlParameter"],
description="number of dimensions in reduced feature vectors",
)
gem_p = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=1,
upper_inclusive=True,
semantic_types=["https://metadata.datadrivendiscovery.org/types/TuningParameter"],
description="parameter p in generalized mean pooling; p > 1 increases the constrast of the \
pooled feature map; p = 1 equivalent to average pooling; p = +inf equivalent to \
max pooling.",
)
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default="TimeSeriesKMeans",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
values=["GlobalAlignmentKernelKMeans", "TimeSeriesKMeans"],
description="type of clustering algorithm to use",
)
nclusters = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=3,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="number of clusters to user in kernel kmeans algorithm",
)
n_init = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=10,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"Number of times the k-means algorithm will be run with different centroid seeds. \
Final result will be the best output on n_init consecutive runs in terms of inertia",
)
time_col_index = hyperparams.Hyperparameter[Union[int, None]](
default=None,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Index of column in input dataframe containing timestamps.",
)
value_col_index = hyperparams.Hyperparameter[Union[int, None]](
default=None,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Index of column in input dataframe containing the values associated with the timestamps.",
)
grouping_col_index = hyperparams.Hyperparameter[Union[int, None]](
default=None,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Index of column in input dataframe containing the values used to mark timeseries groups",
)
output_col_name = hyperparams.Hyperparameter[str](
default="__cluster",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Name to assign to cluster column that is appended to the input dataset",
)
class Hyperparams(hyperparams.Hyperparams):
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 does not contain filenames for supported media types, 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="append",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Should columns with read files be appended, should they replace original columns, or should only columns with read files be returned?",
)
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".',
)
compress_data = hyperparams.Hyperparameter[bool](
default=False,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="If True, applies LZO compression algorithm to the data.\
Store a header consisting of the dtype character and the data shape as unsigned integers.\
Given c struct alignment, will occupy 16 bytes (1 + 4 + 4 + 4 + 3 ) padding",
)
n_jobs = hyperparams.Hyperparameter[int](
default=64,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="The value of the n_jobs parameter for the joblib library",
)
band_column = hyperparams.Hyperparameter[str](
default="band",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Name of the band column used if no band semantic type is present.",
)
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='GlobalAlignmentKernelKMeans',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['GlobalAlignmentKernelKMeans', 'TimeSeriesKMeans'],
description='type of clustering algorithm to use')
nclusters = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=3,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='number of clusters \
to user in kernel kmeans algorithm')
long_format = hyperparams.UniformBool(
default=False,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"whether the input dataset is already formatted in long format or not")
pass
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='TimeSeriesKMeans',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['GlobalAlignmentKernelKMeans', 'TimeSeriesKMeans'],
description='type of clustering algorithm to use')
nclusters = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=3,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='number of clusters \
to user in kernel kmeans algorithm')
n_init = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=10,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='Number of times the k-means algorithm \
will be run with different centroid seeds. Final result will be the best output on n_init consecutive runs in terms of inertia'
)
pass
class VoterHyperparameter(hyperparams.Hyperparams):
classifier_voting_strategy = hyperparams.Enumeration(
values=['random', 'majority'],
default='majority',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="For classification problem, pick a prediction result if there are multiple results based on which strategy"
)
class UEncHyperparameter(hyperparams.Hyperparams):
text2int = hyperparams.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'])
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 Hyperparams(hyperparams.Hyperparams):
metric = hyperparams.Enumeration[str](
values=classification_metrics + regression_metrics +
clustering_metrics,
default="f1Macro",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"The D3M scoring metric to use during the fit phase. This can be any of the regression, classification or "
+ "clustering metrics.",
)
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.",
)
encoder_type = hyperparams.Enumeration(
default="svm",
values=["svm", "tfidf"],
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Vectorization Strategy.",
)
class Hyperparams(hyperparams.Hyperparams):
geocoding_resolution = hyperparams.Enumeration(
default="city",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
values=["city", "country", "state", "postcode"],
description="type of clustering algorithm to use",
)
rampup_timeout = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=100,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"timeout, how much time to give elastic search database to startup, may vary based on infrastructure",
)
cache_size = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=2000,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="LRU cache size",
)
class EnsembleVotingHyperparams(hyperparams.Hyperparams):
ensemble_method = hyperparams.Enumeration(
values=['majority', 'mean', 'max', 'min', 'median', 'random'],
default='majority',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="Controls which ensemble method should be used",
)
class Hyperparams(hyperparams.Hyperparams):
# Added by Mia
endog = hyperparams.Bounded[int](
lower = 2,
upper = None,
default = 3,
description='Array like time seires.',
semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
)
# keep previous
norm = hyperparams.Enumeration[str](
default='l2',
values=['l1', 'l2', 'max'],
description='The norm to use to normalize each non zero sample.',
semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
)
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='new',
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=False,
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\".",
)
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.",
)
return_semantic_type = hyperparams.Enumeration[str](
values=['https://metadata.datadrivendiscovery.org/types/Attribute', 'https://metadata.datadrivendiscovery.org/types/ConstructedAttribute'],
default='https://metadata.datadrivendiscovery.org/types/Attribute',
description='Decides what semantic type to attach to generated attributes',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter']
)
class MetricsHyperparams(hyperparams.Hyperparams, set_names=False):
metric = hyperparams.Enumeration(
values=[metric.name for metric in problem.PerformanceMetric],
# Default is ignored.
# TODO: Remove default. See: https://gitlab.com/datadrivendiscovery/d3m/issues/141
default='ACCURACY',
)
pos_label = hyperparams.Hyperparameter[typing.Union[str, None]](None)
k = hyperparams.Hyperparameter[typing.Union[int, None]](None)
def setup(self):
self.numerical = hyperparams.Uniform(
lower=0,
upper=1,
default=0.5,
)
self.enumeration = hyperparams.Enumeration(
values=list(range(1000)),
default=0,
)
class Hyperparams(hyperparams.Hyperparams): window_size = hyperparams.UniformInt( lower = 0, upper = 100, #TODO: Define the correct the upper bound default=50, semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'], description="window size to calculate" ) # Keep previous dataframe_resource = hyperparams.Hyperparameter[typing.Union[str, None]]( default=None, semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'], description="Resource ID of a DataFrame to extract if there are multiple tabular resources inside a Dataset and none is a dataset entry point.", ) use_columns = hyperparams.Set( elements=hyperparams.Hyperparameter[int](-1), default=(2,), 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=(0,1,3,), 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='new', 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=False, 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\".", ) 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.", ) return_semantic_type = hyperparams.Enumeration[str]( values=['https://metadata.datadrivendiscovery.org/types/Attribute', 'https://metadata.datadrivendiscovery.org/types/ConstructedAttribute'], default='https://metadata.datadrivendiscovery.org/types/Attribute', description='Decides what semantic type to attach to generated attributes', semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'] )
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='text_rank',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['luhn', 'edmundson', 'lsa', 'text_rank', 'sum_basic', 'kl'],
description='type of summarization algorithm to use')
source_type = hyperparams.Enumeration(
default='plain_text',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['plain_text', 'url'],
description='type of source documents to be analyzed')
language = hyperparams.Enumeration(
default='english',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=[
'danish', 'dutch', 'english', 'finnish', 'french', 'german',
'hungarian', 'italian', 'norwegian', 'porter', 'portuguese',
'romanian', 'russian', 'spanish', 'swedish'
],
description='language to use for the NLTK stemming process')
return_result = hyperparams.Enumeration(
default='all',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=['new', 'all', 'replace'],
description='what data should be returned')
nsentences = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=20,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description='number of summary sentences to return')
pass
class Hyperparams(hyperparams.Hyperparams):
max_percent_null = hyperparams.Bounded[float](
default=.5,
lower=0,
upper=1,
description=
'The maximum percentage of null values allowed in returned features. A lower value means features may have more null nulls.',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
max_correlation = hyperparams.Bounded[float](
default=.9,
lower=0,
upper=1,
description=
'The maximum allowed correlation between any two features returned. A lower value means features will be more uncorrelated',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
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='new',
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.",
)
max_features = hyperparams.Hyperparameter[int](
default=100,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
"Cap the number of generated features to this number. If -1, no limit."
)
class Hyperparams(hyperparams.Hyperparams):
parsing_semantics = hyperparams.Set(
elements=hyperparams.Enumeration(
values=[
"http://schema.org/Boolean",
"http://schema.org/Integer",
"http://schema.org/Float",
"https://metadata.datadrivendiscovery.org/types/FloatVector",
"http://schema.org/DateTime",
"https://metadata.datadrivendiscovery.org/types/CategoricalData",
],
default="http://schema.org/Float",
),
default=(
"http://schema.org/Boolean",
"http://schema.org/Integer",
"http://schema.org/Float",
),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="A set of semantic types to parse. One can provide a subset of supported semantic types to limit what the primitive parses.",
)
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.',
)
error_handling = hyperparams.Enumeration[str](
default="coerce",
values=("ignore", "raise", "coerce"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Setting to deal with error when converting a column to numeric value.",
)
fuzzy_time_parsing = hyperparams.UniformBool(
default=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Use fuzzy time parsing.",
)
class Hyperparams(hyperparams.Hyperparams):
reduce_method = hyperparams.Enumeration(
default="pca",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
values=["pca", "svd"],
description=
"dimensionality reduction method that is applied to feature vectors",
)
reduce_dimension = hyperparams.UniformInt(
lower=0,
upper=1024,
default=128,
upper_inclusive=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="number of dimensions in reduced feature vectors",
)
gem_p = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=1,
upper_inclusive=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description=
"parameter p in generalized mean pooling; p > 1 increases the constrast of the \
pooled feature map; p = 1 equivalent to average pooling; p = +inf equivalent to \
max pooling.",
)
denominator_min = hyperparams.UniformInt(
lower=0,
upper=sys.maxsize,
default=5,
upper_inclusive=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"only ranks according to positive annotations until this many negative \
annotations are obtained",
)
dot_products_cache = hyperparams.Hyperparameter[str](
default="dot_product_cache",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"already computed dot products will be cached in this location",
)
class Hyperparams(hyperparams.Hyperparams):
"""
"""
keep_option = hyperparams.Enumeration(
values=['first', 'average'],
default='first',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"When dropping rows, choose to keep the first one of duplicated data or calculate their average",
)
class Hyperparams(hyperparams.Hyperparams):
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.",
)
inference_model = hyperparams.Enumeration(
default="moco",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
values=["amdim", "moco"],
description="type pretrained inference model to use",
)
batch_size = hyperparams.UniformInt(
lower=1,
upper=512,
default=256,
upper_inclusive=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="inference batch size",
)
pool_features = hyperparams.UniformBool(
default=True,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"whether to pool features across spatial dimensions in returned frame",
)
decompress_data = hyperparams.Hyperparameter[bool](
default=False,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="If True, applies LZ4 decompression algorithm to the data. \
Compressed data stores a header consisting of the dtype character and the \
data shape as unsigned integers. Given c struct alignment, will occupy \
16 bytes (1 + 4 + 4 + 4 + 3 ) padding",
)
class Hyperparams(hyperparams.Hyperparams):
continuity_option = hyperparams.Enumeration(
values=['ablation', 'imputation'],
default='imputation',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="Choose ablation or imputation the original data",
)
interval = hyperparams.Uniform(
default=1,
lower=0.000000001,
upper=10000000000,
description='Only used in imputation, give the timestamp interval.',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
])
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(default = 'Disparate_Impact_Remover',
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
values = ['Disparate_Impact_Remover', 'Learning_Fair_Representations', 'Reweighing'],
description = 'type of fairness pre-processing algorithm to use')
protected_attribute_cols = hyperparams.List(
elements=hyperparams.Hyperparameter[int](-1),
default=[],
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to use as protected attributes.",
)
favorable_label = hyperparams.Bounded[float](
lower=0.,
upper=1.,
default=1.,
description='label value which is considered favorable (i.e. positive) in the binary label case',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
)
pass
class Hyperparams(hyperparams.Hyperparams):
algorithm = hyperparams.Enumeration(
default='GlobalAlignmentKernelKMeans',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
values=[
'GlobalAlignmentKernelKMeans', 'TimeSeriesKMeans', 'DBSCAN',
'HDBSCAN'
],
description='type of clustering algorithm to use')
nclusters = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=3,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description='number of clusters \
to user in kernel kmeans algorithm')
eps = hyperparams.Uniform(
lower=0,
upper=sys.maxsize,
default=0.5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'maximum distance between two samples for them to be considered as in the same neigborhood, \
used in DBSCAN algorithm')
min_samples = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=5,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
'number of samples in a neighborhood for a point to be considered as a core point, \
used in DBSCAN and HDBSCAN algorithms')
pass
class Hyperparams(Hyperparams_ODBase):
######## Add more Hyperparamters #######
n_neighbors = hyperparams.Hyperparameter[int](
default=10,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/TuningParameter'
],
description=
"Number of neighbors to use by default for k neighbors queries.",
)
method = hyperparams.Enumeration(
values=['fast', 'default'],
default='fast',
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
"'fast': fast ABOD. Only consider n_neighbors of training points 'default': original ABOD with all training points, which could be slow",
)
