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):
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. The default is all columns.",
)
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.",
)
drop_non_numeric_columns = hyperparams.Hyperparameter[bool](
default=True,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="If True, drop all non-numeric columns",
)
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):
"""
Hyper-parameters
"""
use_row_iter = hyperparams.UniformBool(
default=False,
description=
"Whether or not to use row iteration inplace of column interation on dataframe",
semantic_types=[
'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 cast to the type, 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.",
)
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):
# 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 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):
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 UnfoldHyperparams(hyperparams.Hyperparams):
unfold_semantic_types = hyperparams.Set(
elements=hyperparams.Hyperparameter[str]("str"),
default=[
"https://metadata.datadrivendiscovery.org/types/PredictedTarget"
],
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="""
A set of semantic types that the primitive will unfold.
Only 'https://metadata.datadrivendiscovery.org/types/PredictedTarget' by default.
""",
)
use_pipeline_id_semantic_type = hyperparams.UniformBool(
default=False,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description="""
Controls whether semantic_type will be used for finding pipeline id column in input dataframe.
If true, it will look for 'https://metadata.datadrivendiscovery.org/types/PipelineId' for pipeline id column,
and create attribute columns using header: attribute_{pipeline_id}.
eg. 'binaryClass_{a3180751-33aa-4790-9e70-c79672ce1278}'
If false, create attribute columns using header: attribute_{0,1,2,...}.
eg. 'binaryClass_0', 'binaryClass_1'
""",
)
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.",
)
n_clusters = hyperparams.Hyperparameter[int](
default=8,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Number of clusters to generate",
)
cluster_col_name = hyperparams.Hyperparameter[str](
default="__cluster",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"The name of created cluster column in the returned dataframe",
)
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):
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",
)
target_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"indices of column with geolocation formatted as text that should be converted to lat,lon pairs",
)
cache_size = hyperparams.UniformInt(
lower=1,
upper=sys.maxsize,
default=2000,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="LRU cache size",
)
class Hyperparams(hyperparams.Hyperparams):
datetime_index = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(),
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='if multiple datetime indices exist, this HP specifies which to apply to training data. If \
None, the primitive assumes there is only one datetime index. This HP can also specify multiple indices \
which should be concatenated to form datetime_index')
datetime_index_unique = hyperparams.UniformBool(
default = False,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="whether the datetime "
)
datetime_filter = hyperparams.Hyperparameter[typing.Union[int, None]](
default = None,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='index of column in input dataset that contain unique identifiers of \
time series that have different datetime indices')
filter_index = hyperparams.Hyperparameter[typing.Union[int, None]](
default = None,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='index of column in input dataset that contain unique identifiers of different time series')
n_periods = hyperparams.UniformInt(
lower = 1,
upper = sys.maxsize,
default = 61,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='number of periods to predict')
interval = hyperparams.Hyperparameter[typing.Union[int, None]](
default = None,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='interval with which to sample future predictions')
datetime_interval_exception = hyperparams.Hyperparameter[typing.Union[str, None]](
default = None,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='to handle different prediction intervals (stock market dataset). \
If this HP is set, primitive will just make next forecast for this datetime value \
(not multiple forecasts at multiple intervals')
max_lags = hyperparams.UniformInt(
lower = 1,
upper = sys.maxsize,
default = 10,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='maximum lag order to evluate to find model - eval criterion = AIC')
arma_p = hyperparams.Hyperparameter[typing.Union[int, None]](
default = 0,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='The p order of the ARMA model in case some time series are univariate')
arma_q = hyperparams.Hyperparameter[typing.Union[int, None]](
default = 0,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='The q order of the ARMA model in case some time series are univariate')
weights_filter_value = hyperparams.Hyperparameter[typing.Union[str, None]](
default = None,
semantic_types = ['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='value to select a filter from column filter index for which to return correlation \
coefficient matrix.')
pass
class Hyperparams(hyperparams.Hyperparams):
grouping_key_col = hyperparams.Hyperparameter[typing.Union[int, None]](
default=None,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="The GroupKey column index for the time series data.",
)
time_col = hyperparams.Hyperparameter[typing.Union[int, None]](
default=None,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="",
)
value_cols = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Columns needed in the dataset; all other columns will be removed.",
)
granularity = hyperparams.Enumeration[str](
default="months",
values=("seconds", "minutes", "hours", "days", "weeks", "months",
"years"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="The granularity of the time series timestamp values.",
)
binning_operation = hyperparams.Enumeration[str](
default="sum",
values=("sum", "mean", "min", "max"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Setting operation to bin time series data with.",
)
binning_size = hyperparams.Hyperparameter[int](
default=5,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"If time is numeric, this will be the size to comebine row values.",
)
binning_starting_value = hyperparams.Enumeration[str](
default="zero",
values=("zero", "min"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Where to start binning intervals from. min starts from min of dataset.",
)
class Hyperparams(hyperparams.Hyperparams):
target_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[str](''),
default=(),
max_size=sys.maxsize,
min_size=0,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='names of columns with image paths'
)
output_labels = hyperparams.Set(
elements=hyperparams.Hyperparameter[str](''),
default=(),
max_size=sys.maxsize,
min_size=0,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description='desired names for croc output columns'
)
class Hyperparams(hyperparams.Hyperparams):
metrics = hyperparams.Set(
elements=MetricsHyperparams,
default=(),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of metrics to compute.",
)
all_labels = hyperparams.Set(
elements=AllLabelsHyperparams,
default=(),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="All labels available in a dataset, per target column. When provided for a target column, it overrides all labels from metadata or data for that target column.",
)
add_normalized_scores = hyperparams.UniformBool(
default=True,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Add additional column with normalized scores?"
)
class Hyperparams(hyperparams.Hyperparams):
metafeatures = hyperparams.Set(
metafeature_hyperparam,
default_metafeatures,
min_size=1,
max_size=len(computable_metafeatures),
description="Compute metadata descriptions of the dataset",
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/MetafeatureParameter'
])
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.",
)
class AllLabelsHyperparams(hyperparams.Hyperparams, set_names=False):
# Default is ignored.
# TODO: Remove default. See: https://gitlab.com/datadrivendiscovery/d3m/issues/141
column_name = hyperparams.Hyperparameter[str]('')
labels = hyperparams.Set(
# Default is ignored.
# TODO: Remove default. See: https://gitlab.com/datadrivendiscovery/d3m/issues/141
elements=hyperparams.Hyperparameter[str](''),
default=(),
)
class Hyperparams(hyperparams.Hyperparams):
split_on_column_with_avg_len = hyperparams.Uniform(
default=30,
lower=10,
upper=100,
upper_inclusive=True,
description='Threshold of avg column length for splitting punctuation or alphanumeric',
semantic_types=['http://schema.org/Integer', 'https://metadata.datadrivendiscovery.org/types/ControlParameter'])
metafeatures = hyperparams.Set(
metafeature_hyperparam, default_metafeatures, min_size=1, max_size=len(computable_metafeatures),
description="Compute metadata descriptions of the dataset",
semantic_types=['https://metadata.datadrivendiscovery.org/types/MetafeatureParameter'])
class FileReaderHyperparams(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\".",
)
class Hyperparams(hyperparams.Hyperparams):
vector_col_index = hyperparams.Hyperparameter[typing.Optional[int]](
default=None,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description='Index of source vector column')
labels = hyperparams.Set(
elements=hyperparams.Hyperparameter[str](''),
default=(),
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'
],
description=
'Labels for created columns. If none supplied, labels will auto-generate.'
)
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):
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.",
)
max_one_hot = hyperparams.Hyperparameter[int](
default=16,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/TuningParameter"
],
description="Max number of unique labels a column can have for encoding. If the value is surpassed, the column is skipped.",
)
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.",
)
min_binary = hyperparams.Hyperparameter[int](
default=17,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Min number of unique labels a column can have for binary encoding. If a column has fewer, it will be skipped.",
)
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.",
)
replace = hyperparams.Hyperparameter[bool](
default=False,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Whether or not to replace enriched DateTime columns or append them",
)
class HorizontalConcatHyperparams(hyperparams.Hyperparams):
ignore_index = hyperparams.UniformBool(
default=True,
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Controls whether new df should use original index or not"
)
to_semantic_types = hyperparams.Set(
elements=hyperparams.Hyperparameter[str](""),
default=("https://metadata.datadrivendiscovery.org/types/Attribute",
"https://metadata.datadrivendiscovery.org/types/OrdinalData",
"https://metadata.datadrivendiscovery.org/types/CategoricalData"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"],
description="Sementic typer to add for output dataframe"
)
column_name = hyperparams.Hyperparameter[int](
semantic_types=[
'https://metadata.datadrivendiscovery.org/types/ControlParameter'],
default=100,
description="the control params for index name"
)
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.",
)
strategy = hyperparams.Enumeration[str](
default="most_frequent",
values=("most_frequent", "constant"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Replacement strategy. 'most_frequent' will replace missing values with the mode of the column, 'constant' uses 'fill_value'",
)
fill_value = hyperparams.Hyperparameter[str](
default=MISSING_VALUE_INDICATOR,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"Value to replace missing values with. Only applied when strategy is set to 'constant'",
)
error_on_empty = hyperparams.Hyperparameter[bool](
default=False,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description=
"If True will raise an exception when a column consisting only of empty values is found."
+ "If False, will apply the 'fill_value' to the entire column.",
)
class Hyperparams(hyperparams.Hyperparams):
n_jobs = hyperparams.Hyperparameter[int](
default=-1,
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="The value of the n_jobs parameter for the joblib library",
)
left_col = hyperparams.Union[typing.Union[str, typing.Sequence[str]]](
configuration=collections.OrderedDict(
set=hyperparams.Set(
elements=hyperparams.Hyperparameter[str](
default="",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Name of the column.",
),
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.",
),
str=hyperparams.Hyperparameter[str](
default="",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Name of the column.",
),
),
default="str",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Columns to join on from left dataframe",
)
right_col = hyperparams.Union[typing.Union[str, typing.Sequence[str]]](
configuration=collections.OrderedDict(
set=hyperparams.Set(
elements=hyperparams.Hyperparameter[str](
default="",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Name of the column.",
),
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.",
),
str=hyperparams.Hyperparameter[str](
default="",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Name of the column.",
),
),
default="str",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Columns to join on from right dataframe",
)
accuracy = hyperparams.Union[typing.Union[float, typing.Sequence[float]]](
configuration=collections.OrderedDict(
set=hyperparams.List(
elements=hyperparams.Hyperparameter[float](-1),
default=(),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="A list of accuracies, corresponding respectively to the columns to join on.",
),
float=hyperparams.Hyperparameter[float](0),
),
default="float",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Required accuracy of join ranging from 0.0 to 1.0, where 1.0 is an exact match.",
)
join_type = hyperparams.Enumeration[str](
default="left",
values=("left", "right", "outer", "inner", "cross"),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="The type of join between two dataframes.",
)
absolute_accuracy = hyperparams.Union[typing.Union[bool, typing.Sequence[bool]]](
configuration=collections.OrderedDict(
set=hyperparams.List(
elements=hyperparams.UniformBool(False),
default=(),
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="A list of flags for absolute values, corresponding respectively to the columns to join on.",
),
bool=hyperparams.UniformBool(False),
),
default="bool",
semantic_types=[
"https://metadata.datadrivendiscovery.org/types/ControlParameter"
],
description="Used for numeric to use absolute comparison instead of percentage.",
)
