discontinuum.pipeline

Functions

datetime_to_decimal_year(x)	Convert a timeseries to decimal year.
decimal_year_to_datetime(x)	Convert a decimal year to a datetime.

Classes

BaseTransformer()	Base class for transformers.
ClipTransformer([min, max])	Clip a variable.
ErrorPipeline(steps, *[, transform_input, ...])
LogErrorPipeline()	Pipeline to transform error
LogStandardPipeline()
LogTransformer()	Log-transform a variable.
MetadataManager()
NoOpPipeline()
SquareTransformer()	Square a variable.
StandardErrorPipeline()	Pipeline to transform error
StandardPipeline()
StandardScaler(*[, with_mean, with_std])	Rescale a variable to have a mean of 0 and a standard deviation of 1.
TimePipeline()
TimeTransformer()	Convert a datetime to decimal year.
UnitPipeline()
UnitScaler([zero_value])	Rescale a variable to have a minimum of 0 and a maximum of 1.

class discontinuum.pipeline.BaseTransformer

Base class for transformers.

class discontinuum.pipeline.ClipTransformer(min: float = None, max: float = None)

Clip a variable.

class discontinuum.pipeline.ErrorPipeline(steps, *, transform_input=None, memory=None, verbose=False)

abstractmethod ci(mean, se, ci=0.95)

Calculate confidence interval for a variable.

Parameters:

• mean (float) – Mean of the variable.

• se (float) – Standard error of the variable.

• ci (float) – Confidence level.

Returns:

lower, upper – Lower and upper bound of the confidence interval.

Return type:

Tuple[float, float]

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → ErrorPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.LogErrorPipeline

Pipeline to transform error

inverse_transform converts variance (in log space) to a GSE

ci(mean, se, ci=0.95)

Calculate confidence interval for a log-transformed variable.

Parameters:

• mean (float) – Mean of the variable.

• se (float) – Standard error of the variable.

• ci (float) – Confidence level.

Returns:

lower, upper – Lower and upper bound of the confidence interval.

Return type:

Tuple[float, float]

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → LogErrorPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.LogStandardPipeline

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → LogStandardPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.LogTransformer

Log-transform a variable.

class discontinuum.pipeline.MetadataManager

fit(X, y=None)

Store metadata from a xarray DataArray.

Parameters:

• X (DataArray)

• y (None) – Ignored.

inverse_transform(X)

Add xarray metadata to a numpy array.

Parameters:

X (Numpy array)

Return type:

DataArray

transform(X)

Extract values (numpy array) from xarray DataArray

Parameters:

X (DataArray)

Return type:

Numpy array

class discontinuum.pipeline.NoOpPipeline

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → NoOpPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.SquareTransformer

Square a variable.

class discontinuum.pipeline.StandardErrorPipeline

Pipeline to transform error

inverse_transform converts variance to SE.

ci(mean, se, ci=0.95)

Calculate confidence interval for a standard variable.

Parameters:

• mean (float) – Mean of the variable.

• se (float) – Standard error of the variable.

• ci (float) – Confidence level.

Returns:

lower, upper – Lower and upper bound of the confidence interval.

Return type:

Tuple[float, float]

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → StandardErrorPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.StandardPipeline

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → StandardPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.StandardScaler(*, with_mean=True, with_std=True)

Rescale a variable to have a mean of 0 and a standard deviation of 1.

Reimplemens the sklearn.preprocessing.StandardScaler but removes the requirement of having 2D arrays.

class discontinuum.pipeline.TimePipeline

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → TimePipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.TimeTransformer

Convert a datetime to decimal year.

class discontinuum.pipeline.UnitPipeline

set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → UnitPipeline

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to score.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for sample_weight parameter in score.

selfobject

The updated object.

class discontinuum.pipeline.UnitScaler(zero_value=0)

Rescale a variable to have a minimum of 0 and a maximum of 1.

discontinuum.pipeline.datetime_to_decimal_year(x: Buffer | _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | complex | bytes | str | _NestedSequence[complex | bytes | str]) → Buffer | _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | complex | bytes | str | _NestedSequence[complex | bytes | str]

Convert a timeseries to decimal year.

Parameters:

x (DataArray) – Timeseries to convert.

Returns:

Decimal year array.

Return type:

ArrayLike

discontinuum.pipeline.decimal_year_to_datetime(x: Buffer | _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | complex | bytes | str | _NestedSequence[complex | bytes | str]) → Buffer | _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | complex | bytes | str | _NestedSequence[complex | bytes | str]

Convert a decimal year to a datetime.

Parameters:

x (ArrayLike) – Decimal year to convert.

Returns:

Datetime array.

Return type:

ArrayLike