chaining

Transformations constructed by chaining other transformations.

Classes

ChainTT

Transformation constructed by chaining two transformations.

class ChainTT(transformation1, transformation2, hint=None)

Bases: tmlt.core.transformations.base.Transformation

Transformation constructed by chaining two transformations.

Parameters

• transformation1 (tmlt.core.transformations.base.Transformation) –

• transformation2 (tmlt.core.transformations.base.Transformation) –

• hint (Optional[Callable[[Any, Any], Any]]) –

__init__(transformation1, transformation2, hint=None)

Constructor.

Parameters

• transformation1 (TransformationTransformation) – Transformation to apply first.

• transformation2 (TransformationTransformation) – Transformation to apply second.

• hint ((Any, Any) → Any | NoneOptional[Callable[[Any, Any], Any]] (default: None)) – An optional function to compute the intermediate metric value (after the first transformation, but before the second) for stability_relation(). It takes in the same inputs as stability_relation(), and is only required if the transformation’s stability_function() raises NotImplementedError.

stability_function(d_in)

Returns the smallest d_out satisfied by the transformation.

Returns M.privacy_function(T.stability_function(d_in)).

where:

• T1 is the first transformation applied (transformation1)

• T2 is the second transformation applied (transformation2)

Parameters

d_in (Any) – Distance between inputs under input_metric.

Raises

NotImplementedError – If T2.stability_function(T1.stability_function(d_in)) raises NotImplementedError.

Return type

Any

stability_relation(d_in, d_out)

Returns True only if outputs are close under close inputs.

Let d_mid = T1.stability_function(d_in), or hint(d_in, d_out) if T1.stability_function raises NotImplementedError.

This returns True only if the following hold:

1. T1.stability_relation(d_in, d_mid)

2. T2.stability_relation(d_mid, d_out)

where:

• T1 is the first transformation applied (transformation1)

• T2 is the second transformation applied (transformation2)

• hint is the hint passed to the constructor.

Parameters

• d_in (Any) – Distance between inputs under input_metric.

• d_out (Any) – Distance between outputs under output_metric.

Return type

bool

property transformation1

Returns the first transformation being applied.

Return type

tmlt.core.transformations.base.Transformation

property transformation2

Returns the second transformation being applied.

Return type

tmlt.core.transformations.base.Transformation

__call__(data)

Performs transformation1 followed by transformation2.

Parameters

data (Any) –

Return type

Any

property input_domain

Return input domain for the measurement.

Return type

tmlt.core.domains.base.Domain

property input_metric

Distance metric on input domain.

Return type

tmlt.core.metrics.Metric

property output_domain

Return input domain for the measurement.

Return type

tmlt.core.domains.base.Domain

property output_metric

Distance metric on input domain.

Return type

tmlt.core.metrics.Metric

__or__(other: Transformation) → Transformation

__or__(other: tmlt.core.measurements.base.Measurement) → tmlt.core.measurements.base.Measurement

Return this transformation chained with another component.