mlrl.common.cython.partition_sampling module

@author: Michael Rapp (michael.rapp.ml@gmail.com)

class mlrl.common.cython.partition_sampling.ExampleWiseStratifiedBiPartitionSamplingConfig

Bases: object

Allows to configure a method for partitioning the available training examples into a training set and a holdout set using stratification, where distinct label vectors are treated as individual classes.

get_holdout_set_size() → float

Returns the fraction of examples that are included in the holdout set.

Returns:

The fraction of examples that are included in the holdout set

set_holdout_set_size(holdout_set_size: float) → ExampleWiseStratifiedBiPartitionSamplingConfig

Sets the fraction of examples that should be included in the holdout set.

Parameters:

holdout_set_size – The fraction of examples that should be included in the holdout set, e.g., a value of 0.6 corresponds to 60 % of the available examples. Must be in (0, 1)

Returns:

An ExampleWiseStratifiedBiPartitionSamplingConfig that allows further configuration of the method for partitioning the available training examples into a training set and a holdout set

class mlrl.common.cython.partition_sampling.LabelWiseStratifiedBiPartitionSamplingConfig

Bases: object

Allows to configure a method for partitioning the available training examples into a training set and a holdout set using stratification, such that for each label the proportion of relevant and irrelevant examples is maintained.

get_holdout_set_size() → float

Returns the fraction of examples that are included in the holdout set.

Returns:

The fraction of examples that are included in the holdout set

set_holdout_set_size(holdout_set_size: float) → LabelWiseStratifiedBiPartitionSamplingConfig

Sets the fraction of examples that should be included in the holdout set.

Parameters:

holdout_set_size – The fraction of examples that should be included in the holdout set, e.g., a value of 0.6 corresponds to 60 % of the available examples. Must be in (0, 1)

Returns:

An LabelWiseStratifiedBiPartitionSamplingConfig that allows further configuration of the method for partitioning the available training examples into a training set and a holdout set

class mlrl.common.cython.partition_sampling.RandomBiPartitionSamplingConfig

Bases: object

Allows to configure a method for partitioning the available training examples into a training set and a holdout set that randomly splits the training examples into two mutually exclusive sets.

get_holdout_set_size() → float

Returns the fraction of examples that are included in the holdout set.

Returns:

The fraction of examples that are included in the holdout set

set_holdout_set_size(holdout_set_size: float) → RandomBiPartitionSamplingConfig

Sets the fraction of examples that should be included in the holdout set.

Parameters:

holdout_set_size – The fraction of examples that should be included in the holdout set, e.g., a value of 0.6 corresponds to 60 % of the available examples. Must be in (0, 1)

Returns:

A RandomBiPartitionSamplingConfig that allows further configuration of the method for partitioning the available training examples into a training set and a holdout set