lenskit.splitting.holdout

Per-user rating holdout methods for user-based data splitting.

Classes

HoldoutMethod(*args, **kwargs)	Holdout methods select test rows for a user (or occasionally an item).
LastFrac(frac[, field])	Select a fraction of test rows per user/item.
LastN(n[, field])	Select a fixed number of test rows per user/item, based on ordering by a field.
SampleFrac(frac[, rng_spec])	Randomly select a fraction of test rows per user/item.
SampleN(n[, rng_spec])	Randomly select a fixed number of test rows per user/item.

class lenskit.splitting.holdout.HoldoutMethod(*args, **kwargs)

Bases: Protocol

Holdout methods select test rows for a user (or occasionally an item). Partition methods are callable; when called with a data frame, they return the test entries.

class lenskit.splitting.holdout.SampleN(n, rng_spec=None)

Bases: HoldoutMethod

Randomly select a fixed number of test rows per user/item.

Parameters:

• n (int) – the number of test items to select

• rng – the random number generator or seed

• rng_spec (SeedSequence | int | integer[Any] | ndarray[Any, dtype[Any]] | bytes | memoryview | str | Generator | RandomState | None)

class lenskit.splitting.holdout.SampleFrac(frac, rng_spec=None)

Bases: HoldoutMethod

Randomly select a fraction of test rows per user/item.

Parameters:

• frac (float) – the fraction items to select for testing.

• rng_spec (SeedSequence | int | integer[Any] | ndarray[Any, dtype[Any]] | bytes | memoryview | str | Generator | RandomState | None)

class lenskit.splitting.holdout.LastN(n, field='timestamp')

Bases: HoldoutMethod

Select a fixed number of test rows per user/item, based on ordering by a field.

Parameters:

• n (int) – The number of test items to select.

• field (str) – The field to order by.

class lenskit.splitting.holdout.LastFrac(frac, field='timestamp')

Bases: HoldoutMethod

Select a fraction of test rows per user/item.

Parameters:

• frac (double) – the fraction of items to select for testing.

• field (str)