lenskit.metrics.GeometricRankWeight

class lenskit.metrics.GeometricRankWeight(patience=0.85)

Bases: RankWeight

Geometric cascade weighting for result ranks.

This is the ranking model used by RBP [MZ08].

For patience \(p\), the discount is given by \(p^{k-1}\). The sum of this infinite series is \(\frac{1}{1 - p}\).

Parameters:

patience (float) – The patience parameter \(p\).

Stability:

Caller (see Stability Levels).

__init__(patience=0.85)

Parameters:

patience (Annotated[float, Gt(gt=0.0), Lt(lt=1.0)])

Methods

__init__([patience])
log_weight(ranks)	Compute the (natural) log of the discount for the specified ranks.
series_sum()	Get the sum of the infinite series of this discount function, if known.
weight(ranks)	Compute the discount for the specified ranks.

Attributes

patience

weight(ranks)

Compute the discount for the specified ranks.

Ranks must start with 1.

Return type:

ndarray[tuple[int], dtype[float64]]

log_weight(ranks)

Compute the (natural) log of the discount for the specified ranks.

Ranks must start with 1.

Return type:

ndarray[tuple[int], dtype[float64]]

series_sum()

Get the sum of the infinite series of this discount function, if known. Some metrics (e.g. RBP()) will use this to normalize their measurements.

Return type:

float