API Reference

These pages contain the reference documentation for the LensKit modules, classes, etc.

Core Abstractions

lenskit
data	Data abstractions and data set access.
pipeline	LensKit pipeline abstraction.
diagnostics	Warning and error classes and general LensKit diagnostic code.
operations	Top-level LensKit functions for recommender operations.
training	Interfaces and support for model training.
state	Support code for managing model state.
config	LensKit general configuration

Components and Models

These packages provide various recommendation components and models provided as first-party implementations by LensKit.

als	LensKit ALS implementations.
basic	Basic and baseline pipeline components.
flexmf	Flexible PyTorch matrix factorization models for LensKit.
funksvd	FunkSVD (biased MF).
knn
sklearn	Recommendation models using SciKit-Learn.
stochastic	Components for generating sochastic outputs in LensKit pipelines.

Batch Inference and Evaluation

These package provide evaluation metrics and analysis and batch-inference support. The evaluation code is not directly linked to the rest of LensKit and can be used to evaluate the output of any recommender system implementation.

batch	Batch-run recommendation pipelines for evaluation.
metrics	Metrics for evaluating recommender outputs.
splitting	Splitting data for train-test evaluation.
tuning	Tune parameters using Ray Tune.

Add-On Components

These packages contain component implementations that wrap other libraries.

implicit	Bridges to recommendation models from implicit.
hpf	Hierarchical Poisson factorization from hpfrec.
graphs

Implementation Helpers

These modules provide various utilities and helpers used to implement LensKit, and may be useful in building new models and components for LensKit.

lazy	Types and functions for lazy values. These are used mostly for pipeline inputs.
logging	Logging, progress, and resource records.
math	Mathematical helper routines.
parallel	LensKit parallel computation support.
random	Utilities to manage randomness in LensKit and LensKit experiments.
stats	LensKit statistical computations.
testing	LensKit test harnesses and utilities.
torch	PyTorch utility functions.
_accel	Rust acceleration code.