Dataset construction ========== .. automodule:: lightfm.data :members: :undoc-members: :show-inheritance:

Cross-validation ========== .. automodule:: lightfm.cross_validation :members: :undoc-members:

Examples ========== Many of the examples can be viewed (and run) as Jupyter notebooks in the `examples directory <https://github.com/lyst/lightfm/tree/master/examples>`_ of the LightFM repository. ...

» Examples Examples  Many of the examples can be viewed (and run) as Jupyter notebooks in the examples directory of ...

» Search

.. include:: home.rst Contents ======== .. toctree:: :maxdepth: 2 Home <home> Quickstart <quickstart> The LightFM model class <lightfm> Model evaluation <lightfm.evaluation> Cross validation <cross...

» Module code » lightfm.datasets.movielens Source code for lightfm.datasets.movielens import itertools import os impo...

Datasets ========== .. autofunction:: lightfm.datasets.movielens.fetch_movielens .. autofunction:: lightfm.datasets.stackexchange.fetch_stackexchange

An implicit feedback recommender for the Movielens dataset ========== Implicit feedback ---------- For some time, the recommender system literature focused on explicit feedback: the Netflix prize f...

Using different learning schedules ========== ``lightfm`` implements two learning schedules: adagrad and adadelta. Neither is clearly superior, and, like other hyperparameter choices, the best lear...