v0.3.1

What's Changed

• Build python 3.11 wheel by @tnakae in #106
• Fix max os build by @tohtsky in #107

Full Changelog: v0.3.0...v0.3.1

v0.3.0

What's Changed

• df_to_sparse function improved. If user_ids / item_ids are provided, DataFrame row with unknown user/item ID will be ignored.
• The function arguments with names **_colname is renamed to **_column. See #99.
• Deleted IDMappedRecommender. Instead, use
  • ItemIDMapper for item id <-> sparse matrix column index mappings
  • IDMapper for user/item <-> sparse matrix row/column index mappings
• Added NeuMF-type evaluation example
• Removed *Optimizer class. Recommender performance can be now tuned by **Recommender.tune class method.
• Move to src/irspack layout & always use relative import.

Full Changelog: v0.2.4...v0.3.0

v0.2.4

What's Changed

• Simplify the build script by @tohtsky in #96

Full Changelog: v0.2.3...v0.2.4

v0.2.3

What's Changed

• iALS improvement by @tohtsky in #93
• Fix readme & pre-commit by @tohtsky in #94
• iALS tuning strategy of doubling dimensions by @tohtsky in #95

Full Changelog: v0.2.2...v0.2.3

v0.2.2

What's Changed

• Improve typehint by @tohtsky in #92

Full Changelog: v0.2.1...v0.2.2

v0.2.1

What's Changed

• Drop Python3.6 support & Fix test by @tohtsky in #90
• modify iALS docs by @tohtsky in #91

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• Version 0.2.0 by @tohtsky in #89
• Drop Python3.6 support & Fix test by @tohtsky in #90

Full Changelog: v0.1.20...v0.2.0

Breaking Changes

• iALS's confidence parameter alpha is now reparametrized by alpha0 = 1 / alpha (roughtly) following "Revisiting the Performance of iALS on Item Recommendation Benchmarks"
• Dropped the user cold start module.

v0.1.20

What's Changed

• Improve wheel build by @tohtsky in #88

Full Changelog: v0.1.19...v0.1.20

v0.1.19

What's Changed

• Improve id mapping by @tohtsky in #87

Full Changelog: v0.1.18...v0.1.19

Add dataset & `ceil_n_heldout` options

• add two more data sets (Amazon music & CiteULike-a)
• add ceil_n_heldout option for split functions