V0.2 dev

[dillondaudert]

To Do

Functionality

• Allow multiple "views" of dataset at fit/transform time ( UMAP#206, UMAP#601, UMAP docs )
  • Discrete metric data with discrete distances ( UMAP#624 )
• Support passing precomputed distances
  • As KNNGraph
  • As matrix
• Helper functions to construct fit/transform config

Tests

• config.jl
• utils.jl
• membership_fn.jl
• neighbors.jl
• simplicial_sets.jl
• embeddings.jl
• optimize.jl
• fit.jl
• transform.jl

Docs

• UMAPConfig component structs and how to use
• UMAPResult/UMAPTransformResult
• What is public API vs. unstable/in-progress functionality
• Tutorials for basic vs. advanced usage
• Documenter (?) - we want docs that auto-build, and have some guarantee to be up-to-date...

[Copilot]

Pull Request Overview

This PR restructures the UMAP package for v0.2 by splitting out utilities and neighbor logic, introducing explicit modules for configuration, and greatly expanding the test suite to cover multi-view and simplicial-set operations.

• Refactor and rename fuzzy-set combination functions (merge_local_simplicial_sets, general_simplicial_set_union, general_simplicial_set_intersection) and add column-normalization utilities in src/utils.jl.
• Reorganize src/UMAP.jl to include new modules (config.jl, neighbors.jl, simplicial_sets.jl, etc.) and adjust exports.
• Add comprehensive tests for neighbors, simplicial sets, and utils, and scaffold tests for configuration and membership-function modules.

Reviewed Changes

Copilot reviewed 25 out of 27 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
src/utils.jl	Added merge/intersect of fuzzy sets, normalization, reset tools
src/UMAP.jl	Updated includes/exports to reflect new module split
test/utils_tests.jl	Updated tests for new merge/local-connectivity utilities
test/neighbors_tests.jl	New tests covering knn_search across multiple view scenarios
test/simplicial_sets_tests.jl	New tests for fuzzy_simplicial_set and coalesce_views

Comments suppressed due to low confidence (4)

src/UMAP.jl:21

• The public API no longer exports transform or the UMAP_ constructor, which breaks backwards compatibility. Consider re-adding export transform, UMAP_ if those remain intended public entry points.

export umap

test/membership_fn_tests.jl:2

• The membership_fn_tests.jl file is empty. Add tests for fit_ab (and any other membership-function utilities) to ensure coverage of the new membership_fn module.

@testset "membership_fn tests" begin

test/config_tests.jl:1

• The config_tests.jl file has no assertions. Add tests for the new parameter structs (SourceViewParams, SourceGlobalParams, etc.) to validate construction and argument checks.

@testset "Configuration Tests" begin

src/utils.jl:102

• [nitpick] _norm_sparse lacks a docstring. Please add a brief docstring explaining its purpose, inputs, and the effect on the input sparse matrix.

function _norm_sparse(simplicial_set::AbstractSparseMatrix)