clusterkit 0.2.1 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ed8756bb9b2d2cf253c849f529b18aa57c0043fe0e0b65997fffc62522d21fd6
-  data.tar.gz: adcb4a5186e042a0be6d9e712b8dbff5751c469295ccbef9034bf40688658c21
+  metadata.gz: c3da45be55195b7646566e031639b24724f5ebb27bed4bc40a4121fccede290e
+  data.tar.gz: 9162028aaeb4956368e1a40ccec1d5a5af70e9c7ced9e8148da0dcb9b6711a12
 SHA512:
-  metadata.gz: 3f16b15661cf7db9a42f080dc5cb8835ded9f36518f0f3e095ea50bf7c93555906a1b3233744b11551cb2d45c1b3a9b1d2e5a64051d770b277e6a0669e0698b2
-  data.tar.gz: 36e4df00fbfb48b44bdcacbcb29e9a077c5711cc5cbc79d0ae9091c604db489bea06fa1c354ad89a87aa50e5c7dc8fe2b75f426e1942ae01d46887dda72b5ab1
+  metadata.gz: c1e86b6a03da44fa3b9e49b8b39eabe97aeebd3b4766731c0be629b35aab8a6566ee2d94a81bbbbf47e43c9c03da7d6f44c240461865f062f8e709987f6997ca
+  data.tar.gz: 114362ba8b87b4045da8c0092b8dc365436dc94c975658f63affcfa18c103fed27320353236e67c96ca5b3d5da1ad746176b864656db0ab1f96cf4eb940bf19e

data/README.md

@@ -720,7 +720,7 @@ COVERAGE=true bundle exec rspec
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/cpetersen/clusterkit.
+Bug reports and pull requests are welcome on GitHub at https://github.com/scientist-labs/clusterkit.
 
 ## License
 
@@ -735,7 +735,7 @@ If you use ClusterKit in your research, please cite:
   author = {Chris Petersen},
   title = {ClusterKit: High-Performance Clustering and Dimensionality Reduction for Ruby},
   year = {2024},
-  url = {https://github.com/cpetersen/clusterkit}
+  url = {https://github.com/scientist-labs/clusterkit}
 }
 ```
 

data/clusterkit.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |spec|
 
   spec.summary = "High-performance clustering and dimensionality reduction for Ruby"
   spec.description = "A comprehensive clustering toolkit for Ruby, providing UMAP, PCA, K-means, HDBSCAN and more. Built on top of annembed and hdbscan Rust crates for blazing-fast performance."
-  spec.homepage = "https://github.com/cpetersen/clusterkit"
+  spec.homepage = "https://github.com/scientist-labs/clusterkit"
   spec.license = "MIT"
   spec.required_ruby_version = ">= 2.7.0"
 

data/docs/KNOWN_ISSUES.md

@@ -14,7 +14,7 @@ This gem has three main categories of limitations:
 
 **Reason**: UMAP needs sufficient data to construct a meaningful manifold approximation. With fewer than 10 points, the algorithm cannot create a reliable graph structure.
 
-**Workaround**: 
+**Workaround**:
 - Use PCA for datasets with fewer than 10 points
 - The `transform` method can handle smaller datasets once the model is fitted on adequate training data
 
@@ -30,12 +30,12 @@ This gem has three main categories of limitations:
 
 **Previous Issue**: The box_size assertion would panic and crash the Ruby process.
 
-**Current Status**: **FIXED** in `cpetersen/annembed:fix-box-size-panic` branch
+**Current Status**: **FIXED** in `scientist-labs/annembed:fix-box-size-panic` branch
 - The `"assertion failed: (*f).abs() <= box_size"` panic has been converted to a catchable error
 - Extreme value ranges are now handled gracefully through normalization
 - NaN/Infinite values are detected and reported with clear error messages
 
-**Remaining Uncatchable Errors**: 
+**Remaining Uncatchable Errors**:
 - Array bounds violations (accessing out-of-bounds indices)
 - Some `.unwrap()` calls on `None` or `Err` values
 - These are much less common in normal usage
@@ -98,7 +98,7 @@ def safe_umap_transform(data, options = {})
   # Save data to temporary file before processing
   temp_file = "temp_umap_data_#{Time.now.to_i}.json"
   File.write(temp_file, JSON.dump(data))
-  
+
   begin
     umap = ClusterKit::Dimensionality::UMAP.new(**options)
     result = umap.fit_transform(data)
@@ -127,4 +127,4 @@ def reduce_dimensions(data, n_components: 2)
     pca.fit_transform(data)
   end
 end
-```
+```

data/docs/RUST_ERROR_HANDLING.md

@@ -37,11 +37,11 @@ These use Rust's `assert!` or `panic!` macros and CANNOT be caught. They will cr
 
 | Error | Source | Location | Trigger Condition |
 |-------|--------|----------|-------------------|
-| ~~Box size assertion~~ | ~~annembed~~ | ~~`set_data_box`~~ | **FIXED in cpetersen/annembed:fix-box-size-panic** |
+| ~~Box size assertion~~ | ~~annembed~~ | ~~`set_data_box`~~ | **FIXED in scientist-labs/annembed:fix-box-size-panic** |
 | Array bounds | Various | Index operations | Accessing out-of-bounds indices |
 | Unwrap failures | Various | `.unwrap()` calls | Unwrapping `None` or `Err` |
 
-**Update (2025-08-19):** The box size assertion has been fixed in the `fix-box-size-panic` branch of cpetersen/annembed. It now returns a proper `Result<(), anyhow::Error>` that can be caught and handled gracefully:
+**Update (2025-08-19):** The box size assertion has been fixed in the `fix-box-size-panic` branch of scientist-labs/annembed. It now returns a proper `Result<(), anyhow::Error>` that can be caught and handled gracefully:
 
 ```rust
 // Previously (would panic):
@@ -96,13 +96,13 @@ when /isolated point/i
 
 **Previous Issue:** Would panic and crash the Ruby process
 
-**Current Status:** Fixed in `cpetersen/annembed:fix-box-size-panic` branch
-- Now returns a catchable `anyhow::Error` 
+**Current Status:** Fixed in `scientist-labs/annembed:fix-box-size-panic` branch
+- Now returns a catchable `anyhow::Error`
 - Detects NaN/Infinite values during normalization
 - Handles constant data (max_max = 0) gracefully
 - Extreme value ranges are normalized successfully
 
-**User-visible behavior:** 
+**User-visible behavior:**
 - Previously: Ruby process would crash with assertion failure
 - Now: Raises a catchable Ruby exception with helpful error message
 
@@ -161,4 +161,4 @@ when /isolated point/i
 
 The test suite mocks Rust errors to verify our error handling logic works correctly. However, actual panic conditions cannot be tested without crashing the test process.
 
-See `spec/clusterkit/error_handling_spec.rb` for error handling tests.
+See `spec/clusterkit/error_handling_spec.rb` for error handling tests.

data/ext/clusterkit/Cargo.toml

@@ -8,8 +8,8 @@ crate-type = ["cdylib"]
 
 [dependencies]
 magnus = { version = "0.6", features = ["embed"] }
-annembed = { git = "https://github.com/cpetersen/annembed", tag = "clusterkit-0.1.0" }
-hnsw_rs = { git = "https://github.com/cpetersen/hnswlib-rs", tag = "clusterkit-0.1.0" }
+annembed = { git = "https://github.com/scientist-labs/annembed", tag = "clusterkit-0.1.1" }
+hnsw_rs = { git = "https://github.com/scientist-labs/hnswlib-rs", tag = "clusterkit-0.1.0" }
 hdbscan = "0.11"
 ndarray = "0.16"
 num-traits = "0.2"
@@ -22,4 +22,4 @@ rand = "0.8"
 default = ["openblas-static"]
 openblas-static = ["annembed/openblas-static"]
 openblas-system = ["annembed/openblas-system"]
-intel-mkl-static = ["annembed/intel-mkl-static"]
+intel-mkl-static = ["annembed/intel-mkl-static"]

data/lib/clusterkit/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ClusterKit
-  VERSION = "0.2.1"
+  VERSION = "0.2.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: clusterkit
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.3
 platform: ruby
 authors:
 - Chris Petersen
@@ -171,13 +171,13 @@ files:
 - lib/clusterkit/utils.rb
 - lib/clusterkit/version.rb
 - lib/tasks/visualize.rake
-homepage: https://github.com/cpetersen/clusterkit
+homepage: https://github.com/scientist-labs/clusterkit
 licenses:
 - MIT
 metadata:
-  homepage_uri: https://github.com/cpetersen/clusterkit
-  source_code_uri: https://github.com/cpetersen/clusterkit
-  changelog_uri: https://github.com/cpetersen/clusterkit/blob/main/CHANGELOG.md
+  homepage_uri: https://github.com/scientist-labs/clusterkit
+  source_code_uri: https://github.com/scientist-labs/clusterkit
+  changelog_uri: https://github.com/scientist-labs/clusterkit/blob/main/CHANGELOG.md
 post_install_message:
 rdoc_options: []
 require_paths: