clusterkit 0.1.0.pre.1 → 0.1.0.pre.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fd025da9b7f5c97e370d05fb1062484cb99b0aaaa4a7c310eb27df78336c91b4
-  data.tar.gz: 7665cf847930bc47cb04adc1f466ba09ea33c14da5f242434b08493047945f91
+  metadata.gz: 502f5f9d65ce255e4f075ca506ec0a20fddc27f14cce2df67947055e3b92801e
+  data.tar.gz: e1f26d070737d8fb4e15eb5ed9231eda7bd7e30473e883837ddfd7c780d54645
 SHA512:
-  metadata.gz: a8db6d4738ad99a20887aef90398d4163bdd8bc47bbdb8dda74496adc105602051999e50d2bc6003b4981d16b8121151d71cf55618691262b4a092f3c46a2545
-  data.tar.gz: 1a6e43a00d19d7fdaf35be6deffa5215e994a1f013b140aa23ac9bbb9d982facde94d710a894cba39e1fbd39bccd7c020b86a99e9d32d2aa256f717844623e5e
+  metadata.gz: bccf375389b9c0b98a1426470830b69675b3f7be15ae691366433eaa313270980e71d6232812fb1a2b823a5f4a1370fd9d62e1d54b0b150c491dda19d0c41d63
+  data.tar.gz: 5478910b6c42c50aed1f9e8184638a4e0a3903c34136c724f25c2a531385d89f24d599c4b649b6e569a5e043dd2d9a36dfbce5d796d8e42369613831e38dbe0e

data/README.md

@@ -38,6 +38,22 @@ This gem would not be possible without these foundational libraries. Please cons
   - Comparison of different algorithms
   - Built-in rake tasks for quick experimentation
 
+## API Structure
+
+ClusterKit organizes its functionality into clear modules:
+
+- **`ClusterKit::Dimensionality`** - All dimensionality reduction algorithms
+  - `ClusterKit::Dimensionality::UMAP` - UMAP implementation
+  - `ClusterKit::Dimensionality::PCA` - PCA implementation  
+  - `ClusterKit::Dimensionality::SVD` - SVD implementation
+- **`ClusterKit::Clustering`** - All clustering algorithms
+  - `ClusterKit::Clustering::KMeans` - K-means clustering
+  - `ClusterKit::Clustering::HDBSCAN` - HDBSCAN clustering
+- **`ClusterKit::Utils`** - Utility functions
+- **`ClusterKit::Preprocessing`** - Data preprocessing tools
+
+All user-facing classes are in these modules. Implementation details are kept private.
+
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -222,6 +238,15 @@ test_data = all_data[150..-1]       # Last 50 samples for testing
 umap.fit(training_data)
 test_embedded = umap.transform(test_data)
 
+# Save and load fitted models
+umap.save_model("umap_model.bin")                  # Save the fitted model
+loaded_umap = ClusterKit::Dimensionality::UMAP.load_model("umap_model.bin")  # Load it later
+new_data_embedded = loaded_umap.transform(new_data)  # Use loaded model for new data
+
+# Save and load transformed data (useful for caching results)
+ClusterKit::Dimensionality::UMAP.save_data(embedded, "embeddings.json")
+cached_embeddings = ClusterKit::Dimensionality::UMAP.load_data("embeddings.json")
+
 # Note: The library automatically adjusts n_neighbors if it's too large for your dataset
 ```
 

data/lib/clusterkit/dimensionality/umap.rb

@@ -9,7 +9,7 @@ module ClusterKit
   module Dimensionality
     class UMAP
     attr_reader :n_components, :n_neighbors, :random_seed, :nb_grad_batch, :nb_sampling_by_edge
-    
+
     # Initialize a new UMAP instance
     # @param n_components [Integer] Target number of dimensions (default: 2)
     # @param n_neighbors [Integer] Number of neighbors for manifold approximation (default: 15)
@@ -18,7 +18,7 @@ module ClusterKit
     #                                Controls training iterations - lower = faster but less accurate
     # @param nb_sampling_by_edge [Integer] Number of negative samples per edge (default: 8)
     #                                      Controls sampling quality - lower = faster but less accurate
-    def initialize(n_components: 2, n_neighbors: 15, random_seed: nil, 
+    def initialize(n_components: 2, n_neighbors: 15, random_seed: nil,
                    nb_grad_batch: 10, nb_sampling_by_edge: 8)
       @n_components = n_components
       @n_neighbors = n_neighbors
@@ -29,21 +29,21 @@ module ClusterKit
       # Don't create RustUMAP yet - will be created in fit/fit_transform with adjusted parameters
       @rust_umap = nil
     end
-    
+
     # Fit the model to the data (training)
     # @param data [Array<Array<Numeric>>] Training data as 2D array
     # @return [self] Returns self for method chaining
     # @note UMAP's training process inherently produces embeddings. Since the
-    #       underlying Rust implementation doesn't separate training from 
+    #       underlying Rust implementation doesn't separate training from
     #       transformation, we call fit_transform but discard the embeddings.
     #       Use fit_transform if you need both training and the transformed data.
     def fit(data)
       validate_input(data)
-      
+
       # Always recreate RustUMAP for fit to ensure fresh fit
       @rust_umap = nil
       create_rust_umap_with_adjusted_params(data)
-      
+
       # UMAP doesn't separate training from transformation internally,
       # so we call fit_transform but discard the result
       begin
@@ -59,7 +59,7 @@ module ClusterKit
         handle_umap_error(RuntimeError.new(e.message), data)
       end
     end
-    
+
     # Transform data using the fitted model
     # @param data [Array<Array<Numeric>>] Data to transform
     # @return [Array<Array<Float>>] Transformed data in reduced dimensions
@@ -71,17 +71,17 @@ module ClusterKit
         @rust_umap.transform(data)
       end
     end
-    
+
     # Fit the model and transform the data in one step
     # @param data [Array<Array<Numeric>>] Training data as 2D array
     # @return [Array<Array<Float>>] Transformed data in reduced dimensions
     def fit_transform(data)
       validate_input(data)
-      
+
       # Always recreate RustUMAP for fit_transform to ensure fresh fit
       @rust_umap = nil
       create_rust_umap_with_adjusted_params(data)
-      
+
       begin
         result = Silence.maybe_silence do
           @rust_umap.fit_transform(data)
@@ -95,36 +95,36 @@ module ClusterKit
         handle_umap_error(RuntimeError.new(e.message), data)
       end
     end
-    
+
     # Check if the model has been fitted
     # @return [Boolean] true if model is fitted, false otherwise
     def fitted?
       @fitted
     end
-    
+
     # Save the fitted model to a file
     # @param path [String] Path where to save the model
     # @raise [RuntimeError] If model hasn't been fitted yet
-    def save(path)
+    def save_model(path)
       raise RuntimeError, "No model to save. Call fit or fit_transform first." unless fitted?
-      
+
       # Ensure directory exists
       dir = File.dirname(path)
       FileUtils.mkdir_p(dir) unless dir == '.' || dir == '/'
-      
+
       @rust_umap.save_model(path)
     end
-    
+
     # Load a fitted model from a file
     # @param path [String] Path to the saved model
     # @return [UMAP] A new UMAP instance with the loaded model
     # @raise [ArgumentError] If file doesn't exist
-    def self.load(path)
+    def self.load_model(path)
       raise ArgumentError, "File not found: #{path}" unless File.exist?(path)
-      
-      # Load the Rust model
-      rust_umap = ::ClusterKit::RustUMAP.load_model(path)
-      
+
+      # Load the Rust model (access private constant)
+      rust_umap = ::ClusterKit.const_get(:RustUMAP).load_model(path)
+
       # Create a new UMAP instance with the loaded model
       instance = allocate
       instance.instance_variable_set(:@rust_umap, rust_umap)
@@ -133,172 +133,176 @@ module ClusterKit
       instance.instance_variable_set(:@n_components, nil)
       instance.instance_variable_set(:@n_neighbors, nil)
       instance.instance_variable_set(:@random_seed, nil)
-      
+
       instance
     end
-    
-    # Export transformed data to JSON (utility method for caching)
-    # @param data [Array<Array<Float>>] Transformed data to export
+
+    # Save transformed data to JSON file
+    # @param data [Array<Array<Float>>] Transformed data to save
     # @param path [String] Path where to save the data
-    def self.export_data(data, path)
+    def self.save_data(data, path)
+      FileUtils.mkdir_p(File.dirname(path)) unless File.dirname(path) == '.'
       File.write(path, JSON.pretty_generate(data))
     end
-    
-    # Import transformed data from JSON (utility method for caching)
+
+    # Load transformed data from JSON file
     # @param path [String] Path to the saved data
     # @return [Array<Array<Float>>] The loaded data
-    def self.import_data(path)
+    # @raise [ArgumentError] If file doesn't exist
+    def self.load_data(path)
+      raise ArgumentError, "File not found: #{path}" unless File.exist?(path)
       JSON.parse(File.read(path))
     end
-    
+
     private
-    
+
     def handle_umap_error(error, data)
       error_msg = error.message
       n_samples = data.size
-      
+
       case error_msg
       when /isolated point/i, /graph will not be connected/i
         raise ::ClusterKit::IsolatedPointError, <<~MSG
           UMAP found isolated points in your data that are too far from other points.
-          
+
           This typically happens when:
           • Your data contains outliers that are very different from other points
           • You're using random data without inherent structure
           • The n_neighbors parameter (#{@n_neighbors}) is too high for your data distribution
-          
+
           Solutions:
           1. Reduce n_neighbors (try 5 or even 3): UMAP.new(n_neighbors: 5)
           2. Remove outliers from your data before applying UMAP
           3. Ensure your data has some structure (not purely random)
           4. For small datasets (< 50 points), consider using PCA instead
-          
+
           Your data: #{n_samples} samples, #{data.first&.size || 0} dimensions
         MSG
-        
+
       when /assertion failed.*box_size/i
         raise ::ClusterKit::ConvergenceError, <<~MSG
           UMAP failed to converge due to numerical instability in your data.
-          
+
           This typically happens when:
           • Data points are too spread out or have extreme values
           • The scale of different features varies wildly
           • There are duplicate or nearly-duplicate points
-          
+
           Solutions:
           1. Normalize your data first: ClusterKit::Preprocessing.normalize(data)
-          2. Use a smaller n_neighbors value: UMAP.new(n_neighbors: 5)  
+          2. Use a smaller n_neighbors value: UMAP.new(n_neighbors: 5)
           3. Check for and remove duplicate points
           4. Scale your data to a reasonable range (e.g., 0-1 or -1 to 1)
-          
+
           Your data: #{n_samples} samples, #{data.first&.size || 0} dimensions
         MSG
-        
+
       when /n_neighbors.*larger than/i, /too many neighbors/i
         raise ::ClusterKit::InvalidParameterError, <<~MSG
           The n_neighbors parameter (#{@n_neighbors}) is too large for your dataset size (#{n_samples}).
-          
+
           UMAP needs n_neighbors to be less than the number of samples.
           Suggested value: #{[5, (n_samples * 0.1).to_i].max}
-          
+
           This should have been auto-adjusted. If you're seeing this error, please report it.
         MSG
-        
+
       else
         # For unknown errors, still provide some guidance
         raise ::ClusterKit::Error, <<~MSG
           UMAP encountered an error: #{error_msg}
-          
+
           Common solutions:
           1. Try reducing n_neighbors (current: #{@n_neighbors})
           2. Normalize your data first
           3. Check for NaN or infinite values in your data
           4. Ensure you have at least 10 data points
-          
+
           If this persists, consider using PCA for dimensionality reduction instead.
         MSG
       end
     end
-    
+
     def validate_input(data, check_min_samples: true)
       raise ArgumentError, "Input must be an array" unless data.is_a?(Array)
       raise ArgumentError, "Input cannot be empty" if data.empty?
-      
+
       first_row = data.first
       raise ArgumentError, "Input must be a 2D array (array of arrays)" unless first_row.is_a?(Array)
-      
+
       row_length = first_row.length
       min_val = Float::INFINITY
       max_val = -Float::INFINITY
-      
+
       # First validate data structure and types
       data.each_with_index do |row, i|
         unless row.is_a?(Array)
           raise ArgumentError, "Row #{i} is not an array"
         end
-        
+
         if row.length != row_length
           raise ArgumentError, "All rows must have the same length (row #{i} has #{row.length} elements, expected #{row_length})"
         end
-        
+
         row.each_with_index do |val, j|
           unless val.is_a?(Numeric)
             raise ArgumentError, "Element at position [#{i}, #{j}] is not numeric"
           end
-          
+
           # Only check for NaN/Infinite on floats
           if val.is_a?(Float) && (val.nan? || val.infinite?)
             raise ArgumentError, "Element at position [#{i}, #{j}] is NaN or Infinite"
           end
-          
+
           # Track data range
           val_f = val.to_f
           min_val = val_f if val_f < min_val
           max_val = val_f if val_f > max_val
         end
       end
-      
+
       # Check for sufficient data points after validating structure (only for fit operations)
       if check_min_samples && data.size < 10
         raise ::ClusterKit::InsufficientDataError, <<~MSG
           UMAP requires at least 10 data points, but only #{data.size} provided.
-          
+
           For small datasets, consider:
           1. Using PCA instead: ClusterKit::Dimensionality::PCA.new(n_components: 2)
           2. Collecting more data points
           3. Using simpler visualization methods
         MSG
       end
-      
+
       # Check for extreme data ranges that might cause numerical issues
       data_range = max_val - min_val
       if data_range > 1000
         warn "WARNING: Large data range detected (#{data_range.round(2)}). Consider normalizing your data to prevent numerical instability."
       end
     end
-    
+
     def create_rust_umap_with_adjusted_params(data)
       # Only create if not already created
       return if @rust_umap
-      
+
       n_samples = data.size
-      
+
       # Automatically adjust n_neighbors if it's too high for the dataset
       # n_neighbors should be less than n_samples
       # Use a reasonable default: min(15, n_samples / 4) but at least 2
       max_neighbors = [n_samples - 1, 2].max  # At least 2, but less than n_samples
       suggested_neighbors = [[15, n_samples / 4].min.to_i, 2].max
-      
+
       adjusted_n_neighbors = @n_neighbors
       if @n_neighbors > max_neighbors
         adjusted_n_neighbors = [suggested_neighbors, max_neighbors].min
-        
+
         if ::ClusterKit.configuration.verbose
           warn "UMAP: Adjusted n_neighbors from #{@n_neighbors} to #{adjusted_n_neighbors} for dataset with #{n_samples} samples"
         end
       end
-      
-      @rust_umap = ::ClusterKit::RustUMAP.new({
+
+      # Access the private constant from inside the module
+      @rust_umap = ::ClusterKit.const_get(:RustUMAP).new({
         n_components: @n_components,
         n_neighbors: adjusted_n_neighbors,
         random_seed: @random_seed,

data/lib/clusterkit/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ClusterKit
-  VERSION = "0.1.0.pre.1"
+  VERSION = "0.1.0.pre.2"
 end

data/lib/clusterkit.rb

@@ -21,20 +21,18 @@ module ClusterKit
   class DisconnectedGraphError < DataError; end
   class InsufficientDataError < DataError; end
 
-  # Load modules - can't use autoload with require_relative path issues
-  require_relative "clusterkit/dimensionality"
-  require_relative "clusterkit/clustering"
-  
   # Autoload utilities
   autoload :Utils, "clusterkit/utils"
   autoload :Preprocessing, "clusterkit/preprocessing"
   autoload :Silence, "clusterkit/silence"
   
-  # Load the extension first
-  require_relative "clusterkit/clusterkit"
-  
-  # Now load the modules that depend on the extension
+  # Load modules that depend on the extension
+  require_relative "clusterkit/dimensionality"
   require_relative "clusterkit/clustering"
+  
+  # Make RustUMAP private - it's an implementation detail
+  # Users should use Dimensionality::UMAP instead
+  private_constant :RustUMAP if const_defined?(:RustUMAP)
 
   class << self
     # Quick UMAP embedding

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: clusterkit
 version: !ruby/object:Gem::Version
-  version: 0.1.0.pre.1
+  version: 0.1.0.pre.2
 platform: ruby
 authors:
 - Chris Petersen