xgb 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: dcb0666c9eb0943a77ccdbaa31074b8ca0b139ac196006b5cd6d680f6f91ac30
+  data.tar.gz: 673040af645aafc5f14378121b9dac594b5dc6dae0449f75244cc9cfeaaa10e3
+SHA512:
+  metadata.gz: 3f2838ee9f2b69ea69fdc9f3610a36f412acb8732f726478995dad0ebcf73325f99c6c3afc480ae60458035619c83f9e2c9a03d60020cf8e734ea250334541c0
+  data.tar.gz: 69034ec7cad4174837cc8347ab5cc13144532701927aa702eb93c6819ddf8ffe6d3c5c3752b39de863178e7d404cef017ddd82b7fe811aa4d5f3b62aa051729d

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+## 0.1.0
+
+- First release

data/README.md

@@ -0,0 +1,74 @@
+# Xgb
+
+[XGBoost](https://github.com/dmlc/xgboost) - the high performance machine learning library - for Ruby
+
+:fire: Uses the C API for blazing performance
+
+## Installation
+
+First, [install XGBoost](https://xgboost.readthedocs.io/en/latest/build.html). On Mac, copy `lib/libxgboost.dylib` to `/usr/local/lib`.
+
+Add this line to your application’s Gemfile:
+
+```ruby
+gem 'xgb'
+```
+
+## Getting Started
+
+Train a model
+
+```ruby
+params = {objective: "reg:squarederror"}
+train_set = Xgb::DMatrix.new(x_train, label: y_train)
+booster = Xgb.train(params, train_set)
+```
+
+Predict
+
+```ruby
+booster.predict(x_test)
+```
+
+Save the model to a file
+
+```ruby
+booster.save_model("model.txt")
+```
+
+Load the model from a file
+
+```ruby
+booster = Xgb::Booster.new(model_file: "model.txt")
+```
+
+## Reference
+
+This library follows the [Core Data Structure and Learning APIs](https://xgboost.readthedocs.io/en/latest/python/python_api.html) for the Python library. Some methods and options are missing at the moment. PRs welcome!
+
+## Helpful Resources
+
+- [Parameters](https://xgboost.readthedocs.io/en/latest/parameter.html)
+- [Parameter Tuning](https://xgboost.readthedocs.io/en/latest/tutorials/param_tuning.html)
+
+## Related Projects
+
+- [LightGBM](https://github.com/ankane/lightgbm) - LightGBM for Ruby
+- [Eps](https://github.com/ankane/eps) - Machine Learning for Ruby
+
+## Credits
+
+Thanks to the [xgboost](https://github.com/PairOnAir/xgboost-ruby) gem for serving as an initial reference, and Selva Prabhakaran for the [test datasets](https://github.com/selva86/datasets).
+
+## History
+
+View the [changelog](https://github.com/ankane/xgb/blob/master/CHANGELOG.md)
+
+## Contributing
+
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
+
+- [Report bugs](https://github.com/ankane/xgb/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/xgb/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features

data/lib/xgb.rb

@@ -0,0 +1,26 @@
+# dependencies
+require "ffi"
+
+# modules
+require "xgb/utils"
+require "xgb/booster"
+require "xgb/dmatrix"
+require "xgb/ffi"
+require "xgb/version"
+
+module Xgb
+  class Error < StandardError; end
+
+  class << self
+    def train(params, dtrain, num_boost_round: 10)
+      booster = Booster.new(params: params)
+      booster.set_param("num_feature", dtrain.num_col)
+
+      num_boost_round.times do |iteration|
+        booster.update(dtrain, iteration)
+      end
+
+      booster
+    end
+  end
+end

data/lib/xgb/booster.rb

@@ -0,0 +1,50 @@
+module Xgb
+  class Booster
+    def initialize(params: nil, model_file: nil)
+      @handle = ::FFI::MemoryPointer.new(:pointer)
+      check_result FFI.XGBoosterCreate(nil, 0, @handle)
+      if model_file
+        check_result FFI.XGBoosterLoadModel(handle_pointer, model_file)
+      end
+
+      set_param(params)
+      @num_class = (params && params[:num_class]) || 1
+    end
+
+    def update(dtrain, iteration)
+      check_result FFI.XGBoosterUpdateOneIter(handle_pointer, iteration, dtrain.handle_pointer)
+    end
+
+    def set_param(params, value = nil)
+      if params.is_a?(Enumerable)
+        params.each do |k, v|
+          check_result FFI.XGBoosterSetParam(handle_pointer, k.to_s, v.to_s)
+        end
+      else
+        check_result FFI.XGBoosterSetParam(handle_pointer, params.to_s, value.to_s)
+      end
+    end
+
+    def predict(data, ntree_limit: nil)
+      ntree_limit ||= 0
+      out_len = ::FFI::MemoryPointer.new(:long)
+      out_result = ::FFI::MemoryPointer.new(:pointer)
+      check_result FFI.XGBoosterPredict(handle_pointer, data.handle_pointer, 0, ntree_limit, out_len, out_result)
+      out = out_result.read_pointer.read_array_of_float(out_len.read_long)
+      out = out.each_slice(@num_class).to_a if @num_class > 1
+      out
+    end
+
+    def save_model(fname)
+      check_result FFI.XGBoosterSaveModel(handle_pointer, fname)
+    end
+
+    private
+
+    def handle_pointer
+      @handle.read_pointer
+    end
+
+    include Utils
+  end
+end

data/lib/xgb/dmatrix.rb

@@ -0,0 +1,38 @@
+module Xgb
+  class DMatrix
+    attr_reader :data, :label, :weight
+
+    def initialize(data, label: nil, weight: nil, missing: Float::NAN)
+      @data = data
+      @label = label
+      @weight = weight
+
+      c_data = ::FFI::MemoryPointer.new(:float, data.count * data.first.count)
+      c_data.put_array_of_float(0, data.flatten)
+      @handle = ::FFI::MemoryPointer.new(:pointer)
+      check_result FFI.XGDMatrixCreateFromMat(c_data, data.count, data.first.count, missing, @handle)
+
+      set_float_info("label", label) if label
+    end
+
+    def num_col
+      out = ::FFI::MemoryPointer.new(:long)
+      FFI.XGDMatrixNumCol(handle_pointer, out)
+      out.read_long
+    end
+
+    def handle_pointer
+      @handle.read_pointer
+    end
+
+    private
+
+    def set_float_info(field, data)
+      c_data = ::FFI::MemoryPointer.new(:float, data.count)
+      c_data.put_array_of_float(0, data)
+      check_result FFI.XGDMatrixSetFloatInfo(handle_pointer, field.to_s, c_data, data.size)
+    end
+
+    include Utils
+  end
+end

data/lib/xgb/ffi.rb

@@ -0,0 +1,25 @@
+module Xgb
+  module FFI
+    extend ::FFI::Library
+    ffi_lib ["xgboost"]
+
+    # https://github.com/dmlc/xgboost/blob/master/include/xgboost/c_api.h
+    # keep same order
+
+    # error
+    attach_function :XGBGetLastError, %i[], :string
+
+    # dmatrix
+    attach_function :XGDMatrixCreateFromMat, %i[pointer long long float pointer], :int
+    attach_function :XGDMatrixNumCol, %i[pointer pointer], :int
+    attach_function :XGDMatrixSetFloatInfo, %i[pointer string pointer long], :int
+
+    # booster
+    attach_function :XGBoosterCreate, %i[pointer int pointer], :int
+    attach_function :XGBoosterUpdateOneIter, %i[pointer int pointer], :int
+    attach_function :XGBoosterSetParam, %i[pointer string string], :int
+    attach_function :XGBoosterPredict, %i[pointer pointer int int pointer pointer], :int
+    attach_function :XGBoosterLoadModel, %i[pointer string], :int
+    attach_function :XGBoosterSaveModel, %i[pointer string], :int
+  end
+end

data/lib/xgb/utils.rb

@@ -0,0 +1,9 @@
+module Xgb
+  module Utils
+    private
+
+    def check_result(err)
+      raise Xgb::Error, FFI.XGBGetLastError if err != 0
+    end
+  end
+end

data/lib/xgb/version.rb

@@ -0,0 +1,3 @@
+module Xgb
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,106 @@
+--- !ruby/object:Gem::Specification
+name: xgb
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Andrew Kane
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-08-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ffi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5'
+description: 
+email: andrew@chartkick.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- README.md
+- lib/xgb.rb
+- lib/xgb/booster.rb
+- lib/xgb/dmatrix.rb
+- lib/xgb/ffi.rb
+- lib/xgb/utils.rb
+- lib/xgb/version.rb
+homepage: https://github.com/ankane/xgb
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.4'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.4
+signing_key: 
+specification_version: 4
+summary: XGBoost - the high performance machine learning library - for Ruby
+test_files: []