xgb 0.3.1 → 0.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 295787749986ba153354f61845509079f470a5d11015c20cb89a5c58f04b133a
-  data.tar.gz: e111099514e9a9a48d51a5033214a3e897eeff209302e47e1f30d79c818833c5
+  metadata.gz: d2cea39eebbe29b40f1d4248bb9b4e3f4f112f2fcfcb2554bdf87c1fae0b5f3f
+  data.tar.gz: 197dcfb49e37fc72a3f5ab5bb593f0faa7912fbc60219c1b49dd235b869e57eb
 SHA512:
-  metadata.gz: 803003072dafa5d2de97da7721042b94315b125f62f4f524f818923c5e5f8d3277624b146cedd7b88d9ca0769bec074e99717fb27ce56f5d2bf079ba627d52f7
-  data.tar.gz: b9b14da27b6f8c03415d770c31dd16fdd112922daa2af3022df8554301eb5e43d0e873f21c65da13799e7a62d832cadbabff50188783aad5b5e7a577a9334005
+  metadata.gz: 6c58598a08cf976a2bf7b013ae3218f96ea6c96c0e345d2fe4d3e488ad8f409f905cf060e925b3307077cf844ae27babd9581bc3ff03c8c693cf812d08593808
+  data.tar.gz: 424a5542cb90830a017f976f706d85989f64d497dc2fd4351f95fb944ab8a48b51ad62f2b3fb7d4f1215428fdf49f913eb7b7c6beb82f0edebe35076c8f18ab3

data/CHANGELOG.md

@@ -1,3 +1,27 @@
+## 0.5.2 (2021-03-09)
+
+- Added ARM shared library for Mac
+
+## 0.5.1 (2021-02-08)
+
+- Fixed error with validation sets without early stopping
+
+## 0.5.0 (2020-12-12)
+
+- Updated XGBoost to 1.3.0
+
+## 0.4.1 (2020-08-26)
+
+- Updated XGBoost to 1.2.0
+
+## 0.4.0 (2020-05-17)
+
+- Updated XGBoost to 1.1.0
+- Changed default `learning_rate` and `max_depth` for Scikit-Learn API to match Python
+- Added support for Rover
+- Improved performance of Numo datasets
+- Improved error message when OpenMP not found on Mac
+
 ## 0.3.1 (2020-04-16)
 
 - Added `feature_names` and `feature_types` to `DMatrix`

data/NOTICE.txt

@@ -1,4 +1,5 @@
-Copyright 2019-2020 Andrew Kane
+Copyright XGBoost contributors
+Copyright 2019-2021 Andrew Kane
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

data/README.md

@@ -2,7 +2,7 @@
 
 [XGBoost](https://github.com/dmlc/xgboost) - high performance gradient boosting - for Ruby
 
-[![Build Status](https://travis-ci.org/ankane/xgboost.svg?branch=master)](https://travis-ci.org/ankane/xgboost) [![Build status](https://ci.appveyor.com/api/projects/status/s8umwyuahvj68m6p/branch/master?svg=true)](https://ci.appveyor.com/project/ankane/xgboost/branch/master)
+[![Build Status](https://github.com/ankane/xgboost/workflows/build/badge.svg?branch=master)](https://github.com/ankane/xgboost/actions)
 
 ## Installation
 
@@ -137,16 +137,22 @@ Data can be an array of arrays
 [[1, 2, 3], [4, 5, 6]]
 ```
 
-Or a Daru data frame
+Or a Numo array
 
 ```ruby
-Daru::DataFrame.from_csv("houses.csv")
+Numo::NArray.cast([[1, 2, 3], [4, 5, 6]])
+```
+
+Or a Rover data frame
+
+```ruby
+Rover.read_csv("houses.csv")
 ```
 
-Or a Numo NArray
+Or a Daru data frame
 
 ```ruby
-Numo::DFloat.new(3, 2).seq
+Daru::DataFrame.from_csv("houses.csv")
 ```
 
 ## Helpful Resources

data/lib/xgboost.rb

@@ -19,7 +19,12 @@ module XGBoost
   class << self
     attr_accessor :ffi_lib
   end
-  lib_name = FFI.map_library_name("xgboost")
+  lib_name =
+    if RbConfig::CONFIG["host_os"] =~ /darwin/i && RbConfig::CONFIG["host_cpu"] =~ /arm/i
+      FFI.map_library_name("xgboost.arm64")
+    else
+      FFI.map_library_name("xgboost")
+    end
   vendor_lib = File.expand_path("../vendor/#{lib_name}", __dir__)
   self.ffi_lib = [vendor_lib]
 
@@ -61,7 +66,7 @@ module XGBoost
             best_score = score
             best_iter = iteration
             best_message = message
-          elsif iteration - best_iter >= early_stopping_rounds
+          elsif early_stopping_rounds && iteration - best_iter >= early_stopping_rounds
             booster.best_iteration = best_iter
             puts "Stopping. Best iteration:\n#{best_message}" if verbose_eval
             break

data/lib/xgboost/classifier.rb

@@ -1,6 +1,6 @@
 module XGBoost
   class Classifier < Model
-    def initialize(max_depth: 3, learning_rate: 0.1, n_estimators: 100, objective: "binary:logistic", importance_type: "gain", **options)
+    def initialize(n_estimators: 100, objective: "binary:logistic", importance_type: "gain", **options)
       super
     end
 

data/lib/xgboost/dmatrix.rb

@@ -27,18 +27,25 @@ module XGBoost
                 raise Error, "Unknown feature type: #{v}"
               end
             end
-        elsif narray?(data)
+        elsif numo?(data)
           nrow, ncol = data.shape
-          flat_data = data.flatten.to_a
+        elsif rover?(data)
+          nrow, ncol = data.shape
+          @feature_names = data.keys
+          data = data.to_numo
         else
           nrow = data.count
           ncol = data.first.count
           flat_data = data.flatten
         end
 
-        handle_missing(flat_data, missing)
         c_data = ::FFI::MemoryPointer.new(:float, nrow * ncol)
-        c_data.write_array_of_float(flat_data)
+        if numo?(data)
+          c_data.write_bytes(data.cast_to(Numo::SFloat).to_string)
+        else
+          handle_missing(flat_data, missing)
+          c_data.write_array_of_float(flat_data)
+        end
         check_result FFI.XGDMatrixCreateFromMat(c_data, nrow, ncol, missing, @handle)
 
         ObjectSpace.define_finalizer(self, self.class.finalize(handle_pointer))
@@ -134,10 +141,14 @@ module XGBoost
       defined?(Daru::DataFrame) && data.is_a?(Daru::DataFrame)
     end
 
-    def narray?(data)
+    def numo?(data)
       defined?(Numo::NArray) && data.is_a?(Numo::NArray)
     end
 
+    def rover?(data)
+      defined?(Rover::DataFrame) && data.is_a?(Rover::DataFrame)
+    end
+
     def handle_missing(data, missing)
       data.map! { |v| v.nil? ? missing : v }
     end

data/lib/xgboost/ffi.rb

@@ -2,7 +2,15 @@ module XGBoost
   module FFI
     extend ::FFI::Library
 
-    ffi_lib XGBoost.ffi_lib
+    begin
+      ffi_lib XGBoost.ffi_lib
+    rescue LoadError => e
+      if ["/usr/local", "/opt/homebrew"].any? { |v| e.message.include?("Library not loaded: #{v}/opt/libomp/lib/libomp.dylib") } && e.message.include?("Reason: image not found")
+        raise LoadError, "OpenMP not found. Run `brew install libomp`"
+      else
+        raise e
+      end
+    end
 
     # https://github.com/dmlc/xgboost/blob/master/include/xgboost/c_api.h
     # keep same order

data/lib/xgboost/regressor.rb

@@ -1,6 +1,6 @@
 module XGBoost
   class Regressor < Model
-    def initialize(max_depth: 3, learning_rate: 0.1, n_estimators: 100, objective: "reg:squarederror", importance_type: "gain", **options)
+    def initialize(n_estimators: 100, objective: "reg:squarederror", importance_type: "gain", **options)
       super
     end
 

data/lib/xgboost/version.rb

@@ -1,3 +1,3 @@
 module XGBoost
-  VERSION = "0.3.1"
+  VERSION = "0.5.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xgb
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.5.2
 platform: ruby
 authors:
 - Andrew Kane
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-04-16 00:00:00.000000000 Z
+date: 2021-03-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ffi
@@ -24,78 +24,8 @@ dependencies:
     - - ">="
       - !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'
-- !ruby/object:Gem::Dependency
-  name: daru
-  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: numo-narray
-  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'
-description: 
-email: andrew@chartkick.com
+description:
+email: andrew@ankane.org
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -116,6 +46,7 @@ files:
 - lib/xgboost/utils.rb
 - lib/xgboost/version.rb
 - vendor/LICENSE
+- vendor/libxgboost.arm64.dylib
 - vendor/libxgboost.dylib
 - vendor/libxgboost.so
 - vendor/xgboost.dll
@@ -123,7 +54,7 @@ homepage: https://github.com/ankane/xgboost
 licenses:
 - Apache-2.0
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -138,8 +69,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: High performance gradient boosting for Ruby
 test_files: []