xgb 0.3.0 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e9ad2900e477bc8e8fa5aca236a49fb4d41d8ec28b3c975049b16023a89cfe60
-  data.tar.gz: 3228781e80b95310a5c874b27fd69ab29ec875e79daf1bdbe99d09178c1ed2b2
+  metadata.gz: 73bd02bae172bccd30215402bc58a761f2f39c46002c6fee42d429e052470861
+  data.tar.gz: 2773ef6f7e0cb2cd2e71cf5c9329beb08aaca79806e1e359b448b78b684273c0
 SHA512:
-  metadata.gz: 228b317e43933701e2b9d3bdd0a1fc9c8781e64e2ec494b63a8be3efa5487350b022b64bcaffb4088e7e24c5698c39f23864248a87277e63d07ed7bd17573a09
-  data.tar.gz: f8cb92f5f10b20bb7342ee126a75cfb44fc85b0bd01e941b2031ad5b957be9c5c6060b22737ac04584f51eb0ed41668431c849a0417484358496606abf3690de
+  metadata.gz: 04e3534c0a6cb921016a39b9331fea803ff8a54c5b9c16ea982f7f9cbde8503f51b088e2a77148ca516c215c505e7081b89e026cc7d230a607bbc03fc8a6873d
+  data.tar.gz: 38252580d26db1407d7e843b8c88210d3f65641bc9b0359d3318d22fc94fef8be834fba69f30e7cb35c24d8c364fb3ab18a0dc67f0141c73b30593c3a0154dd4

data/CHANGELOG.md

@@ -1,3 +1,28 @@
+## 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`
+- Added feature names to `dump`
+
 ## 0.3.0 (2020-02-19)
 
 - Updated XGBoost to 1.0.0

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

@@ -31,7 +31,8 @@ module XGBoost
       booster = Booster.new(params: params)
       num_feature = dtrain.num_col
       booster.set_param("num_feature", num_feature)
-      booster.feature_names = num_feature.times.map { |i| "f#{i}" }
+      booster.feature_names = dtrain.feature_names
+      booster.feature_types = dtrain.feature_types
       evals ||= []
 
       if early_stopping_rounds
@@ -60,7 +61,7 @@ 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/booster.rb

@@ -1,6 +1,6 @@
 module XGBoost
   class Booster
-    attr_accessor :best_iteration, :feature_names
+    attr_accessor :best_iteration, :feature_names, :feature_types
 
     def initialize(params: nil, model_file: nil)
       @handle = ::FFI::MemoryPointer.new(:pointer)
@@ -25,11 +25,8 @@ module XGBoost
     end
 
     def eval_set(evals, iteration)
-      dmats = ::FFI::MemoryPointer.new(:pointer, evals.size)
-      dmats.write_array_of_pointer(evals.map { |v| v[0].handle_pointer })
-
-      evnames = ::FFI::MemoryPointer.new(:pointer, evals.size)
-      evnames.write_array_of_pointer(evals.map { |v| ::FFI::MemoryPointer.from_string(v[1]) })
+      dmats = array_of_pointers(evals.map { |v| v[0].handle_pointer })
+      evnames = array_of_pointers(evals.map { |v| string_pointer(v[1]) })
 
       out_result = ::FFI::MemoryPointer.new(:pointer)
 
@@ -67,7 +64,13 @@ module XGBoost
     def dump(fmap: "", with_stats: false, dump_format: "text")
       out_len = ::FFI::MemoryPointer.new(:uint64)
       out_result = ::FFI::MemoryPointer.new(:pointer)
-      check_result FFI.XGBoosterDumpModelEx(handle_pointer, fmap, with_stats ? 1 : 0, dump_format, out_len, out_result)
+
+      names = feature_names || []
+      fnames = array_of_pointers(names.map { |fname| string_pointer(fname) })
+      ftypes = array_of_pointers(feature_types || Array.new(names.size, string_pointer("float")))
+
+      check_result FFI.XGBoosterDumpModelExWithFeatures(handle_pointer, names.size, fnames, ftypes, with_stats ? 1 : 0, dump_format, out_len, out_result)
+
       out_result.read_pointer.get_array_of_string(0, read_uint64(out_len))
     end
 
@@ -155,7 +158,7 @@ module XGBoost
     end
 
     def [](key_name)
-      key = ::FFI::MemoryPointer.from_string(key_name)
+      key = string_pointer(key_name)
       success = ::FFI::MemoryPointer.new(:int)
       out_result = ::FFI::MemoryPointer.new(:pointer)
 
@@ -165,8 +168,8 @@ module XGBoost
     end
 
     def []=(key_name, raw_value)
-      key = ::FFI::MemoryPointer.from_string(key_name)
-      value = raw_value.nil? ? nil : ::FFI::MemoryPointer.from_string(raw_value)
+      key = string_pointer(key_name)
+      value = raw_value.nil? ? nil : string_pointer(raw_value)
 
       check_result FFI.XGBoosterSetAttr(handle_pointer, key, value)
     end
@@ -188,6 +191,14 @@ module XGBoost
       @handle.read_pointer
     end
 
+    def array_of_pointers(values)
+      ::FFI::MemoryPointer.new(:pointer, values.size).write_array_of_pointer(values)
+    end
+
+    def string_pointer(value)
+      ::FFI::MemoryPointer.from_string(value.to_s)
+    end
+
     include Utils
   end
 end

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

@@ -1,6 +1,6 @@
 module XGBoost
   class DMatrix
-    attr_reader :data
+    attr_reader :data, :feature_names, :feature_types
 
     def initialize(data, label: nil, weight: nil, missing: Float::NAN)
       @data = data
@@ -15,21 +15,42 @@ module XGBoost
         elsif daru?(data)
           nrow, ncol = data.shape
           flat_data = data.map_rows(&:to_a).flatten
-        elsif narray?(data)
+          @feature_names = data.each_vector.map(&:name)
+          @feature_types =
+            data.each_vector.map(&:db_type).map do |v|
+              case v
+              when "INTEGER"
+                "int"
+              when "DOUBLE"
+                "float"
+              else
+                raise Error, "Unknown feature type: #{v}"
+              end
+            end
+        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))
+
+        @feature_names ||= ncol.times.map { |i| "f#{i}" }
       end
 
       self.label = label if label
@@ -120,10 +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 e.message.include?("Library not loaded: /usr/local/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
@@ -31,7 +39,7 @@ module XGBoost
     attach_function :XGBoosterPredict, %i[pointer pointer int int int pointer pointer], :int
     attach_function :XGBoosterLoadModel, %i[pointer string], :int
     attach_function :XGBoosterSaveModel, %i[pointer string], :int
-    attach_function :XGBoosterDumpModelEx, %i[pointer string int string pointer pointer], :int
+    attach_function :XGBoosterDumpModelExWithFeatures, %i[pointer int pointer pointer int string pointer pointer], :int
     attach_function :XGBoosterGetAttr, %i[pointer pointer pointer pointer], :int
     attach_function :XGBoosterSetAttr, %i[pointer pointer pointer], :int
     attach_function :XGBoosterGetAttrNames, %i[pointer pointer pointer], :int

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 = "0.3.0"
+  VERSION = "0.5.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xgb
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.5.1
 platform: ruby
 authors:
 - Andrew Kane
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-02-20 00:00:00.000000000 Z
+date: 2021-02-09 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: []
@@ -123,7 +53,7 @@ homepage: https://github.com/ankane/xgboost
 licenses:
 - Apache-2.0
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -138,8 +68,8 @@ 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: []