isotree 0.1.5 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a5974c65c4adc4fd79ee7770f324c906a2788534f3fe6f381d61711e7cdce78c
-  data.tar.gz: d401e7c5aaabcd5dcffd5e4f54d93ea4d0966698854e70d3475fd79a92e1e241
+  metadata.gz: 1876c50ef4d9bbd7fc7898c222b9f10b8d287a38cf9d37af53e9841f63494299
+  data.tar.gz: ea7b60ae9683498df1910fb3f4774ce8c94daf9fe2a6e23ffd87a9d488bcc5ce
 SHA512:
-  metadata.gz: d00de0c3902b4f7fd3e13e08f0738ec4daf8be173f60cf46f49318e76f5be3c4ef3edd925f83074e03b4fe181aa6384d43c749f5f72247cf08d44f6811a6fe80
-  data.tar.gz: 70195ae442c2e4762b2f900a82a891d8f991ace1e521d625f910a1b5e3482334a299674c255e1aebf855728ee169ab5886428baf6df9a5e436bc73f3aff6dda6
+  metadata.gz: 3d0f6d95cac8b7dd457512c0ce41c3ae286cf8f344ccc8a47dee1c00104657b3d2d9c97be1c1211fcb253065ba7fcf3d3b955a89dd9bac8b2b6e5e35516c7b7d
+  data.tar.gz: 476d7c8ffe5c252ba94ecc7a68e59fc3afbbb2a732fd9e3127e032e543a74957fcdef6173b6225dfee7370dbb86625b61b02d16a68cc7257be8f7cbdae87a581

data/CHANGELOG.md

@@ -1,3 +1,16 @@
+## 0.2.2 (2022-06-12)
+
+- Fixed segfault when data is smaller than sample size
+
+## 0.2.1 (2021-05-23)
+
+- Improved performance
+
+## 0.2.0 (2021-05-17)
+
+- Updated to Rice 4
+- Dropped support for Ruby < 2.6
+
 ## 0.1.5 (2021-03-14)
 
 - Updated Isotree to 0.1.25

data/README.md

@@ -1,19 +1,19 @@
-# IsoTree
+# IsoTree Ruby
 
 :evergreen_tree: [IsoTree](https://github.com/david-cortes/isotree) - outlier/anomaly detection using Isolation Forest - for Ruby
 
 Learn how [Isolation Forest](https://www.youtube.com/watch?v=RyFQXQf4w4w) works
 
-:deciduous_tree: Check out [OutlierTree](https://github.com/ankane/outliertree) for human-readable explanations of outliers
+:deciduous_tree: Check out [OutlierTree](https://github.com/ankane/outliertree-ruby) for human-readable explanations of outliers
 
-[![Build Status](https://github.com/ankane/isotree/workflows/build/badge.svg?branch=master)](https://github.com/ankane/isotree/actions)
+[![Build Status](https://github.com/ankane/isotree-ruby/workflows/build/badge.svg?branch=master)](https://github.com/ankane/isotree-ruby/actions)
 
 ## Installation
 
 Add this line to your application’s Gemfile:
 
 ```ruby
-gem 'isotree'
+gem "isotree"
 ```
 
 ## Getting Started
@@ -147,22 +147,22 @@ model.predict(data, output: "avg_depth")
 
 ## History
 
-View the [changelog](https://github.com/ankane/isotree/blob/master/CHANGELOG.md)
+View the [changelog](https://github.com/ankane/isotree-ruby/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/isotree/issues)
-- Fix bugs and [submit pull requests](https://github.com/ankane/isotree/pulls)
+- [Report bugs](https://github.com/ankane/isotree-ruby/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/isotree-ruby/pulls)
 - Write, clarify, or fix documentation
 - Suggest or add new features
 
 To get started with development:
 
 ```sh
-git clone --recursive https://github.com/ankane/isotree.git
-cd isotree
+git clone --recursive https://github.com/ankane/isotree-ruby.git
+cd isotree-ruby
 bundle install
 bundle exec rake compile
 bundle exec rake test

data/ext/isotree/ext.cpp

@@ -2,12 +2,7 @@
 #include <isotree.hpp>
 
 // rice
-#include <rice/Array.hpp>
-#include <rice/Hash.hpp>
-#include <rice/Module.hpp>
-#include <rice/Object.hpp>
-#include <rice/String.hpp>
-#include <rice/Symbol.hpp>
+#include <rice/rice.hpp>
 
 using Rice::Array;
 using Rice::Hash;
@@ -18,62 +13,89 @@ using Rice::Symbol;
 using Rice::define_class_under;
 using Rice::define_module;
 
-template<>
-NewCategAction from_ruby<NewCategAction>(Object x)
+namespace Rice::detail
 {
-  auto value = x.to_s().str();
-  if (value == "weighted") return Weighted;
-  if (value == "smallest") return Smallest;
-  if (value == "random") return Random;
-  throw std::runtime_error("Unknown new categ action: " + value);
-}
+  template<>
+  class From_Ruby<NewCategAction>
+  {
+  public:
+    NewCategAction convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "weighted") return Weighted;
+      if (value == "smallest") return Smallest;
+      if (value == "random") return Random;
+      throw std::runtime_error("Unknown new categ action: " + value);
+    }
+  };
 
-template<>
-MissingAction from_ruby<MissingAction>(Object x)
-{
-  auto value = x.to_s().str();
-  if (value == "divide") return Divide;
-  if (value == "impute") return Impute;
-  if (value == "fail") return Fail;
-  throw std::runtime_error("Unknown missing action: " + value);
-}
+  template<>
+  class From_Ruby<MissingAction>
+  {
+  public:
+    MissingAction convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "divide") return Divide;
+      if (value == "impute") return Impute;
+      if (value == "fail") return Fail;
+      throw std::runtime_error("Unknown missing action: " + value);
+    }
+  };
 
-template<>
-CategSplit from_ruby<CategSplit>(Object x)
-{
-  auto value = x.to_s().str();
-  if (value == "subset") return SubSet;
-  if (value == "single_categ") return SingleCateg;
-  throw std::runtime_error("Unknown categ split: " + value);
-}
+  template<>
+  class From_Ruby<CategSplit>
+  {
+  public:
+    CategSplit convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "subset") return SubSet;
+      if (value == "single_categ") return SingleCateg;
+      throw std::runtime_error("Unknown categ split: " + value);
+    }
+  };
 
-template<>
-CoefType from_ruby<CoefType>(Object x)
-{
-  auto value = x.to_s().str();
-  if (value == "uniform") return Uniform;
-  if (value == "normal") return Normal;
-  throw std::runtime_error("Unknown coef type: " + value);
-}
+  template<>
+  class From_Ruby<CoefType>
+  {
+  public:
+    CoefType convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "uniform") return Uniform;
+      if (value == "normal") return Normal;
+      throw std::runtime_error("Unknown coef type: " + value);
+    }
+  };
 
-template<>
-UseDepthImp from_ruby<UseDepthImp>(Object x)
-{
-  auto value = x.to_s().str();
-  if (value == "lower") return Lower;
-  if (value == "higher") return Higher;
-  if (value == "same") return Same;
-  throw std::runtime_error("Unknown depth imp: " + value);
-}
+  template<>
+  class From_Ruby<UseDepthImp>
+  {
+  public:
+    UseDepthImp convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "lower") return Lower;
+      if (value == "higher") return Higher;
+      if (value == "same") return Same;
+      throw std::runtime_error("Unknown depth imp: " + value);
+    }
+  };
 
-template<>
-WeighImpRows from_ruby<WeighImpRows>(Object x)
-{
-  auto value = x.to_s().str();
-  if (value == "inverse") return Inverse;
-  if (value == "prop") return Prop;
-  if (value == "flat") return Flat;
-  throw std::runtime_error("Unknown weight imp rows: " + value);
+  template<>
+  class From_Ruby<WeighImpRows>
+  {
+  public:
+    WeighImpRows convert(VALUE x)
+    {
+      auto value = Object(x).to_s().str();
+      if (value == "inverse") return Inverse;
+      if (value == "prop") return Prop;
+      if (value == "flat") return Flat;
+      throw std::runtime_error("Unknown weight imp rows: " + value);
+    }
+  };
 }
 
 extern "C"
@@ -85,9 +107,9 @@ void Init_ext()
   define_class_under<ExtIsoForest>(rb_mExt, "ExtIsoForest");
 
   rb_mExt
-    .define_singleton_method(
+    .define_singleton_function(
       "fit_iforest",
-      *[](Hash options) {
+      [](Hash options) {
         // model
         ExtIsoForest iso;
 
@@ -204,9 +226,9 @@ void Init_ext()
 
         return iso;
       })
-    .define_singleton_method(
+    .define_singleton_function(
       "predict_iforest",
-      *[](ExtIsoForest& iso, Hash options) {
+      [](ExtIsoForest& iso, Hash options) {
         // data
         size_t nrows = options.get<size_t, Symbol>("nrows");
         size_t ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
@@ -260,9 +282,9 @@ void Init_ext()
         }
         return ret;
       })
-    .define_singleton_method(
+    .define_singleton_function(
       "serialize_ext_isoforest",
-      *[](ExtIsoForest& iso, String path) {
+      [](ExtIsoForest& iso, String path) {
         #ifdef _MSC_VER
         // TODO convert to wchar_t
         throw std::runtime_error("Not supported on Windows yet");
@@ -270,9 +292,9 @@ void Init_ext()
         serialize_ext_isoforest(iso, path.c_str());
         #endif
       })
-    .define_singleton_method(
+    .define_singleton_function(
       "deserialize_ext_isoforest",
-      *[](String path) {
+      [](String path) {
         ExtIsoForest iso;
 
         #ifdef _MSC_VER

data/ext/isotree/extconf.rb

@@ -1,6 +1,6 @@
 require "mkmf-rice"
 
-$CXXFLAGS += " -std=c++11 -D_USE_MERSENNE_TWISTER -D_ENABLE_CEREAL"
+$CXXFLAGS += " -std=c++17 $(optflags) -D_USE_MERSENNE_TWISTER -D_ENABLE_CEREAL"
 
 apple_clang = RbConfig::CONFIG["CC_VERSION_MESSAGE"] =~ /apple clang/i
 

data/lib/isotree/dataset.rb

@@ -32,7 +32,6 @@ module IsoTree
           raise ArgumentError, "Array elements must be all hashes or arrays"
         end
 
-        nrows = data.size
         ncols = data.first ? data.first.size : 0
         if data.any? { |r| r.size != ncols }
           raise ArgumentError, "All rows must have the same number of columns"

data/lib/isotree/isolation_forest.rb

@@ -44,6 +44,10 @@ module IsoTree
       prep_fit(x)
       options = data_options(x).merge(fit_options)
       options[:sample_size] ||= options[:nrows]
+
+      # prevent segfault
+      options[:sample_size] = options[:nrows] if options[:sample_size] > options[:nrows]
+
       @ext_iso_forest = Ext.fit_iforest(options)
     end
 

data/lib/isotree/version.rb

@@ -1,3 +1,3 @@
 module IsoTree
-  VERSION = "0.1.5"
+  VERSION = "0.2.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: isotree
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.2.2
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-03-15 00:00:00.000000000 Z
+date: 2022-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '2.2'
+        version: 4.0.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '2.2'
+        version: 4.0.2
 description:
 email: andrew@ankane.org
 executables: []
@@ -149,7 +149,7 @@ files:
 - vendor/isotree/src/serialize.cpp
 - vendor/isotree/src/sql.cpp
 - vendor/isotree/src/utils.cpp
-homepage: https://github.com/ankane/isotree
+homepage: https://github.com/ankane/isotree-ruby
 licenses:
 - BSD-2-Clause
 metadata: {}
@@ -161,14 +161,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
 summary: Outlier/anomaly detection for Ruby using Isolation Forest