isotree 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 596a94951a4e195e6163d33726cecf07ae2e2b83c22558b0c9f3dbb35ddf4e8c
-  data.tar.gz: 2180cd020fa613142c140b67b4bdce30a929c327e93bff7c60364e6bfd171e16
+  metadata.gz: fc614bbd4c6751f60bb22751881a739965950eb4bc8fe225521d6d0caa67e0c1
+  data.tar.gz: ef7305b765fc240173173f9926057bef019347a2769f3f91cafd048c9493957b
 SHA512:
-  metadata.gz: 44c74b863d7d65cee9f15a8f051f31757004fc304760a8ea3acef1f15fbe3ea90dc986cf75a32389fbd9f4a17f974928ee388fb1d77a89bfe68a0d56ad8a6f8b
-  data.tar.gz: 93136839736e65d7f0cc8d7b23e57f85528d5f356ec94ef4fb58848dd4fe7e2aca49bc70ec9b88202ef2fce47c5f65322939187907e975dca066ec3b5371d65b
+  metadata.gz: 641b9f59f1ec699dfdcbc19f882173306f677156ddfd9f8f6b49754c4fc703ef1d873ec30db152a5a252937f01b9a233d849645406346bed780e2f87ba827763
+  data.tar.gz: 8be8a5643ecd5dfde93aef878d643e3e47cf84943062137c66dbb27c7fd1501a3df746520764b420568bc6e8d162cbd8f3b8d37a94aa8f2e64292a35d5a8e6fa

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.5.0 (2026-04-07)
+
+- Dropped support for Ruby < 3.3
+
+## 0.4.1 (2025-10-26)
+
+- Fixed error with Rice 4.7
+
 ## 0.4.0 (2024-06-11)
 
 - Updated IsoTree to 0.6.1

data/LICENSE.txt

@@ -1,7 +1,7 @@
 BSD 2-Clause License
 
 Copyright (c) 2019-2023, David Cortes
-Copyright (c) 2020-2023, Andrew Kane
+Copyright (c) 2020-2026, Andrew Kane
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -157,12 +157,6 @@ Get the average isolation depth
 model.predict(data, output: "avg_depth")
 ```
 
-## Upgrading
-
-### 0.3.0
-
-This version uses IsoTree’s new serialization format. Exported models must be recreated.
-
 ## History
 
 View the [changelog](https://github.com/ankane/isotree-ruby/blob/master/CHANGELOG.md)

data/ext/isotree/ext.cpp

@@ -1,7 +1,13 @@
 // stdlib
 #include <cmath>
+#include <cstddef>
+#include <cstdint>
 #include <fstream>
 #include <iostream>
+#include <stdexcept>
+#include <string>
+#include <string_view>
+#include <vector>
 
 // isotree
 #include <isotree.hpp>
@@ -11,21 +17,15 @@
 
 using Rice::Array;
 using Rice::Hash;
-using Rice::Module;
 using Rice::Object;
 using Rice::String;
 using Rice::Symbol;
-using Rice::define_class_under;
-using Rice::define_module;
 
-namespace Rice::detail
-{
+namespace Rice::detail {
   template<>
-  class From_Ruby<NewCategAction>
-  {
+  class From_Ruby<NewCategAction> {
   public:
-    NewCategAction convert(VALUE x)
-    {
+    NewCategAction convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "weighted" || value == "impute") return Weighted;
       if (value == "smallest") return Smallest;
@@ -35,11 +35,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<MissingAction>
-  {
+  class From_Ruby<MissingAction> {
   public:
-    MissingAction convert(VALUE x)
-    {
+    MissingAction convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "divide") return Divide;
       if (value == "impute") return Impute;
@@ -49,11 +47,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<CategSplit>
-  {
+  class From_Ruby<CategSplit> {
   public:
-    CategSplit convert(VALUE x)
-    {
+    CategSplit convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "subset") return SubSet;
       if (value == "single_categ") return SingleCateg;
@@ -62,11 +58,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<CoefType>
-  {
+  class From_Ruby<CoefType> {
   public:
-    CoefType convert(VALUE x)
-    {
+    CoefType convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "uniform") return Uniform;
       if (value == "normal") return Normal;
@@ -75,11 +69,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<UseDepthImp>
-  {
+  class From_Ruby<UseDepthImp> {
   public:
-    UseDepthImp convert(VALUE x)
-    {
+    UseDepthImp convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "lower") return Lower;
       if (value == "higher") return Higher;
@@ -89,11 +81,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<WeighImpRows>
-  {
+  class From_Ruby<WeighImpRows> {
   public:
-    WeighImpRows convert(VALUE x)
-    {
+    WeighImpRows convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "inverse") return Inverse;
       if (value == "prop") return Prop;
@@ -103,11 +93,9 @@ namespace Rice::detail
   };
 
   template<>
-  class From_Ruby<ScoringMetric>
-  {
+  class From_Ruby<ScoringMetric> {
   public:
-    ScoringMetric convert(VALUE x)
-    {
+    ScoringMetric convert(VALUE x) {
       auto value = Object(x).to_s().str();
       if (value == "depth") return Depth;
       if (value == "adj_depth") return AdjDepth;
@@ -119,15 +107,14 @@ namespace Rice::detail
       throw std::runtime_error("Unknown scoring metric: " + value);
     }
   };
-}
+} // namespace Rice::detail
 
 extern "C"
-void Init_ext()
-{
-  Module rb_mIsoTree = define_module("IsoTree");
+void Init_ext() {
+  Rice::Module rb_mIsoTree = Rice::define_module("IsoTree");
 
-  Module rb_mExt = define_module_under(rb_mIsoTree, "Ext");
-  define_class_under<ExtIsoForest>(rb_mExt, "ExtIsoForest");
+  Rice::Module rb_mExt = Rice::define_module_under(rb_mIsoTree, "Ext");
+  Rice::define_class_under<ExtIsoForest>(rb_mExt, "ExtIsoForest");
 
   rb_mExt
     .define_singleton_function(
@@ -137,77 +124,77 @@ void Init_ext()
         ExtIsoForest iso;
 
         // data
-        size_t nrows = options.get<size_t, Symbol>("nrows");
-        size_t ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
-        size_t ncols_categ = options.get<size_t, Symbol>("ncols_categ");
+        auto nrows = options.get<size_t, Symbol>("nrows");
+        auto ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
+        auto ncols_categ = options.get<size_t, Symbol>("ncols_categ");
 
-        real_t* numeric_data = NULL;
+        real_t* numeric_data = nullptr;
         if (ncols_numeric > 0) {
-          numeric_data = (double*) options.get<String, Symbol>("numeric_data").c_str();
+          numeric_data = reinterpret_cast<real_t*>(const_cast<char*>(options.get<String, Symbol>("numeric_data").c_str()));
         }
 
-        int* categorical_data = NULL;
-        int* ncat = NULL;
+        int* categorical_data = nullptr;
+        int* ncat = nullptr;
         if (ncols_categ > 0) {
-          categorical_data = (int*) options.get<String, Symbol>("categorical_data").c_str();
-          ncat = (int*) options.get<String, Symbol>("ncat").c_str();
+          categorical_data = reinterpret_cast<int*>(const_cast<char*>(options.get<String, Symbol>("categorical_data").c_str()));
+          ncat = reinterpret_cast<int*>(const_cast<char*>(options.get<String, Symbol>("ncat").c_str()));
         }
 
         // not used (sparse matrices)
-        real_t* Xc = NULL;
-        sparse_ix* Xc_ind = NULL;
-        sparse_ix* Xc_indptr = NULL;
+        real_t* Xc = nullptr;
+        sparse_ix* Xc_ind = nullptr;
+        sparse_ix* Xc_indptr = nullptr;
 
         // options
         // Rice has limit of 14 arguments, so use hash
-        size_t sample_size = options.get<size_t, Symbol>("sample_size");
-        size_t ndim = options.get<size_t, Symbol>("ndim");
-        size_t ntrees = options.get<size_t, Symbol>("ntrees");
-        size_t ntry = options.get<size_t, Symbol>("ntry");
-        double prob_pick_by_gain_avg = options.get<double, Symbol>("prob_pick_avg_gain");
-        double prob_pick_by_gain_pl = options.get<double, Symbol>("prob_pick_pooled_gain");
-        double min_gain = options.get<double, Symbol>("min_gain");
-        MissingAction missing_action = options.get<MissingAction, Symbol>("missing_action");
-        CategSplit cat_split_type = options.get<CategSplit, Symbol>("categ_split_type");
-        NewCategAction new_cat_action = options.get<NewCategAction, Symbol>("new_categ_action");
-        bool all_perm = options.get<bool, Symbol>("all_perm");
-        bool coef_by_prop = options.get<bool, Symbol>("coef_by_prop");
-        bool with_replacement = options.get<bool, Symbol>("sample_with_replacement");
-        bool penalize_range = options.get<bool, Symbol>("penalize_range");
-        bool weigh_by_kurt = options.get<bool, Symbol>("weigh_by_kurtosis");
-        CoefType coef_type = options.get<CoefType, Symbol>("coefs");
-        size_t min_imp_obs = options.get<size_t, Symbol>("min_imp_obs");
-        UseDepthImp depth_imp = options.get<UseDepthImp, Symbol>("depth_imp");
-        WeighImpRows weigh_imp_rows = options.get<WeighImpRows, Symbol>("weigh_imp_rows");
-        uint64_t random_seed = options.get<uint64_t, Symbol>("random_seed");
-        bool use_long_double = options.get<bool, Symbol>("use_long_double");
-        int nthreads = options.get<int, Symbol>("nthreads");
+        auto sample_size = options.get<size_t, Symbol>("sample_size");
+        auto ndim = options.get<size_t, Symbol>("ndim");
+        auto ntrees = options.get<size_t, Symbol>("ntrees");
+        auto ntry = options.get<size_t, Symbol>("ntry");
+        auto prob_pick_by_gain_avg = options.get<double, Symbol>("prob_pick_avg_gain");
+        auto prob_pick_by_gain_pl = options.get<double, Symbol>("prob_pick_pooled_gain");
+        auto min_gain = options.get<double, Symbol>("min_gain");
+        auto missing_action = options.get<MissingAction, Symbol>("missing_action");
+        auto cat_split_type = options.get<CategSplit, Symbol>("categ_split_type");
+        auto new_cat_action = options.get<NewCategAction, Symbol>("new_categ_action");
+        auto all_perm = options.get<bool, Symbol>("all_perm");
+        auto coef_by_prop = options.get<bool, Symbol>("coef_by_prop");
+        auto with_replacement = options.get<bool, Symbol>("sample_with_replacement");
+        auto penalize_range = options.get<bool, Symbol>("penalize_range");
+        auto weigh_by_kurt = options.get<bool, Symbol>("weigh_by_kurtosis");
+        auto coef_type = options.get<CoefType, Symbol>("coefs");
+        auto min_imp_obs = options.get<size_t, Symbol>("min_imp_obs");
+        auto depth_imp = options.get<UseDepthImp, Symbol>("depth_imp");
+        auto weigh_imp_rows = options.get<WeighImpRows, Symbol>("weigh_imp_rows");
+        auto random_seed = options.get<uint64_t, Symbol>("random_seed");
+        auto use_long_double = options.get<bool, Symbol>("use_long_double");
+        auto nthreads = options.get<int, Symbol>("nthreads");
 
         // TODO options
-        double* sample_weights = NULL;
-        bool weight_as_sample = options.get<bool, Symbol>("weights_as_sample_prob");
-        size_t max_depth = options.get<size_t, Symbol>("max_depth");
-        bool limit_depth = options.get<bool, Symbol>("limit_depth");
+        double* sample_weights = nullptr;
+        auto weight_as_sample = options.get<bool, Symbol>("weights_as_sample_prob");
+        auto max_depth = options.get<size_t, Symbol>("max_depth");
+        auto limit_depth = options.get<bool, Symbol>("limit_depth");
         bool standardize_dist = false;
-        double* tmat = NULL;
-        double* output_depths = NULL;
+        double* tmat = nullptr;
+        double* output_depths = nullptr;
         bool standardize_depth = false;
-        real_t* col_weights = NULL;
-        Imputer* imputer = NULL;
+        real_t* col_weights = nullptr;
+        Imputer* imputer = nullptr;
         bool impute_at_fit = false;
 
-        int ncols_per_tree = options.get<int, Symbol>("ncols_per_tree");
-        bool standardize_data = options.get<bool, Symbol>("standardize_data");
-        ScoringMetric scoring_metric = options.get<ScoringMetric, Symbol>("scoring_metric");
-        bool fast_bratio = options.get<bool, Symbol>("fast_bratio");
-        double prob_pick_by_full_gain = options.get<double, Symbol>("prob_pick_full_gain");
-        double prob_pick_by_dens = options.get<double, Symbol>("prob_pick_dens");
-        double prob_pick_col_by_range = options.get<double, Symbol>("prob_pick_col_by_range");
-        double prob_pick_col_by_var = options.get<double, Symbol>("prob_pick_col_by_var");
-        double prob_pick_col_by_kurt = options.get<double, Symbol>("prob_pick_col_by_kurt");
+        auto ncols_per_tree = options.get<int, Symbol>("ncols_per_tree");
+        auto standardize_data = options.get<bool, Symbol>("standardize_data");
+        auto scoring_metric = options.get<ScoringMetric, Symbol>("scoring_metric");
+        auto fast_bratio = options.get<bool, Symbol>("fast_bratio");
+        auto prob_pick_by_full_gain = options.get<double, Symbol>("prob_pick_full_gain");
+        auto prob_pick_by_dens = options.get<double, Symbol>("prob_pick_dens");
+        auto prob_pick_col_by_range = options.get<double, Symbol>("prob_pick_col_by_range");
+        auto prob_pick_col_by_var = options.get<double, Symbol>("prob_pick_col_by_var");
+        auto prob_pick_col_by_kurt = options.get<double, Symbol>("prob_pick_col_by_kurt");
 
         fit_iforest(
-          NULL,
+          nullptr,
           &iso,
           numeric_data,
           ncols_numeric,
@@ -268,37 +255,37 @@ void Init_ext()
       "predict_iforest",
       [](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");
-        size_t ncols_categ = options.get<size_t, Symbol>("ncols_categ");
+        auto nrows = options.get<size_t, Symbol>("nrows");
+        auto ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
+        auto ncols_categ = options.get<size_t, Symbol>("ncols_categ");
 
-        real_t* numeric_data = NULL;
+        real_t* numeric_data = nullptr;
         if (ncols_numeric > 0) {
-          numeric_data = (double*) options.get<String, Symbol>("numeric_data").c_str();
+          numeric_data = reinterpret_cast<real_t*>(const_cast<char*>(options.get<String, Symbol>("numeric_data").c_str()));
         }
 
-        int* categorical_data = NULL;
+        int* categorical_data = nullptr;
         if (ncols_categ > 0) {
-          categorical_data = (int*) options.get<String, Symbol>("categorical_data").c_str();
+          categorical_data = reinterpret_cast<int*>(const_cast<char*>(options.get<String, Symbol>("categorical_data").c_str()));
         }
 
         // not used (sparse matrices)
-        real_t* Xc = NULL;
-        sparse_ix* Xc_ind = NULL;
-        sparse_ix* Xc_indptr = NULL;
-        real_t* Xr = NULL;
-        sparse_ix* Xr_ind = NULL;
-        sparse_ix* Xr_indptr = NULL;
+        real_t* Xc = nullptr;
+        sparse_ix* Xc_ind = nullptr;
+        sparse_ix* Xc_indptr = nullptr;
+        real_t* Xr = nullptr;
+        sparse_ix* Xr_ind = nullptr;
+        sparse_ix* Xr_indptr = nullptr;
 
         // options
-        int nthreads = options.get<int, Symbol>("nthreads");
-        bool standardize = options.get<bool, Symbol>("standardize");
+        auto nthreads = options.get<int, Symbol>("nthreads");
+        auto standardize = options.get<bool, Symbol>("standardize");
         std::vector<double> outlier_scores(nrows);
-        sparse_ix* tree_num = NULL;
+        sparse_ix* tree_num = nullptr;
         bool is_col_major = true;
         size_t ld_numeric = 0;
         size_t ld_categ = 0;
-        double* per_tree_depths = NULL;
+        double* per_tree_depths = nullptr;
 
         predict_iforest(
           numeric_data,
@@ -315,49 +302,49 @@ void Init_ext()
           nrows,
           nthreads,
           standardize,
-          NULL,
+          nullptr,
           &iso,
           outlier_scores.data(),
           tree_num,
           per_tree_depths,
-          NULL
+          nullptr
         );
 
         Array ret;
-        for (size_t i = 0; i < outlier_scores.size(); i++) {
-          ret.push(outlier_scores[i]);
+        for (auto v : outlier_scores) {
+          ret.push(v, false);
         }
         return ret;
       })
     .define_singleton_function(
       "serialize_combined",
       [](ExtIsoForest& iso, String path, String metadata) {
-        #ifdef _MSC_VER
+#ifdef _MSC_VER
         // TODO convert to wchar_t
         throw std::runtime_error("Not supported on Windows yet");
-        #else
+#else
         std::ofstream file;
         file.open(path.c_str());
         serialize_combined(
-          NULL,
+          nullptr,
           &iso,
-          NULL,
-          NULL,
+          nullptr,
+          nullptr,
           metadata.c_str(),
           // returns bytesize (RSTRING_LEN)
           metadata.length(),
           file
         );
         file.close();
-        #endif
+#endif
       })
     .define_singleton_function(
       "deserialize_combined",
       [](String path) {
-        #ifdef _MSC_VER
+#ifdef _MSC_VER
         // TODO convert to wchar_t
         throw std::runtime_error("Not supported on Windows yet");
-        #else
+#else
         Array ret;
 
         std::ifstream file;
@@ -403,20 +390,15 @@ void Init_ext()
         ExtIsoForest model_ext = ExtIsoForest();
         Imputer imputer = Imputer();
         TreesIndexer indexer = TreesIndexer();
-        char *optional_metadata = (char*) calloc(size_metadata, sizeof(char));
-        if (optional_metadata == NULL) {
-          throw std::runtime_error("Cannot allocate memory");
-        }
+        std::vector<char> optional_metadata(size_metadata, 0);
 
-        deserialize_combined(file, &model, &model_ext, &imputer, &indexer, optional_metadata);
+        deserialize_combined(file, &model, &model_ext, &imputer, &indexer, optional_metadata.data());
         file.close();
 
-        ret.push(Object(Rice::detail::To_Ruby<ExtIsoForest>().convert(model_ext)));
-        ret.push(String(std::string(optional_metadata, size_metadata)));
-
-        free(optional_metadata);
+        ret.push(Object(Rice::detail::To_Ruby<ExtIsoForest>().convert(model_ext)), false);
+        ret.push(String(std::string_view{optional_metadata.data(), optional_metadata.size()}), false);
 
         return ret;
-        #endif
+#endif
       });
 }

data/lib/isotree/isolation_forest.rb

@@ -1,24 +1,44 @@
 module IsoTree
   class IsolationForest
     def initialize(
-      sample_size: "auto", ntrees: 500, ndim: 3, ntry: 1,
+      sample_size: "auto",
+      ntrees: 500,
+      ndim: 3,
+      ntry: 1,
       # categ_cols: nil,
-      max_depth: "auto", ncols_per_tree: nil,
-      prob_pick_pooled_gain: 0.0, prob_pick_avg_gain: 0.0,
-      prob_pick_full_gain: 0.0, prob_pick_dens: 0.0,
-      prob_pick_col_by_range: 0.0, prob_pick_col_by_var: 0.0, prob_pick_col_by_kurt: 0.0,
-      min_gain: 0.0, missing_action: "auto", new_categ_action: "auto",
-      categ_split_type: "auto", all_perm: false, coef_by_prop: false,
+      max_depth: "auto",
+      ncols_per_tree: nil,
+      prob_pick_pooled_gain: 0.0,
+      prob_pick_avg_gain: 0.0,
+      prob_pick_full_gain: 0.0,
+      prob_pick_dens: 0.0,
+      prob_pick_col_by_range: 0.0,
+      prob_pick_col_by_var: 0.0,
+      prob_pick_col_by_kurt: 0.0,
+      min_gain: 0.0,
+      missing_action: "auto",
+      new_categ_action: "auto",
+      categ_split_type: "auto",
+      all_perm: false,
+      coef_by_prop: false,
       # recode_categ: false,
       weights_as_sample_prob: true,
-      sample_with_replacement: false, penalize_range: false, standardize_data: true,
-      scoring_metric: "depth", fast_bratio: true,
-      weigh_by_kurtosis: false, coefs: "uniform", assume_full_distr: true,
+      sample_with_replacement: false,
+      penalize_range: false,
+      standardize_data: true,
+      scoring_metric: "depth",
+      fast_bratio: true,
+      weigh_by_kurtosis: false,
+      coefs: "uniform",
+      assume_full_distr: true,
       # build_imputer: false,
-      min_imp_obs: 3, depth_imp: "higher",
-      weigh_imp_rows: "inverse", random_seed: 1, use_long_double: false, nthreads: -1
+      min_imp_obs: 3,
+      depth_imp: "higher",
+      weigh_imp_rows: "inverse",
+      random_seed: 1,
+      use_long_double: false,
+      nthreads: -1
     )
-
       @sample_size = sample_size
       @ntrees = ntrees
       @ndim = ndim

data/lib/isotree/version.rb

@@ -1,3 +1,3 @@
 module IsoTree
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: isotree
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Andrew Kane
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-12 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice
@@ -16,15 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4.3'
+        version: '4.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4.3'
-description:
+        version: '4.7'
 email: andrew@ankane.org
 executables: []
 extensions:
@@ -88,7 +86,6 @@ homepage: https://github.com/ankane/isotree-ruby
 licenses:
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -96,15 +93,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.1'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.9
-signing_key:
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Outlier/anomaly detection for Ruby using Isolation Forest
 test_files: []