anomaly 0.3.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7cf7957fa3d0c9ddf4fb5dbc59c6b153ae0122d6777dffc4b088156a34b44c04
-  data.tar.gz: a4130a661e44bf2363ef024c8e5296803cab479d9bc69cff7661a5d702feccb7
+  metadata.gz: 1159161d09e4681534d64580d0de094e0b6e9b9d393a60054e3201d69e668b37
+  data.tar.gz: 2332587591c8fec6cee8446e9c505e5c444d730643fbd8f4dab68e2df8218db1
 SHA512:
-  metadata.gz: 3c13a829fdc03e54b408b7bfc8ab0ea5ccb6b7092a12146ee092071ccf81e73da278b7910b0dd44d846b2a3619580567da5c2116968d0d73b4bd13d5df414c1c
-  data.tar.gz: e7b7aff28acbaf2c9c3a95d62ccf8c10829689896a98e32a5f85ce22114754d42eeb0e5ccf70bbf49a4fda850fadcb367747caabc41b944db5e82bfd7686f351
+  metadata.gz: d3250db6d40d85ee4f63e3563367e9da2b14a27e65bb2d50c5cad75784476b368ec135a6958efd21fa0c7d51c02136e317b5f634cd515c653cd16e9ff2033b70
+  data.tar.gz: 5c23dff5e507185e6ca904f88bcaf4e8091a650bcf404f4ced7350f2ad1645e4132249567485a76aac49b1a0b38a34c8d180fe363481ca5d1709d7316511a3ff

data/CHANGELOG.md

@@ -1,3 +1,15 @@
+## 0.5.0 (2026-04-01)
+
+- Added support for JSON serialization
+- Improved error classes
+- Removed `eps` option from `train` method (use initializer instead)
+- Dropped support for `nmatrix`
+- Dropped support for Ruby < 3.3
+
+## 0.4.0 (2024-10-23)
+
+- Dropped support for Ruby < 3.1
+
 ## 0.3.0 (2022-09-05)
 
 - Dropped support for `narray` (use `numo-narray` instead)
@@ -15,4 +27,16 @@
 
 ## 0.1.0 (2011-12-18)
 
-- Started changelog
+- Automatically find the best value for epsilon
+
+## 0.0.3 (2011-12-11)
+
+- Keep probabilities between 0 and 1
+
+## 0.0.2 (2011-12-11)
+
+- Handle very small standard deviations more gracefully
+
+## 0.0.1 (2011-12-11)
+
+- First release

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2011-2022 Andrew Kane
+Copyright (c) 2011-2026 Andrew Kane
 
 MIT License
 

data/README.md

@@ -2,7 +2,7 @@
 
 Easy-to-use anomaly detection for Ruby
 
-[![Build Status](https://github.com/ankane/anomaly/workflows/build/badge.svg?branch=master)](https://github.com/ankane/anomaly/actions)
+[![Build Status](https://github.com/ankane/anomaly/actions/workflows/build.yml/badge.svg)](https://github.com/ankane/anomaly/actions)
 
 ## Installation
 
@@ -59,15 +59,14 @@ detector = Anomaly::Detector.new(weather_data, eps: 0.01)
 You can easily persist the detector to a file or database - it’s very tiny.
 
 ```ruby
-bin = Marshal.dump(detector)
-File.binwrite("detector.bin", bin)
+File.write("detector.json", detector.to_json)
 ```
 
 Then read it later:
 
 ```ruby
-bin = File.binread("detector.bin")
-detector = Marshal.load(bin)
+json = File.read("detector.json")
+detector = Anomaly::Detector.load_json(json)
 ```
 
 ## Related Projects
@@ -77,6 +76,7 @@ detector = Marshal.load(bin)
 - [IsoTree](https://github.com/ankane/isotree-ruby) - Outlier/anomaly detection for Ruby using Isolation Forest
 - [OutlierTree](https://github.com/ankane/outliertree-ruby) - Explainable outlier/anomaly detection for Ruby
 - [MIDAS](https://github.com/ankane/midas-ruby) - Edge stream anomaly detection for Ruby
+- [Random Cut Forest](https://github.com/ankane/random-cut-forest-ruby) - Random Cut Forest anomaly detection for Ruby
 - [Trend](https://github.com/ankane/trend-ruby) - Anomaly detection and forecasting for Ruby
 
 ## Credits
@@ -102,5 +102,5 @@ To get started with development:
 git clone https://github.com/ankane/anomaly.git
 cd anomaly
 bundle install
-bundle exec rake spec
+bundle exec rake test
 ```

data/lib/anomaly/detector.rb

@@ -1,20 +1,20 @@
 module Anomaly
   class Detector
-    attr_reader :mean, :std
-    attr_accessor :eps
+    attr_reader :eps, :mean, :std
 
-    def initialize(examples = nil, **opts)
+    def initialize(examples = nil, eps: nil)
       @m = 0
-      train(examples, **opts) if examples
+      @eps = eps || 0
+      train(examples) if examples
     end
 
-    def train(examples, eps: 0)
+    def train(examples)
       # for Numo::NArray
       # TODO make more efficient when possible
       examples = examples.to_a
 
-      raise "No examples" if examples.empty?
-      raise "Must have at least two columns" if examples.first.size < 2
+      raise ArgumentError, "No examples" if examples.empty?
+      raise ArgumentError, "Must have at least two columns" if examples.first.size < 2
 
       # Divide into groups since we only want to train with non-anomalies.
       anomalies = []
@@ -27,9 +27,8 @@ module Anomaly
         end
       end
 
-      raise "Must have at least one non-anomaly" if non_anomalies.empty?
+      raise ArgumentError, "Must have at least one non-anomaly" if non_anomalies.empty?
 
-      @eps = eps
       if @eps > 0
         # Use all non-anomalies to train.
         training_examples = non_anomalies
@@ -47,11 +46,6 @@ module Anomaly
         # Convert these to an Array for Marshal.dump
         @mean = training_examples.mean(0).to_a
         @std = training_examples.stddev(0).to_a
-      elsif defined?(NMatrix)
-        training_examples = NMatrix.to_na(training_examples)
-        # Convert these to an Array for Marshal.dump
-        @mean = training_examples.mean(1).to_a
-        @std = training_examples.stddev(1).to_a
       else
         # Default to Array, since built-in Matrix does not give us a big performance advantage.
         cols = @n.times.map { |i| training_examples.map { |r| r[i] } }
@@ -76,7 +70,7 @@ module Anomaly
     # to keep probabilities at same scale.
     # Use log to prevent underflow
     def probability(x)
-      raise "Train me first" unless trained?
+      raise Error, "Train me first" unless trained?
 
       singular = !x.first.is_a?(Array)
       x = [x] if singular
@@ -106,8 +100,40 @@ module Anomaly
       end
     end
 
+    def to_json
+      require "json"
+
+      obj = {
+        m: @m,
+        n: @n,
+        eps: @eps,
+        mean: @mean,
+        std: @std
+      }
+
+      JSON.generate(obj)
+    end
+
+    def self.load_json(json)
+      require "json"
+
+      obj = JSON.parse(json)
+
+      detector = new
+      detector.send(:json_load, obj)
+      detector
+    end
+
     protected
 
+    def json_load(obj)
+      @m = obj["m"].to_i
+      @n = obj["n"].to_i
+      @eps = obj["eps"].to_f
+      @mean = obj["mean"].map(&:to_f)
+      @std = obj["std"].map(&:to_f)
+    end
+
     SQRT2PI = Math.sqrt(2 * Math::PI)
 
     def normal_pdf(x, mean = 0, std = 1)

data/lib/anomaly/version.rb

@@ -1,3 +1,3 @@
 module Anomaly
-  VERSION = "0.3.0"
+  VERSION = "0.5.0"
 end

data/lib/anomaly.rb

@@ -1,2 +1,7 @@
-require "anomaly/version"
-require "anomaly/detector"
+# modules
+require_relative "anomaly/detector"
+require_relative "anomaly/version"
+
+module Anomaly
+  class Error < StandardError; end
+end

metadata

@@ -1,16 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: anomaly
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Andrew Kane
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-09-05 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies: []
-description:
 email: andrew@ankane.org
 executables: []
 extensions: []
@@ -26,7 +24,6 @@ homepage: https://github.com/ankane/anomaly
 licenses:
 - MIT
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -34,15 +31,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
-signing_key:
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Easy-to-use anomaly detection for Ruby
 test_files: []