anomaly 0.1.0 → 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 301e930624aaaf4c39f66458571f05b9e09cd06015c7d2682444a93d0424f2a7
+  data.tar.gz: 38841ca328edf7405bf0ae7b631538485ca7e226416d03b6977591897847bb3c
+SHA512:
+  metadata.gz: 26ccb948b275b2a2787e1368abe909e7ef9f78793743cf14065b6be830861c1def870a49d862ba466995fbdea4a6a012479cc51fcc4c2f9ea99ff341ad4ecd87
+  data.tar.gz: a4bc731756ce68306d681433cc251af40e06cf1bd1ac21edd21ebfd7b8ef45ab05cffe3e557b2b731354bb377ade915f6e0e0f8b9b4fd945217bac3a278240c0

data/CHANGELOG.md

@@ -0,0 +1,9 @@
+# 0.2.0
+
+- Switched to Ruby `sum` for performance
+- Added support for Numo::NArray
+- Use keyword arguments
+
+# 0.1.0
+
+- Started changelog

data/README.md

@@ -2,31 +2,19 @@
 
 Easy-to-use anomaly detection
 
+[![Build Status](https://travis-ci.org/ankane/anomaly.svg?branch=master)](https://travis-ci.org/ankane/anomaly)
+
 ## Installation
 
-Add this line to your application's Gemfile:
+Add this line to your application’s Gemfile:
 
 ```ruby
 gem "anomaly"
 ```
 
-And then execute:
-
-```sh
-bundle install
-```
-
-For max performance (trains ~3x faster for large datasets), also install the NArray gem:
-
-```ruby
-gem "narray"
-```
-
-Anomaly will automatically detect it and use it.
-
-## How to Use
+## Getting Started
 
-Say we have weather data and we want to predict if it's sunny. In this example, sunny days are non-anomalies, and days with other types of weather (rain, snow, etc.) are anomalies. The data looks like:
+Say we have weather data and we want to predict if it’s sunny. In this example, sunny days are non-anomalies, and days with other types of weather (rain, snow, etc.) are anomalies. The data looks like:
 
 ```ruby
 # [temperature(°F), humidity(%), pressure(in), sunny?(y=0, n=1)]
@@ -44,54 +32,53 @@ The last column **must** be 0 for non-anomalies, 1 for anomalies. Non-anomalies
 To train the detector and test for anomalies, run:
 
 ```ruby
-ad = Anomaly::Detector.new(weather_data)
+detector = Anomaly::Detector.new(weather_data)
 
 # 85°F, 42% humidity, 12.3 in. pressure
-ad.anomaly?([85, 42, 12.3])
-# => true
+detector.anomaly?([85, 42, 12.3])
 ```
 
 Anomaly automatically finds the best value for ε, which you can access with:
 
 ```ruby
-ad.eps
+detector.eps
 ```
 
 If you already know you want ε = 0.01, initialize the detector with:
 
 ```ruby
-ad = Anomaly::Detector.new(weather_data, {:eps => 0.01})
+detector = Anomaly::Detector.new(weather_data, eps: 0.01)
 ```
 
-### Persistence
+## Persistence
 
-You can easily persist the detector to a file or database - it's very tiny.
+You can easily persist the detector to a file or database - it’s very tiny.
 
 ```ruby
-serialized_ad = Marshal.dump(ad)
-
-# Save to a file
-File.open("anomaly_detector.dump", "w") {|f| f.write(serialized_ad) }
+dump = Marshal.dump(detector)
+File.binwrite("detector.dump", dump)
+```
 
-# ...
+Then read it later:
 
-# Read it later
-ad2 = Marshal.load(File.open("anomaly_detector.dump", "r").read)
+```ruby
+dump = File.binread("detector.dump")
+detector = Marshal.load(dump)
 ```
 
-## TODO
+## Credits
+
+A special thanks to [Andrew Ng](http://www.ml-class.org).
 
-- Train in chunks (for very large datasets)
-- Multivariate normal distribution (possibly)
+## History
 
-## Contributing
+View the [changelog](https://github.com/ankane/anomaly/blob/master/CHANGELOG.md)
 
-1. Fork it
-2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Commit your changes (`git commit -am 'Added some feature'`)
-4. Push to the branch (`git push origin my-new-feature`)
-5. Create new Pull Request
+## Contributing
 
-## Thanks
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
 
-A special thanks to [Andrew Ng](http://www.ml-class.org).
+- [Report bugs](https://github.com/ankane/anomaly/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/anomaly/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features

data/lib/anomaly/detector.rb

@@ -1,13 +1,18 @@
 module Anomaly
   class Detector
+    attr_reader :mean, :std
     attr_accessor :eps
 
-    def initialize(examples = nil, opts = {})
+    def initialize(examples = nil, **opts)
       @m = 0
-      train(examples, opts) if examples
+      train(examples, **opts) if examples
     end
 
-    def train(examples, opts = {})
+    def train(examples, eps: 0)
+      # 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
 
@@ -24,7 +29,7 @@ module Anomaly
 
       raise "Must have at least one non-anomaly" if non_anomalies.empty?
 
-      @eps = (opts[:eps] || 0).to_f
+      @eps = eps
       if @eps > 0
         # Use all non-anomalies to train.
         training_examples = non_anomalies
@@ -33,28 +38,33 @@ module Anomaly
         test_examples.concat(anomalies)
       end
       # Remove last column.
-      training_examples = training_examples.map{|e| e[0..-2]}
+      training_examples = training_examples.map { |e| e[0..-2] }
       @m = training_examples.size
       @n = training_examples.first.size
 
-      if defined?(NMatrix)
+      if defined?(Numo::SFloat)
+        training_examples = Numo::SFloat.cast(training_examples)
+        # 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]}}
-        @mean = cols.map{|c| mean(c)}
-        @std = cols.each_with_index.map{|c,i| std(c, @mean[i])}
+        cols = @n.times.map { |i| training_examples.map { |r| r[i] } }
+        @mean = cols.map { |c| alt_mean(c) }
+        @std = cols.each_with_index.map { |c, i| alt_std(c, @mean[i]) }
       end
-      @std.map!{|std| (std == 0 or std.nan?) ? Float::MIN : std}
+      @std.map! { |std| (std == 0 || std.nan?) ? Float::MIN : std }
 
       if @eps == 0
         # Find the best eps.
-        epss = (1..9).map{|i| [1,3,5,7,9].map{|j| (j*10**(-i)).to_f }}.flatten
-        f1_scores = epss.map{|eps| [eps, compute_f1_score(test_examples, eps)] }
-        @eps, best_f1 = f1_scores.max_by{|v| v[1]}
+        epss = (1..9).map { |i| [1, 3, 5, 7, 9].map { |j| (j * 10**(-i)).to_f } }.flatten
+        f1_scores = epss.map { |eps| [eps, compute_f1_score(test_examples, eps)] }
+        @eps, _ = f1_scores.max_by { |v| v[1] }
       end
     end
 
@@ -69,7 +79,7 @@ module Anomaly
       raise ArgumentError, "First argument must have #{@n} elements" if x.size != @n
       @n.times.map do |i|
         p = normal_pdf(x[i], @mean[i], @std[i])
-        (p.nan? or p > 1) ? 1 : p
+        (p.nan? || p > 1) ? 1 : p
       end.reduce(1, :*)
     end
 
@@ -79,10 +89,10 @@ module Anomaly
 
     protected
 
-    SQRT2PI = Math.sqrt(2*Math::PI)
+    SQRT2PI = Math.sqrt(2 * Math::PI)
 
     def normal_pdf(x, mean = 0, std = 1)
-      1/(SQRT2PI*std)*Math.exp(-((x - mean)**2/(2.0*(std**2))))
+      1 / (SQRT2PI * std) * Math.exp(-((x - mean)**2 / (2.0 * (std**2))))
     end
 
     # Find best eps.
@@ -99,8 +109,8 @@ module Anomaly
       fn = 0
       examples.each do |example|
         act = example.last != 0
-        pred = self.anomaly?(example[0..-2], eps)
-        if act and pred
+        pred = anomaly?(example[0..-2], eps)
+        if act && pred
           tp += 1
         elsif pred # and !act
           fp += 1
@@ -120,13 +130,12 @@ module Anomaly
 
     # Not used for NArray
 
-    def mean(x)
-      x.inject(0.0){|a, i| a + i}/x.size
+    def alt_mean(x)
+      x.sum / x.size
     end
 
-    def std(x, mean)
-      Math.sqrt(x.inject(0.0){|a, i| a + (i - mean) ** 2}/(x.size - 1))
+    def alt_std(x, mean)
+      Math.sqrt(x.sum { |i| (i - mean)**2 }.to_f / (x.size - 1))
     end
-
   end
 end

data/lib/anomaly/version.rb

@@ -1,3 +1,3 @@
 module Anomaly
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,98 +1,117 @@
 --- !ruby/object:Gem::Specification
 name: anomaly
 version: !ruby/object:Gem::Version
-  version: 0.1.0
-  prerelease: 
+  version: 0.2.0
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-12-19 00:00:00.000000000Z
+date: 2019-10-28 00:00:00.000000000 Z
 dependencies:
+- !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: &2155813680 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2155813680
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2155813180 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: '2'
   type: :development
   prerelease: false
-  version_requirements: *2155813180
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2'
 - !ruby/object:Gem::Dependency
   name: narray
-  requirement: &2155812760 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2155812760
-description: Easy-to-use anomaly detection
-email:
-- andrew@getformidable.com
+  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
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .rspec
-- Gemfile
-- LICENSE
+- CHANGELOG.md
 - README.md
-- Rakefile
-- anomaly.gemspec
 - lib/anomaly.rb
 - lib/anomaly/detector.rb
 - lib/anomaly/version.rb
-- spec/anomaly/detector_spec.rb
-- spec/spec_helper.rb
 homepage: https://github.com/ankane/anomaly
-licenses: []
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
-      segments:
-      - 0
-      hash: 1886385059125072633
+      version: '2.4'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: 1886385059125072633
 requirements: []
-rubyforge_project: 
-rubygems_version: 1.8.11
+rubygems_version: 3.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Easy-to-use anomaly detection
-test_files:
-- spec/anomaly/detector_spec.rb
-- spec/spec_helper.rb
+test_files: []

data/.gitignore

@@ -1,17 +0,0 @@
-*.gem
-*.rbc
-.bundle
-.config
-.yardoc
-Gemfile.lock
-InstalledFiles
-_yardoc
-coverage
-doc/
-lib/bundler/man
-pkg
-rdoc
-spec/reports
-test/tmp
-test/version_tmp
-tmp

data/.rspec

@@ -1 +0,0 @@
---color

data/Gemfile

@@ -1,4 +0,0 @@
-source 'https://rubygems.org'
-
-# Specify your gem's dependencies in anomaly.gemspec
-gemspec

data/LICENSE

@@ -1,22 +0,0 @@
-Copyright (c) 2011 Andrew Kane
-
-MIT License
-
-Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
-LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
-OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
-WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Rakefile

@@ -1,25 +0,0 @@
-#!/usr/bin/env rake
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
-RSpec::Core::RakeTask.new("spec")
-
-require "benchmark"
-require "anomaly"
-
-task :benchmark do
-  examples = 1_000_000.times.map{ [rand, rand, rand, 0] }
-
-  Benchmark.bm do |x|
-    x.report { Anomaly::Detector.new(examples, {:eps => 0.5}) }
-    require "narray"
-    x.report { Anomaly::Detector.new(examples, {:eps => 0.5}) }
-  end
-end
-
-task :random_examples do
-  examples = 10_000.times.map{ [rand, rand(10), rand(100), 0] } +
-    100.times.map{ [rand + 1, rand(10) + 2, rand(100) + 20, 1] }
-
-  ad = Anomaly::Detector.new(examples)
-  puts ad.eps
-end

data/anomaly.gemspec

@@ -1,21 +0,0 @@
-# -*- encoding: utf-8 -*-
-require File.expand_path('../lib/anomaly/version', __FILE__)
-
-Gem::Specification.new do |gem|
-  gem.authors       = ["Andrew Kane"]
-  gem.email         = ["andrew@getformidable.com"]
-  gem.description   = %q{Easy-to-use anomaly detection}
-  gem.summary       = %q{Easy-to-use anomaly detection}
-  gem.homepage      = "https://github.com/ankane/anomaly"
-
-  gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
-  gem.files         = `git ls-files`.split("\n")
-  gem.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
-  gem.name          = "anomaly"
-  gem.require_paths = ["lib"]
-  gem.version       = Anomaly::VERSION
-
-  gem.add_development_dependency "rake"
-  gem.add_development_dependency "rspec", ">= 2.0.0"
-  gem.add_development_dependency "narray"
-end

data/spec/anomaly/detector_spec.rb

@@ -1,71 +0,0 @@
-require "spec_helper"
-
-describe Anomaly::Detector do
-  let(:examples) { [[-1,-2,0],[0,0,0],[1,2,0]] }
-  let(:ad) { Anomaly::Detector.new(examples) }
-
-  # mean = [0, 0], std = [1, 2]
-  it "computes the right probability" do
-    ad.probability([0,0]).should == 0.079577471545947667
-  end
-
-  it "marshalizes" do
-    expect{ Marshal.dump(ad) }.to_not raise_error
-  end
-
-  context "when standard deviation is 0" do
-    let(:examples) { [[0,0],[0,0]] }
-
-    it "returns infinity for mean" do
-      ad.probability([0]).should == 1
-    end
-
-    it "returns 0 for not mean" do
-      ad.probability([1]).should == 0
-    end
-  end
-
-  context "when examples is an array" do
-    let(:examples) { [[-1,-2,0],[0,0,0],[1,2,0]] }
-    let(:sample) { [rand, rand] }
-
-    it "returns the same probability as an NMatrix" do
-      prob = ad.probability(sample)
-      Object.send(:remove_const, :NMatrix)
-      prob.should == Anomaly::Detector.new(examples).probability(sample)
-    end
-  end
-
-  context "when lots of samples" do
-    let(:examples) { m.times.map{[0,0]} }
-    let(:m) { rand(100) + 1 }
-
-    it { ad.trained?.should be_true }
-  end
-
-  context "when no samples" do
-    let(:examples) { nil }
-
-    it { ad.trained?.should be_false }
-  end
-
-  context "when pdf is greater than 1" do
-    let(:examples) { 100.times.map{[0,0]}.push([1,0]) }
-
-    it { ad.probability([0]).should == 1 }
-  end
-
-  context "when only anomalies" do
-    let(:examples) { [[0,1]] }
-
-    it "raises error" do
-      expect{ ad }.to raise_error RuntimeError, "Must have at least one non-anomaly"
-    end
-  end
-
-  context "when only one non-anomaly" do
-    let(:examples) { [[0,0]] }
-
-    it { ad.eps.should == 1e-1 }
-  end
-end

data/spec/spec_helper.rb

@@ -1,8 +0,0 @@
-require "rubygems"
-require "bundler/setup"
-
-require "anomaly"
-require "narray"
-
-RSpec.configure do |config|
-end