anomaly 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 301e930624aaaf4c39f66458571f05b9e09cd06015c7d2682444a93d0424f2a7
-  data.tar.gz: 38841ca328edf7405bf0ae7b631538485ca7e226416d03b6977591897847bb3c
+  metadata.gz: 25ddca87f47c228cbbd18c12951a42d739673989bc9d7ec462d22b6b77594e58
+  data.tar.gz: cf70dd6cb3b84a78875c1d0aafead1255f03cf222f00c3fa001b2cdffd5008c9
 SHA512:
-  metadata.gz: 26ccb948b275b2a2787e1368abe909e7ef9f78793743cf14065b6be830861c1def870a49d862ba466995fbdea4a6a012479cc51fcc4c2f9ea99ff341ad4ecd87
-  data.tar.gz: a4bc731756ce68306d681433cc251af40e06cf1bd1ac21edd21ebfd7b8ef45ab05cffe3e557b2b731354bb377ade915f6e0e0f8b9b4fd945217bac3a278240c0
+  metadata.gz: b3c2c7457ce5ad155ef78e13450777ebb44da4dd208ba85d232b67bccdd1c12563745d5764df36e9b4a78e0a28366da9061b4cd77c334d733e18c80c5d0a3ac7
+  data.tar.gz: 7b5c91f014e7861e52a7b5a28d7e9189f1c67b63e064c688e59d114bb0a6806aefc4b79d1494c72182b917eb337edb361d6573eb5926dc275fcccac825b2e86a

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+# 0.2.1 (2020-04-16)
+
+- Added support for multiple predictions
+
 # 0.2.0
 
 - Switched to Ruby `sum` for performance

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2011-2019 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/README.md

@@ -29,11 +29,15 @@ weather_data = [
 
 The last column **must** be 0 for non-anomalies, 1 for anomalies. Non-anomalies are used to train the detector, and both anomalies and non-anomalies are used to find the best value of ε.
 
-To train the detector and test for anomalies, run:
+Train the detector
 
 ```ruby
 detector = Anomaly::Detector.new(weather_data)
+```
+
+Test for anomalies
 
+```ruby
 # 85°F, 42% humidity, 12.3 in. pressure
 detector.anomaly?([85, 42, 12.3])
 ```
@@ -55,20 +59,20 @@ 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
-dump = Marshal.dump(detector)
-File.binwrite("detector.dump", dump)
+bin = Marshal.dump(detector)
+File.binwrite("detector.bin", bin)
 ```
 
 Then read it later:
 
 ```ruby
-dump = File.binread("detector.dump")
-detector = Marshal.load(dump)
+bin = File.binread("detector.bin")
+detector = Marshal.load(bin)
 ```
 
 ## Credits
 
-A special thanks to [Andrew Ng](http://www.ml-class.org).
+A special thanks to [Andrew Ng](https://www.coursera.org/learn/machine-learning).
 
 ## History
 
@@ -82,3 +86,12 @@ Everyone is encouraged to help improve this project. Here are a few ways you can
 - Fix bugs and [submit pull requests](https://github.com/ankane/anomaly/pulls)
 - Write, clarify, or fix documentation
 - Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/ankane/anomaly.git
+cd anomaly
+bundle install
+bundle exec rake spec
+```

data/lib/anomaly/detector.rb

@@ -58,7 +58,7 @@ module Anomaly
         @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 || std.nan?) ? Float::MIN : std }
+      @std.map! { |std| (std == 0 || std.nan?) ? 1e-10 : std }
 
       if @eps == 0
         # Find the best eps.
@@ -74,17 +74,36 @@ module Anomaly
 
     # Limit the probability of features to [0,1]
     # to keep probabilities at same scale.
+    # Use log to prevent underflow
     def probability(x)
       raise "Train me first" unless trained?
-      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? || p > 1) ? 1 : p
-      end.reduce(1, :*)
+
+      singular = !x.first.is_a?(Array)
+      x = [x] if singular
+
+      y =
+        x.map do |xi|
+          prob = 0
+          @n.times.map do |i|
+            pi = normal_pdf(xi[i], @mean[i], @std[i])
+            prob += Math.log(pi > 1 ? 1 : pi)
+          end
+          Math.exp(prob)
+        end
+
+      singular ? y.first : y
     end
 
     def anomaly?(x, eps = @eps)
-      probability(x) < eps
+      y = probability(x)
+
+      if y.is_a?(Array)
+        y.map do |yi|
+          yi < eps
+        end
+      else
+        y < eps
+      end
     end
 
     protected

data/lib/anomaly/version.rb

@@ -1,3 +1,3 @@
 module Anomaly
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: anomaly
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-10-28 00:00:00.000000000 Z
+date: 2020-04-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -87,6 +87,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - CHANGELOG.md
+- LICENSE.txt
 - README.md
 - lib/anomaly.rb
 - lib/anomaly/detector.rb
@@ -110,7 +111,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Easy-to-use anomaly detection