bayesnet 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9501e7b169bda69caf717e26a63ba141fbfcb413607f8888cd62a66eaf3ab78c
-  data.tar.gz: 4ca8a547e3f71d4b5690a73ae4430700a7115f97bbee974974da094701e192b3
+  metadata.gz: 9a746d994d25c279f3246613b9a918fb84720c7c9c78f85ce1ffdc5fbd6bcf9c
+  data.tar.gz: 3b8ee59eab90bf75172239601ddef479926f5a27db475688f1191c71298ca757
 SHA512:
-  metadata.gz: 11c61de5da370ee1a5b75014c1d74644d8b38cb45a5daa81e2292efac233beaf35ee85059074b09296d7d3ce842e67353921fbcf54f92109c5ace3b09459159a
-  data.tar.gz: 9abb2ee0bcd8661546b6ca3e27f9a3d3f96a2679c5b6b60e06ea7e26b759542f043f39a8fa7dc1de8270032b9485fc531b23a0895ca2001119a357de13797216
+  metadata.gz: 72985a24e9d529b04e8d275a46cc6eadbd55aa4380f2aed73a41d2e3c3c7e7528419aa99fa0004d4d3aab1692484021c3b577e1f9262ee9ef4d89664523d8335
+  data.tar.gz: 8be39618f74ccd85750569a74e18a0a384aa3a12c4c52a35315958d8d4ad4045abbe8bee83d510459e3fd6b29de68bab4120e3540cee0cadc9a024f1b2389ffb

data/.ruby-version

@@ -1 +1 @@
-3.0.3
+3.1.0

data/CHANGELOG.md

@@ -1,5 +1,20 @@
 ## [Unreleased]
 
-## [0.1.0] - 2021-12-18
+## [0.5.0] - 2022-02-26
+
+- Constructing networks out of the `.BIF` ([Interchange Format for Bayesian Networks](https://www.cs.washington.edu/dm/vfml/appendixes/bif.htm)) files.
+- Fixing inference bug
+- Network children nodes could be specified ***before** their parents
+
+## [0.0.3] - 2021-12-29
+
+- Fixing terminoloty used in Factor class
+
+## [0.0.2] - 2021-12-28
+
+- README, CI/CD for Ruby 2.6, 2.7, 3.1 added
+
+## [0.0.1] - 2021-12-28
 
 - Initial release
+

data/Gemfile

@@ -6,10 +6,10 @@ source "https://rubygems.org"
 gemspec
 
 gem "rake", "~> 13.0"
+gem "treetop", "~> 1.6"
 
 group :development, :test do
   gem "m", "~> 1.5.0"
   gem "minitest", "~> 5.0"
   gem "pry-byebug", "~> 3.9.0"
-  gem "standard", "~> 1.3"
 end

data/Gemfile.lock

@@ -1,12 +1,11 @@
 PATH
   remote: .
   specs:
-    bayesnet (0.0.1)
+    bayesnet (0.1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    ast (2.4.2)
     byebug (11.1.3)
     coderay (1.1.3)
     m (1.5.1)
@@ -14,38 +13,16 @@ GEM
       rake (>= 0.9.2.2)
     method_source (1.0.0)
     minitest (5.15.0)
-    parallel (1.21.0)
-    parser (3.0.3.2)
-      ast (~> 2.4.1)
+    polyglot (0.3.5)
     pry (0.13.1)
       coderay (~> 1.1)
       method_source (~> 1.0)
     pry-byebug (3.9.0)
       byebug (~> 11.0)
       pry (~> 0.13.0)
-    rainbow (3.0.0)
     rake (13.0.6)
-    regexp_parser (2.2.0)
-    rexml (3.2.5)
-    rubocop (1.23.0)
-      parallel (~> 1.10)
-      parser (>= 3.0.0.0)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.12.0, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.15.0)
-      parser (>= 3.0.1.1)
-    rubocop-performance (1.12.0)
-      rubocop (>= 1.7.0, < 2.0)
-      rubocop-ast (>= 0.4.0)
-    ruby-progressbar (1.11.0)
-    standard (1.5.0)
-      rubocop (= 1.23.0)
-      rubocop-performance (= 1.12.0)
-    unicode-display_width (2.1.0)
+    treetop (1.6.11)
+      polyglot (~> 0.3)
 
 PLATFORMS
   x86_64-darwin-19
@@ -57,7 +34,7 @@ DEPENDENCIES
   minitest (~> 5.0)
   pry-byebug (~> 3.9.0)
   rake (~> 13.0)
-  standard (~> 1.3)
+  treetop (~> 1.6)
 
 BUNDLED WITH
-   2.2.32
+   2.3.3

data/README.md

@@ -1,15 +1,80 @@
 # Bayesnet
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/bayesnet`. To experiment with that code, run `bin/console` for an interactive prompt.
+This gem provides an DSL for constructing Bayesian networks and let to execute basic inference queries. It is also capable of parsing .BIF format ([The Interchange Format for Bayesian Networks](https://www.cs.washington.edu/dm/vfml/appendixes/bif.htm)).
 
-TODO: Delete this and the text above, and describe your gem
+
+### Example:
+
+Someone has decided to study how some sleep hours followed by a cup of coffee are affecting a morning mood. 
+Here is the graphical model:
+
+![model](./doc/morning-mood-model.png "Morning Mood Model")
+
+`Sleep hours` could have values `:six, :seven, :eight`. `Mood` could be `:bad, :moderate, :good` and variable 
+`Coffee` could take values `:yes, :no`. Here is how accumulated statistics could be compiled in a Bayesian network and then defined in the code:
+
+```
+net = Bayesnet.define do
+      node :coffee do
+        values yes: 0.7, no: 0.3
+      end
+
+      node :sleep_hours do
+        values six: 0.1, seven: 0.3, eight: 0.6
+      end
+
+      node :mood, parents: [:coffee, :sleep_hours] do
+        values [:good, :moderate, :bad] do
+          distributions do
+            as [0.8, 0.1, 0.1], given: [:yes, :eight]
+            as [0.6, 0.2, 0.2], given: [:yes, :seven]
+            as [0.4, 0.4, 0.2], given: [:yes, :six]
+            as [0.7, 0.2, 0.1], given: [:no, :eight]
+            as [0.5, 0.3, 0.2], given: [:no, :seven]
+            as [0.3, 0.4, 0.3], given: [:no, :six]
+          end
+        end
+      end
+    end
+```
+
+Above, must be read as:
+someone could be observed having morning coffee in 70% of all cases and when that person has a morning coffee after sleeping 8 hours, chances to find her in
+  - `:good` mood - 80%
+  - `:moderate` mood - 10%
+  - `:bad` mood - 10%
+  
+i.e. `[0.8, 0.1, 0.1]` is a conditional distribution.
+
+Given the model above the following queries could be executed:
+
+#### Given sleep time is six hours and mood is good, what chances cup of coffee has been consumed?
+```
+net.chances({coffee: :yes}, evidence: {mood: :good, sleep_hours: :six}) # 0.757
+```
+
+#### Given sleep time is six hours and mood is good, what is the most likely value for a `:coffee` variable?
+```
+net.most_likely_value(:coffee, evidence: {mood: :good, sleep_hours: :six}) # :yes
+```
+
+#### A broader question than the two above: Given sleep time is six hours and mood is good, what is the distribution for a `:coffee` variable?
+```
+net.distribution(over: [:coffee], evidence: {mood: :good, sleep_hours: :six}) # [:yes, 0.757], [:no, 0.243]
+```
+
+The inference is based on summing over joint distribution, i.e. it is the simplest and
+most expensive way to calculate it. No optimization is implemented in this version; the code
+is more a proof of API.
+
+### [Another example](https://afurmanov.com/reducing-anxiety-with-bayesian-network) of using this gem
 
 ## Installation
 
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'bayesnet'
+em 'bayesnet'
 ```
 
 And then execute:
@@ -20,9 +85,6 @@ Or install it yourself as:
 
     $ gem install bayesnet
 
-## Usage
-
-TODO: Write usage instructions here
 
 ## Development
 

data/Rakefile

@@ -9,6 +9,9 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList["test/**/*_test.rb"]
 end
 
-require "standard/rake"
+Rake::TestTask.new("regen-bif") do |t|
+  `rm ./lib/bayesnet/parsers/bif.rb`
+  `tt ./lib/bayesnet/parsers/bif.treetop`
+end
 
-task default: %i[test standard]
+task default: %i[test]

data/bayesnet.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |spec|
 
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = spec.homepage
-  spec.metadata["changelog_uri"] = "#{spec.homepage}/blob/main/CHANGELOG.md"
+  spec.metadata["changelog_uri"] = "#{spec.homepage}/blob/master/CHANGELOG.md"
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
@@ -34,7 +34,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "m", "~> 1.5.0"
   spec.add_development_dependency "minitest", "~> 5.0"
   spec.add_development_dependency "pry-byebug", "~> 3.9.0"
-  spec.add_development_dependency "standard", "~> 1.3"
 
   # For more information and examples about making a new gem, checkout our
   # guide at: https://bundler.io/guides/creating_gem.html

data/lib/bayesnet/dsl.rb

@@ -1,10 +1,14 @@
+# frozen_string_literal: true
+
 require "bayesnet/graph"
 
 module Bayesnet
+  # Bayesnet::DSL.define ...
   module DSL
     def define(&block)
       graph = Graph.new
       graph.instance_eval(&block) if block
+      graph.resolve_factors
       graph
     end
   end

data/lib/bayesnet/error.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Bayesnet
   class Error < StandardError
   end

data/lib/bayesnet/factor.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Bayesnet
   # Factor if a function of sevaral variables (A, B, ...) each defined on values from finite set
   class Factor
@@ -8,26 +10,26 @@ module Bayesnet
     end
 
     # Specifies variable name together with its values
-    def var(var_name_to_values)
-      @vars.merge!(var_name_to_values)
+    def scope(var_name_to_values)
+      @scope.merge!(var_name_to_values)
     end
 
-    # Specifies function values for args. Latest args is an function value, all previous are argument values
-    def val(*args)
-      args = args[0] if args.size == 1 && args[0].is_a?(Array)
-      @vals[args[..-2]] = args[-1]
+    # Specifies value for a scope context. Value is the last element in `context_and_val`
+    def val(*context_and_val)
+      context_and_val = context_and_val[0] if context_and_val.size == 1 && context_and_val[0].is_a?(Array)
+      @vals[context_and_val[0..-2]] = context_and_val[-1]
     end
 
     def var_names
-      @vars.keys
+      @scope.keys
     end
 
-    def [](*args)
-      key = if args.size == 1 && args[0].is_a?(Hash)
-        args[0].slice(*var_names).values
-      else
-        args
-      end
+    def [](*context)
+      key = if context.size == 1 && context[0].is_a?(Hash)
+              context[0].slice(*var_names).values
+            else
+              context
+            end
       @vals[key]
     end
 
@@ -35,9 +37,10 @@ module Bayesnet
       self.class.new(var_distribution.keys, var_distribution.values.map(&:to_a))
     end
 
-    def args(*var_names)
+    def contextes(*var_names)
       return [] if var_names.empty?
-      @vars[var_names[0]].product(*var_names[1..].map { |var_name| @vars[var_name] })
+
+      @scope[var_names[0]].product(*var_names[1..].map { |var_name| @scope[var_name] })
     end
 
     def values
@@ -47,41 +50,52 @@ module Bayesnet
     def normalize
       vals = @vals.clone
       norm_factor = vals.map(&:last).sum * 1.0
-      vals.each { |k, v| vals[k] /= norm_factor }
-      self.class.new(@vars.clone, vals)
+      vals.each { |k, _v| vals[k] /= norm_factor }
+      self.class.new(@scope.clone, vals)
     end
 
-    def limit_by(evidence)
-      vars = @vars.except(*evidence.keys)
+    def reduce_to(context)
+      # TODO: use Hash#except when Ruby 2.6 support no longer needed
+      context_keys_set = context.keys.to_set
+      scope = @scope.reject { |k, _| context_keys_set.include?(k) }
 
-      evidence_vals = evidence.values
-      indices = evidence.keys.map { |k| index_by_var_name[k] }
-      vals = @vals.select { |k, v| indices.map { |i| k[i] } == evidence_vals }
-      vals.transform_keys! { |k| k - evidence_vals }
+      context_vals = context.values
+      indices = context.keys.map { |k| index_by_var_name[k] }
+      vals = @vals.select { |k, _v| indices.map { |i| k[i] } == context_vals }
+      vals.transform_keys! { |k| delete_by_indices(k, indices) }
+
+      self.class.new(scope, vals)
+    end
 
-      self.class.new(vars, vals)
+    def delete_by_indices(array, indices)
+      result = array.dup
+      indices.map { |i| result[i] = nil }
+      result.compact
     end
 
-    def reduce(over_vars)
-      vars = @vars.slice(*over_vars)
-      indices = vars.keys.map { |k| index_by_var_name[k] }
-      vals = @vals.group_by { |args, val| indices.map { |i| args[i] } }
+    # groups by `var_names` having same context and sum out values.
+    def marginalize(var_names)
+      scope = @scope.slice(*var_names)
+
+      indices = scope.keys.map { |k| index_by_var_name[k] }
+      vals = @vals.group_by { |context, _val| indices.map { |i| context[i] } }
       vals.transform_values! { |v| v.map(&:last).sum }
-      reduced = self.class.new(vars, vals)
-      reduced.normalize
+
+      self.class.new(scope, vals)
     end
 
     private
 
-    def initialize(vars = {}, vals = {})
-      @vars = vars
+    def initialize(scope = {}, vals = {})
+      @scope = scope
       @vals = vals
     end
 
     def index_by_var_name
       return @index_by_var_name if @index_by_var_name
+
       @index_by_var_name = {}
-      @vars.each_with_index { |(k, v), i| @index_by_var_name[k] = i }
+      @scope.each_with_index { |(k, _v), i| @index_by_var_name[k] = i }
       @index_by_var_name
     end
   end

data/lib/bayesnet/graph.rb

@@ -1,6 +1,9 @@
+# frozen_string_literal: true
+
 require "bayesnet/node"
 
 module Bayesnet
+  # Acyclic graph
   class Graph
     attr_reader :nodes
 
@@ -14,20 +17,29 @@ module Bayesnet
 
     def node(name, parents: [], &block)
       raise Error, "DSL error, #node requires a &block" unless block
-      node = Node.new(name, @nodes.slice(*parents))
+
+      node = Node.new(name, parents)
       node.instance_eval(&block)
       @nodes[name] = node
     end
 
+    def resolve_factors
+      @nodes.values.each do |node|
+        node.resolve_factor(@nodes.slice(*node.parent_nodes))
+      end
+    end
+
     def distribution(over: [], evidence: {})
-      limited = joint_distribution.limit_by(evidence)
-      limited.reduce(over)
+      joint_distribution
+        .reduce_to(evidence)
+        .marginalize(over)
+        .normalize
     end
 
     # This is MAP query, i.e. Maximum a Posteriory
     def most_likely_value(var_name, evidence:)
       posterior_distribution = distribution(over: [var_name], evidence: evidence)
-      mode = posterior_distribution.args(var_name).zip(posterior_distribution.values).max_by(&:last)
+      mode = posterior_distribution.contextes(var_name).zip(posterior_distribution.values).max_by(&:last)
       mode.first.first
     end
 
@@ -47,17 +59,21 @@ module Bayesnet
 
       factor = Factor.new
       @nodes.each do |node_name, node|
-        factor.var node_name => node.values
+        factor.scope node_name => node.values
       end
 
-      factor.args(*var_names).each do |args|
-        val_by_name = var_names.zip(args).to_h
+      factor.contextes(*var_names).each do |context|
+        val_by_name = var_names.zip(context).to_h
         val = nodes.values.reduce(1.0) do |prob, node|
           prob * node.factor[val_by_name]
         end
-        factor.val args + [val]
+        factor.val context + [val]
       end
       @joint_distribution = factor.normalize
     end
+
+    def parameters
+      nodes.values.map(&:parameters).sum
+    end
   end
 end

data/lib/bayesnet/node.rb

@@ -16,7 +16,7 @@ module Bayesnet
         @values = hash_or_array.keys
         node = self
         @factor = Factor.build do
-          var node.name => node.values
+          scope node.name => node.values
           hash_or_array.each do |value, probability|
             val [value, probability]
           end
@@ -24,14 +24,22 @@ module Bayesnet
       when Array
         raise Error, "DSL error, #values requires a &block when first argument is an Array" unless block
         @values = hash_or_array
+        @factor = block
+      end
+    end
+
+    def resolve_factor(parent_nodes)
+      @parent_nodes = parent_nodes
+      if @factor.is_a?(Proc)
+        proc = @factor
         node = self
         @factor = Factor.build do
-          var node.name => node.values
+          scope node.name => node.values
           node.parent_nodes.each do |parent_node_name, parent_node|
-            var parent_node_name => parent_node.values
+            scope parent_node_name => parent_node.values
           end
         end
-        instance_eval(&block)
+        instance_eval(&proc)
       end
     end
 
@@ -39,6 +47,10 @@ module Bayesnet
       instance_eval(&block)
     end
 
+    def parameters
+      (values.size - 1) * parent_nodes.values.reduce(1) { |mul, n| mul * n.values.size }
+    end
+
     def as(distribution, given:)
       @values.zip(distribution).each do |value, probability|
         @factor.val [value] + given + [probability]