eps 0.3.2 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 50f5a4273111ebc5ba1265d07d4e925d770006fce330b01cfbe4fe97221548d9
-  data.tar.gz: a785ca5533618243b933248ef2f418c5d0d048d8ff1051c9a2e7fae5f8c87ba3
+  metadata.gz: 8133bd3887423fb41421aa2a4270aa0c7fc75b741ea60a6c55fb97308f3ddea4
+  data.tar.gz: '018283d9934459202f8395b4c3f4ba201894296e3cfa185bb884cc5b73981f0a'
 SHA512:
-  metadata.gz: 3adffd0fbb0d16163a06720adfd97a83c6bf4bf2554e30b3a6f3599828511834826477a8296f93720c3efd52d19ca412e8b7695b013a4e7361073e3c5bcf5ee5
-  data.tar.gz: 69847d6d49742f61b3b4fac6e9298e5c954d4cc22e5302b716f258e6190f71df4eee1820e844c4159e1fdf99385a36c2cb697065e78d5f6557c6d1dbca70f9de
+  metadata.gz: 2e1439f4a9a268a0434dc926a68822731db9267c746d4c76fa43a8debdbc49c25a502ff2051254fbf3453edb33141d35c02fa067afcddf2761e92b96e9d85751
+  data.tar.gz: 0c87d327d5f8083349cc75ea6b6e725e15ad20ac2535dc37dbc6b7955e6eca4408db93140287e8a9bfa7cee9da11956eb018600851bb07072c9e4347978d89dc

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.3.3 (2020-02-24)
+
+- Fixed errors and incorrect predictions with boolean columns
+- Fixed deprecation warnings in Ruby 2.7
+
 ## 0.3.2 (2019-12-08)
 
 - Added support for GSLR

data/README.md

@@ -357,7 +357,7 @@ Eps supports:
 
 #### Performance
 
-To speed up training on large datasets with linear regression, [install GSL](https://www.gnu.org/software/gsl/). With Homebrew, you can use:
+To speed up training on large datasets with linear regression, [install GSL](https://github.com/ankane/gslr#gsl-installation). With Homebrew, you can use:
 
 ```sh
 brew install gsl

data/lib/eps/base_estimator.rb

@@ -4,6 +4,7 @@ module Eps
       @options = options.dup
       # TODO better pattern - don't pass most options to train
       options.delete(:intercept)
+      @trained = false
       train(data, y, **options) if data
     end
 
@@ -48,6 +49,8 @@ module Eps
     end
 
     def summary(extended: false)
+      raise "Summary not available for loaded models" unless @trained
+
       str = String.new("")
 
       if @validation_set
@@ -169,6 +172,8 @@ module Eps
       # reset pmml
       @pmml = nil
 
+      @trained = true
+
       nil
     end
 
@@ -205,7 +210,7 @@ module Eps
 
         # TODO determine max features automatically
         # start based on number of rows
-        encoder = Eps::TextEncoder.new(v)
+        encoder = Eps::TextEncoder.new(**v)
         counts = encoder.fit(train_set.columns.delete(k))
         encoder.vocabulary.each do |word|
           train_set.columns[[k, word]] = [0] * counts.size

data/lib/eps/evaluators/lightgbm.rb

@@ -16,7 +16,7 @@ module Eps
 
         # sparse matrix
         @text_features.each do |k, v|
-          encoder = TextEncoder.new(v)
+          encoder = TextEncoder.new(**v)
 
           values = data.columns.delete(k)
           counts = encoder.transform(values)
@@ -81,7 +81,7 @@ module Eps
           else
             case node.operator
             when "equal"
-              v == node.value
+              v.to_s == node.value
             when "in"
               node.value.include?(v)
             when "greaterThan"

data/lib/eps/evaluators/linear_regression.rb

@@ -19,10 +19,11 @@ module Eps
           case type
           when "categorical"
             x.columns[k].each_with_index do |xv, i|
-              scores[i] += @coefficients[[k, xv]].to_f
+              # TODO clean up
+              scores[i] += (@coefficients[[k, xv]] || @coefficients[[k, xv.to_s]]).to_f
             end
           when "text"
-            encoder = TextEncoder.new(@text_features[k])
+            encoder = TextEncoder.new(**@text_features[k])
             counts = encoder.transform(x.columns[k])
             coef = {}
             @coefficients.each do |k2, v|

data/lib/eps/evaluators/naive_bayes.rb

@@ -38,7 +38,8 @@ module Eps
             case type
             when "categorical"
               x.columns[k].each_with_index do |xi, i|
-                vc = probabilities[:conditional][k][xi]
+                # TODO clean this up
+                vc = probabilities[:conditional][k][xi] || probabilities[:conditional][k][xi.to_s]
 
                 # unknown value if not vc
                 if vc

data/lib/eps/pmml/generator.rb

@@ -210,10 +210,10 @@ module Eps
               probabilities[:conditional].each do |k, v|
                 xml.BayesInput(fieldName: k) do
                   if features[k] == "categorical"
-                    v.sort_by { |k2, _| k2 }.each do |k2, v2|
+                    v.sort_by { |k2, _| k2.to_s }.each do |k2, v2|
                       xml.PairCounts(value: k2) do
                         xml.TargetValueCounts do
-                          v2.sort_by { |k2, _| k2 }.each do |k3, v3|
+                          v2.sort_by { |k2, _| k2.to_s }.each do |k3, v3|
                             xml.TargetValueCount(value: k3, count: v3)
                           end
                         end
@@ -221,7 +221,7 @@ module Eps
                     end
                   else
                     xml.TargetValueStats do
-                      v.sort_by { |k2, _| k2 }.each do |k2, v2|
+                      v.sort_by { |k2, _| k2.to_s }.each do |k2, v2|
                         xml.TargetValueStat(value: k2) do
                           xml.GaussianDistribution(mean: v2[:mean], variance: v2[:stdev]**2)
                         end
@@ -233,7 +233,7 @@ module Eps
             end
             xml.BayesOutput(fieldName: "target") do
               xml.TargetValueCounts do
-                probabilities[:prior].sort_by { |k, _| k }.each do |k, v|
+                probabilities[:prior].sort_by { |k, _| k.to_s }.each do |k, v|
                   xml.TargetValueCount(value: k, count: v)
                 end
               end

data/lib/eps/version.rb

@@ -1,3 +1,3 @@
 module Eps
-  VERSION = "0.3.2"
+  VERSION = "0.3.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: eps
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-12-09 00:00:00.000000000 Z
+date: 2020-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lightgbm
@@ -143,7 +143,7 @@ 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: Machine learning for Ruby. Supports regression (linear regression) and classification