eps 0.6.0 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 701cde7907172e33d54d05ee0f2236dbfa84486744e7a510190618848c878418
-  data.tar.gz: a6be730db321a5143e34727497c6ed675f8d734b6195cd4fdc5f8e6bc4e98ff1
+  metadata.gz: 9559f4d440f2a7cb6d541073600829a0b1bdd0df61c6abe166e0ff731a34fe18
+  data.tar.gz: 6a9f37c76d6bdec50f877d9932f805bda751b87c03c0a69f187830dc7c1876d4
 SHA512:
-  metadata.gz: 6c76ec99a116a91cb9550b9a007b3150689b76649b14aa0c85582176fb44a08957b37c40e54ed1adb6447d8c5ec06757a611fad51a582581031f5724317ee888
-  data.tar.gz: 2176bf4351c26df4562a2879ecb2f0637d2d23bb624dc683790befa2029c2a3d89388b7d5b3183d4d48789801068d7442807c28c2a53439089e2ba0943e0bc9b
+  metadata.gz: c12d5b688bbe9884a0350efd3900de68f1244264dc0cf56f7a8a64145b3ff4a2f08608146e596d0052c1a7da4cc52c4606ae9a5e52b180c1fe1e60d034170e9f
+  data.tar.gz: 5fe61bd82055f22210f27f7d1cceb7adbb71d50dd6750336ddc731ae617d749e2c9c478ada19f6a2ad8def2c51d8e2e13a0269ba7687ee97331490a49f59d7c4

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.7.0 (2026-04-14)
+
+- Dropped support for Daru
+- Dropped support for Ruby < 3.3
+
 ## 0.6.0 (2025-02-01)
 
 - Dropped support for Ruby < 3.1

data/LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2018-2024 Andrew Kane
+Copyright (c) 2018-2026 Andrew Kane
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -147,7 +147,7 @@ You can set advanced options with:
 ```ruby
 text_features: {
   description: {
-    min_occurences: 5,          # min times a word must appear to be included in the model
+    min_occurrences: 5,         # min times a word must appear to be included in the model
     max_features: 1000,         # max number of words to include in the model
     min_length: 1,              # min length of words to be included
     case_sensitive: true,       # how to treat words with different case
@@ -336,13 +336,6 @@ df = Rover.read_csv("houses.csv")
 Eps::Model.new(df, target: "price")
 ```
 
-Or a Daru data frame
-
-```ruby
-df = Daru::DataFrame.from_csv("houses.csv")
-Eps::Model.new(df, target: "price")
-```
-
 When reading CSV files directly, be sure to convert numeric fields. The `table` method does this automatically.
 
 ```ruby

data/lib/eps/base_estimator.rb

@@ -27,8 +27,8 @@ module Eps
 
     def self.load_pmml(pmml)
       model = new
-      model.instance_variable_set("@evaluator", PMML.load(pmml))
-      model.instance_variable_set("@pmml", pmml.respond_to?(:to_xml) ? pmml.to_xml : pmml) # cache data
+      model.instance_variable_set(:@evaluator, PMML.load(pmml))
+      model.instance_variable_set(:@pmml, pmml.respond_to?(:to_xml) ? pmml.to_xml : pmml) # cache data
       model
     end
 

data/lib/eps/data_frame.rb

@@ -10,7 +10,7 @@ module Eps
         data.columns.each do |k, v|
           @columns[k] = v
         end
-      elsif rover?(data) || daru?(data)
+      elsif rover?(data)
         data.to_h.each do |k, v|
           @columns[k.to_s] = v.to_a
         end
@@ -152,9 +152,5 @@ module Eps
     def rover?(x)
       defined?(Rover::DataFrame) && x.is_a?(Rover::DataFrame)
     end
-
-    def daru?(x)
-      defined?(Daru::DataFrame) && x.is_a?(Daru::DataFrame)
-    end
   end
 end

data/lib/eps/evaluators/naive_bayes.rb

@@ -14,7 +14,7 @@ module Eps
         probs = calculate_class_probabilities(x)
         probs.map do |xp|
           if probabilities
-            sum = xp.values.map { |v| Math.exp(v) }.sum.to_f
+            sum = xp.values.sum { |v| Math.exp(v) }.to_f
             xp.map { |k, v| [k, Math.exp(v) / sum] }.to_h
           else
             xp.sort_by { |k, v| [-v, k] }[0][0]
@@ -44,7 +44,7 @@ module Eps
 
                 # unknown value if not vc
                 if vc
-                  denom = probabilities[:conditional][k].map { |k, v| v[c] }.sum.to_f
+                  denom = probabilities[:conditional][k].sum { |k, v| v[c] }.to_f
                   p2 = vc[c].to_f / denom
 
                   # TODO use proper smoothing instead

data/lib/eps/lightgbm.rb

@@ -20,7 +20,6 @@ module Eps
     def _train(verbose: nil, early_stopping: nil, learning_rate: 0.1)
       train_set = @train_set
       validation_set = @validation_set.dup
-      summary_label = train_set.label
 
       # create check set
       evaluator_set = validation_set || train_set
@@ -134,7 +133,6 @@ module Eps
         actual = evaluator.predict(evaluator_set)
       end
 
-      regression = objective == "regression" || objective == "binary"
       bad_observations = []
       expected.zip(actual).each_with_index do |(exp, act), i|
         success = (act - exp).abs < 0.001

data/lib/eps/linear_regression.rb

@@ -221,13 +221,13 @@ module Eps
 
     # total sum of squares
     def sst
-      @sst ||= @train_set.label.map { |y| (y - y_bar)**2 }.sum
+      @sst ||= @train_set.label.sum { |y| (y - y_bar)**2 }
     end
 
     # sum of squared errors of prediction
     # not to be confused with "explained sum of squares"
     def sse
-      @sse ||= @train_set.label.zip(y_hat).map { |y, yh| (y - yh)**2 }.sum
+      @sse ||= @train_set.label.zip(y_hat).sum { |y, yh| (y - yh)**2 }
     end
 
     def mst

data/lib/eps/naive_bayes.rb

@@ -73,7 +73,7 @@ module Eps
           # smooth
           if smoothing
             labels.each do |label|
-              sum = prob.map { |k2, v2| v2[label] }.sum.to_f
+              sum = prob.sum { |k2, v2| v2[label] }.to_f
               prob.each do |k2, v|
                 v[label] = (v[label] + smoothing) * sum / (sum + (prob.size * smoothing))
               end

data/lib/eps/pmml/generator.rb

@@ -151,7 +151,7 @@ module Eps
       end
 
       def linear_regression
-        predictors = model.instance_variable_get("@coefficients").dup
+        predictors = model.instance_variable_get(:@coefficients).dup
         intercept = predictors.delete("_intercept") || 0.0
 
         data_fields = {}
@@ -377,43 +377,43 @@ module Eps
       # TODO create instance methods on model for all of these features
 
       def features
-        model.instance_variable_get("@features")
+        model.instance_variable_get(:@features)
       end
 
       def text_features
-        model.instance_variable_get("@text_features")
+        model.instance_variable_get(:@text_features)
       end
 
       def text_encoders
-        model.instance_variable_get("@text_encoders")
+        model.instance_variable_get(:@text_encoders)
       end
 
       def feature_importance
-        model.instance_variable_get("@feature_importance")
+        model.instance_variable_get(:@feature_importance)
       end
 
       def labels
-        model.instance_variable_get("@labels")
+        model.instance_variable_get(:@labels)
       end
 
       def trees
-        model.instance_variable_get("@trees")
+        model.instance_variable_get(:@trees)
       end
 
       def target
-        model.instance_variable_get("@target")
+        model.instance_variable_get(:@target)
       end
 
       def label_encoders
-        model.instance_variable_get("@label_encoders")
+        model.instance_variable_get(:@label_encoders)
       end
 
       def objective
-        model.instance_variable_get("@objective")
+        model.instance_variable_get(:@objective)
       end
 
       def probabilities
-        model.instance_variable_get("@probabilities")
+        model.instance_variable_get(:@probabilities)
       end
 
       # end TODO

data/lib/eps/pmml/loader.rb

@@ -139,8 +139,6 @@ module Eps
           features[name] = n.css("TargetValueStat").any? ? "numeric" : "categorical"
         end
 
-        target = node.css("BayesOutput").attribute("fieldName").value
-
         probabilities = {
           prior: prior,
           conditional: conditional

data/lib/eps/statistics.rb

@@ -47,7 +47,7 @@ module Eps
         return start + sign * (z - a) / 2.0
       end
 
-      # tail series expanation for large t-values
+      # tail series expansion for large t-values
       a = Math.sqrt(b)
       y = a * n
       j = 0

data/lib/eps/text_encoder.rb

@@ -36,7 +36,7 @@ module Eps
     end
 
     def transform(arr)
-      counts, fit = count_and_fit(arr)
+      _, fit = count_and_fit(arr)
       fit
     end
 

data/lib/eps/utils.rb

@@ -3,14 +3,14 @@ module Eps
     def self.column_type(c, k)
       if !c
         raise ArgumentError, "Missing column: #{k}"
-      elsif c.all? { |v| v.nil? }
+      elsif c.all?(&:nil?)
         # goes here for empty as well
         nil
-      elsif c.any? { |v| v.nil? }
+      elsif c.any?(&:nil?)
         raise ArgumentError, "Missing values in column #{k}"
-      elsif c.all? { |v| v.is_a?(Numeric) }
+      elsif c.all?(Numeric)
         "numeric"
-      elsif c.all? { |v| v.is_a?(String) }
+      elsif c.all?(String)
         "categorical"
       elsif c.all? { |v| v == true || v == false }
         "categorical" # boolean

data/lib/eps/version.rb

@@ -1,3 +1,3 @@
 module Eps
-  VERSION = "0.6.0"
+  VERSION = "0.7.0"
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: eps
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.7.0
 platform: ruby
 authors:
 - Andrew Kane
 bindir: bin
 cert_chain: []
-date: 2025-02-01 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lightgbm
@@ -15,14 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.7
+        version: '0.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.7
+        version: '0.4'
 - !ruby/object:Gem::Dependency
   name: matrix
   requirement: !ruby/object:Gem::Requirement
@@ -91,14 +91,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.1'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Machine learning for Ruby. Supports regression (linear regression) and classification
   (naive Bayes)