eps 0.3.3 → 0.3.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8133bd3887423fb41421aa2a4270aa0c7fc75b741ea60a6c55fb97308f3ddea4
-  data.tar.gz: '018283d9934459202f8395b4c3f4ba201894296e3cfa185bb884cc5b73981f0a'
+  metadata.gz: e1f8c1d5af8015ba568528bce2c928cf59c97bda5c4f91a6ace0af72a9a864da
+  data.tar.gz: 3cbb6dfca84687c833051147a0fcad16cd258dd09f48a93da61f051c2081f62c
 SHA512:
-  metadata.gz: 2e1439f4a9a268a0434dc926a68822731db9267c746d4c76fa43a8debdbc49c25a502ff2051254fbf3453edb33141d35c02fa067afcddf2761e92b96e9d85751
-  data.tar.gz: 0c87d327d5f8083349cc75ea6b6e725e15ad20ac2535dc37dbc6b7955e6eca4408db93140287e8a9bfa7cee9da11956eb018600851bb07072c9e4347978d89dc
+  metadata.gz: 83477bb53b14a04798ab85f2efc9d4bb3af3195bd100ca42d601d2dbb2bc7fa09e7886f414e5a1e3041128bd671e3d15e39e071fe8de9d8d19dacc4c7e702cfc
+  data.tar.gz: 1914eeb9509916e9b4eb530f56dab0bfa73683a9197e157c8030fc11c96efca983a0d0f257d2845d890c9772ccfb6550651fb9fba60d1671db914c51b3675fc8

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.3.4 (2020-04-05)
+
+- Added `predict_probability` for classification
+
 ## 0.3.3 (2020-02-24)
 
 - Fixed errors and incorrect predictions with boolean columns

data/README.md

@@ -4,7 +4,6 @@ Machine learning for Ruby
 
 - Build predictive models quickly and easily
 - Serve models built in Ruby, Python, R, and more
-- No prior knowledge of machine learning required :tada:
 
 Check out [this post](https://ankane.org/rails-meet-data-science) for more info on machine learning with Rails
 
@@ -379,6 +378,16 @@ By default, an intercept is included. Disable this with:
 Eps::Model.new(data, intercept: false)
 ```
 
+## Probability
+
+To get the probability of each category for predictions with classification, use:
+
+```ruby
+model.predict_probability(data)
+```
+
+Naive Bayes is known to produce poor probability estimates, so stick with LightGBM if you need this.
+
 ## Validation Options
 
 Pass your own validation set with:
@@ -414,7 +423,7 @@ The database is another place you can store models. It’s good if you retrain m
 Create an ActiveRecord model to store the predictive model.
 
 ```sh
-rails g model Model key:string:uniq data:text
+rails generate model Model key:string:uniq data:text
 ```
 
 Store the model with:
@@ -524,11 +533,11 @@ Everyone is encouraged to help improve this project. Here are a few ways you can
 - Write, clarify, or fix documentation
 - Suggest or add new features
 
-To get started with development and testing:
+To get started with development:
 
 ```sh
 git clone https://github.com/ankane/eps.git
 cd eps
 bundle install
-rake test
+bundle exec rake test
 ```

data/lib/eps/base_estimator.rb

@@ -9,27 +9,11 @@ module Eps
     end
 
     def predict(data)
-      singular = data.is_a?(Hash)
-      data = [data] if singular
-
-      data = Eps::DataFrame.new(data)
-
-      @evaluator.features.each do |k, type|
-        values = data.columns[k]
-        raise ArgumentError, "Missing column: #{k}" if !values
-        column_type = Utils.column_type(values.compact, k) if values
-
-        if !column_type.nil?
-          if (type == "numeric" && column_type != "numeric") || (type != "numeric" && column_type != "categorical")
-            raise ArgumentError, "Bad type for column #{k}: Expected #{type} but got #{column_type}"
-          end
-        end
-        # TODO check for unknown values for categorical features
-      end
-
-      predictions = @evaluator.predict(data)
+      _predict(data, false)
+    end
 
-      singular ? predictions.first : predictions
+    def predict_probability(data)
+      _predict(data, true)
     end
 
     def evaluate(data, y = nil, target: nil, weight: nil)
@@ -75,6 +59,30 @@ module Eps
 
     private
 
+    def _predict(data, probabilities)
+      singular = data.is_a?(Hash)
+      data = [data] if singular
+
+      data = Eps::DataFrame.new(data)
+
+      @evaluator.features.each do |k, type|
+        values = data.columns[k]
+        raise ArgumentError, "Missing column: #{k}" if !values
+        column_type = Utils.column_type(values.compact, k) if values
+
+        if !column_type.nil?
+          if (type == "numeric" && column_type != "numeric") || (type != "numeric" && column_type != "categorical")
+            raise ArgumentError, "Bad type for column #{k}: Expected #{type} but got #{column_type}"
+          end
+        end
+        # TODO check for unknown values for categorical features
+      end
+
+      predictions = @evaluator.predict(data, probabilities: probabilities)
+
+      singular ? predictions.first : predictions
+    end
+
     def train(data, y = nil, target: nil, weight: nil, split: nil, validation_set: nil, verbose: nil, text_features: nil, early_stopping: nil)
       data, @target = prep_data(data, y, target, weight)
       @target_type = Utils.column_type(data.label, @target)

data/lib/eps/evaluators/lightgbm.rb

@@ -11,7 +11,9 @@ module Eps
         @text_features = text_features
       end
 
-      def predict(data)
+      def predict(data, probabilities: false)
+        raise "Probabilities not supported" if probabilities && @objective == "regression"
+
         rows = data.map(&:to_h)
 
         # sparse matrix
@@ -38,7 +40,12 @@ module Eps
         when "regression"
           sum_trees(rows, @trees)
         when "binary"
-          sum_trees(rows, @trees).map { |s| @labels[sigmoid(s) > 0.5 ? 1 : 0] }
+          prob = sum_trees(rows, @trees).map { |s| sigmoid(s) }
+          if probabilities
+            prob.map { |v| @labels.zip([1 - v, v]).to_h }
+          else
+            prob.map { |v| @labels[v > 0.5 ? 1 : 0] }
+          end
         else
           tree_scores = []
           num_trees = @trees.size / @labels.size
@@ -47,8 +54,14 @@ module Eps
           end
           data.size.times.map do |i|
             v = tree_scores.map { |s| s[i] }
-            idx = v.map.with_index.max_by { |v2, _| v2 }.last
-            @labels[idx]
+            if probabilities
+              exp = v.map { |vi| Math.exp(vi) }
+              sum = exp.sum
+              @labels.zip(exp.map { |e| e / sum }).to_h
+            else
+              idx = v.map.with_index.max_by { |v2, _| v2 }.last
+              @labels[idx]
+            end
           end
         end
       end
@@ -109,7 +122,7 @@ module Eps
       end
 
       def sigmoid(x)
-        1.0 / (1 + Math::E**(-x))
+        1.0 / (1 + Math.exp(-x))
       end
     end
   end

data/lib/eps/evaluators/linear_regression.rb

@@ -9,7 +9,9 @@ module Eps
         @text_features = text_features || {}
       end
 
-      def predict(x)
+      def predict(x, probabilities: false)
+        raise "Probabilities not supported" if probabilities
+
         intercept = @coefficients["_intercept"] || 0.0
         scores = [intercept] * x.size
 

data/lib/eps/evaluators/naive_bayes.rb

@@ -10,14 +10,15 @@ module Eps
         @legacy = legacy
       end
 
-      def predict(x)
+      def predict(x, probabilities: false)
         probs = calculate_class_probabilities(x)
         probs.map do |xp|
-          # convert probabilities
-          # not needed when just returning label
-          # sum = xp.values.map { |v| Math.exp(v) }.sum.to_f
-          # p xp.map { |k, v| [k, Math.exp(v) / sum] }.to_h
-          xp.sort_by { |k, v| [-v, k] }[0][0]
+          if probabilities
+            sum = xp.values.map { |v| Math.exp(v) }.sum.to_f
+            xp.map { |k, v| [k, Math.exp(v) / sum] }.to_h
+          else
+            xp.sort_by { |k, v| [-v, k] }[0][0]
+          end
         end
       end
 

data/lib/eps/lightgbm.rb

@@ -121,18 +121,20 @@ module Eps
     def check_evaluator(objective, labels, booster, booster_set, evaluator, evaluator_set)
       expected = @booster.predict(booster_set.map_rows(&:to_a))
       if objective == "multiclass"
-        expected.map! do |v|
-          labels[v.map.with_index.max_by { |v2, _| v2 }.last]
-        end
+        actual = evaluator.predict(evaluator_set, probabilities: true)
+        # just compare first for now
+        expected.map! { |v| v.first }
+        actual.map! { |v| v.values.first }
       elsif objective == "binary"
-        expected.map! { |v| labels[v >= 0.5 ? 1 : 0] }
+        actual = evaluator.predict(evaluator_set, probabilities: true).map { |v| v.values.last }
+      else
+        actual = evaluator.predict(evaluator_set)
       end
-      actual = evaluator.predict(evaluator_set)
 
-      regression = objective == "regression"
+      regression = objective == "regression" || objective == "binary"
       bad_observations = []
       expected.zip(actual).each_with_index do |(exp, act), i|
-        success = regression ? (act - exp).abs < 0.001 : act == exp
+        success = (act - exp).abs < 0.001
         unless success
           bad_observations << {expected: exp, actual: act, data_point: evaluator_set[i].map(&:itself).first}
         end

data/lib/eps/version.rb

@@ -1,3 +1,3 @@
 module Eps
-  VERSION = "0.3.3"
+  VERSION = "0.3.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: eps
 version: !ruby/object:Gem::Version
-  version: 0.3.3
+  version: 0.3.4
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-02-25 00:00:00.000000000 Z
+date: 2020-04-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lightgbm