eps 0.3.4 → 0.3.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e1f8c1d5af8015ba568528bce2c928cf59c97bda5c4f91a6ace0af72a9a864da
-  data.tar.gz: 3cbb6dfca84687c833051147a0fcad16cd258dd09f48a93da61f051c2081f62c
+  metadata.gz: 1369016c3cae228f169fe580b54fca3c0d240cda202fa7d03ecc7a4e156ee8c7
+  data.tar.gz: bf83ca424c509798d1a1436806b52cba0cfdbefecb8d827d5b17aec7b807b121
 SHA512:
-  metadata.gz: 83477bb53b14a04798ab85f2efc9d4bb3af3195bd100ca42d601d2dbb2bc7fa09e7886f414e5a1e3041128bd671e3d15e39e071fe8de9d8d19dacc4c7e702cfc
-  data.tar.gz: 1914eeb9509916e9b4eb530f56dab0bfa73683a9197e157c8030fc11c96efca983a0d0f257d2845d890c9772ccfb6550651fb9fba60d1671db914c51b3675fc8
+  metadata.gz: 2bf47d80a301eb546c348aaa71f847fa22ace5bed63d97a1f19eb14bc15388b056cd3f545ccf251b2bbf2afc485ef81e5559849ff7459e9dd9f88a71c7cbf83a
+  data.tar.gz: 82d65d84e95a6518cd132c2a42cdec20afd05c0013192941b59ee0edb524874d12b2dd9082dd89be1422872c88e827e031469e43b80336c48c7eab7ff4fe611e

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.3.5 (2020-06-10)
+
+- Added `learning_rate` option for LightGBM
+- Added support for Numo and Rover
+
 ## 0.3.4 (2020-04-05)
 
 - Added `predict_probability` for classification

data/README.md

@@ -313,7 +313,7 @@ y = [1, 2, 3]
 Eps::Model.new(x, y)
 ```
 
-Or pass arrays of arrays
+Data can be an array of arrays
 
 ```ruby
 x = [[1, 2], [2, 0], [3, 1]]
@@ -321,9 +321,22 @@ y = [1, 2, 3]
 Eps::Model.new(x, y)
 ```
 
-### Daru
+Or Numo arrays
 
-Eps works well with Daru data frames.
+```ruby
+x = Numo::NArray.cast([[1, 2], [2, 0], [3, 1]])
+y = Numo::NArray.cast([1, 2, 3])
+Eps::Model.new(x, y)
+```
+
+Or a Rover data frame
+
+```ruby
+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")
@@ -352,6 +365,14 @@ Eps supports:
 - Linear Regression
 - Naive Bayes
 
+### LightGBM
+
+Pass the learning rate with:
+
+```ruby
+Eps::Model.new(data, learning_rate: 0.01)
+```
+
 ### Linear Regression
 
 #### Performance

data/lib/eps/base_estimator.rb

@@ -2,9 +2,8 @@ module Eps
   class BaseEstimator
     def initialize(data = nil, y = nil, **options)
       @options = options.dup
-      # TODO better pattern - don't pass most options to train
-      options.delete(:intercept)
       @trained = false
+      # TODO better pattern - don't pass most options to train
       train(data, y, **options) if data
     end
 
@@ -83,7 +82,7 @@ module Eps
       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)
+    def train(data, y = nil, target: nil, weight: nil, split: nil, validation_set: nil, text_features: nil, **options)
       data, @target = prep_data(data, y, target, weight)
       @target_type = Utils.column_type(data.label, @target)
 
@@ -175,7 +174,7 @@ module Eps
       raise "No data in validation set" if validation_set && validation_set.empty?
 
       @validation_set = validation_set
-      @evaluator = _train(verbose: verbose, early_stopping: early_stopping)
+      @evaluator = _train(**options)
 
       # reset pmml
       @pmml = nil
@@ -246,7 +245,7 @@ module Eps
 
     def check_missing(c, name)
       raise ArgumentError, "Missing column: #{name}" if !c
-      raise ArgumentError, "Missing values in column #{name}" if c.any?(&:nil?)
+      raise ArgumentError, "Missing values in column #{name}" if c.to_a.any?(&:nil?)
     end
 
     def check_missing_value(df)

data/lib/eps/data_frame.rb

@@ -10,7 +10,7 @@ module Eps
         data.columns.each do |k, v|
           @columns[k] = v
         end
-      elsif daru?(data)
+      elsif rover?(data) || daru?(data)
         data.to_h.each do |k, v|
           @columns[k.to_s] = v.to_a
         end
@@ -19,6 +19,8 @@ module Eps
           @columns[k.to_s] = v.to_a
         end
       else
+        data = data.to_a if numo?(data)
+
         if data.any?
           row = data[0]
 
@@ -140,8 +142,16 @@ module Eps
 
     private
 
+    def numo?(x)
+      defined?(Numo::NArray) && x.is_a?(Numo::NArray)
+    end
+
+    def rover?(x)
+      defined?(Rover::DataFrame) && x.is_a?(Rover::DataFrame)
+    end
+
     def daru?(x)
-      defined?(Daru) && x.is_a?(Daru::DataFrame)
+      defined?(Daru::DataFrame) && x.is_a?(Daru::DataFrame)
     end
   end
 end

data/lib/eps/lightgbm.rb

@@ -17,7 +17,7 @@ module Eps
       str
     end
 
-    def _train(verbose: nil, early_stopping: nil)
+    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
@@ -60,7 +60,10 @@ module Eps
       prep_text_features(validation_set) if validation_set
 
       # create params
-      params = {objective: objective}
+      params = {
+        objective: objective,
+        learning_rate: learning_rate
+      }
       params[:num_classes] = labels.size if objective == "multiclass"
       if train_set.size < 30
         params[:min_data_in_bin] = 1

data/lib/eps/linear_regression.rb

@@ -37,6 +37,7 @@ module Eps
       str
     end
 
+    # TODO use keyword arguments for gsl and intercept in 0.4.0
     def _train(**options)
       raise "Target must be numeric" if @target_type != "numeric"
       check_missing_value(@train_set)
@@ -61,7 +62,7 @@ module Eps
           false
         end
 
-      intercept = @options.key?(:intercept) ? @options[:intercept] : true
+      intercept = options.key?(:intercept) ? options[:intercept] : true
       if intercept && gsl != :gslr
         data.size.times do |i|
           x[i].unshift(1)

data/lib/eps/naive_bayes.rb

@@ -17,7 +17,7 @@ module Eps
       str
     end
 
-    def _train(smoothing: 1, **options)
+    def _train(smoothing: 1)
       raise "Target must be strings" if @target_type != "categorical"
       check_missing_value(@train_set)
       check_missing_value(@validation_set) if @validation_set

data/lib/eps/version.rb

@@ -1,3 +1,3 @@
 module Eps
-  VERSION = "0.3.4"
+  VERSION = "0.3.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: eps
 version: !ruby/object:Gem::Version
-  version: 0.3.4
+  version: 0.3.5
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-04-05 00:00:00.000000000 Z
+date: 2020-06-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lightgbm
@@ -80,6 +80,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: numo-narray
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -94,6 +108,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rover-df
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 
 email: andrew@chartkick.com
 executables: []