red_amber 0.2.3 → 0.3.0

data/lib/red_amber/vector_updatable.rb

@@ -7,6 +7,9 @@ module RedAmber
   # mix-in for class Vector
   # Functions to make up some data (especially missing) for new data.
   module VectorUpdatable
+    # Add properties to Arrow::Array and Arrow::ChunkedArray
+    using RefineArrayLike
+
     # Replace data
     # @param specifier [Array, Vector, Arrow::Array] index or booleans.
     # @param replacer [Scalar, Array, Vector, Arrow::Array] new data to replace for.
@@ -14,7 +17,7 @@ module RedAmber
     #   If specifier has no true, return self.
     #
     def replace(specifier, replacer)
-      vector = parse_to_vector(Array(specifier))
+      vector = Vector.new(parse_args(Array(specifier), size))
       return self if vector.empty? || empty?
 
       booleans =
@@ -42,7 +45,9 @@ module RedAmber
         else # Broadcast scalar to Array
           Arrow::Array.new(Array(replacer) * booleans.to_a.count(true))
         end
-      raise VectorArgumentError, 'Replacements size unmatch' if booleans.sum != replacer_array.length
+      if booleans.sum != replacer_array.length
+        raise VectorArgumentError, 'Replacements size unmatch'
+      end
 
       replace_with(booleans.data, replacer_array)
     end
@@ -57,7 +62,7 @@ module RedAmber
       raise VectorTypeError, 'Reciever must be a boolean' unless boolean?
 
       datum = find(:if_else).execute([data, true_choice, false_choice])
-      Vector.new(datum.value)
+      Vector.create(datum.value)
     end
 
     # same behavior as Ruby's invert
@@ -80,11 +85,134 @@ module RedAmber
       end
     end
 
+    # Split string Vector and returns Array of columns.
+    #
+    # @param sep [nil, String, Regexp] separater.
+    #   If separator is nil (or no argeument given), the column will be splitted by
+    #   Arrow's split function using any ASCII whitespace.
+    #   Otherwise sep will passed to String#split.
+    # @param limit [Integer] maximum number to limit separation. Passed to String#split.
+    # @return [Array<Vector>] an Array of Vectors.
+    # @note nil will separated as nil's at same row. ex) `nil => [nil, nil]`
+    #
+    def split_to_columns(sep = nil, limit = 0)
+      l = split(sep, limit)
+      l.list_separate
+    end
+
+    # Split string Vector and flatten into rows.
+    #
+    # @param sep [nil, String, Regexp] separater.
+    #   If separator is nil (or no argeument given), the column will be splitted by
+    #   Arrow's split function using any ASCII whitespace.
+    #   Otherwise sep will passed to String#split.
+    # @param limit [Integer] maximum number to limit separation. Passed to String#split.
+    # @return [Vector] a flatten Vector.
+    # @note nil will separated as nil's at same row. ex) `nil => [nil, nil]`
+    #
+    def split_to_rows(sep = nil, limit = 0)
+      l = split(sep, limit)
+      l.list_flatten
+    end
+
+    # return element size Array for list Vector.
+    #
+    # @api private
+    #
+    def list_sizes
+      Vector.create find(:list_value_length).execute([data]).value
+    end
+
+    # Separate list Vector by columns.
+    #
+    # @api private
+    #
+    def list_separate
+      len = list_sizes.data
+      min, max = Arrow::Function.find(:min_max).execute([len]).value.value.map(&:value)
+
+      result = []
+      (0...min).each do |i|
+        result << Vector.create(find(:list_element).execute([data, i]).value)
+      end
+      return result if min == max
+
+      (min...max).each do |i|
+        result << Vector.new(data.map { |e| e&.[](i) })
+      end
+      result
+    end
+
+    # Flatten list Vector for rows.
+    #
+    # @api private
+    #
+    def list_flatten
+      Vector.create find(:list_flatten).execute([data]).value
+    end
+
+    # Split string Vector by each element with separator and returns list Array.
+    #
+    # @note if sep is not specified, use Arrow's ascii_split_whitespace.
+    #   It will separate string by ascii whitespaces.
+    # @note if sep specified, sep and limit will passed to String#split.
+    #
+    def split(sep = nil, limit = 0)
+      if empty? || !string?
+        raise VectorTypeError, "self is not a valid string Vector: #{self}"
+      end
+      if self[0].nil? && uniq.to_a == [nil] # Avoid heavy check to be activated always.
+        raise VectorTypeError, 'self contains only nil'
+      end
+
+      list =
+        if sep
+          Arrow::Array.new(to_a.map { |e| e&.split(sep, limit) })
+        else
+          find(:ascii_split_whitespace).execute([data]).value
+        end
+      Vector.create(list)
+    end
+
+    # Merge String or other string Vector to self.
+    #   Self must be a string Vector.
+    #
+    # @param other [String, Vector]
+    #   merger from right. It will be broadcasted if it is a scalar String.
+    # @param sep [String] separator.
+    # @return [Vector] merged Vector
+    #
+    def merge(other, sep: ' ')
+      if empty? || !string?
+        raise VectorTypeError,
+              "self is not a string Vector: #{self}"
+      end
+      unless sep.is_a?(String)
+        raise VectorArgumentError, "separator is not a String: #{sep}"
+      end
+
+      other_array =
+        case other
+        in String => s
+          [s] * size
+        in (Vector | Arrow::Array | Arrow::ChunkedArray) => x if x.string?
+          x.to_a
+        else
+          raise VectorArgumentError,
+                "other is not a String or a string Vector: #{self}"
+        end
+
+      list = Arrow::Array.new(to_a.zip(other_array))
+      datum = find(:binary_join).execute([list, sep])
+      Vector.create(datum.value)
+    end
+
     private
 
     # Replace elements selected with a boolean mask
     #
-    # @param boolean_mask [Arrow::BooleanArray] Boolean mask which indicates the position to be replaced.
+    # @param boolean_mask [Arrow::BooleanArray]
+    #   Boolean mask which indicates the position to be replaced.
     #   - Position with true will be replaced.
     #   - Position with nil will be nil.
     #
@@ -104,12 +232,13 @@ module RedAmber
       values = replacer.class.new(data) # Upcast
 
       datum = find(:replace_with_mask).execute([values, boolean_mask, replacer])
-      Vector.new(datum.value)
+      Vector.create(datum.value)
     end
 
     # Replace elements selected with a boolean mask by nil
     #
-    # @param boolean_mask [Arrow::BooleanArray] Boolean mask which indicates the position to be replaced.
+    # @param boolean_mask [Arrow::BooleanArray]
+    #   Boolean mask which indicates the position to be replaced.
     #   - Position with true will be replaced by nil
     #   - Position with nil will remain as nil.
     # @return [Vector] Replaced vector.
@@ -117,7 +246,7 @@ module RedAmber
     def replace_to_nil(boolean_mask)
       nil_array = data.class.new([nil] * size) # Casted nil Array
       datum = find(:if_else).execute([boolean_mask, nil_array, data])
-      Vector.new(datum.value)
+      Vector.create(datum.value)
     end
   end
 end

data/lib/red_amber/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RedAmber
-  VERSION = '0.2.3'
+  VERSION = '0.3.0'
 end

data/lib/red_amber.rb

@@ -2,7 +2,9 @@
 
 require 'arrow'
 
+require_relative 'red_amber/refinements'
 require_relative 'red_amber/helper'
+
 require_relative 'red_amber/data_frame_combinable'
 require_relative 'red_amber/data_frame_displayable'
 require_relative 'red_amber/data_frame_indexable'

data/red_amber.gemspec

@@ -9,10 +9,11 @@ Gem::Specification.new do |spec|
   spec.email = ['heronshoes877@gmail.com']
 
   spec.summary = 'Simple dataframe library for Ruby'
-  spec.description = 'RedAmber is a simple dataframe library inspired by Rover-df and powered by Red Arrow.'
+  spec.description = 'RedAmber is a simple dataframe library' \
+                     'inspired by Rover-df and powered by Red Arrow.'
   spec.homepage = 'https://github.com/heronshoes/red_amber'
   spec.license = 'MIT'
-  spec.required_ruby_version = '>= 2.7'
+  spec.required_ruby_version = '>= 3.0'
 
   spec.metadata['homepage_uri'] = spec.homepage
   spec.metadata['source_code_uri'] = 'https://github.com/heronshoes/red_amber'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: red_amber
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.3.0
 platform: ruby
 authors:
 - Hirokazu SUZUKI (heronshoes)
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-11-16 00:00:00.000000000 Z
+date: 2022-12-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: red-arrow
@@ -24,7 +24,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 10.0.0
-description: RedAmber is a simple dataframe library inspired by Rover-df and powered
+description: RedAmber is a simple dataframe libraryinspired by Rover-df and powered
   by Red Arrow.
 email:
 - heronshoes877@gmail.com
@@ -42,6 +42,7 @@ files:
 - Rakefile
 - benchmark/basic.yml
 - benchmark/combine.yml
+- benchmark/dataframe.yml
 - benchmark/drop_nil.yml
 - benchmark/group.yml
 - benchmark/reshape.yml
@@ -50,6 +51,7 @@ files:
 - benchmark/rover/penguins.yml
 - benchmark/rover/planes.yml
 - benchmark/rover/weather.yml
+- benchmark/vector.yml
 - doc/CODE_OF_CONDUCT.md
 - doc/DataFrame.md
 - doc/Vector.md
@@ -95,6 +97,7 @@ files:
 - lib/red_amber/data_frame_variable_operation.rb
 - lib/red_amber/group.rb
 - lib/red_amber/helper.rb
+- lib/red_amber/refinements.rb
 - lib/red_amber/vector.rb
 - lib/red_amber/vector_functions.rb
 - lib/red_amber/vector_selectable.rb
@@ -110,7 +113,7 @@ metadata:
   source_code_uri: https://github.com/heronshoes/red_amber
   changelog_uri: https://github.com/heronshoes/red_amber/blob/main/CHANGELOG.md
   rubygems_mfa_required: 'true'
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -118,15 +121,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
-signing_key: 
+rubygems_version: 3.3.26
+signing_key:
 specification_version: 4
 summary: Simple dataframe library for Ruby
 test_files: []