red_amber 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 00ba2e99b2b1d6f977b2e2e5c7d60b9313972cf3e831918606e5388d51442137
-  data.tar.gz: f0fc831937bff5fede4ee0f0537b0ef5fdfb8a1faa8a57082a197a627562252c
+  metadata.gz: 54de345111ab7c3918e119abe820d2ff207007f1ce9731e2f8954513d47c76a9
+  data.tar.gz: 75e4251c6d6be8eab05739f75e064a2e65cbe3abdafaa574c559d9356fe93a20
 SHA512:
-  metadata.gz: 7bc020b8663c3523426461e3bd54642d4eb85a86296a8db3f5d94315091ee4475ec8b910fb87165c5d029e35fa9dc45f119bea6278e023d3cc63ad011388fbfb
-  data.tar.gz: 78dd55182b40ee9bec769efdbcac23adb85ad93bbafe3f74c4ded9d56ab40e39da0ce1e34a841d5705e6b94fea85312057e360140965fa217243eede0d238eb5
+  metadata.gz: 60c2d11d30b91947b67e608864e5e4fe13e544662f671789256e6e2e624a892577f616572e4ba55be4de99affd528d020060b4be56f8820250697db2a80132a2
+  data.tar.gz: 19170b7cd3d6b1174b7de44c0b8841d47acc4d1832fe72fdc8adc7171245e031c922614aca979755ae035566deae0a711644a3e483cecbceabdcfc411efb2263

data/.rubocop.yml

@@ -45,7 +45,7 @@ Lint/BinaryOperatorWithIdenticalOperands:
 
 # Max: 120
 Layout/LineLength:
-  Max: 100
+  Max: 118
   Exclude:
     - 'test/**/*'
 
@@ -53,7 +53,7 @@ Layout/LineLength:
 # 18..30 unsatisfactory
 # > 30 dangerous
 Metrics/AbcSize:
-  Max: 19
+  Max: 23
   Exclude:
     - 'lib/red_amber/data_frame_output.rb' # Max: 78
 
@@ -84,6 +84,11 @@ Metrics/MethodLength:
 
 # Max: 8
 Metrics/PerceivedComplexity:
-  Max: 9
+  Max: 11
   Exclude:
     - 'lib/red_amber/data_frame_output.rb' # Max: 12
+
+# Necessary to test when range.end == -1
+Style/SlicingWithRange:
+  Exclude:
+    - 'test/test_data_frame_selectable.rb'

data/.rubocop_todo.yml

@@ -1,17 +1,11 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2022-04-27 00:29:57 UTC using RuboCop version 1.27.0.
+# on 2022-05-08 02:37:36 UTC using RuboCop version 1.27.0.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 1
-# This cop supports unsafe auto-correction (--auto-correct-all).
-Style/SlicingWithRange:
-  Exclude:
-    - 'lib/red_amber/data_frame_selectable.rb'
-
 # Offense count: 1
 # This cop supports unsafe auto-correction (--auto-correct-all).
 # Configuration parameters: EnforcedStyle.

data/CHANGELOG.md

@@ -1,17 +1,29 @@
-## [0.1.2] - Unreleased
+## [0.1.3] - Unreleased
 
-- Add support for Arrow 8.0.0
 - `DataFrame`
-  - Introduce updating
+  - Introduce updating capabilities
   - Introduce NA support
   - Add slice method
 - `Vector`
   - Add NaN support for functions
   - More functions
 
+## [0.1.2] - 2022-05-08 (experimental)
+
+- Bug fixes:
+  - `DataFrame`
+    - Fix bug in `#[]` with end-less Range
+- New features and improvements
+  - Add support for Arrow 8.0.0
+  - `DataFrame`
+    - `types` and `data_types`
+    - Range is usable to specify columns in `#[]`
+  - `Vector`
+    - `type` and `data_type`
+
 ## [0.1.1] - 2022-05-06 (experimental)
 
-- Release on rubygem.org
+- Release on rubygems.org
 - Introduce class `DataFrame`
   -  New from Hash, schema/rows, `Arrow::Table`, `Rover::DataFrame`
   -  Load from file, string, URI

data/README.md

@@ -8,8 +8,8 @@ A simple dataframe library for Ruby (experimental)
 ## Requirements
 
 ```ruby
-gem 'red-arrow',   '~> 7.0.0'
-gem 'red-parquet', '~> 7.0.0' # if you use IO from/to parquet
+gem 'red-arrow',   '>= 7.0.0'
+gem 'red-parquet', '>= 7.0.0' # if you use IO from/to parquet
 gem 'rover-df',    '~> 0.3.0' # if you use IO from/to Rover::DataFrame
 ```
 
@@ -89,10 +89,13 @@ Or install it yourself as:
   
   Returns num of column names by an Array.
 
-- [x] `types(class_name: false)`
+- [x] `types`
   
-  Returns types of columns by an Array.
-  If `class_name: true` returns an Array of `Arrow::DataType`.
+  Returns types of columns by an Array of Symbols.
+
+- [x] `data_types`
+
+  Returns types of columns by an Array of `Arrow::DataType`.
 
 - [x] `vectors`
 
@@ -128,20 +131,50 @@ Or install it yourself as:
 
   Shows some information about self.
 
+```ruby
+hash = {a: [1, 2, 3], b: %w[A B C], c: [1.0, 2, 3]}
+RedAmber::DataFrame.new(hash)
+# =>
+RedAmber::DataFrame : 3 observations(rows) of 3 variables(columns)
+Variables : 2 numeric, 1 string
+# key type   level data_preview
+1 :a  uint8      3 [1, 2, 3]
+2 :b  string     3 [A, B, C]
+3 :c  double     3 [1.0, 2.0, 3.0]
+```
+
   - tally_level: max level to use tally mode
   - max_element: max num of element to show values in each row
 
 ### Selecting
 
-- [x] Selecting columns by `[]`
-
-  `[key]`, `[keys]`, `[keys[index]]`
-
-- [x] Selecting rows by `[]`
+- [x] Select columns by `[]` as `[key]`, `[keys]`, `[keys[index]]`
+  - Key in a Symbol: `df[:symbol]`
+  - Key in a String: `df["string"]`
+  - Keys in an Array: `df[:symbol1`, `"string"`, `:symbol2`
+  - Keys in indeces: `df[df.keys[0]`, `df[df.keys[1,2]]`, `df[df.keys[1..]]`
+  - Keys in a Range:
+    A end-less Range can be used to represent keys.
+```ruby
+hash = {a: [1, 2, 3], b: %w[A B C], c: [1.0, 2, 3]}
+df = RedAmber::DataFrame.new(hash)
+df[:b..:c, "a"]
+# =>
+RedAmber::DataFrame : 3 observations(rows) of 3 variables(columns)
+Variables : 2 numeric, 1 string
+# key type   level data_preview
+1 :b  string     3 [A, B, C]
+2 :c  double     3 [1.0, 2.0, 3.0]
+3 :a  uint8      3 [1, 2, 3]
+```
 
-  `[index]`, `[range]`, `[array]`
+- [x] Select rows by `[]` as `[index]`, `[range]`, `[array]`
+  - Select a row by index: `df[0]`
+  - Select rows by indeces in a Range: `df[1..2]`
+  - Select rows by indeces in an Array: `df[1, 2]`
+  - Mixed case: `df[2, 0..]`
 
-- [x] Selecting rows from top or bottom
+- [x] Select rows from top or bottom
 
   `head(n=5)`, `tail(n=5)`, `first(n=1)`, `last(n=1)`
 
@@ -213,6 +246,8 @@ Or install it yourself as:
 
 - [x] `type`
 
+- [x] `data_type`
+
 - [ ] `each`
 
 - [ ] `chunked?`
@@ -324,7 +359,7 @@ Or install it yourself as:
 
 ## Development
 
-```
+```shell
 git clone https://github.com/heronshoes/red_amber.git
 cd red_amber
 bundle install

data/lib/red_amber/data_frame.rb

@@ -9,13 +9,13 @@ module RedAmber
     include DataFrameOutput
 
     def initialize(*args)
-      # accepts: DataFrame.new, DataFrame.new([]), DataFrame.new(nil)
+      # DataFrame.new, DataFrame.new([]), DataFrame.new({}), DataFrame.new(nil)
       #   returns empty DataFrame
       @table = Arrow::Table.new({}, [])
       # bug in gobject-introspection: ruby-gnome/ruby-gnome#1472
       #  [Arrow::Table] == [nil] shows ArgumentError
       #  temporary use yoda condition to workaround
-      return if args.empty? || args == [[]] || [nil] == args
+      return if args.empty? || args == [[]] || args == [{}] || [nil] == args
 
       if args.size > 1
         @table = Arrow::Table.new(*args)
@@ -26,11 +26,9 @@ module RedAmber
           when Arrow::Table then arg
           when DataFrame then arg.table
           when Rover::DataFrame then Arrow::Table.new(arg.to_h)
-          when Hash
-            args << [] if arg.empty? # create empty df from DataFrame.new({})
-            Arrow::Table.new(*args)
+          when Hash then Arrow::Table.new(arg)
           else
-            raise DataFrameTypeError, "invalid argument: #{args}"
+            raise DataFrameTypeError, "invalid argument: #{arg}"
           end
       end
     end
@@ -69,10 +67,15 @@ module RedAmber
     alias_method :keys, :column_names
     alias_method :header, :column_names
 
-    def types(class_name: false)
+    def types
       @table.columns.map do |column|
-        r = column.data_type
-        class_name ? r.class : r.to_s.to_sym
+        column.data_type.to_s.to_sym
+      end
+    end
+
+    def data_types
+      @table.columns.map do |column|
+        column.data_type.class
       end
     end
 

data/lib/red_amber/data_frame_output.rb

@@ -35,7 +35,7 @@ module RedAmber
         "#{self.class} : #{nrow} observation#{r}(row#{r}) of #{ncol} variable#{c}(column#{c})"
 
       # 2nd row: show var counts by type
-      type_groups = types(class_name: true).map { |t| type_group(t) }
+      type_groups = data_types.map { |t| type_group(t) }
 
       stringio.puts "Variable#{pl(ncol)} : #{var_type_count(type_groups).join(', ')}"
 

data/lib/red_amber/data_frame_selectable.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module RedAmber
-  # mix-ins for the class DataFrame
+  # mix-in for the class DataFrame
   module DataFrameSelectable
     # select columns: [symbol] or [string]
     # select rows: [array of index], [range]
@@ -12,25 +12,25 @@ module RedAmber
       # expand Range like [1..3, 4] to [1, 2, 3, 4]
       expanded =
         args.each_with_object([]) do |e, a|
-          e.is_a?(Range) ? a.concat(e.to_a) : a.append(e)
+          e.is_a?(Range) ? a.concat(normalized_array(e)) : a.append(e)
         end
 
       return select_rows(expanded) if integers?(expanded)
       return select_columns(expanded.map(&:to_sym)) if sym_or_str?(expanded)
 
-      raise DataFrameArgumentError, "invalid argument #{args}"
+      raise DataFrameArgumentError, "Invalid argument #{args}"
     end
 
     def head(n_rows = 5)
-      raise DataFrameArgumentError, "index is out of range #{n_rows}" if n_rows.negative?
+      raise DataFrameArgumentError, "Index is out of range #{n_rows}" if n_rows.negative?
 
       self[0...[n_rows, size].min]
     end
 
     def tail(n_rows = 5)
-      raise DataFrameArgumentError, "index is out of range #{n_rows}" if n_rows.negative?
+      raise DataFrameArgumentError, "Index is out of range #{n_rows}" if n_rows.negative?
 
-      self[-[n_rows, size].min..-1]
+      self[-[n_rows, size].min..]
     end
 
     def first(n_rows = 1)
@@ -52,14 +52,27 @@ module RedAmber
     end
 
     def select_rows(indeces)
-      if out_of_range?(indeces)
-        raise DataFrameArgumentError, "invalid index: #{indeces} for [0..#{size - 1}]"
-      end
+      out_of_range?(indeces) && raise(DataFrameArgumentError, "Invalid index: #{indeces} for 0..#{size - 1}")
 
       a = indeces.map { |i| @table.slice(i).to_a }
       DataFrame.new(@table.schema, a)
     end
 
+    def normalized_array(range)
+      both_end = [range.begin, range.end]
+      both_end[1] -= 1 if range.exclude_end? && range.end.is_a?(Integer)
+
+      if both_end.any?(Integer) || both_end.all?(&:nil?)
+        if both_end.any? { |e| e&.>=(size) || e&.<(-size) }
+          raise DataFrameArgumentError, "Index out of range: #{range} for 0..#{size - 1}"
+        end
+
+        (0...size).to_a[range]
+      else
+        range.to_a
+      end
+    end
+
     def out_of_range?(indeces)
       indeces.max >= size || indeces.min < -size
     end

data/lib/red_amber/vector.rb

@@ -49,6 +49,10 @@ module RedAmber
       @data.value_type.nick.to_sym
     end
 
+    def data_type
+      @data.value_type
+    end
+
     # def each() end
 
     def chunked?

data/lib/red_amber/vector_functions.rb

@@ -164,7 +164,7 @@ module RedAmber
         when Rover::Vector
           func.execute([data, other.to_a])
         else
-          raise ArgumentError, "operand is not supported: #{other.class}"
+          raise ArgumentError, "Operand is not supported: #{other.class}"
         end
       options[:aggregate] ? output.value : Vector.new(output.value)
     end

data/lib/red_amber/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RedAmber
-  VERSION = '0.1.1'
+  VERSION = '0.1.2'
 end

data/red_amber.gemspec

@@ -6,10 +6,10 @@ Gem::Specification.new do |spec|
   spec.name = 'red_amber'
   spec.version = RedAmber::VERSION
   spec.authors = ['Hirokazu SUZUKI (heronshoes)']
-  spec.email = ['63298319+heronshoes@users.noreply.github.com']
+  spec.email = ['heronshoes877@gmail.com']
 
-  spec.summary = 'Simple data frames for Ruby'
-  spec.description = 'Powered by Red Arrow and simple API similar to Rover-df'
+  spec.summary = 'Simple dataframe library for Ruby'
+  spec.description = 'RedAmber is a simple dataframe library powered by Red Arrow with simple API similar to Rover-df.'
   spec.homepage = 'https://github.com/heronshoes/red_amber'
   spec.license = 'MIT'
   spec.required_ruby_version = '>= 2.7'
@@ -30,8 +30,8 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'red-arrow', '~> 7.0.0'
-  spec.add_dependency 'red-parquet', '~> 7.0.0'
+  spec.add_dependency 'red-arrow', '>= 7.0.0'
+  spec.add_dependency 'red-parquet', '>= 7.0.0'
   spec.add_dependency 'rover-df', '~> 0.3.0'
 
   # Development dependency has gone to the Gemfile (rubygems/bundler#7237)

metadata

@@ -1,41 +1,41 @@
 --- !ruby/object:Gem::Specification
 name: red_amber
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Hirokazu SUZUKI (heronshoes)
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-05-06 00:00:00.000000000 Z
+date: 2022-05-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: red-arrow
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: 7.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: 7.0.0
 - !ruby/object:Gem::Dependency
   name: red-parquet
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: 7.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: 7.0.0
 - !ruby/object:Gem::Dependency
@@ -52,9 +52,10 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.3.0
-description: Powered by Red Arrow and simple API similar to Rover-df
+description: RedAmber is a simple dataframe library powered by Red Arrow with simple
+  API similar to Rover-df.
 email:
-- 63298319+heronshoes@users.noreply.github.com
+- heronshoes877@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -102,5 +103,5 @@ requirements: []
 rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
-summary: Simple data frames for Ruby
+summary: Simple dataframe library for Ruby
 test_files: []