red_amber 0.4.2 → 0.5.1

data/lib/red_amber/data_frame_displayable.rb

@@ -269,12 +269,13 @@ module RedAmber
     end
     alias_method :glimpse, :tdr
 
-    # Shortcut for `tdr(:all)``.
+    # Shortcut for `tdr(:all)`.
     #
+    # @param (see #tdr)
     # @return (see #tdr)
     #
-    def tdra
-      puts tdr_str(:all)
+    def tdra(tally: 5, elements: 5)
+      puts tdr_str(:all, tally: tally, elements: elements)
     end
 
     # rubocop:enable Layout/LineLength
@@ -504,9 +505,9 @@ module RedAmber
           row.zip(formats).map do |elem, format|
             non_ascii_diff = elem.ascii_only? ? 0 : elem.width - elem.size
             if format.negative?
-              elem.ljust(-format + non_ascii_diff)
+              elem.ljust(-format - non_ascii_diff)
             else
-              elem.rjust(format + non_ascii_diff)
+              elem.rjust(format - non_ascii_diff)
             end
           end
         str.puts a.join(' ').rstrip
@@ -539,7 +540,7 @@ module RedAmber
             in ''
               '""'
             in String
-              element.sub(/^(\s+)$/, '"\1"') # blank spaces
+              element.sub(/\A(\s+)$/, '"\1"') # blank spaces
             in Float
               format('%g', element)
             in Integer

data/lib/red_amber/data_frame_loadsave.rb

@@ -44,7 +44,7 @@ module RedAmber
       #   BUFFER
       #
       # @example Load from a Buffer skipping comment line
-      #   DataFrame.load(Arrow::Buffer.new(<<~BUFFER), format: :csv, skip_lines: /^#/)
+      #   DataFrame.load(Arrow::Buffer.new(<<~BUFFER), format: :csv, skip_lines: /\A#/)
       #     # comment
       #     name,age
       #     Yasuko,68

data/lib/red_amber/data_frame_selectable.rb

@@ -39,7 +39,7 @@ module RedAmber
     #     penguins[:bill_length_mm]
     #
     #     # =>
-    #     #<RedAmber::Vector(:double, size=344):0x00000000000104dc>
+    #     #<RedAmber::Vector(:double, size=344, chunked):0x0000000000008f0c>
     #     [39.1, 39.5, 40.3, nil, 36.7, 39.3, 38.9, 39.2, 34.1, 42.0, 37.8, 37.8, 41.1, ... ]
     #
     # @overload [](keys)
@@ -173,7 +173,7 @@ module RedAmber
     #   penguins.v(:bill_length_mm)
     #
     #   # =>
-    #   #<RedAmber::Vector(:double, size=344):0x000000000000f140>
+    #   #<RedAmber::Vector(:double, size=344, chunked):0x0000000000008f0c>
     #   [39.1, 39.5, 40.3, nil, 36.7, 39.3, 38.9, 39.2, 34.1, 42.0, 37.8, 37.8, 41.1, ... ]
     #
     def v(key)
@@ -836,6 +836,55 @@ module RedAmber
       tail(n_obs)
     end
 
+    # Select records randomly to create a DataFrame.
+    #   This method calls `indices.sample`.
+    #   We can use the same arguments in `Vector#sample`.
+    # @note This method requires 'arrow-numo-narray' gem.
+    #
+    # @overload sample()
+    #   Return a DataFrame with a randomly selected record.
+    #
+    #   @return [DataFrame]
+    #     a DataFrame with single record.
+    #
+    # @overload sample(n)
+    #   Return a DataFrame with n records selected at random.
+    #
+    #   @param n [Integer]
+    #     positive number of records to select.
+    #     If n is smaller or equal to size, records are selected by non-repeating.
+    #     If n is greater than `size`, records are selected repeatedly.
+    #   @return [DataFrame]
+    #     a DataFrame with sampled records.
+    #
+    # @overload sample(prop)
+    #   Return a DataFrame with records by proportion `prop` at random.
+    #
+    #   @param prop [Float]
+    #     positive proportion of records to select.
+    #     Absolute number of records to select:`prop*size` is rounded (by `half: :up`).
+    #     If prop is smaller or equal to 1.0, records are selected by non-repeating.
+    #     If prop is greater than 1.0, some records are selected repeatedly.
+    #   @return [Vector]
+    #     a DataFrame with sampled records.
+    #
+    # @since 0.5.0
+    #
+    def sample(n_or_prop = nil)
+      slice { indices.sample(n_or_prop) }
+    end
+
+    # Returns a DataFrame with shuffled rows.
+    #
+    # @note This method requires 'arrow-numo-narray' gem.
+    # @note Same behavior as `DataFrame#sample(1.0)`
+    # @return (see #sample)
+    # @since 0.5.0
+    #
+    def shuffle
+      sample(1.0)
+    end
+
     # Select records by index Array to create a DataFrame.
     #
     # - TODO: support for option `boundscheck: true`

data/lib/red_amber/data_frame_variable_operation.rb

@@ -44,7 +44,7 @@ module RedAmber
     #     languages[:Language]
     #
     #     # =>
-    #     #<RedAmber::Vector(:string, size=4):0x000000000010359c>
+    #     #<RedAmber::Vector(:string, size=4, chunked):0x000000000010359c>
     #     ["Ruby", "Python", "R", "Rust"]
     #
     # @overload pick(booleans)
@@ -512,8 +512,8 @@ module RedAmber
     #     1 Rui           49          78 (nil)
     #     2 Hinata        28          57 Momotaro
     #
-    def assign(*assigner, &block)
-      assign_update(*assigner, append_to_left: false, &block)
+    def assign(...)
+      assign_update(false, ...)
     end
 
     # Assign new or updated variables (columns) and create an updated DataFrame.
@@ -583,13 +583,13 @@ module RedAmber
     #   @return [DataFrame]
     #     assigned DataFrame.
     #
-    def assign_left(*assigner, &block)
-      assign_update(*assigner, append_to_left: true, &block)
+    def assign_left(...)
+      assign_update(true, ...)
     end
 
     private
 
-    def assign_update(*assigner, append_to_left: false, &block)
+    def assign_update(append_to_left, *assigner, &block)
       if block
         assigner_from_block = instance_eval(&block)
         assigner =