carray-dataframe 1.1.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c0561562238eb969944e6e7977f3cdc4edbe3370187ea1f7ba01a2f6af60bf40
-  data.tar.gz: 738a716a1b5055fefb8b182dd26a3a9ac559563072b02df151bf16eab652f245
+  metadata.gz: 00a3f769c9096380db116cb74660aebc6451f5508029c8e97d720ed254b9847b
+  data.tar.gz: 6e810823d0ee16ef2a7a60295b983ffdb46ccb83591c49b19c0285a49c14d4cb
 SHA512:
-  metadata.gz: 320b6326fb40b111bc601c38d0e2a5a917434dedfd96f9830c4d24dd66df507d7450d30027829f2a832c0673c69bbe20cb7bb5201adad4cc41728505ecbea9d3
-  data.tar.gz: 4bd51f6c826a561dbb108aa57988520ca870fc02d8615babaa65644ca4869dd781b48c6015b19ba5235943fa7d793d0789ced918ae3675b9f4ae3aef0eb0aaf7
+  metadata.gz: 14880525aec99af0ba133d08eb19ec0715f2be56777593cdccb21f7e54ab4c0c51335ffaf557f86621f0eda815e6859dc4bc18465f7f74355f3f7365c7abfadd
+  data.tar.gz: '028c8109f1ada33196663884043c44134491ce58649a5e9341f91e616f9edbb113fbc202965782bf762bf398d483ce12fdd18cf0d511cce03237f4ad174cb612'

data/carray-dataframe.gemspec

@@ -1,6 +1,6 @@
 
 Gem::Specification::new do |s|
-  version = "1.1.1"
+  version = "1.2.0"
 
   files = Dir.glob("**/*") - [ 
                                Dir.glob("carray-dataframe*.gem"), 
@@ -22,6 +22,6 @@ Gem::Specification::new do |s|
   s.files       = files
   s.required_ruby_version = ">= 1.8.1"
   s.add_runtime_dependency 'carray', '~> 1.5'
-  s.add_runtime_dependency 'axlsx', '~> 2.0'
+  s.add_runtime_dependency 'caxlsx', '~> 3.0'
   s.add_runtime_dependency 'spreadsheet', '~> 1.1'
 end

data/lib/carray-dataframe.rb

@@ -1,4 +1,5 @@
 require "carray-timeindex"
+require "carray-io-csv"
 require "carray-dataframe/dataframe"
 require "carray-dataframe/reference"
 require "carray-dataframe/loc_accessor"

data/lib/carray-dataframe/converter.rb

@@ -73,7 +73,7 @@ class CADataFrame
   end
 
   def to_xlsx (filename, sheet_name: 'Sheet1', with_row_index: false, &block)
-    require "axlsx"
+    require "caxlsx"
     xl = Axlsx::Package.new
     xl.use_shared_strings = true
     sheet = xl.workbook.add_worksheet(name: sheet_name)

data/lib/carray-dataframe/dataframe.rb

@@ -28,7 +28,11 @@ class CADataFrame
         @column_names = columns.map(&:to_s)
       else
         if data.respond_to?(:column_names)
-          @column_names = data.column_names.map(&:to_s)
+          if data.column_names.is_a?(Array)
+            @column_names = data.column_names.map(&:to_s)
+          else
+            @column_names = data.dim1.times.map{|i| "c#{i}" }
+          end
         elsif order
           @column_names = order.map(&:to_s)
         else
@@ -88,9 +92,13 @@ class CADataFrame
     end
 
     # Sets @row_number and check column length
-    @row_number   = @column_data.first[1].size
-    if @column_names.any?{ |key| @column_data[key].size != @row_number }
-      raise "column sizes mismatch"
+    if @column_data.empty? and index
+      @row_number = index.size
+    else
+      @row_number   = @column_data.first[1].size
+      if @column_names.any?{ |key| @column_data[key].size != @row_number }
+        raise "column sizes mismatch"
+      end
     end
 
     # Processing option 'index'
@@ -206,6 +214,10 @@ class CADataFrame
     end
   end
 
+  def has_index?
+    @row_index ? true : false
+  end
+
   def replace (other)
     @column_names = other.column_names
     @column_data  = other.column_data
@@ -215,8 +227,13 @@ class CADataFrame
     return self
   end
 
-  def has_column?(name)
-    return @column_names.include?(name)
+  def has_column? (name)
+    case name.to_s
+    when "index"
+      return has_index?
+    else
+      return @column_names.include?(name)
+    end
   end
 
   def column_types
@@ -239,6 +256,18 @@ class CADataFrame
   end
   alias col column
 
+  def set_column (spec, col)
+    case spec
+    when Integer
+      return @column_data[@column_names[spec]] = col
+    when String, Symbol
+      return @column_data[spec.to_s] = col
+    else
+      raise "invalid column specifier"
+    end
+  end
+  private set_column
+
   def loc
     @loc ||= CADataFrame::LocAccessor.new(self)
     return @loc 
@@ -429,10 +458,11 @@ class CADataFrame
   end
 
   def append_column (name, new_column = nil, &block)
+    name = name.to_s
     if new_column
       # do nothing
     elsif block
-      new_column = instance_exec(&block)
+      new_column = instance_exec(self, &block)
     else
       new_column = @column_data.first[1].template(:object)
     end
@@ -442,18 +472,39 @@ class CADataFrame
     if new_column.rank != 1 or new_column.size != @row_number
       raise "invalid shape of appended column"
     end
-    @column_names.push(name.to_s)
-    @column_data[name.to_s] = new_column
+    @column_names.push(name)
+    @column_data[name] = new_column
+    return new_column
+  end
+
+  def insert_column (pos, name, new_column = nil, &block)
+    name = name.to_s
+    if new_column
+      # do nothing
+    elsif block
+      new_column = instance_exec(self, &block)
+    else
+      new_column = @column_data.first[1].template(:object)
+    end
+    unless new_column.is_a?(CArray)
+      new_column = new_column.to_ca
+    end
+    if new_column.rank != 1 or new_column.size != @row_number
+      raise "invalid shape of appended column"
+    end
+    @column_names.insert(pos, name)
+    @column_data[name] = new_column
     return new_column
   end
 
   alias append append_column
 
   def prepend_column (name, new_column = nil, &block)
+    name = name.to_s
     if new_column
       # do nothing
     elsif block
-      new_column = instance_exec(&block)
+      new_column = instance_exec(self, &block)
     else
       new_column = @column_data.first[1].template(:object)
     end
@@ -463,8 +514,8 @@ class CADataFrame
     if new_column.rank != 1 or new_column.size != @row_number
       raise "invalid shape of appended column"
     end
-    @column_names.unshift(name.to_s)
-    @column_data[name.to_s] = new_column
+    @column_names.unshift(name)
+    @column_data[name] = new_column
     return new_column
   end
 
@@ -572,6 +623,7 @@ class CADataFrame
     end
     new_columns = {}
     names.map(&:to_s).each do |name|
+      raise "unknown column '#{name}'" unless column(name)
       new_columns[name] = column(name)[row]
     end
     return CADataFrame.new(new_columns, index: @row_index ? @row_index[row] : nil)
@@ -977,11 +1029,11 @@ end
 class CADataFrame
 
   def matchup (keyname, reference)
-    key = column(keyname.to_s)
+    key = column(keyname)
     idx = reference.matchup(key)
     new_columns = {}
     each_column_name do |name|
-      if name == keyname
+      if name == keyname.to_s
         new_columns[name] = reference
       else
         new_columns[name] = column(name).project(idx)
@@ -992,9 +1044,7 @@ class CADataFrame
     else
       new_row_index = nil
     end
-    return CADataFrame.new(new_columns, index: new_row_index) {
-      self.send(keyname)[] = reference
-    }
+    return CADataFrame.new(new_columns, index: new_row_index)
   end
 
   def histogram (name, scale = nil, options = nil)

data/lib/carray-dataframe/io.rb

@@ -4,6 +4,8 @@
 #
 ######################################
 require "spreadsheet"
+require "carray-io-sqlite3"
+
 class CArray
 
   def save_excel (filename, &block)
@@ -42,8 +44,8 @@ class CADataFrame
     end
   end
 
-  def self.load_csv (file, sep: ",", rs: $/, encoding: nil, index: nil, &block)
-    df = CArray.load_csv(file, sep: sep, rs: rs, encoding: encoding, &block).to_dataframe(index: index)
+  def self.read_csv (file, sep: ",", rs: $/, quote_char: '"', encoding: nil, index: nil, &block)
+    df = CArray.read_csv(file, sep: sep, rs: rs, quote_char: quote_char, encoding: encoding, &block).to_dataframe(index: index)
     if df
       return df.arrange{ 
         column_names.each do |name|
@@ -55,8 +57,13 @@ class CADataFrame
     end
   end
 
-  def self.from_csv (file, sep: ",", rs: $/, index: nil, &block)
-    df = CArray.from_csv(file, sep: sep, rs: rs, &block).to_dataframe(index: index)
+  def self.load_csv (file, sep: ",", rs: $/, encoding: nil, quote_char: '"', index: nil, &block)
+    warn "CADataFrame.load_csv will be obsolete, use CADataFrame.read_csv"
+    self.read_csv(file, sep: sep, rs: rs, quote_char: quote_char, encoding: encoding, &block)
+  end
+
+  def self.parse_csv (file, sep: ",", rs: $/, quote_char: '"', index: nil, &block)
+    df = CArray.parse_csv(file, sep: sep, rs: rs, quote_char: quote_char, &block).to_dataframe(index: index)
     if df
       return df.arrange{ 
         column_names.each do |name|
@@ -68,8 +75,14 @@ class CADataFrame
     end
   end
 
-  def to_sqlite3 (*args)
-    self.to_ca.to_sqlite3(*args)
+  def self.from_csv (file, sep: ",", rs: $/, quote_char: '"', index: nil, &block)
+    warn "CADataFrame.from_csv will be obsolete, use CADataFrame.parse_csv"
+    self.parse_csv(file, sep: sep, rs: rs, index: index, &block)
+  end
+
+
+  def to_sqlite3 (**args)
+    self.to_ca.to_sqlite3(**args)
   end
 
   def to_sql (tablename)

data/lib/carray-dataframe/io.rb~

@@ -0,0 +1,96 @@
+######################################
+#
+#  IO methods
+#
+######################################
+require "spreadsheet"
+class CArray
+
+  def save_excel (filename, &block)
+    if self.rank >= 3
+      raise "too large rank (>2) to write excel file"
+    end
+    book = Spreadsheet::Workbook.new
+    worksheet = book.create_worksheet
+    self.dim0.times do |i|
+      worksheet.row(i).push *self[i,nil]
+    end
+    if block
+      block.call(worksheet)
+    end
+    book.write(filename)
+  end
+
+  def self.load_excel (filename, sheet=0)
+    book = Spreadsheet.open(filename)
+    sheet = book.worksheet(sheet)
+    return sheet.map(&:to_a).to_ca
+  end
+end
+class CADataFrame
+
+  def self.load_sqlite3 (*args)
+    df = CArray.load_sqlite3(*args).to_dataframe
+    if df
+      return df.arrange{ 
+        column_names.each do |name|
+          mask name, nil
+        end
+      }
+    else
+      return nil
+    end
+  end
+
+  def self.load_csv (file, sep: ",", rs: $/, encoding: nil, index: nil, &block)
+    df = CArray.load_csv(file, sep: sep, rs: rs, encoding: encoding, &block).to_dataframe(index: index)
+    if df
+      return df.arrange{ 
+        column_names.each do |name|
+          mask name, nil
+        end
+      }
+    else
+      return nil
+    end
+  end
+
+  def self.from_csv (file, sep: ",", rs: $/, index: nil, &block)
+    df = CArray.from_csv(file, sep: sep, rs: rs, &block).to_dataframe(index: index)
+    if df
+      return df.arrange{ 
+        column_names.each do |name|
+          mask name, nil
+        end
+      }
+    else
+      return nil
+    end
+  end
+
+  def to_sqlite3 (*args)
+    self.to_ca.to_sqlite3(*args)
+  end
+
+  def to_sql (tablename)
+    if @column_names.any?{ |s| s =~ /[\. \-]/ }
+      columns = {}
+      each_column_name do |name|
+        name2 = name.gsub(/[\. \-]/, '_')
+        columns[name2] = column(name)
+      end
+      df = CADataFrame.new(columns)
+      return df.to_sqlite3(database: ":memory:", table: tablename)
+    else
+      return to_sqlite3(database: ":memory:", table: tablename)
+    end
+  end
+end
+module SQLite3
+  class Database
+
+    def to_df (expr)
+      return CADataFrame.load_sqlite3 self, expr
+    end
+  end
+end

data/lib/carray-dataframe/join.rb

@@ -27,7 +27,9 @@ class CADataFrame
     CADataFrame::Merge.join(self, other_df, opts)
   end
 end
+
 class CADataFrame
+
     class MergeFrame
       class NilSorter
         include Comparable
@@ -65,7 +67,12 @@ class CADataFrame
           rkey = first_right_key
           row(lkey, rkey).tap { |r| res << r if r }
         end
-        CADataFrame.new(res, order: dataframe_vector_names)
+        df = CADataFrame.new(res, order: dataframe_vector_names)
+        if dataframe_vector_names.include?("index")
+          df.set_index("index")
+        else
+          df
+        end
       end
       private
       attr_reader :on, :indicator,

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: carray-dataframe
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.2.0
 platform: ruby
 authors:
 - Hiroki Motoyoshi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-09-09 00:00:00.000000000 Z
+date: 2021-06-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: carray
@@ -25,19 +25,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.5'
 - !ruby/object:Gem::Dependency
-  name: axlsx
+  name: caxlsx
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: spreadsheet
   requirement: !ruby/object:Gem::Requirement
@@ -70,6 +70,7 @@ files:
 - lib/carray-dataframe/group.rb
 - lib/carray-dataframe/iloc_accessor.rb
 - lib/carray-dataframe/io.rb
+- lib/carray-dataframe/io.rb~
 - lib/carray-dataframe/join.rb
 - lib/carray-dataframe/loc_accessor.rb
 - lib/carray-dataframe/pivot.rb