Class: CADataFrame
- Inherits:
-
Object
- Object
- CADataFrame
- Defined in:
- lib/carray/dataframe/dataframe.rb,
lib/R.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb,
lib/carray/dataframe/dataframe.rb
Overview
PIVOT TABLE
Defined Under Namespace
Classes: Arranger
Instance Attribute Summary collapse
-
#column_names ⇒ Object
readonly
Attributes.
-
#column_number ⇒ Object
readonly
Attributes.
-
#columns ⇒ Object
readonly
Attributes.
-
#row_index ⇒ Object
readonly
Attributes.
-
#row_number ⇒ Object
readonly
Attributes.
Class Method Summary collapse
- .concat(*args) ⇒ Object
- .from_csv(*args, &block) ⇒ Object
- .from_R_data_frame(obj) ⇒ Object
- .load_csv(*args, &block) ⇒ Object
- .load_sqlite3(*args) ⇒ Object
- .merge(*args) ⇒ Object
Instance Method Summary collapse
- #-@ ⇒ Object
- #<(other) ⇒ Object
- #<=(other) ⇒ Object
- #>(other) ⇒ Object
- #>=(other) ⇒ Object
-
#[](*argv) ⇒ Object
Referencing.
-
#[]=(*argv) ⇒ Object
Setting Values.
- #__methods__ ⇒ Object
- #add_suffix(suf) ⇒ Object
- #append(name, new_column = nil, &block) ⇒ Object
-
#arrange(&block) ⇒ Object
Arrange.
- #as_r ⇒ Object
- #ascii_table(rowmax = :full) ⇒ Object
- #ca(*names) ⇒ Object
- #calculate(label, &block) ⇒ Object
- #classify(name, scale = nil, opt = {}) ⇒ Object
-
#column(name_or_index) ⇒ Object
(also: #col)
Column, Row Access.
- #column_types ⇒ Object
- #columns_to_hash(key_name, value_names) ⇒ Object
- #cross(name1, name2) ⇒ Object
- #detouch! ⇒ Object
- #downcase ⇒ Object
-
#each_column(&block) ⇒ Object
Iterators.
- #each_column_name(&block) ⇒ Object
- #each_row(with: Array, &block) ⇒ Object
- #each_row_index(&block) ⇒ Object
- #each_row_with_row_index(with: Array, &block) ⇒ Object
-
#eliminate_columns(*names) ⇒ Object
Transformation.
- #execute(&block) ⇒ Object
- #fill(*names, value) ⇒ Object
- #group_by(*names) ⇒ Object
- #has_column?(name) ⇒ Boolean
- #histogram(name, scale = nil, options = nil) ⇒ Object
- #index ⇒ Object
-
#initialize(columns_or_table, row_index: nil, column_names: nil, &block) ⇒ CADataFrame
constructor
Constructor.
- #inspect ⇒ Object
- #is_finite ⇒ Object
- #is_masked ⇒ Object
- #join(table, on: nil) ⇒ Object
- #lead(name, new_column = nil, &block) ⇒ Object
- #matchup(keyname, reference) ⇒ Object
- #merge(*args) ⇒ Object
- #method(hash) ⇒ Object
- #method_missing(name, *args) ⇒ Object
- #objectify ⇒ Object
- #order_by(*names, &block) ⇒ Object
- #pivot(name1, name2) ⇒ Object
- #rename(name1, name2) ⇒ Object
- #reorder(&block) ⇒ Object
- #replace(other) ⇒ Object
- #resample(&block) ⇒ Object
- #reverse ⇒ Object
- #row(idx) ⇒ Object
- #select(*names, &block) ⇒ Object
- #to_ary ⇒ Object
- #to_ca(*names) ⇒ Object
- #to_csv(io = "", option = {}, rs: $/, sep: ",", fill: "", with_row_index: true, &block) ⇒ Object
- #to_daru ⇒ Object
-
#to_df ⇒ Object
Conversions.
- #to_hash ⇒ Object
- #to_s ⇒ Object
- #to_sql(tablename) ⇒ Object
- #to_sqlite3(*args) ⇒ Object
- #to_xlsx(filename, sheet_name: 'Sheet1', with_row_index: false, &block) ⇒ Object
- #transpose(column_names: nil) ⇒ Object
- #unmask(value = nil) ⇒ Object
-
#unmask!(value = nil) ⇒ Object
Maintenance.
- #vacant_copy ⇒ Object
- #where(mask, value) ⇒ Object
Constructor Details
#initialize(columns_or_table, row_index: nil, column_names: nil, &block) ⇒ CADataFrame
Constructor
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
# File 'lib/carray/dataframe/dataframe.rb', line 35 def initialize (columns_or_table, row_index: nil, column_names: nil, &block) case columns_or_table when Hash columns = columns_or_table @column_names = columns.keys.map(&:to_s) @columns = normalize_columns(columns) @row_number = @columns.first[1].size if @column_names.any?{ |key| @columns[key].size != @row_number } raise "column sizes mismatch" end when CArray table = columns_or_table if column_names @column_names = column_names.map(&:to_s) else if table.respond_to?(:column_names) @column_names = table.column_names.map(&:to_s) else raise "data table (CArray) has no method 'column_names'." end end @columns = table_to_columns(table) @row_number = table.dim0 else raise "unknown data" end if row_index @row_index = row_index.to_ca.object else @row_index = nil end @__methods__ = {} if block_given? arrange(&block) end end |
Dynamic Method Handling
This class handles dynamic methods through the method_missing method
#method_missing(name, *args) ⇒ Object
167 168 169 170 171 172 173 174 175 176 177 178 179 |
# File 'lib/carray/dataframe/dataframe.rb', line 167 def method_missing (name, *args) if args.size == 0 name = name.to_s if has_column?(name) return @columns[name] elsif has_column?(name.gsub(/_/,'.')) ### For R return @columns[name.gsub(/_/,'.')] elsif @__methods__.include?(name) return @columns[@__methods__[name]] end end raise "no method '#{name}' for CADataFrame" end |
Instance Attribute Details
#column_names ⇒ Object (readonly)
Attributes
121 122 123 |
# File 'lib/carray/dataframe/dataframe.rb', line 121 def column_names @column_names end |
#column_number ⇒ Object (readonly)
Attributes
121 122 123 |
# File 'lib/carray/dataframe/dataframe.rb', line 121 def column_number @column_number end |
#columns ⇒ Object (readonly)
Attributes
121 122 123 |
# File 'lib/carray/dataframe/dataframe.rb', line 121 def columns @columns end |
#row_index ⇒ Object (readonly)
Attributes
121 122 123 |
# File 'lib/carray/dataframe/dataframe.rb', line 121 def row_index @row_index end |
#row_number ⇒ Object (readonly)
Attributes
121 122 123 |
# File 'lib/carray/dataframe/dataframe.rb', line 121 def row_number @row_number end |
Class Method Details
.concat(*args) ⇒ Object
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 |
# File 'lib/carray/dataframe/dataframe.rb', line 1003 def self.concat (*args) ref = args.first column_names = ref.column_names new_columns = {} column_names.each do |name| list = args.map{|t| t.col(name) } data_type = list.first.data_type new_columns[name] = CArray.bind(data_type, list, 0) end if args.map(&:row_index).all? new_row_index = CArray.join(*args.map(&:row_index)) else new_row_index = nil end return CADataFrame.new(new_columns, row_index: new_row_index) end |
.from_csv(*args, &block) ⇒ Object
1583 1584 1585 |
# File 'lib/carray/dataframe/dataframe.rb', line 1583 def self.from_csv (*args, &block) return CArray.from_csv(*args, &block).to_dataframe.arrange{ maskout nil, *column_names } end |
.from_R_data_frame(obj) ⇒ Object
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
# File 'lib/R.rb', line 292 def self.from_R_data_frame (obj) r = R.instance RSRuby.set_default_mode(RSRuby::PROC_CONVERSION) r.proc_table[lambda{|x| true }] = R::CONVERTER dataframe = obj column_names = r.colnames(obj).to_a column_names = [column_names].flatten row_names = r.attr(obj, 'row.names') columns = {} column_names.each do |name| value = r['$'].call(obj, name.to_s) case value when CArray columns[name] = value when Array columns[name] = value.to_ca else columns[name] = [value].to_ca end end column_names.each do |name| column = columns[name] column.maskout!(nil) end return CADataFrame.new(columns, row_index: row_names ? row_names.to_ca : nil) end |
.load_csv(*args, &block) ⇒ Object
1579 1580 1581 |
# File 'lib/carray/dataframe/dataframe.rb', line 1579 def self.load_csv (*args, &block) return CArray.load_csv(*args, &block).to_dataframe.arrange{ maskout nil, *column_names } end |
.load_sqlite3(*args) ⇒ Object
1574 1575 1576 |
# File 'lib/carray/dataframe/dataframe.rb', line 1574 def self.load_sqlite3 (*args) return CArray.load_sqlite3(*args).to_dataframe.arrange{ maskout nil, *column_names } end |
.merge(*args) ⇒ Object
992 993 994 995 996 997 998 999 1000 1001 |
# File 'lib/carray/dataframe/dataframe.rb', line 992 def self.merge (*args) ref = args.first new_columns = {} args.each do |table| table.column_names.each do |name| new_columns[name] = table.col(name) end end return CADataFrame.new(new_columns, row_index: ref.row_index) end |
Instance Method Details
#-@ ⇒ Object
1093 1094 1095 |
# File 'lib/carray/dataframe/dataframe.rb', line 1093 def -@ return cmp(:-@) end |
#<(other) ⇒ Object
1097 1098 1099 |
# File 'lib/carray/dataframe/dataframe.rb', line 1097 def < (other) return cmp(:<, other) end |
#<=(other) ⇒ Object
1101 1102 1103 |
# File 'lib/carray/dataframe/dataframe.rb', line 1101 def <= (other) return cmp(:<=, other) end |
#>(other) ⇒ Object
1105 1106 1107 |
# File 'lib/carray/dataframe/dataframe.rb', line 1105 def > (other) return cmp(:>, other) end |
#>=(other) ⇒ Object
1109 1110 1111 |
# File 'lib/carray/dataframe/dataframe.rb', line 1109 def >= (other) return cmp(:>=, other) end |
#[](*argv) ⇒ Object
Referencing
257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 |
# File 'lib/carray/dataframe/dataframe.rb', line 257 def [] (*argv) row, col = *argv new_columns = {} if col.is_a?(NilClass) case row when CADataFrame each_column_name do |key| if row.has_column?(key) new_columns[key] = column(key).maskout(row.column(key)) else new_columns[key] = column(key).to_ca end end return CADataFrame.new(new_columns, row_index: row.row_index ? row.row_index : nil) when String return self[nil,row] when Array if row.all?{|s| s.is_a?(String) } return self[nil,row] else @column_names.each do |key| new_columns[key] = @columns[key][row] end end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[row] : nil) else if row.is_a?(Integer) row = [row] end @column_names.each do |key| new_columns[key] = @columns[key][row] end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[row] : nil) end else if row.is_a?(Integer) row = [row] end case col when String, Symbol key = col.to_s if has_column?(key) return column(key)[row] else raise "unknow column name '#{key}'" end when Array if col.all?{|s| s.is_a?(String) } col.each do |key| key = key.to_s if has_column?(key) new_columns[key] = column(key)[row] else raise "unknow column name '#{key}'" end end else keys = @column_names.to_ca[col].to_a keys.each do |key| new_columns[key] = column(key)[row] end end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[row] : nil) else if col.is_a?(Integer) col = [col] end keys = @column_names.to_ca[col].to_a keys.each do |key| new_columns[key] = column(key)[row] end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[row] : nil) end end end |
#[]=(*argv) ⇒ Object
Setting Values
337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 |
# File 'lib/carray/dataframe/dataframe.rb', line 337 def []= (*argv) value = argv.pop row, col = *argv case col when NilClass case row when CADataFrame each_column_name do |key| if row.has_column?(key) column(key)[row.column(key)] = value end end when String self[nil,row] = value else col = @column_names.to_a self[row,col] = value end when String, Symbol key = col.to_s if has_column?(key) column(key)[row] = value else arrange { append key, value } end when Array col.each do |key| key = key.to_s if has_column?(key) column(key)[row] = value else raise "unknow column name '#{key}'" end end else if col.is_a?(Integer) col = [col] end keys = @column_names.to_ca[col].to_a keys.each do |key| column(key)[row] = value end end return value end |
#__methods__ ⇒ Object
72 73 74 |
# File 'lib/carray/dataframe/dataframe.rb', line 72 def __methods__ return @__methods__ end |
#add_suffix(suf) ⇒ Object
622 623 624 625 626 627 628 629 |
# File 'lib/carray/dataframe/dataframe.rb', line 622 def add_suffix (suf) new_columns = {} each_column_name do |name| new_name = (name.to_s + suf).to_s new_columns[new_name] = column(name) end return CADataFrame.new(new_columns, row_index: @row_index) end |
#append(name, new_column = nil, &block) ⇒ Object
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 |
# File 'lib/carray/dataframe/dataframe.rb', line 434 def append (name, new_column = nil, &block) if new_column # do nothing elsif block new_column = instance_exec(&block) else new_column = @columns.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.push(name) @columns[name] = new_column return new_column end |
#arrange(&block) ⇒ Object
Arrange
407 408 409 |
# File 'lib/carray/dataframe/dataframe.rb', line 407 def arrange (&block) return Arranger.new(self).arrange(&block) end |
#as_r ⇒ Object
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 |
# File 'lib/R.rb', line 319 def as_r r = R.instance new_columns = {} @column_names.each do |name| column = @columns[name] if column.has_mask? case column.guess_column_type_for_R when "integer" column = column.unmask_copy(R.NA_integer_) when "numeric" column = column.unmask_copy(R.NA_real_) else column = column.unmask_copy(R.NA_character_) end end new_columns[name] = R.__converter__(column.to_a) end mode = RSRuby.get_default_mode RSRuby.set_default_mode(RSRuby::NO_CONVERSION) return r.as_data_frame(:x => new_columns) ensure RSRuby.set_default_mode(mode) end |
#ascii_table(rowmax = :full) ⇒ Object
722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 |
# File 'lib/carray/dataframe/dataframe.rb', line 722 def ascii_table (rowmax = :full) if @row_index namelist = [" "] + @column_names tbl = CADFArray.new(namelist, @columns.clone.update(" " => @row_index)) else namelist = [" "] + @column_names tbl = CADFArray.new(namelist, @columns.clone.update(" " => CArray.int(@row_number).seq)) end if rowmax.is_a?(Integer) and @row_number > rowmax list = tbl[0..(rowmax/2),nil].to_a list.push namelist.map { "..." } list.push *(tbl[-rowmax/2+1..-1,nil].to_a) tbl = list.to_ca end datastr = tbl.convert {|c| __obj_to_string__(c) }.unmask("") datamb = datastr.convert(:boolean, &:"ascii_only?").not.sum(0).ne(0) namemb = namelist.to_ca.convert(:boolean) {|c| c.to_s.ascii_only? }.eq(0) mb = datamb.or(namemb) namelen = namelist.map(&:length).to_ca datalen = datastr.convert(&:length) if mb.max == 0 if datalen.size == 0 lengths = namelen.to_a else lengths = datalen.max(0).pmax(namelen).to_a end hrule = "-" + lengths.map {|len| "-"*len}.join("--") + "-" header = " " + [namelist, lengths].transpose.map{|name, len| "#{name.to_s.ljust(len)}" }.join(" ") + " " ary = [hrule, header, hrule] if datalen.size > 0 datastr[:i,nil].each_with_index do |blk, i| list = blk.flatten.to_a ary << " " + [list, lengths].transpose.map{|value, len| "#{value.ljust(len)}"}.join(" ") + " " end end ary << hrule return "DataFrame: rows#=#{@row_number}: \n" + ary.join("\n") else namewidth = namelist.to_ca.convert{|c| __strwidth__(c.to_s) } if datalen.size == 0 maxwidth = namewidth else datawidth = datastr.convert{|c| __strwidth__(c.to_s) } maxwidth = datawidth.max(0).pmax(namewidth) end len = maxwidth[:*,nil] - datawidth + datalen hrule = "-" + maxwidth.map {|len| "-"*len}.join("--") + "-" header = " " + [namelist, maxwidth.to_a].transpose.map{|name, len| "#{name.to_s.ljust(len-__strwidth__(name.to_s)+name.to_s.length)}" }.join(" ") + " " ary = [hrule, header, hrule] if datalen.size > 0 datastr[:i,nil].each_with_addr do |blk, i| list = blk.flatten.to_a ary << " " + list.map.with_index {|value, j| "#{value.ljust(len[i,j])}"}.join(" ") + " " end end ary << hrule return "DataFrame: row#=#{@row_number}: \n" + ary.join("\n") end end |
#ca(*names) ⇒ Object
651 652 653 654 655 656 657 |
# File 'lib/carray/dataframe/dataframe.rb', line 651 def ca (*names) if names.empty? return CADFArray.new(@column_names, @columns) else return CADFArray.new(names.map(&:to_s), @columns) end end |
#calculate(label, &block) ⇒ Object
488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 |
# File 'lib/carray/dataframe/dataframe.rb', line 488 def calculate (label, &block) hash = {} each_column_name do |name| begin if block hash[name] = [yield(name, column(name))] else hash[name] = [column(name).send(label.intern)] end rescue hash[name] = [UNDEF] end end return CADataFrame.new(hash, row_index: [label]) end |
#classify(name, scale = nil, opt = {}) ⇒ Object
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 |
# File 'lib/carray/dataframe/dataframe.rb', line 1181 def classify (name, scale = nil, opt = {}) if not scale column = @columns[name.to_s] mids = column.uniq mapper = {} mids.each_with_index do |v,i| mapper[v] = i end cls = columns.convert(:int32) {|v| mapper[v] } hash = { "#{name}_M" => mids, "#{name}_L" => mids, "#{name}_R" => mids, "#{name}_CLASS" => cls } else option = { :include_upper => false, :include_lowest => true, :offset => 0, }.update(opt) column = @columns[name.to_s] cls = scale.bin(column, option[:include_upper], option[:include_lowest], option[:offset]) mids = ((scale + scale.shifted(-1))/2)[0..-2].to_ca left = scale[0..-2] right = scale.shift(-1)[0..-2] hash = { "#{name}_M" => mids.project(cls).to_ca, "#{name}_L" => left.project(cls).to_ca, "#{name}_R" => right.project(cls).to_ca, "#{name}_CLASS" => cls } end return CADataFrame.new(hash) end |
#column(name_or_index) ⇒ Object Also known as: col
Column, Row Access
135 136 137 138 139 140 141 142 |
# File 'lib/carray/dataframe/dataframe.rb', line 135 def column (name_or_index) case name_or_index when Integer return @columns[@column_names[name_or_index]] when String, Symbol return @columns[name_or_index.to_s] end end |
#column_types ⇒ Object
127 128 129 |
# File 'lib/carray/dataframe/dataframe.rb', line 127 def column_types return @columns_names.map{|name| @columns[name].data_type_name } end |
#columns_to_hash(key_name, value_names) ⇒ Object
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 |
# File 'lib/carray/dataframe/dataframe.rb', line 671 def columns_to_hash (key_name, value_names) hash = {} unless @column_names.include?(key_name) raise ArgumentError, "include invalid key column name #{key_name}" end case value_names when String unless @column_names.include?(value_names) raise ArgumentError, "invalid key column name #{value_names}" end key_columns = @columns[key_name] value_columns = @columns[value_names] @row_number.times do |i| hash[key_columns[i]] = value_columns[i] end when Array unless value_names.all?{|s| @column_names.include?(s) } raise ArgumentError, "include invalid column name in #{value_names.join(' ')}" end key_columns = @columns[key_name] value_columns = @columns.values_at(*value_names) @row_number.times do |i| hash[key_columns[i]] = value_columns.map{|c| c[i]} end else raise ArgumentError, "invalud argument" end return hash end |
#cross(name1, name2) ⇒ Object
1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 |
# File 'lib/carray/dataframe/dataframe.rb', line 1220 def cross (name1, name2) col1 = column(name1) col2 = column(name2) var1 = col1.uniq.sort var2 = col2.uniq.sort hash = {} count = Hash.new {0} var1.each do |v1| var2.each do |v2| hash[[v1,v2]] = 0 end end list = CArray.join([col1, col2]).to_a list.each do |item| hash[item] += 1 end out = CArray.object(var1.size, var2.size) { 0 } var1.each_with_index do |v1, i| var2.each_with_index do |v2, j| out[i,j] = hash[[v1,v2]] end end return CADataFrame.new(out, row_index: var1, column_names: var2) end |
#detouch! ⇒ Object
546 547 548 549 550 551 552 553 554 555 |
# File 'lib/carray/dataframe/dataframe.rb', line 546 def detouch! @columns = @columns.clone each_column_name do |name| @columns[name] = @columns[name].to_ca end if @row_index @row_index = @row_index.clone end return self end |
#downcase ⇒ Object
422 423 424 425 426 427 428 429 430 431 432 |
# File 'lib/carray/dataframe/dataframe.rb', line 422 def downcase new_column_names = [] new_columns = {} each_column_name do |name| new_column_names << name.downcase new_columns[name.downcase] = column(name) end @column_names = new_column_names @columns = new_columns return self end |
#each_column(&block) ⇒ Object
Iterators
186 187 188 |
# File 'lib/carray/dataframe/dataframe.rb', line 186 def each_column (&block) return @columns.each(&block) end |
#each_column_name(&block) ⇒ Object
190 191 192 |
# File 'lib/carray/dataframe/dataframe.rb', line 190 def each_column_name (&block) return @column_names.each(&block) end |
#each_row(with: Array, &block) ⇒ Object
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
# File 'lib/carray/dataframe/dataframe.rb', line 202 def each_row (with: Array, &block) if with == Array @row_number.times do |i| yield @columns.map{|n,c| c[i] } end elsif with == Hash row = {} @row_number.times do |i| @column_names.each do |c| row[c] = @columns[c][i] end yield row end else raise "invalid data type for loop variable" end end |
#each_row_index(&block) ⇒ Object
194 195 196 197 198 199 200 |
# File 'lib/carray/dataframe/dataframe.rb', line 194 def each_row_index (&block) if @row_index @row_index.each(&block) else @row_number.times(&block) end end |
#each_row_with_row_index(with: Array, &block) ⇒ Object
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 |
# File 'lib/carray/dataframe/dataframe.rb', line 220 def each_row_with_row_index (with: Array, &block) if with == Array if @row_index @row_index.each_with_index do |idx, i| yield @columns.map{|n,c| c[i] }, idx end else @row_number.times do |i| yield @columns.map{|n,c| c[i] }, i end end elsif with == Hash row = {} if @row_index @row_index.each_with_index do |idx, i| @column_names.each do |c| row[c] = @columns[c][i] end yield row, @row_index[i] end else @row_number.times do |idx, i| @column_names.each do |c| row[c] = @columns[c][i] end yield row, @row_index[i] end end else raise "invalid data type for loop variable" end end |
#eliminate_columns(*names) ⇒ Object
Transformation
561 562 563 564 565 566 567 568 569 570 571 572 573 |
# File 'lib/carray/dataframe/dataframe.rb', line 561 def eliminate_columns (*names) if names.empty? return self end names = names.map(&:to_s) new_columns = {} each_column_name do |name| unless names.include?(name) new_columns[name] = column(name) end end return CADataFrame.new(new_columns, row_index: @row_index) end |
#execute(&block) ⇒ Object
484 485 486 |
# File 'lib/carray/dataframe/dataframe.rb', line 484 def execute (&block) return instance_exec(&block) end |
#fill(*names, value) ⇒ Object
394 395 396 397 398 399 400 401 |
# File 'lib/carray/dataframe/dataframe.rb', line 394 def fill (*names, value) names.each do |name| if has_column?(name) column(name).fill(value) end end return self end |
#group_by(*names) ⇒ Object
1256 1257 1258 1259 1260 1261 1262 |
# File 'lib/carray/dataframe/dataframe.rb', line 1256 def group_by (*names) if names.size == 1 return CADataFrameGroup.new(self, names[0]) else return CADataFrameGroupMulti.new(self, *names) end end |
#has_column?(name) ⇒ Boolean
123 124 125 |
# File 'lib/carray/dataframe/dataframe.rb', line 123 def has_column?(name) return @column_names.include?(name) end |
#histogram(name, scale = nil, options = nil) ⇒ Object
1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 |
# File 'lib/carray/dataframe/dataframe.rb', line 1161 def histogram (name, scale = nil, = nil) if scale.nil? return group_by(name).table{ { :count => col(name).count_valid } } else if hist = CAHistogram.int(scale, ) else hist = CAHistogram.int(scale) end hist.increment(@columns[name.to_s]) hash = { name.to_s => hist.midpoints[0], "#{name}_L".to_s => scale[0..-2], "#{name}_R".to_s => scale.shift(-1)[0..-2], :count => hist[0..-2].to_ca, } return CADataFrame.new(hash) end end |
#index ⇒ Object
155 156 157 |
# File 'lib/carray/dataframe/dataframe.rb', line 155 def index return CArray.int(@row_number).seq end |
#inspect ⇒ Object
789 790 791 |
# File 'lib/carray/dataframe/dataframe.rb', line 789 def inspect return ascii_table(10) end |
#is_finite ⇒ Object
1117 1118 1119 |
# File 'lib/carray/dataframe/dataframe.rb', line 1117 def is_finite return cmp(:is_finite) end |
#is_masked ⇒ Object
1113 1114 1115 |
# File 'lib/carray/dataframe/dataframe.rb', line 1113 def is_masked return cmp(:is_masked) end |
#join(table, on: nil) ⇒ Object
1158 1159 |
# File 'lib/carray/dataframe/dataframe.rb', line 1158 def join (table, on: nil) end |
#lead(name, new_column = nil, &block) ⇒ Object
453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 |
# File 'lib/carray/dataframe/dataframe.rb', line 453 def lead (name, new_column = nil, &block) if new_column # do nothing elsif block new_column = instance_exec(&block) else new_column = @columns.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.unshift(name) @columns[name] = new_column return new_column end |
#matchup(keyname, reference) ⇒ Object
1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 |
# File 'lib/carray/dataframe/dataframe.rb', line 1137 def matchup (keyname, reference) key = column(keyname.to_s) idx = reference.matchup(key) new_columns = {} each_column_name do |name| if name == keyname new_columns[name] = reference else new_columns[name] = column(name).project(idx) end end if @row_index new_row_index = @row_index.project(idx).unmask(nil) else new_row_index = nil end return CADataFrame.new(new_columns, row_index: new_row_index) { self.send(keyname)[] = reference } end |
#merge(*args) ⇒ Object
480 481 482 |
# File 'lib/carray/dataframe/dataframe.rb', line 480 def merge (*args) return CADataFrame.merge(self, *args) end |
#method(hash) ⇒ Object
159 160 161 162 163 164 165 |
# File 'lib/carray/dataframe/dataframe.rb', line 159 def method (hash) new_hash = {} hash.each do |key, value| new_hash[key.to_s] = value.to_s end @__methods__.update(new_hash) end |
#objectify ⇒ Object
643 644 645 646 647 648 649 |
# File 'lib/carray/dataframe/dataframe.rb', line 643 def objectify new_columns = {} each_column_name do |name| new_columns[name] = column(name).object end return CADataFrame.new(new_columns, row_index: @row_index) end |
#order_by(*names, &block) ⇒ Object
584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 |
# File 'lib/carray/dataframe/dataframe.rb', line 584 def order_by (*names, &block) if names.empty? if block ret = instance_exec(&block) case ret when CArray list = [ret] when Array list = ret end end else list = @columns.values_at(*names.map{|s| s.to_s}) end return reorder { CA.sort_addr(*list) } end |
#pivot(name1, name2) ⇒ Object
1427 1428 1429 |
# File 'lib/carray/dataframe/dataframe.rb', line 1427 def pivot (name1, name2) return CADataFramePivot.new(self, name1, name2) end |
#rename(name1, name2) ⇒ Object
411 412 413 414 415 416 417 418 419 420 |
# File 'lib/carray/dataframe/dataframe.rb', line 411 def rename (name1, name2) if idx = @column_names.index(name1.to_s) @column_names[idx] = name2.to_s column = @columns[name1.to_s] @columns.delete(name1.to_s) @columns[name2.to_s] = column else raise "unknown column name #{name1}" end end |
#reorder(&block) ⇒ Object
575 576 577 578 579 580 581 582 |
# File 'lib/carray/dataframe/dataframe.rb', line 575 def reorder (&block) index = instance_exec(&block) new_columns = {} each_column_name do |name| new_columns[name] = column(name)[index] end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[index] : nil) end |
#replace(other) ⇒ Object
76 77 78 79 80 81 82 83 |
# File 'lib/carray/dataframe/dataframe.rb', line 76 def replace (other) @column_names = other.column_names @columns = other.columns @row_index = other.row_index @row_number = other.row_number @__methors__ = other.__methods__ return self end |
#resample(&block) ⇒ Object
504 505 506 507 508 509 510 511 512 513 |
# File 'lib/carray/dataframe/dataframe.rb', line 504 def resample (&block) new_columns = {} each_column_name do |name| begin new_columns[name] = yield(name, column(name)) rescue end end return CADataFrame.new(new_columns) end |
#reverse ⇒ Object
601 602 603 604 605 606 607 |
# File 'lib/carray/dataframe/dataframe.rb', line 601 def reverse new_columns = {} each_column_name do |name| new_columns[name] = column(name).reverse end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index.reverse : nil) end |
#row(idx) ⇒ Object
146 147 148 149 150 151 152 153 |
# File 'lib/carray/dataframe/dataframe.rb', line 146 def row (idx) if @row_index addr = @row_index.search(idx) return @column_names.map{|name| @columns[name][addr]}.to_ca else return @column_names.map{|name| @columns[name][idx]}.to_ca end end |
#select(*names, &block) ⇒ Object
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 |
# File 'lib/carray/dataframe/dataframe.rb', line 515 def select (*names, &block) if names.empty? names = @column_names end if block row = instance_exec(&block) else row = nil end new_columns = {} names.map(&:to_s).each do |name| new_columns[name] = column(name)[row] end return CADataFrame.new(new_columns, row_index: @row_index ? @row_index[row] : nil) end |
#to_ary ⇒ Object
797 798 799 |
# File 'lib/carray/dataframe/dataframe.rb', line 797 def to_ary return [to_s] end |
#to_ca(*names) ⇒ Object
659 660 661 |
# File 'lib/carray/dataframe/dataframe.rb', line 659 def to_ca (*names) return ca(*names).to_ca end |
#to_csv(io = "", option = {}, rs: $/, sep: ",", fill: "", with_row_index: true, &block) ⇒ Object
1587 1588 1589 1590 1591 1592 1593 1594 1595 |
# File 'lib/carray/dataframe/dataframe.rb', line 1587 def to_csv (io = "", option = {}, rs: $/, sep: ",", fill: "", with_row_index: true, &block) if @row_index and with_row_index namelist = [""] + @column_names tbl = CADFArray.new(namelist, @columns.clone.update("" => @row_index)) else tbl = ca.to_ca end return tbl.to_csv(io, option, rs: rs, sep: sep, fill: fill, &block) end |
#to_daru ⇒ Object
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 |
# File 'lib/carray/dataframe/dataframe.rb', line 1597 def to_daru require "daru" columns = {} each_column_name do |name| columns[name] = column(name).to_a end if @row_index return Daru::DataFrame.new(columns, index: @row_index.to_a, order: @column_names) else return Daru::DataFrame.new(columns, order: @column_names) end end |
#to_df ⇒ Object
Conversions
635 636 637 638 639 640 641 |
# File 'lib/carray/dataframe/dataframe.rb', line 635 def to_df new_columns = {} each_column_name do |name| new_columns[name] = column(name) end return CADataFrame.new(new_columns, row_index: @row_index).detouch! end |
#to_hash ⇒ Object
663 664 665 666 667 668 669 |
# File 'lib/carray/dataframe/dataframe.rb', line 663 def to_hash hash = {} @columns.each do |k,v| hash[k] = v.to_a end return hash end |
#to_s ⇒ Object
793 794 795 |
# File 'lib/carray/dataframe/dataframe.rb', line 793 def to_s return ascii_table end |
#to_sql(tablename) ⇒ Object
1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 |
# File 'lib/carray/dataframe/dataframe.rb', line 1511 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 |
#to_sqlite3(*args) ⇒ Object
1507 1508 1509 |
# File 'lib/carray/dataframe/dataframe.rb', line 1507 def to_sqlite3 (*args) self.ca.to_sqlite3(*args) end |
#to_xlsx(filename, sheet_name: 'Sheet1', with_row_index: false, &block) ⇒ Object
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 |
# File 'lib/carray/dataframe/dataframe.rb', line 1610 def to_xlsx (filename, sheet_name: 'Sheet1', with_row_index: false, &block) require "axlsx" xl = Axlsx::Package.new xl.use_shared_strings = true sheet = xl.workbook.add_worksheet(name: sheet_name) df = self.to_df.objectify.unmask("=NA()") if with_row_index sheet.add_row([""] + column_names) df.each_row_with_row_index(with: Array) do |list, i| sheet.add_row([i] + list) end else sheet.add_row(column_names) df.each_row(with: Array) do |list| sheet.add_row(list) end end if block_given? yield sheet end xl.serialize(filename) end |
#transpose(column_names: nil) ⇒ Object
609 610 611 612 613 614 615 616 617 618 619 620 |
# File 'lib/carray/dataframe/dataframe.rb', line 609 def transpose (column_names: nil) if column_names column_names = header.map(&:to_s) else if @row_index column_names = @row_index.convert(:object) {|v| v.to_s } else column_names = CArray.object(@row_number).seq("a",:succ) end end return CADataFrame.new(ca.transpose, row_index: @column_names.to_ca, column_names: column_names) end |
#unmask(value = nil) ⇒ Object
542 543 544 |
# File 'lib/carray/dataframe/dataframe.rb', line 542 def unmask (value = nil) return to_df.unmask!(value) end |
#unmask!(value = nil) ⇒ Object
Maintenance
535 536 537 538 539 540 |
# File 'lib/carray/dataframe/dataframe.rb', line 535 def unmask! (value = nil) each_column_name do |name| column(name).unmask(value) end return self end |
#vacant_copy ⇒ Object
472 473 474 475 476 477 478 |
# File 'lib/carray/dataframe/dataframe.rb', line 472 def vacant_copy new_columns = {} each_column_name do |key| new_columns[key] = CArray.object(0) end return CADataFrame.new(new_columns) end |
#where(mask, value) ⇒ Object
385 386 387 388 389 390 391 392 |
# File 'lib/carray/dataframe/dataframe.rb', line 385 def where (mask, value) mask.column_names.each do |key| if has_column?(key) column(key)[mask.column(key).boolean.not] = value end end return value end |