Class: Arrow::Table
- Inherits:
-
Object
- Object
- Arrow::Table
- Includes:
- ColumnContainable, RecordContainable
- Defined in:
- lib/arrow/table.rb
Class Method Summary collapse
Instance Method Summary collapse
- #each_record_batch ⇒ Object
-
#group(*keys) ⇒ Object
Experimental.
-
#initialize(*args) ⇒ Table
constructor
Creates a new Table.
- #inspect ⇒ Object
- #inspect_raw ⇒ Object
-
#merge(other) ⇒ Arrow::Table
TODO.
- #method_missing(name, *args, &block) ⇒ Object
- #pack ⇒ Object
- #remove_column(name_or_index) ⇒ Object
- #remove_column_raw ⇒ Object
- #respond_to_missing?(name, include_private) ⇒ Boolean
- #save(path, options = {}) ⇒ Object
-
#select_columns(*selectors, &block) ⇒ Arrow::Table
TODO.
- #slice(*args) ⇒ Object
- #slice_raw ⇒ Object
- #to_s(options = {}) ⇒ Object
- #to_s_raw ⇒ Object
-
#window(size: nil) ⇒ Object
Experimental.
Methods included from RecordContainable
Methods included from ColumnContainable
#columns, #each_column, #find_column
Constructor Details
#initialize(columns) ⇒ Table #initialize(raw_table) ⇒ Table #initialize(raw_table) ⇒ Table #initialize(raw_table) ⇒ Table #initialize(schema, columns) ⇒ Table #initialize(schema, arrays) ⇒ Table #initialize(schema, record_batches) ⇒ Table #initialize(schema, raw_records) ⇒ Table
Creates a new Arrow::Table.
170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 |
# File 'lib/arrow/table.rb', line 170 def initialize(*args) n_args = args.size case n_args when 1 if args[0][0].is_a?(Column) columns = args[0] fields = columns.collect(&:field) values = columns.collect(&:data) schema = Schema.new(fields) else raw_table = args[0] fields = [] values = [] raw_table.each do |name, array| array = ArrayBuilder.build(array) if array.is_a?(::Array) fields << Field.new(name.to_s, array.value_data_type) values << array end schema = Schema.new(fields) end when 2 schema = args[0] schema = Schema.new(schema) unless schema.is_a?(Schema) values = args[1] case values[0] when ::Array values = [RecordBatch.new(schema, values)] when Column values = values.collect(&:data) end else = "wrong number of arguments (given #{n_args}, expected 1..2)" raise ArgumentError, end initialize_raw(schema, values) end |
Dynamic Method Handling
This class handles dynamic methods through the method_missing method
#method_missing(name, *args, &block) ⇒ Object
508 509 510 511 512 513 514 |
# File 'lib/arrow/table.rb', line 508 def method_missing(name, *args, &block) if args.empty? column = find_column(name) return column if column end super end |
Class Method Details
.load(path, options = {}) ⇒ Object
28 29 30 |
# File 'lib/arrow/table.rb', line 28 def load(path, ={}) TableLoader.load(path, ) end |
Instance Method Details
#each_record_batch ⇒ Object
207 208 209 210 211 212 213 214 |
# File 'lib/arrow/table.rb', line 207 def each_record_batch return to_enum(__method__) unless block_given? reader = TableBatchReader.new(self) while record_batch = reader.read_next yield(record_batch) end end |
#group(*keys) ⇒ Object
Experimental
459 460 461 |
# File 'lib/arrow/table.rb', line 459 def group(*keys) Group.new(self, keys) end |
#inspect ⇒ Object
499 500 501 |
# File 'lib/arrow/table.rb', line 499 def inspect "#{super}\n#{to_s}" end |
#inspect_raw ⇒ Object
498 |
# File 'lib/arrow/table.rb', line 498 alias_method :inspect_raw, :inspect |
#merge(other) ⇒ Arrow::Table
TODO
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 |
# File 'lib/arrow/table.rb', line 352 def merge(other) added_columns = {} removed_columns = {} case other when Hash other.each do |name, value| name = name.to_s if value added_columns[name] = ensure_raw_column(name, value) else removed_columns[name] = true end end when Table added_columns = {} other.columns.each do |column| name = column.name added_columns[name] = ensure_raw_column(name, column) end else = "merge target must be Hash or Arrow::Table: " + "<#{other.inspect}>: #{inspect}" raise ArgumentError, end new_columns = [] columns.each do |column| column_name = column.name new_column = added_columns.delete(column_name) if new_column new_columns << new_column next end next if removed_columns.key?(column_name) new_columns << ensure_raw_column(column_name, column) end added_columns.each do |name, new_column| new_columns << new_column end new_fields = [] new_arrays = [] new_columns.each do |new_column| new_fields << new_column[:field] new_arrays << new_column[:data] end self.class.new(new_fields, new_arrays) end |
#pack ⇒ Object
473 474 475 476 477 478 |
# File 'lib/arrow/table.rb', line 473 def pack packed_arrays = columns.collect do |column| column.data.pack end self.class.new(schema, packed_arrays) end |
#remove_column(name_or_index) ⇒ Object
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 |
# File 'lib/arrow/table.rb', line 402 def remove_column(name_or_index) case name_or_index when String, Symbol name = name_or_index.to_s index = columns.index {|column| column.name == name} if index.nil? = "unknown column: #{name_or_index.inspect}: #{inspect}" raise KeyError.new() end else index = name_or_index index += n_columns if index < 0 if index < 0 or index >= n_columns = "out of index (0..#{n_columns - 1}): " + "#{name_or_index.inspect}: #{inspect}" raise IndexError.new() end end remove_column_raw(index) end |
#remove_column_raw ⇒ Object
401 |
# File 'lib/arrow/table.rb', line 401 alias_method :remove_column_raw, :remove_column |
#respond_to_missing?(name, include_private) ⇒ Boolean
503 504 505 506 |
# File 'lib/arrow/table.rb', line 503 def respond_to_missing?(name, include_private) return true if find_column(name) super end |
#save(path, options = {}) ⇒ Object
468 469 470 471 |
# File 'lib/arrow/table.rb', line 468 def save(path, ={}) saver = TableSaver.new(self, path, ) saver.save end |
#select_columns(*selectors, &block) ⇒ Arrow::Table
TODO
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 |
# File 'lib/arrow/table.rb', line 426 def select_columns(*selectors, &block) if selectors.empty? return to_enum(__method__) unless block_given? selected_columns = columns.select(&block) else selected_columns = [] selectors.each do |selector| case selector when String, Symbol column = find_column(selector) if column.nil? = "unknown column: #{selector.inspect}: #{inspect}" raise KeyError.new() end selected_columns << column when Range selected_columns.concat(columns[selector]) else column = columns[selector] if column.nil? = "out of index (0..#{n_columns - 1}): " + "#{selector.inspect}: #{inspect}" raise IndexError.new() end selected_columns << column end end selected_columns = selected_columns.select(&block) if block_given? end self.class.new(selected_columns) end |
#slice(offset, length) ⇒ Arrow::Table #slice(index) ⇒ Arrow::Record #slice(booleans) ⇒ Arrow::Table #slice(boolean_array) ⇒ Arrow::Table #slice(range) ⇒ Arrow::Table #slice {|slicer| ... } ⇒ Arrow::Table
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 |
# File 'lib/arrow/table.rb', line 270 def slice(*args) slicers = [] if block_given? unless args.empty? raise ArgumentError, "must not specify both arguments and block" end block_slicer = yield(Slicer.new(self)) case block_slicer when ::Array slicers.concat(block_slicer) else slicers << block_slicer end else expected_n_args = nil case args.size when 1 if args[0].is_a?(Integer) index = args[0] index += n_rows if index < 0 return nil if index < 0 return nil if index >= n_rows return Record.new(self, index) else slicers << args[0] end when 2 offset, length = args slicers << (offset...(offset + length)) else expected_n_args = "1..2" end if expected_n_args = "wrong number of arguments " + "(given #{args.size}, expected #{expected_n_args})" raise ArgumentError, end end ranges = [] slicers.each do |slicer| slicer = slicer.evaluate if slicer.respond_to?(:evaluate) case slicer when Integer slicer += n_rows if slicer < 0 ranges << [slicer, n_rows - 1] when Range original_from = from = slicer.first to = slicer.last to -= 1 if slicer.exclude_end? from += n_rows if from < 0 if from < 0 or from >= n_rows = "offset is out of range (-#{n_rows + 1},#{n_rows}): " + "#{original_from}" raise ArgumentError, end to += n_rows if to < 0 ranges << [from, to] when ::Array boolean_array_to_slice_ranges(slicer, 0, ranges) when ChunkedArray offset = 0 slicer.each_chunk do |array| boolean_array_to_slice_ranges(array, offset, ranges) offset += array.length end when BooleanArray boolean_array_to_slice_ranges(slicer, 0, ranges) else = "slicer must be Integer, Range, (from, to), " + "Arrow::ChunkedArray of Arrow::BooleanArray, " + "Arrow::BooleanArray or Arrow::Slicer::Condition: #{slicer.inspect}" raise ArgumentError, end end slice_by_ranges(ranges) end |
#slice_raw ⇒ Object
221 |
# File 'lib/arrow/table.rb', line 221 alias_method :slice_raw, :slice |
#to_s(options = {}) ⇒ Object
481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 |
# File 'lib/arrow/table.rb', line 481 def to_s(={}) format = [:format] case format when :column return to_s_raw when :list formatter_class = TableListFormatter when :table, nil formatter_class = TableTableFormatter else = ":format must be :column, :list, :table or nil" raise ArgumentError, "#{}: <#{format.inspect}>" end formatter = formatter_class.new(self, ) formatter.format end |
#to_s_raw ⇒ Object
480 |
# File 'lib/arrow/table.rb', line 480 alias_method :to_s_raw, :to_s |
#window(size: nil) ⇒ Object
Experimental
464 465 466 |
# File 'lib/arrow/table.rb', line 464 def window(size: nil) RollingWindow.new(self, size) end |