Module: Polars::IO
- Included in:
- Polars
- Defined in:
- lib/polars/io.rb
Instance Method Summary collapse
-
#read_avro(source, columns: nil, n_rows: nil) ⇒ DataFrame
Read into a DataFrame from Apache Avro format.
-
#read_csv(source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 8192, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, storage_options: nil, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false) ⇒ DataFrame
Read a CSV file into a DataFrame.
-
#read_csv_batched(source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 50_000, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false) ⇒ BatchedCsvReader
Read a CSV file in batches.
-
#read_database(query, schema_overrides: nil) ⇒ DataFrame
(also: #read_sql)
Read a SQL query into a DataFrame.
-
#read_ipc(source, columns: nil, n_rows: nil, memory_map: true, storage_options: nil, row_count_name: nil, row_count_offset: 0, rechunk: true) ⇒ DataFrame
Read into a DataFrame from Arrow IPC (Feather v2) file.
-
#read_ipc_schema(source) ⇒ Hash
Get a schema of the IPC file without reading data.
-
#read_json(source) ⇒ DataFrame
Read into a DataFrame from a JSON file.
-
#read_ndjson(source) ⇒ DataFrame
Read into a DataFrame from a newline delimited JSON file.
-
#read_parquet(source, columns: nil, n_rows: nil, storage_options: nil, parallel: "auto", row_count_name: nil, row_count_offset: 0, low_memory: false, use_statistics: true, rechunk: true) ⇒ DataFrame
Read into a DataFrame from a parquet file.
-
#read_parquet_schema(source) ⇒ Hash
Get a schema of the Parquet file without reading data.
-
#scan_csv(source, has_header: true, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, cache: true, with_column_names: nil, infer_schema_length: 100, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, parse_dates: false, eol_char: "\n", truncate_ragged_lines: false) ⇒ LazyFrame
Lazily read from a CSV file or multiple files via glob patterns.
-
#scan_ipc(source, n_rows: nil, cache: true, rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, memory_map: true) ⇒ LazyFrame
Lazily read from an Arrow IPC (Feather v2) file or multiple files via glob patterns.
-
#scan_ndjson(source, infer_schema_length: 100, batch_size: 1024, n_rows: nil, low_memory: false, rechunk: true, row_count_name: nil, row_count_offset: 0) ⇒ LazyFrame
Lazily read from a newline delimited JSON file.
-
#scan_parquet(source, n_rows: nil, cache: true, parallel: "auto", rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, low_memory: false) ⇒ LazyFrame
Lazily read from a parquet file or multiple files via glob patterns.
Instance Method Details
#read_avro(source, columns: nil, n_rows: nil) ⇒ DataFrame
Read into a DataFrame from Apache Avro format.
473 474 475 476 477 478 479 |
# File 'lib/polars/io.rb', line 473 def read_avro(source, columns: nil, n_rows: nil) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end DataFrame._read_avro(source, n_rows: n_rows, columns: columns) end |
#read_csv(source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 8192, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, storage_options: nil, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false) ⇒ DataFrame
This operation defaults to a rechunk
operation at the end, meaning that
all data will be stored continuously in memory.
Set rechunk: false
if you are benchmarking the csv-reader. A rechunk
is
an expensive operation.
Read a CSV file into a DataFrame.
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
# File 'lib/polars/io.rb', line 93 def read_csv( source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 8192, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, storage_options: nil, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false ) Utils._check_arg_is_1byte("sep", sep, false) Utils._check_arg_is_1byte("comment_char", comment_char, false) Utils._check_arg_is_1byte("quote_char", quote_char, true) Utils._check_arg_is_1byte("eol_char", eol_char, false) projection, columns = Utils.handle_projection_columns(columns) ||= {} if columns && !has_header columns.each do |column| if !column.start_with?("column_") raise ArgumentError, "Specified column names do not start with \"column_\", but autogenerated header names were requested." end end end if projection || new_columns raise Todo end df = nil _prepare_file_arg(source) do |data| df = DataFrame._read_csv( data, has_header: has_header, columns: columns || projection, sep: sep, comment_char: comment_char, quote_char: quote_char, skip_rows: skip_rows, dtypes: dtypes, null_values: null_values, ignore_errors: ignore_errors, parse_dates: parse_dates, n_threads: n_threads, infer_schema_length: infer_schema_length, batch_size: batch_size, n_rows: n_rows, encoding: encoding == "utf8-lossy" ? encoding : "utf8", low_memory: low_memory, rechunk: rechunk, skip_rows_after_header: skip_rows_after_header, row_count_name: row_count_name, row_count_offset: row_count_offset, sample_size: sample_size, eol_char: eol_char, truncate_ragged_lines: truncate_ragged_lines ) end if new_columns Utils._update_columns(df, new_columns) else df end end |
#read_csv_batched(source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 50_000, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false) ⇒ BatchedCsvReader
Read a CSV file in batches.
Upon creation of the BatchedCsvReader
,
polars will gather statistics and determine the
file chunks. After that work will only be done
if next_batches
is called.
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 |
# File 'lib/polars/io.rb', line 776 def read_csv_batched( source, has_header: true, columns: nil, new_columns: nil, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, parse_dates: false, n_threads: nil, infer_schema_length: 100, batch_size: 50_000, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, sample_size: 1024, eol_char: "\n", truncate_ragged_lines: false ) projection, columns = Utils.handle_projection_columns(columns) if columns && !has_header columns.each do |column| if !column.start_with?("column_") raise ArgumentError, "Specified column names do not start with \"column_\", but autogenerated header names were requested." end end end if projection || new_columns raise Todo end BatchedCsvReader.new( source, has_header: has_header, columns: columns || projection, sep: sep, comment_char: comment_char, quote_char: quote_char, skip_rows: skip_rows, dtypes: dtypes, null_values: null_values, ignore_errors: ignore_errors, parse_dates: parse_dates, n_threads: n_threads, infer_schema_length: infer_schema_length, batch_size: batch_size, n_rows: n_rows, encoding: encoding == "utf8-lossy" ? encoding : "utf8", low_memory: low_memory, rechunk: rechunk, skip_rows_after_header: skip_rows_after_header, row_count_name: row_count_name, row_count_offset: row_count_offset, sample_size: sample_size, eol_char: eol_char, new_columns: new_columns, truncate_ragged_lines: truncate_ragged_lines ) end |
#read_database(query, schema_overrides: nil) ⇒ DataFrame Also known as: read_sql
Read a SQL query into a DataFrame.
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 |
# File 'lib/polars/io.rb', line 620 def read_database(query, schema_overrides: nil) if !defined?(ActiveRecord) raise Error, "Active Record not available" end result = if query.is_a?(ActiveRecord::Result) query elsif query.is_a?(ActiveRecord::Relation) query.connection.select_all(query.to_sql) elsif query.is_a?(::String) ActiveRecord::Base.connection.select_all(query) else raise ArgumentError, "Expected ActiveRecord::Relation, ActiveRecord::Result, or String" end data = {} schema_overrides = (schema_overrides || {}).transform_keys(&:to_s) result.columns.each_with_index do |k, i| column_type = result.column_types[i] data[k] = if column_type result.rows.map { |r| column_type.deserialize(r[i]) } else result.rows.map { |r| r[i] } end polars_type = case column_type&.type when :binary Binary when :boolean Boolean when :date Date when :datetime, :timestamp Datetime when :decimal Decimal when :float Float64 when :integer Int64 when :string, :text String when :time Time # TODO fix issue with null # when :json, :jsonb # Struct end schema_overrides[k] ||= polars_type if polars_type end DataFrame.new(data, schema_overrides: schema_overrides) end |
#read_ipc(source, columns: nil, n_rows: nil, memory_map: true, storage_options: nil, row_count_name: nil, row_count_offset: 0, rechunk: true) ⇒ DataFrame
Read into a DataFrame from Arrow IPC (Feather v2) file.
505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 |
# File 'lib/polars/io.rb', line 505 def read_ipc( source, columns: nil, n_rows: nil, memory_map: true, storage_options: nil, row_count_name: nil, row_count_offset: 0, rechunk: true ) ||= {} _prepare_file_arg(source, **) do |data| DataFrame._read_ipc( data, columns: columns, n_rows: n_rows, row_count_name: row_count_name, row_count_offset: row_count_offset, rechunk: rechunk, memory_map: memory_map ) end end |
#read_ipc_schema(source) ⇒ Hash
Get a schema of the IPC file without reading data.
852 853 854 855 856 857 858 |
# File 'lib/polars/io.rb', line 852 def read_ipc_schema(source) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end Plr.ipc_schema(source) end |
#read_json(source) ⇒ DataFrame
Read into a DataFrame from a JSON file.
597 598 599 |
# File 'lib/polars/io.rb', line 597 def read_json(source) DataFrame._read_json(source) end |
#read_ndjson(source) ⇒ DataFrame
Read into a DataFrame from a newline delimited JSON file.
607 608 609 |
# File 'lib/polars/io.rb', line 607 def read_ndjson(source) DataFrame._read_ndjson(source) end |
#read_parquet(source, columns: nil, n_rows: nil, storage_options: nil, parallel: "auto", row_count_name: nil, row_count_offset: 0, low_memory: false, use_statistics: true, rechunk: true) ⇒ DataFrame
This operation defaults to a rechunk
operation at the end, meaning that
all data will be stored continuously in memory.
Set rechunk: false
if you are benchmarking the parquet-reader. A rechunk
is
an expensive operation.
Read into a DataFrame from a parquet file.
564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 |
# File 'lib/polars/io.rb', line 564 def read_parquet( source, columns: nil, n_rows: nil, storage_options: nil, parallel: "auto", row_count_name: nil, row_count_offset: 0, low_memory: false, use_statistics: true, rechunk: true ) _prepare_file_arg(source) do |data| DataFrame._read_parquet( data, columns: columns, n_rows: n_rows, parallel: parallel, row_count_name: row_count_name, row_count_offset: row_count_offset, low_memory: low_memory, use_statistics: use_statistics, rechunk: rechunk ) end end |
#read_parquet_schema(source) ⇒ Hash
Get a schema of the Parquet file without reading data.
866 867 868 869 870 871 872 |
# File 'lib/polars/io.rb', line 866 def read_parquet_schema(source) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end Plr.parquet_schema(source) end |
#scan_csv(source, has_header: true, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, cache: true, with_column_names: nil, infer_schema_length: 100, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, parse_dates: false, eol_char: "\n", truncate_ragged_lines: false) ⇒ LazyFrame
Lazily read from a CSV file or multiple files via glob patterns.
This allows the query optimizer to push down predicates and projections to the scan level, thereby potentially reducing memory overhead.
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
# File 'lib/polars/io.rb', line 250 def scan_csv( source, has_header: true, sep: ",", comment_char: nil, quote_char: '"', skip_rows: 0, dtypes: nil, null_values: nil, ignore_errors: false, cache: true, with_column_names: nil, infer_schema_length: 100, n_rows: nil, encoding: "utf8", low_memory: false, rechunk: true, skip_rows_after_header: 0, row_count_name: nil, row_count_offset: 0, parse_dates: false, eol_char: "\n", truncate_ragged_lines: false ) Utils._check_arg_is_1byte("sep", sep, false) Utils._check_arg_is_1byte("comment_char", comment_char, false) Utils._check_arg_is_1byte("quote_char", quote_char, true) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end LazyFrame._scan_csv( source, has_header: has_header, sep: sep, comment_char: comment_char, quote_char: quote_char, skip_rows: skip_rows, dtypes: dtypes, null_values: null_values, ignore_errors: ignore_errors, cache: cache, with_column_names: with_column_names, infer_schema_length: infer_schema_length, n_rows: n_rows, low_memory: low_memory, rechunk: rechunk, skip_rows_after_header: skip_rows_after_header, encoding: encoding, row_count_name: row_count_name, row_count_offset: row_count_offset, parse_dates: parse_dates, eol_char: eol_char, truncate_ragged_lines: truncate_ragged_lines ) end |
#scan_ipc(source, n_rows: nil, cache: true, rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, memory_map: true) ⇒ LazyFrame
Lazily read from an Arrow IPC (Feather v2) file or multiple files via glob patterns.
This allows the query optimizer to push down predicates and projections to the scan level, thereby potentially reducing memory overhead.
334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 |
# File 'lib/polars/io.rb', line 334 def scan_ipc( source, n_rows: nil, cache: true, rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, memory_map: true ) LazyFrame._scan_ipc( source, n_rows: n_rows, cache: cache, rechunk: rechunk, row_count_name: row_count_name, row_count_offset: row_count_offset, storage_options: , memory_map: memory_map ) end |
#scan_ndjson(source, infer_schema_length: 100, batch_size: 1024, n_rows: nil, low_memory: false, rechunk: true, row_count_name: nil, row_count_offset: 0) ⇒ LazyFrame
Lazily read from a newline delimited JSON file.
This allows the query optimizer to push down predicates and projections to the scan level, thereby potentially reducing memory overhead.
436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 |
# File 'lib/polars/io.rb', line 436 def scan_ndjson( source, infer_schema_length: 100, batch_size: 1024, n_rows: nil, low_memory: false, rechunk: true, row_count_name: nil, row_count_offset: 0 ) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end LazyFrame._scan_ndjson( source, infer_schema_length: infer_schema_length, batch_size: batch_size, n_rows: n_rows, low_memory: low_memory, rechunk: rechunk, row_count_name: row_count_name, row_count_offset: row_count_offset, ) end |
#scan_parquet(source, n_rows: nil, cache: true, parallel: "auto", rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, low_memory: false) ⇒ LazyFrame
Lazily read from a parquet file or multiple files via glob patterns.
This allows the query optimizer to push down predicates and projections to the scan level, thereby potentially reducing memory overhead.
384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 |
# File 'lib/polars/io.rb', line 384 def scan_parquet( source, n_rows: nil, cache: true, parallel: "auto", rechunk: true, row_count_name: nil, row_count_offset: 0, storage_options: nil, low_memory: false ) if Utils.pathlike?(source) source = Utils.normalise_filepath(source) end LazyFrame._scan_parquet( source, n_rows:n_rows, cache: cache, parallel: parallel, rechunk: rechunk, row_count_name: row_count_name, row_count_offset: row_count_offset, storage_options: , low_memory: low_memory ) end |