forked from apache/datafusion-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdataframe.py
More file actions
1171 lines (953 loc) · 42.8 KB
/
dataframe.py
File metadata and controls
1171 lines (953 loc) · 42.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
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
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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
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
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
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
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
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
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
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
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
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
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
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
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
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
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
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
""":py:class:`DataFrame` is one of the core concepts in DataFusion.
See :ref:`user_guide_concepts` in the online documentation for more information.
"""
from __future__ import annotations
import warnings
from typing import (
TYPE_CHECKING,
Any,
Iterable,
Literal,
Optional,
Union,
overload,
)
try:
from warnings import deprecated # Python 3.13+
except ImportError:
from typing_extensions import deprecated # Python 3.12
from datafusion._internal import DataFrame as DataFrameInternal
from datafusion._internal import ParquetColumnOptions as ParquetColumnOptionsInternal
from datafusion._internal import ParquetWriterOptions as ParquetWriterOptionsInternal
from datafusion.expr import Expr, SortExpr, sort_or_default
from datafusion.plan import ExecutionPlan, LogicalPlan
from datafusion.record_batch import RecordBatchStream
if TYPE_CHECKING:
import pathlib
from typing import Callable, Sequence
import pandas as pd
import polars as pl
import pyarrow as pa
from datafusion._internal import expr as expr_internal
from enum import Enum
# excerpt from deltalake
# https://github.com/apache/datafusion-python/pull/981#discussion_r1905619163
class Compression(Enum):
"""Enum representing the available compression types for Parquet files."""
UNCOMPRESSED = "uncompressed"
SNAPPY = "snappy"
GZIP = "gzip"
BROTLI = "brotli"
LZ4 = "lz4"
# lzo is not implemented yet
# https://github.com/apache/arrow-rs/issues/6970
# LZO = "lzo"
ZSTD = "zstd"
LZ4_RAW = "lz4_raw"
@classmethod
def from_str(cls: type[Compression], value: str) -> Compression:
"""Convert a string to a Compression enum value.
Args:
value: The string representation of the compression type.
Returns:
The Compression enum lowercase value.
Raises:
ValueError: If the string does not match any Compression enum value.
"""
try:
return cls(value.lower())
except ValueError as err:
valid_values = str([item.value for item in Compression])
error_msg = f"""
{value} is not a valid Compression.
Valid values are: {valid_values}
"""
raise ValueError(error_msg) from err
def get_default_level(self) -> Optional[int]:
"""Get the default compression level for the compression type.
Returns:
The default compression level for the compression type.
"""
# GZIP, BROTLI default values from deltalake repo
# https://github.com/apache/datafusion-python/pull/981#discussion_r1905619163
# ZSTD default value from delta-rs
# https://github.com/apache/datafusion-python/pull/981#discussion_r1904789223
if self == Compression.GZIP:
return 6
if self == Compression.BROTLI:
return 1
if self == Compression.ZSTD:
return 4
return None
class ParquetWriterOptions:
"""Advanced parquet writer options.
Allows settings the writer options that apply to the entire file. Some options can
also be set on a column by column basis, with the field ``column_specific_options``
(see ``ParquetColumnOptions``).
"""
def __init__(
self,
data_pagesize_limit: int = 1024 * 1024,
write_batch_size: int = 1024,
writer_version: str = "1.0",
skip_arrow_metadata: bool = False,
compression: Optional[str] = "zstd(3)",
compression_level: Optional[int] = None,
dictionary_enabled: Optional[bool] = True,
dictionary_page_size_limit: int = 1024 * 1024,
statistics_enabled: Optional[str] = "page",
max_row_group_size: int = 1024 * 1024,
created_by: str = "datafusion-python",
column_index_truncate_length: Optional[int] = 64,
statistics_truncate_length: Optional[int] = None,
data_page_row_count_limit: int = 20_000,
encoding: Optional[str] = None,
bloom_filter_on_write: bool = False,
bloom_filter_fpp: Optional[float] = None,
bloom_filter_ndv: Optional[int] = None,
allow_single_file_parallelism: bool = True,
maximum_parallel_row_group_writers: int = 1,
maximum_buffered_record_batches_per_stream: int = 2,
column_specific_options: Optional[dict[str, ParquetColumnOptions]] = None,
) -> None:
"""Initialize the ParquetWriterOptions.
Args:
data_pagesize_limit: Sets best effort maximum size of data page in bytes.
write_batch_size: Sets write_batch_size in bytes.
writer_version: Sets parquet writer version. Valid values are ``1.0`` and
``2.0``.
skip_arrow_metadata: Skip encoding the embedded arrow metadata in the
KV_meta.
compression: Compression type to use. Default is ``zstd(3)``.
Available compression types are
- ``uncompressed``: No compression.
- ``snappy``: Snappy compression.
- ``gzip(n)``: Gzip compression with level n.
- ``brotli(n)``: Brotli compression with level n.
- ``lz4``: LZ4 compression.
- ``lz4_raw``: LZ4_RAW compression.
- ``zstd(n)``: Zstandard compression with level n.
compression_level: Compression level to set.
dictionary_enabled: Sets if dictionary encoding is enabled. If ``None``,
uses the default parquet writer setting.
dictionary_page_size_limit: Sets best effort maximum dictionary page size,
in bytes.
statistics_enabled: Sets if statistics are enabled for any column Valid
values are ``none``, ``chunk``, and ``page``. If ``None``, uses the
default parquet writer setting.
max_row_group_size: Target maximum number of rows in each row group
(defaults to 1M rows). Writing larger row groups requires more memory
to write, but can get better compression and be faster to read.
created_by: Sets "created by" property.
column_index_truncate_length: Sets column index truncate length.
statistics_truncate_length: Sets statistics truncate length. If ``None``,
uses the default parquet writer setting.
data_page_row_count_limit: Sets best effort maximum number of rows in a data
page.
encoding: Sets default encoding for any column. Valid values are ``plain``,
``plain_dictionary``, ``rle``, ``bit_packed``, ``delta_binary_packed``,
``delta_length_byte_array``, ``delta_byte_array``, ``rle_dictionary``,
and ``byte_stream_split``. If ``None``, uses the default parquet writer
setting.
bloom_filter_on_write: Write bloom filters for all columns when creating
parquet files.
bloom_filter_fpp: Sets bloom filter false positive probability. If ``None``,
uses the default parquet writer setting
bloom_filter_ndv: Sets bloom filter number of distinct values. If ``None``,
uses the default parquet writer setting.
allow_single_file_parallelism: Controls whether DataFusion will attempt to
speed up writing parquet files by serializing them in parallel. Each
column in each row group in each output file are serialized in parallel
leveraging a maximum possible core count of
``n_files * n_row_groups * n_columns``.
maximum_parallel_row_group_writers: By default parallel parquet writer is
tuned for minimum memory usage in a streaming execution plan. You may
see a performance benefit when writing large parquet files by increasing
``maximum_parallel_row_group_writers`` and
``maximum_buffered_record_batches_per_stream`` if your system has idle
cores and can tolerate additional memory usage. Boosting these values is
likely worthwhile when writing out already in-memory data, such as from
a cached data frame.
maximum_buffered_record_batches_per_stream: See
``maximum_parallel_row_group_writers``.
column_specific_options: Overrides options for specific columns. If a column
is not a part of this dictionary, it will use the parameters provided
here.
"""
self.data_pagesize_limit = data_pagesize_limit
self.write_batch_size = write_batch_size
self.writer_version = writer_version
self.skip_arrow_metadata = skip_arrow_metadata
if compression_level is not None:
self.compression = f"{compression}({compression_level})"
else:
self.compression = compression
self.dictionary_enabled = dictionary_enabled
self.dictionary_page_size_limit = dictionary_page_size_limit
self.statistics_enabled = statistics_enabled
self.max_row_group_size = max_row_group_size
self.created_by = created_by
self.column_index_truncate_length = column_index_truncate_length
self.statistics_truncate_length = statistics_truncate_length
self.data_page_row_count_limit = data_page_row_count_limit
self.encoding = encoding
self.bloom_filter_on_write = bloom_filter_on_write
self.bloom_filter_fpp = bloom_filter_fpp
self.bloom_filter_ndv = bloom_filter_ndv
self.allow_single_file_parallelism = allow_single_file_parallelism
self.maximum_parallel_row_group_writers = maximum_parallel_row_group_writers
self.maximum_buffered_record_batches_per_stream = (
maximum_buffered_record_batches_per_stream
)
self.column_specific_options = column_specific_options
class ParquetColumnOptions:
"""Parquet options for individual columns.
Contains the available options that can be applied for an individual Parquet column,
replacing the global options in ``ParquetWriterOptions``.
"""
def __init__(
self,
encoding: Optional[str] = None,
dictionary_enabled: Optional[bool] = None,
compression: Optional[str] = None,
statistics_enabled: Optional[str] = None,
bloom_filter_enabled: Optional[bool] = None,
bloom_filter_fpp: Optional[float] = None,
bloom_filter_ndv: Optional[int] = None,
) -> None:
"""Initialize the ParquetColumnOptions.
Args:
encoding: Sets encoding for the column path. Valid values are: ``plain``,
``plain_dictionary``, ``rle``, ``bit_packed``, ``delta_binary_packed``,
``delta_length_byte_array``, ``delta_byte_array``, ``rle_dictionary``,
and ``byte_stream_split``. These values are not case-sensitive. If
``None``, uses the default parquet options
dictionary_enabled: Sets if dictionary encoding is enabled for the column
path. If `None`, uses the default parquet options
compression: Sets default parquet compression codec for the column path.
Valid values are ``uncompressed``, ``snappy``, ``gzip(level)``, ``lzo``,
``brotli(level)``, ``lz4``, ``zstd(level)``, and ``lz4_raw``. These
values are not case-sensitive. If ``None``, uses the default parquet
options.
statistics_enabled: Sets if statistics are enabled for the column Valid
values are: ``none``, ``chunk``, and ``page`` These values are not case
sensitive. If ``None``, uses the default parquet options.
bloom_filter_enabled: Sets if bloom filter is enabled for the column path.
If ``None``, uses the default parquet options.
bloom_filter_fpp: Sets bloom filter false positive probability for the
column path. If ``None``, uses the default parquet options.
bloom_filter_ndv: Sets bloom filter number of distinct values. If ``None``,
uses the default parquet options.
"""
self.encoding = encoding
self.dictionary_enabled = dictionary_enabled
self.compression = compression
self.statistics_enabled = statistics_enabled
self.bloom_filter_enabled = bloom_filter_enabled
self.bloom_filter_fpp = bloom_filter_fpp
self.bloom_filter_ndv = bloom_filter_ndv
class DataFrame:
"""Two dimensional table representation of data.
See :ref:`user_guide_concepts` in the online documentation for more information.
"""
def __init__(self, df: DataFrameInternal) -> None:
"""This constructor is not to be used by the end user.
See :py:class:`~datafusion.context.SessionContext` for methods to
create a :py:class:`DataFrame`.
"""
self.df = df
def into_view(self) -> pa.Table:
"""Convert DataFrame as a ViewTable which can be used in register_table."""
return self.df.into_view()
def __getitem__(self, key: str | list[str]) -> DataFrame:
"""Return a new :py:class`DataFrame` with the specified column or columns.
Args:
key: Column name or list of column names to select.
Returns:
DataFrame with the specified column or columns.
"""
return DataFrame(self.df.__getitem__(key))
def __repr__(self) -> str:
"""Return a string representation of the DataFrame.
Returns:
String representation of the DataFrame.
"""
return self.df.__repr__()
def _repr_html_(self) -> str:
return self.df._repr_html_()
@staticmethod
def default_str_repr(
batches: list[pa.RecordBatch],
schema: pa.Schema,
has_more: bool,
table_uuid: str | None = None,
) -> str:
"""Return the default string representation of a DataFrame.
This method is used by the default formatter and implemented in Rust for
performance reasons.
"""
return DataFrameInternal.default_str_repr(batches, schema, has_more, table_uuid)
def describe(self) -> DataFrame:
"""Return the statistics for this DataFrame.
Only summarized numeric datatypes at the moments and returns nulls
for non-numeric datatypes.
The output format is modeled after pandas.
Returns:
A summary DataFrame containing statistics.
"""
return DataFrame(self.df.describe())
def schema(self) -> pa.Schema:
"""Return the :py:class:`pyarrow.Schema` of this DataFrame.
The output schema contains information on the name, data type, and
nullability for each column.
Returns:
Describing schema of the DataFrame
"""
return self.df.schema()
@deprecated(
"select_columns() is deprecated. Use :py:meth:`~DataFrame.select` instead"
)
def select_columns(self, *args: str) -> DataFrame:
"""Filter the DataFrame by columns.
Returns:
DataFrame only containing the specified columns.
"""
return self.select(*args)
def select(self, *exprs: Expr | str) -> DataFrame:
"""Project arbitrary expressions into a new :py:class:`DataFrame`.
Args:
exprs: Either column names or :py:class:`~datafusion.expr.Expr` to select.
Returns:
DataFrame after projection. It has one column for each expression.
Example usage:
The following example will return 3 columns from the original dataframe.
The first two columns will be the original column ``a`` and ``b`` since the
string "a" is assumed to refer to column selection. Also a duplicate of
column ``a`` will be returned with the column name ``alternate_a``::
df = df.select("a", col("b"), col("a").alias("alternate_a"))
"""
exprs_internal = [
Expr.column(arg).expr if isinstance(arg, str) else arg.expr for arg in exprs
]
return DataFrame(self.df.select(*exprs_internal))
def drop(self, *columns: str) -> DataFrame:
"""Drop arbitrary amount of columns.
Args:
columns: Column names to drop from the dataframe.
Returns:
DataFrame with those columns removed in the projection.
"""
return DataFrame(self.df.drop(*columns))
def filter(self, *predicates: Expr) -> DataFrame:
"""Return a DataFrame for which ``predicate`` evaluates to ``True``.
Rows for which ``predicate`` evaluates to ``False`` or ``None`` are filtered
out. If more than one predicate is provided, these predicates will be
combined as a logical AND. If more complex logic is required, see the
logical operations in :py:mod:`~datafusion.functions`.
Args:
predicates: Predicate expression(s) to filter the DataFrame.
Returns:
DataFrame after filtering.
"""
df = self.df
for p in predicates:
df = df.filter(p.expr)
return DataFrame(df)
def with_column(self, name: str, expr: Expr) -> DataFrame:
"""Add an additional column to the DataFrame.
Args:
name: Name of the column to add.
expr: Expression to compute the column.
Returns:
DataFrame with the new column.
"""
return DataFrame(self.df.with_column(name, expr.expr))
def with_columns(
self, *exprs: Expr | Iterable[Expr], **named_exprs: Expr
) -> DataFrame:
"""Add columns to the DataFrame.
By passing expressions, iteratables of expressions, or named expressions. To
pass named expressions use the form name=Expr.
Example usage: The following will add 4 columns labeled a, b, c, and d::
df = df.with_columns(
lit(0).alias('a'),
[lit(1).alias('b'), lit(2).alias('c')],
d=lit(3)
)
Args:
exprs: Either a single expression or an iterable of expressions to add.
named_exprs: Named expressions in the form of ``name=expr``
Returns:
DataFrame with the new columns added.
"""
def _simplify_expression(
*exprs: Expr | Iterable[Expr], **named_exprs: Expr
) -> list[expr_internal.Expr]:
expr_list = []
for expr in exprs:
if isinstance(expr, Expr):
expr_list.append(expr.expr)
elif isinstance(expr, Iterable):
expr_list.extend(inner_expr.expr for inner_expr in expr)
else:
raise NotImplementedError
if named_exprs:
for alias, expr in named_exprs.items():
expr_list.append(expr.alias(alias).expr)
return expr_list
expressions = _simplify_expression(*exprs, **named_exprs)
return DataFrame(self.df.with_columns(expressions))
def with_column_renamed(self, old_name: str, new_name: str) -> DataFrame:
r"""Rename one column by applying a new projection.
This is a no-op if the column to be renamed does not exist.
The method supports case sensitive rename with wrapping column name
into one the following symbols (" or ' or \`).
Args:
old_name: Old column name.
new_name: New column name.
Returns:
DataFrame with the column renamed.
"""
return DataFrame(self.df.with_column_renamed(old_name, new_name))
def aggregate(
self, group_by: list[Expr] | Expr, aggs: list[Expr] | Expr
) -> DataFrame:
"""Aggregates the rows of the current DataFrame.
Args:
group_by: List of expressions to group by.
aggs: List of expressions to aggregate.
Returns:
DataFrame after aggregation.
"""
group_by = group_by if isinstance(group_by, list) else [group_by]
aggs = aggs if isinstance(aggs, list) else [aggs]
group_by = [e.expr for e in group_by]
aggs = [e.expr for e in aggs]
return DataFrame(self.df.aggregate(group_by, aggs))
def sort(self, *exprs: Expr | SortExpr) -> DataFrame:
"""Sort the DataFrame by the specified sorting expressions.
Note that any expression can be turned into a sort expression by
calling its` ``sort`` method.
Args:
exprs: Sort expressions, applied in order.
Returns:
DataFrame after sorting.
"""
exprs_raw = [sort_or_default(expr) for expr in exprs]
return DataFrame(self.df.sort(*exprs_raw))
def cast(self, mapping: dict[str, pa.DataType[Any]]) -> DataFrame:
"""Cast one or more columns to a different data type.
Args:
mapping: Mapped with column as key and column dtype as value.
Returns:
DataFrame after casting columns
"""
exprs = [Expr.column(col).cast(dtype) for col, dtype in mapping.items()]
return self.with_columns(exprs)
def limit(self, count: int, offset: int = 0) -> DataFrame:
"""Return a new :py:class:`DataFrame` with a limited number of rows.
Args:
count: Number of rows to limit the DataFrame to.
offset: Number of rows to skip.
Returns:
DataFrame after limiting.
"""
return DataFrame(self.df.limit(count, offset))
def head(self, n: int = 5) -> DataFrame:
"""Return a new :py:class:`DataFrame` with a limited number of rows.
Args:
n: Number of rows to take from the head of the DataFrame.
Returns:
DataFrame after limiting.
"""
return DataFrame(self.df.limit(n, 0))
def tail(self, n: int = 5) -> DataFrame:
"""Return a new :py:class:`DataFrame` with a limited number of rows.
Be aware this could be potentially expensive since the row size needs to be
determined of the dataframe. This is done by collecting it.
Args:
n: Number of rows to take from the tail of the DataFrame.
Returns:
DataFrame after limiting.
"""
return DataFrame(self.df.limit(n, max(0, self.count() - n)))
def collect(self) -> list[pa.RecordBatch]:
"""Execute this :py:class:`DataFrame` and collect results into memory.
Prior to calling ``collect``, modifying a DataFrame simply updates a plan
(no actual computation is performed). Calling ``collect`` triggers the
computation.
Returns:
List of :py:class:`pyarrow.RecordBatch` collected from the DataFrame.
"""
return self.df.collect()
def cache(self) -> DataFrame:
"""Cache the DataFrame as a memory table.
Returns:
Cached DataFrame.
"""
return DataFrame(self.df.cache())
def collect_partitioned(self) -> list[list[pa.RecordBatch]]:
"""Execute this DataFrame and collect all partitioned results.
This operation returns :py:class:`pyarrow.RecordBatch` maintaining the input
partitioning.
Returns:
List of list of :py:class:`RecordBatch` collected from the
DataFrame.
"""
return self.df.collect_partitioned()
def show(self, num: int = 20) -> None:
"""Execute the DataFrame and print the result to the console.
Args:
num: Number of lines to show.
"""
self.df.show(num)
def distinct(self) -> DataFrame:
"""Return a new :py:class:`DataFrame` with all duplicated rows removed.
Returns:
DataFrame after removing duplicates.
"""
return DataFrame(self.df.distinct())
@overload
def join(
self,
right: DataFrame,
on: str | Sequence[str],
how: Literal["inner", "left", "right", "full", "semi", "anti"] = "inner",
*,
left_on: None = None,
right_on: None = None,
join_keys: None = None,
) -> DataFrame: ...
@overload
def join(
self,
right: DataFrame,
on: None = None,
how: Literal["inner", "left", "right", "full", "semi", "anti"] = "inner",
*,
left_on: str | Sequence[str],
right_on: str | Sequence[str],
join_keys: tuple[list[str], list[str]] | None = None,
) -> DataFrame: ...
@overload
def join(
self,
right: DataFrame,
on: None = None,
how: Literal["inner", "left", "right", "full", "semi", "anti"] = "inner",
*,
join_keys: tuple[list[str], list[str]],
left_on: None = None,
right_on: None = None,
) -> DataFrame: ...
def join(
self,
right: DataFrame,
on: str | Sequence[str] | tuple[list[str], list[str]] | None = None,
how: Literal["inner", "left", "right", "full", "semi", "anti"] = "inner",
*,
left_on: str | Sequence[str] | None = None,
right_on: str | Sequence[str] | None = None,
join_keys: tuple[list[str], list[str]] | None = None,
) -> DataFrame:
"""Join this :py:class:`DataFrame` with another :py:class:`DataFrame`.
`on` has to be provided or both `left_on` and `right_on` in conjunction.
Args:
right: Other DataFrame to join with.
on: Column names to join on in both dataframes.
how: Type of join to perform. Supported types are "inner", "left",
"right", "full", "semi", "anti".
left_on: Join column of the left dataframe.
right_on: Join column of the right dataframe.
join_keys: Tuple of two lists of column names to join on. [Deprecated]
Returns:
DataFrame after join.
"""
# This check is to prevent breaking API changes where users prior to
# DF 43.0.0 would pass the join_keys as a positional argument instead
# of a keyword argument.
if (
isinstance(on, tuple)
and len(on) == 2
and isinstance(on[0], list)
and isinstance(on[1], list)
):
# We know this is safe because we've checked the types
join_keys = on # type: ignore[assignment]
on = None
if join_keys is not None:
warnings.warn(
"`join_keys` is deprecated, use `on` or `left_on` with `right_on`",
category=DeprecationWarning,
stacklevel=2,
)
left_on = join_keys[0]
right_on = join_keys[1]
if on is not None:
if left_on is not None or right_on is not None:
error_msg = "`left_on` or `right_on` should not provided with `on`"
raise ValueError(error_msg)
left_on = on
right_on = on
elif left_on is not None or right_on is not None:
if left_on is None or right_on is None:
error_msg = "`left_on` and `right_on` should both be provided."
raise ValueError(error_msg)
else:
error_msg = "either `on` or `left_on` and `right_on` should be provided."
raise ValueError(error_msg)
if isinstance(left_on, str):
left_on = [left_on]
if isinstance(right_on, str):
right_on = [right_on]
return DataFrame(self.df.join(right.df, how, left_on, right_on))
def join_on(
self,
right: DataFrame,
*on_exprs: Expr,
how: Literal["inner", "left", "right", "full", "semi", "anti"] = "inner",
) -> DataFrame:
"""Join two :py:class:`DataFrame` using the specified expressions.
On expressions are used to support in-equality predicates. Equality
predicates are correctly optimized
Args:
right: Other DataFrame to join with.
on_exprs: single or multiple (in)-equality predicates.
how: Type of join to perform. Supported types are "inner", "left",
"right", "full", "semi", "anti".
Returns:
DataFrame after join.
"""
exprs = [expr.expr for expr in on_exprs]
return DataFrame(self.df.join_on(right.df, exprs, how))
def explain(self, verbose: bool = False, analyze: bool = False) -> None:
"""Print an explanation of the DataFrame's plan so far.
If ``analyze`` is specified, runs the plan and reports metrics.
Args:
verbose: If ``True``, more details will be included.
analyze: If ``True``, the plan will run and metrics reported.
"""
self.df.explain(verbose, analyze)
def logical_plan(self) -> LogicalPlan:
"""Return the unoptimized ``LogicalPlan``.
Returns:
Unoptimized logical plan.
"""
return LogicalPlan(self.df.logical_plan())
def optimized_logical_plan(self) -> LogicalPlan:
"""Return the optimized ``LogicalPlan``.
Returns:
Optimized logical plan.
"""
return LogicalPlan(self.df.optimized_logical_plan())
def execution_plan(self) -> ExecutionPlan:
"""Return the execution/physical plan.
Returns:
Execution plan.
"""
return ExecutionPlan(self.df.execution_plan())
def repartition(self, num: int) -> DataFrame:
"""Repartition a DataFrame into ``num`` partitions.
The batches allocation uses a round-robin algorithm.
Args:
num: Number of partitions to repartition the DataFrame into.
Returns:
Repartitioned DataFrame.
"""
return DataFrame(self.df.repartition(num))
def repartition_by_hash(self, *exprs: Expr, num: int) -> DataFrame:
"""Repartition a DataFrame using a hash partitioning scheme.
Args:
exprs: Expressions to evaluate and perform hashing on.
num: Number of partitions to repartition the DataFrame into.
Returns:
Repartitioned DataFrame.
"""
exprs = [expr.expr for expr in exprs]
return DataFrame(self.df.repartition_by_hash(*exprs, num=num))
def union(self, other: DataFrame, distinct: bool = False) -> DataFrame:
"""Calculate the union of two :py:class:`DataFrame`.
The two :py:class:`DataFrame` must have exactly the same schema.
Args:
other: DataFrame to union with.
distinct: If ``True``, duplicate rows will be removed.
Returns:
DataFrame after union.
"""
return DataFrame(self.df.union(other.df, distinct))
def union_distinct(self, other: DataFrame) -> DataFrame:
"""Calculate the distinct union of two :py:class:`DataFrame`.
The two :py:class:`DataFrame` must have exactly the same schema.
Any duplicate rows are discarded.
Args:
other: DataFrame to union with.
Returns:
DataFrame after union.
"""
return DataFrame(self.df.union_distinct(other.df))
def intersect(self, other: DataFrame) -> DataFrame:
"""Calculate the intersection of two :py:class:`DataFrame`.
The two :py:class:`DataFrame` must have exactly the same schema.
Args:
other: DataFrame to intersect with.
Returns:
DataFrame after intersection.
"""
return DataFrame(self.df.intersect(other.df))
def except_all(self, other: DataFrame) -> DataFrame:
"""Calculate the exception of two :py:class:`DataFrame`.
The two :py:class:`DataFrame` must have exactly the same schema.
Args:
other: DataFrame to calculate exception with.
Returns:
DataFrame after exception.
"""
return DataFrame(self.df.except_all(other.df))
def write_csv(self, path: str | pathlib.Path, with_header: bool = False) -> None:
"""Execute the :py:class:`DataFrame` and write the results to a CSV file.
Args:
path: Path of the CSV file to write.
with_header: If true, output the CSV header row.
"""
self.df.write_csv(str(path), with_header)
@overload
def write_parquet(
self,
path: str | pathlib.Path,
compression: str,
compression_level: int | None = None,
) -> None: ...
@overload
def write_parquet(
self,
path: str | pathlib.Path,
compression: Compression = Compression.ZSTD,
compression_level: int | None = None,
) -> None: ...
@overload
def write_parquet(
self,
path: str | pathlib.Path,
compression: ParquetWriterOptions,
compression_level: None = None,
) -> None: ...
def write_parquet(
self,
path: str | pathlib.Path,
compression: Union[str, Compression, ParquetWriterOptions] = Compression.ZSTD,
compression_level: int | None = None,
) -> None:
"""Execute the :py:class:`DataFrame` and write the results to a Parquet file.
Args:
path: Path of the Parquet file to write.
compression: Compression type to use. Default is "ZSTD".
Available compression types are:
- "uncompressed": No compression.
- "snappy": Snappy compression.
- "gzip": Gzip compression.
- "brotli": Brotli compression.
- "lz4": LZ4 compression.
- "lz4_raw": LZ4_RAW compression.
- "zstd": Zstandard compression.
Note: LZO is not yet implemented in arrow-rs and is therefore excluded.
compression_level: Compression level to use. For ZSTD, the
recommended range is 1 to 22, with the default being 4. Higher levels
provide better compression but slower speed.
"""
if isinstance(compression, ParquetWriterOptions):
if compression_level is not None:
msg = "compression_level should be None when using ParquetWriterOptions"
raise ValueError(msg)
self.write_parquet_with_options(path, compression)
return
if isinstance(compression, str):
compression = Compression.from_str(compression)
if (
compression in {Compression.GZIP, Compression.BROTLI, Compression.ZSTD}
and compression_level is None
):
compression_level = compression.get_default_level()
self.df.write_parquet(str(path), compression.value, compression_level)
def write_parquet_with_options(
self, path: str | pathlib.Path, options: ParquetWriterOptions
) -> None:
"""Execute the :py:class:`DataFrame` and write the results to a Parquet file.
Allows advanced writer options to be set with `ParquetWriterOptions`.
Args:
path: Path of the Parquet file to write.
options: Sets the writer parquet options (see `ParquetWriterOptions`).
"""
options_internal = ParquetWriterOptionsInternal(
options.data_pagesize_limit,
options.write_batch_size,
options.writer_version,
options.skip_arrow_metadata,
options.compression,
options.dictionary_enabled,
options.dictionary_page_size_limit,
options.statistics_enabled,
options.max_row_group_size,
options.created_by,
options.column_index_truncate_length,
options.statistics_truncate_length,
options.data_page_row_count_limit,
options.encoding,
options.bloom_filter_on_write,
options.bloom_filter_fpp,
options.bloom_filter_ndv,
options.allow_single_file_parallelism,
options.maximum_parallel_row_group_writers,
options.maximum_buffered_record_batches_per_stream,
)
column_specific_options_internal = {}
for column, opts in (options.column_specific_options or {}).items():
column_specific_options_internal[column] = ParquetColumnOptionsInternal(
bloom_filter_enabled=opts.bloom_filter_enabled,
encoding=opts.encoding,
dictionary_enabled=opts.dictionary_enabled,
compression=opts.compression,