forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathdataframe.py
More file actions
1508 lines (1249 loc) · 54.4 KB
/
Copy pathdataframe.py
File metadata and controls
1508 lines (1249 loc) · 54.4 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.
#
import sys
import warnings
import random
if sys.version >= '3':
basestring = unicode = str
long = int
from functools import reduce
else:
from itertools import imap as map
from pyspark import since
from pyspark.rdd import RDD, _load_from_socket, ignore_unicode_prefix
from pyspark.serializers import BatchedSerializer, PickleSerializer, UTF8Deserializer
from pyspark.storagelevel import StorageLevel
from pyspark.traceback_utils import SCCallSiteSync
from pyspark.sql.types import _parse_datatype_json_string
from pyspark.sql.column import Column, _to_seq, _to_list, _to_java_column
from pyspark.sql.readwriter import DataFrameWriter
from pyspark.sql.types import *
__all__ = ["DataFrame", "DataFrameNaFunctions", "DataFrameStatFunctions"]
class DataFrame(object):
"""A distributed collection of data grouped into named columns.
A :class:`DataFrame` is equivalent to a relational table in Spark SQL,
and can be created using various functions in :class:`SQLContext`::
people = sqlContext.read.parquet("...")
Once created, it can be manipulated using the various domain-specific-language
(DSL) functions defined in: :class:`DataFrame`, :class:`Column`.
To select a column from the data frame, use the apply method::
ageCol = people.age
A more concrete example::
# To create DataFrame using SQLContext
people = sqlContext.read.parquet("...")
department = sqlContext.read.parquet("...")
people.filter(people.age > 30).join(department, people.deptId == department.id)) \
.groupBy(department.name, "gender").agg({"salary": "avg", "age": "max"})
.. note:: Experimental
.. versionadded:: 1.3
"""
def __init__(self, jdf, sql_ctx):
self._jdf = jdf
self.sql_ctx = sql_ctx
self._sc = sql_ctx and sql_ctx._sc
self.is_cached = False
self._schema = None # initialized lazily
self._lazy_rdd = None
@property
@since(1.3)
def rdd(self):
"""Returns the content as an :class:`pyspark.RDD` of :class:`Row`.
"""
if self._lazy_rdd is None:
jrdd = self._jdf.javaToPython()
self._lazy_rdd = RDD(jrdd, self.sql_ctx._sc, BatchedSerializer(PickleSerializer()))
return self._lazy_rdd
@property
@since("1.3.1")
def na(self):
"""Returns a :class:`DataFrameNaFunctions` for handling missing values.
"""
return DataFrameNaFunctions(self)
@property
@since(1.4)
def stat(self):
"""Returns a :class:`DataFrameStatFunctions` for statistic functions.
"""
return DataFrameStatFunctions(self)
@ignore_unicode_prefix
@since(1.3)
def toJSON(self, use_unicode=True):
"""Converts a :class:`DataFrame` into a :class:`RDD` of string.
Each row is turned into a JSON document as one element in the returned RDD.
>>> df.toJSON().first()
u'{"age":2,"name":"Alice"}'
"""
rdd = self._jdf.toJSON()
return RDD(rdd.toJavaRDD(), self._sc, UTF8Deserializer(use_unicode))
@since(1.3)
def registerTempTable(self, name):
"""Registers this RDD as a temporary table using the given name.
The lifetime of this temporary table is tied to the :class:`SQLContext`
that was used to create this :class:`DataFrame`.
>>> df.registerTempTable("people")
>>> df2 = sqlContext.sql("select * from people")
>>> sorted(df.collect()) == sorted(df2.collect())
True
"""
self._jdf.registerTempTable(name)
@property
@since(1.4)
def write(self):
"""
Interface for saving the content of the :class:`DataFrame` out into external storage.
:return: :class:`DataFrameWriter`
"""
return DataFrameWriter(self)
@property
@since(1.3)
def schema(self):
"""Returns the schema of this :class:`DataFrame` as a :class:`types.StructType`.
>>> df.schema
StructType(List(StructField(age,IntegerType,true),StructField(name,StringType,true)))
"""
if self._schema is None:
try:
self._schema = _parse_datatype_json_string(self._jdf.schema().json())
except AttributeError as e:
raise Exception(
"Unable to parse datatype from schema. %s" % e)
return self._schema
@since(1.3)
def printSchema(self):
"""Prints out the schema in the tree format.
>>> df.printSchema()
root
|-- age: integer (nullable = true)
|-- name: string (nullable = true)
<BLANKLINE>
"""
print(self._jdf.schema().treeString())
@since(1.3)
def explain(self, extended=False):
"""Prints the (logical and physical) plans to the console for debugging purpose.
:param extended: boolean, default ``False``. If ``False``, prints only the physical plan.
>>> df.explain()
== Physical Plan ==
WholeStageCodegen
: +- Scan ExistingRDD[age#0,name#1]
>>> df.explain(True)
== Parsed Logical Plan ==
...
== Analyzed Logical Plan ==
...
== Optimized Logical Plan ==
...
== Physical Plan ==
...
"""
if extended:
print(self._jdf.queryExecution().toString())
else:
print(self._jdf.queryExecution().simpleString())
@since(1.3)
def isLocal(self):
"""Returns ``True`` if the :func:`collect` and :func:`take` methods can be run locally
(without any Spark executors).
"""
return self._jdf.isLocal()
@since(1.3)
def show(self, n=20, truncate=True):
"""Prints the first ``n`` rows to the console.
:param n: Number of rows to show.
:param truncate: Whether truncate long strings and align cells right.
>>> df
DataFrame[age: int, name: string]
>>> df.show()
+---+-----+
|age| name|
+---+-----+
| 2|Alice|
| 5| Bob|
+---+-----+
"""
print(self._jdf.showString(n, truncate))
def __repr__(self):
return "DataFrame[%s]" % (", ".join("%s: %s" % c for c in self.dtypes))
@since(1.3)
def count(self):
"""Returns the number of rows in this :class:`DataFrame`.
>>> df.count()
2
"""
return int(self._jdf.count())
@ignore_unicode_prefix
@since(1.3)
def collect(self):
"""Returns all the records as a list of :class:`Row`.
>>> df.collect()
[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
"""
with SCCallSiteSync(self._sc) as css:
port = self._jdf.collectToPython()
return list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
@ignore_unicode_prefix
@since(1.3)
def limit(self, num):
"""Limits the result count to the number specified.
>>> df.limit(1).collect()
[Row(age=2, name=u'Alice')]
>>> df.limit(0).collect()
[]
"""
jdf = self._jdf.limit(num)
return DataFrame(jdf, self.sql_ctx)
@ignore_unicode_prefix
@since(1.3)
def take(self, num):
"""Returns the first ``num`` rows as a :class:`list` of :class:`Row`.
>>> df.take(2)
[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
"""
with SCCallSiteSync(self._sc) as css:
port = self._sc._jvm.org.apache.spark.sql.execution.python.EvaluatePython.takeAndServe(
self._jdf, num)
return list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
@ignore_unicode_prefix
@since(1.3)
def map(self, f):
""" Returns a new :class:`RDD` by applying a the ``f`` function to each :class:`Row`.
This is a shorthand for ``df.rdd.map()``.
>>> df.map(lambda p: p.name).collect()
[u'Alice', u'Bob']
"""
return self.rdd.map(f)
@ignore_unicode_prefix
@since(1.3)
def flatMap(self, f):
""" Returns a new :class:`RDD` by first applying the ``f`` function to each :class:`Row`,
and then flattening the results.
This is a shorthand for ``df.rdd.flatMap()``.
>>> df.flatMap(lambda p: p.name).collect()
[u'A', u'l', u'i', u'c', u'e', u'B', u'o', u'b']
"""
return self.rdd.flatMap(f)
@since(1.3)
def mapPartitions(self, f, preservesPartitioning=False):
"""Returns a new :class:`RDD` by applying the ``f`` function to each partition.
This is a shorthand for ``df.rdd.mapPartitions()``.
>>> rdd = sc.parallelize([1, 2, 3, 4], 4)
>>> def f(iterator): yield 1
>>> rdd.mapPartitions(f).sum()
4
"""
return self.rdd.mapPartitions(f, preservesPartitioning)
@since(1.3)
def foreach(self, f):
"""Applies the ``f`` function to all :class:`Row` of this :class:`DataFrame`.
This is a shorthand for ``df.rdd.foreach()``.
>>> def f(person):
... print(person.name)
>>> df.foreach(f)
"""
return self.rdd.foreach(f)
@since(1.3)
def foreachPartition(self, f):
"""Applies the ``f`` function to each partition of this :class:`DataFrame`.
This a shorthand for ``df.rdd.foreachPartition()``.
>>> def f(people):
... for person in people:
... print(person.name)
>>> df.foreachPartition(f)
"""
return self.rdd.foreachPartition(f)
@since(1.3)
def cache(self):
""" Persists with the default storage level (C{MEMORY_ONLY}).
"""
self.is_cached = True
self._jdf.cache()
return self
@since(1.3)
def persist(self, storageLevel=StorageLevel.MEMORY_ONLY):
"""Sets the storage level to persist its values across operations
after the first time it is computed. This can only be used to assign
a new storage level if the RDD does not have a storage level set yet.
If no storage level is specified defaults to (C{MEMORY_ONLY}).
"""
self.is_cached = True
javaStorageLevel = self._sc._getJavaStorageLevel(storageLevel)
self._jdf.persist(javaStorageLevel)
return self
@since(1.3)
def unpersist(self, blocking=True):
"""Marks the :class:`DataFrame` as non-persistent, and remove all blocks for it from
memory and disk.
"""
self.is_cached = False
self._jdf.unpersist(blocking)
return self
@since(1.4)
def coalesce(self, numPartitions):
"""
Returns a new :class:`DataFrame` that has exactly `numPartitions` partitions.
Similar to coalesce defined on an :class:`RDD`, this operation results in a
narrow dependency, e.g. if you go from 1000 partitions to 100 partitions,
there will not be a shuffle, instead each of the 100 new partitions will
claim 10 of the current partitions.
>>> df.coalesce(1).rdd.getNumPartitions()
1
"""
return DataFrame(self._jdf.coalesce(numPartitions), self.sql_ctx)
@since(1.3)
def repartition(self, numPartitions):
"""Returns a new :class:`DataFrame` that has exactly ``numPartitions`` partitions.
>>> df.repartition(10).rdd.getNumPartitions()
10
"""
return DataFrame(self._jdf.repartition(numPartitions), self.sql_ctx)
@since(1.3)
def repartition(self, numPartitions, *cols):
"""
Returns a new :class:`DataFrame` partitioned by the given partitioning expressions. The
resulting DataFrame is hash partitioned.
``numPartitions`` can be an int to specify the target number of partitions or a Column.
If it is a Column, it will be used as the first partitioning column. If not specified,
the default number of partitions is used.
.. versionchanged:: 1.6
Added optional arguments to specify the partitioning columns. Also made numPartitions
optional if partitioning columns are specified.
>>> df.repartition(10).rdd.getNumPartitions()
10
>>> data = df.unionAll(df).repartition("age")
>>> data.show()
+---+-----+
|age| name|
+---+-----+
| 5| Bob|
| 5| Bob|
| 2|Alice|
| 2|Alice|
+---+-----+
>>> data = data.repartition(7, "age")
>>> data.show()
+---+-----+
|age| name|
+---+-----+
| 5| Bob|
| 5| Bob|
| 2|Alice|
| 2|Alice|
+---+-----+
>>> data.rdd.getNumPartitions()
7
>>> data = data.repartition("name", "age")
>>> data.show()
+---+-----+
|age| name|
+---+-----+
| 5| Bob|
| 5| Bob|
| 2|Alice|
| 2|Alice|
+---+-----+
"""
if isinstance(numPartitions, int):
if len(cols) == 0:
return DataFrame(self._jdf.repartition(numPartitions), self.sql_ctx)
else:
return DataFrame(
self._jdf.repartition(numPartitions, self._jcols(*cols)), self.sql_ctx)
elif isinstance(numPartitions, (basestring, Column)):
cols = (numPartitions, ) + cols
return DataFrame(self._jdf.repartition(self._jcols(*cols)), self.sql_ctx)
else:
raise TypeError("numPartitions should be an int or Column")
@since(1.3)
def distinct(self):
"""Returns a new :class:`DataFrame` containing the distinct rows in this :class:`DataFrame`.
>>> df.distinct().count()
2
"""
return DataFrame(self._jdf.distinct(), self.sql_ctx)
@since(1.3)
def sample(self, withReplacement, fraction, seed=None):
"""Returns a sampled subset of this :class:`DataFrame`.
>>> df.sample(False, 0.5, 42).count()
2
"""
assert fraction >= 0.0, "Negative fraction value: %s" % fraction
seed = seed if seed is not None else random.randint(0, sys.maxsize)
rdd = self._jdf.sample(withReplacement, fraction, long(seed))
return DataFrame(rdd, self.sql_ctx)
@since(1.5)
def sampleBy(self, col, fractions, seed=None):
"""
Returns a stratified sample without replacement based on the
fraction given on each stratum.
:param col: column that defines strata
:param fractions:
sampling fraction for each stratum. If a stratum is not
specified, we treat its fraction as zero.
:param seed: random seed
:return: a new DataFrame that represents the stratified sample
>>> from pyspark.sql.functions import col
>>> dataset = sqlContext.range(0, 100).select((col("id") % 3).alias("key"))
>>> sampled = dataset.sampleBy("key", fractions={0: 0.1, 1: 0.2}, seed=0)
>>> sampled.groupBy("key").count().orderBy("key").show()
+---+-----+
|key|count|
+---+-----+
| 0| 5|
| 1| 9|
+---+-----+
"""
if not isinstance(col, str):
raise ValueError("col must be a string, but got %r" % type(col))
if not isinstance(fractions, dict):
raise ValueError("fractions must be a dict but got %r" % type(fractions))
for k, v in fractions.items():
if not isinstance(k, (float, int, long, basestring)):
raise ValueError("key must be float, int, long, or string, but got %r" % type(k))
fractions[k] = float(v)
seed = seed if seed is not None else random.randint(0, sys.maxsize)
return DataFrame(self._jdf.stat().sampleBy(col, self._jmap(fractions), seed), self.sql_ctx)
@since(1.4)
def randomSplit(self, weights, seed=None):
"""Randomly splits this :class:`DataFrame` with the provided weights.
:param weights: list of doubles as weights with which to split the DataFrame. Weights will
be normalized if they don't sum up to 1.0.
:param seed: The seed for sampling.
>>> splits = df4.randomSplit([1.0, 2.0], 24)
>>> splits[0].count()
1
>>> splits[1].count()
3
"""
for w in weights:
if w < 0.0:
raise ValueError("Weights must be positive. Found weight value: %s" % w)
seed = seed if seed is not None else random.randint(0, sys.maxsize)
rdd_array = self._jdf.randomSplit(_to_list(self.sql_ctx._sc, weights), long(seed))
return [DataFrame(rdd, self.sql_ctx) for rdd in rdd_array]
@property
@since(1.3)
def dtypes(self):
"""Returns all column names and their data types as a list.
>>> df.dtypes
[('age', 'int'), ('name', 'string')]
"""
return [(str(f.name), f.dataType.simpleString()) for f in self.schema.fields]
@property
@since(1.3)
def columns(self):
"""Returns all column names as a list.
>>> df.columns
['age', 'name']
"""
return [f.name for f in self.schema.fields]
@ignore_unicode_prefix
@since(1.3)
def alias(self, alias):
"""Returns a new :class:`DataFrame` with an alias set.
>>> from pyspark.sql.functions import *
>>> df_as1 = df.alias("df_as1")
>>> df_as2 = df.alias("df_as2")
>>> joined_df = df_as1.join(df_as2, col("df_as1.name") == col("df_as2.name"), 'inner')
>>> joined_df.select("df_as1.name", "df_as2.name", "df_as2.age").collect()
[Row(name=u'Alice', name=u'Alice', age=2), Row(name=u'Bob', name=u'Bob', age=5)]
"""
assert isinstance(alias, basestring), "alias should be a string"
return DataFrame(getattr(self._jdf, "as")(alias), self.sql_ctx)
@ignore_unicode_prefix
@since(1.3)
def join(self, other, on=None, how=None):
"""Joins with another :class:`DataFrame`, using the given join expression.
The following performs a full outer join between ``df1`` and ``df2``.
:param other: Right side of the join
:param on: a string for join column name, a list of column names,
, a join expression (Column) or a list of Columns.
If `on` is a string or a list of string indicating the name of the join column(s),
the column(s) must exist on both sides, and this performs an equi-join.
:param how: str, default 'inner'.
One of `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
>>> df.join(df2, df.name == df2.name, 'outer').select(df.name, df2.height).collect()
[Row(name=None, height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)]
>>> df.join(df2, 'name', 'outer').select('name', 'height').collect()
[Row(name=u'Tom', height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)]
>>> cond = [df.name == df3.name, df.age == df3.age]
>>> df.join(df3, cond, 'outer').select(df.name, df3.age).collect()
[Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]
>>> df.join(df2, 'name').select(df.name, df2.height).collect()
[Row(name=u'Bob', height=85)]
>>> df.join(df4, ['name', 'age']).select(df.name, df.age).collect()
[Row(name=u'Bob', age=5)]
"""
if on is not None and not isinstance(on, list):
on = [on]
if on is None or len(on) == 0:
jdf = self._jdf.join(other._jdf)
elif isinstance(on[0], basestring):
if how is None:
jdf = self._jdf.join(other._jdf, self._jseq(on), "inner")
else:
assert isinstance(how, basestring), "how should be basestring"
jdf = self._jdf.join(other._jdf, self._jseq(on), how)
else:
assert isinstance(on[0], Column), "on should be Column or list of Column"
if len(on) > 1:
on = reduce(lambda x, y: x.__and__(y), on)
else:
on = on[0]
if how is None:
jdf = self._jdf.join(other._jdf, on._jc, "inner")
else:
assert isinstance(how, basestring), "how should be basestring"
jdf = self._jdf.join(other._jdf, on._jc, how)
return DataFrame(jdf, self.sql_ctx)
@since(1.6)
def sortWithinPartitions(self, *cols, **kwargs):
"""Returns a new :class:`DataFrame` with each partition sorted by the specified column(s).
:param cols: list of :class:`Column` or column names to sort by.
:param ascending: boolean or list of boolean (default True).
Sort ascending vs. descending. Specify list for multiple sort orders.
If a list is specified, length of the list must equal length of the `cols`.
>>> df.sortWithinPartitions("age", ascending=False).show()
+---+-----+
|age| name|
+---+-----+
| 2|Alice|
| 5| Bob|
+---+-----+
"""
jdf = self._jdf.sortWithinPartitions(self._sort_cols(cols, kwargs))
return DataFrame(jdf, self.sql_ctx)
@ignore_unicode_prefix
@since(1.3)
def sort(self, *cols, **kwargs):
"""Returns a new :class:`DataFrame` sorted by the specified column(s).
:param cols: list of :class:`Column` or column names to sort by.
:param ascending: boolean or list of boolean (default True).
Sort ascending vs. descending. Specify list for multiple sort orders.
If a list is specified, length of the list must equal length of the `cols`.
>>> df.sort(df.age.desc()).collect()
[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
>>> df.sort("age", ascending=False).collect()
[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
>>> df.orderBy(df.age.desc()).collect()
[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
>>> from pyspark.sql.functions import *
>>> df.sort(asc("age")).collect()
[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
>>> df.orderBy(desc("age"), "name").collect()
[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
>>> df.orderBy(["age", "name"], ascending=[0, 1]).collect()
[Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
"""
jdf = self._jdf.sort(self._sort_cols(cols, kwargs))
return DataFrame(jdf, self.sql_ctx)
orderBy = sort
def _jseq(self, cols, converter=None):
"""Return a JVM Seq of Columns from a list of Column or names"""
return _to_seq(self.sql_ctx._sc, cols, converter)
def _jmap(self, jm):
"""Return a JVM Scala Map from a dict"""
return _to_scala_map(self.sql_ctx._sc, jm)
def _jcols(self, *cols):
"""Return a JVM Seq of Columns from a list of Column or column names
If `cols` has only one list in it, cols[0] will be used as the list.
"""
if len(cols) == 1 and isinstance(cols[0], list):
cols = cols[0]
return self._jseq(cols, _to_java_column)
def _sort_cols(self, cols, kwargs):
""" Return a JVM Seq of Columns that describes the sort order
"""
if not cols:
raise ValueError("should sort by at least one column")
if len(cols) == 1 and isinstance(cols[0], list):
cols = cols[0]
jcols = [_to_java_column(c) for c in cols]
ascending = kwargs.get('ascending', True)
if isinstance(ascending, (bool, int)):
if not ascending:
jcols = [jc.desc() for jc in jcols]
elif isinstance(ascending, list):
jcols = [jc if asc else jc.desc()
for asc, jc in zip(ascending, jcols)]
else:
raise TypeError("ascending can only be boolean or list, but got %s" % type(ascending))
return self._jseq(jcols)
@since("1.3.1")
def describe(self, *cols):
"""Computes statistics for numeric columns.
This include count, mean, stddev, min, and max. If no columns are
given, this function computes statistics for all numerical columns.
.. note:: This function is meant for exploratory data analysis, as we make no \
guarantee about the backward compatibility of the schema of the resulting DataFrame.
>>> df.describe().show()
+-------+------------------+
|summary| age|
+-------+------------------+
| count| 2|
| mean| 3.5|
| stddev|2.1213203435596424|
| min| 2|
| max| 5|
+-------+------------------+
>>> df.describe(['age', 'name']).show()
+-------+------------------+-----+
|summary| age| name|
+-------+------------------+-----+
| count| 2| 2|
| mean| 3.5| null|
| stddev|2.1213203435596424| null|
| min| 2|Alice|
| max| 5| Bob|
+-------+------------------+-----+
"""
if len(cols) == 1 and isinstance(cols[0], list):
cols = cols[0]
jdf = self._jdf.describe(self._jseq(cols))
return DataFrame(jdf, self.sql_ctx)
@ignore_unicode_prefix
@since(1.3)
def head(self, n=None):
"""Returns the first ``n`` rows.
Note that this method should only be used if the resulting array is expected
to be small, as all the data is loaded into the driver's memory.
:param n: int, default 1. Number of rows to return.
:return: If n is greater than 1, return a list of :class:`Row`.
If n is 1, return a single Row.
>>> df.head()
Row(age=2, name=u'Alice')
>>> df.head(1)
[Row(age=2, name=u'Alice')]
"""
if n is None:
rs = self.head(1)
return rs[0] if rs else None
return self.take(n)
@ignore_unicode_prefix
@since(1.3)
def first(self):
"""Returns the first row as a :class:`Row`.
>>> df.first()
Row(age=2, name=u'Alice')
"""
return self.head()
@ignore_unicode_prefix
@since(1.3)
def __getitem__(self, item):
"""Returns the column as a :class:`Column`.
>>> df.select(df['age']).collect()
[Row(age=2), Row(age=5)]
>>> df[ ["name", "age"]].collect()
[Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]
>>> df[ df.age > 3 ].collect()
[Row(age=5, name=u'Bob')]
>>> df[df[0] > 3].collect()
[Row(age=5, name=u'Bob')]
"""
if isinstance(item, basestring):
jc = self._jdf.apply(item)
return Column(jc)
elif isinstance(item, Column):
return self.filter(item)
elif isinstance(item, (list, tuple)):
return self.select(*item)
elif isinstance(item, int):
jc = self._jdf.apply(self.columns[item])
return Column(jc)
else:
raise TypeError("unexpected item type: %s" % type(item))
@since(1.3)
def __getattr__(self, name):
"""Returns the :class:`Column` denoted by ``name``.
>>> df.select(df.age).collect()
[Row(age=2), Row(age=5)]
"""
if name not in self.columns:
raise AttributeError(
"'%s' object has no attribute '%s'" % (self.__class__.__name__, name))
jc = self._jdf.apply(name)
return Column(jc)
@ignore_unicode_prefix
@since(1.3)
def select(self, *cols):
"""Projects a set of expressions and returns a new :class:`DataFrame`.
:param cols: list of column names (string) or expressions (:class:`Column`).
If one of the column names is '*', that column is expanded to include all columns
in the current DataFrame.
>>> df.select('*').collect()
[Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
>>> df.select('name', 'age').collect()
[Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]
>>> df.select(df.name, (df.age + 10).alias('age')).collect()
[Row(name=u'Alice', age=12), Row(name=u'Bob', age=15)]
"""
jdf = self._jdf.select(self._jcols(*cols))
return DataFrame(jdf, self.sql_ctx)
@since(1.3)
def selectExpr(self, *expr):
"""Projects a set of SQL expressions and returns a new :class:`DataFrame`.
This is a variant of :func:`select` that accepts SQL expressions.
>>> df.selectExpr("age * 2", "abs(age)").collect()
[Row((age * 2)=4, abs(age)=2), Row((age * 2)=10, abs(age)=5)]
"""
if len(expr) == 1 and isinstance(expr[0], list):
expr = expr[0]
jdf = self._jdf.selectExpr(self._jseq(expr))
return DataFrame(jdf, self.sql_ctx)
@ignore_unicode_prefix
@since(1.3)
def filter(self, condition):
"""Filters rows using the given condition.
:func:`where` is an alias for :func:`filter`.
:param condition: a :class:`Column` of :class:`types.BooleanType`
or a string of SQL expression.
>>> df.filter(df.age > 3).collect()
[Row(age=5, name=u'Bob')]
>>> df.where(df.age == 2).collect()
[Row(age=2, name=u'Alice')]
>>> df.filter("age > 3").collect()
[Row(age=5, name=u'Bob')]
>>> df.where("age = 2").collect()
[Row(age=2, name=u'Alice')]
"""
if isinstance(condition, basestring):
jdf = self._jdf.filter(condition)
elif isinstance(condition, Column):
jdf = self._jdf.filter(condition._jc)
else:
raise TypeError("condition should be string or Column")
return DataFrame(jdf, self.sql_ctx)
where = filter
@ignore_unicode_prefix
@since(1.3)
def groupBy(self, *cols):
"""Groups the :class:`DataFrame` using the specified columns,
so we can run aggregation on them. See :class:`GroupedData`
for all the available aggregate functions.
:func:`groupby` is an alias for :func:`groupBy`.
:param cols: list of columns to group by.
Each element should be a column name (string) or an expression (:class:`Column`).
>>> df.groupBy().avg().collect()
[Row(avg(age)=3.5)]
>>> sorted(df.groupBy('name').agg({'age': 'mean'}).collect())
[Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)]
>>> sorted(df.groupBy(df.name).avg().collect())
[Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)]
>>> sorted(df.groupBy(['name', df.age]).count().collect())
[Row(name=u'Alice', age=2, count=1), Row(name=u'Bob', age=5, count=1)]
"""
jgd = self._jdf.groupBy(self._jcols(*cols))
from pyspark.sql.group import GroupedData
return GroupedData(jgd, self.sql_ctx)
@since(1.4)
def rollup(self, *cols):
"""
Create a multi-dimensional rollup for the current :class:`DataFrame` using
the specified columns, so we can run aggregation on them.
>>> df.rollup("name", df.age).count().orderBy("name", "age").show()
+-----+----+-----+
| name| age|count|
+-----+----+-----+
| null|null| 2|
|Alice|null| 1|
|Alice| 2| 1|
| Bob|null| 1|
| Bob| 5| 1|
+-----+----+-----+
"""
jgd = self._jdf.rollup(self._jcols(*cols))
from pyspark.sql.group import GroupedData
return GroupedData(jgd, self.sql_ctx)
@since(1.4)
def cube(self, *cols):
"""
Create a multi-dimensional cube for the current :class:`DataFrame` using
the specified columns, so we can run aggregation on them.
>>> df.cube("name", df.age).count().orderBy("name", "age").show()
+-----+----+-----+
| name| age|count|
+-----+----+-----+
| null|null| 2|
| null| 2| 1|
| null| 5| 1|
|Alice|null| 1|
|Alice| 2| 1|
| Bob|null| 1|
| Bob| 5| 1|
+-----+----+-----+
"""
jgd = self._jdf.cube(self._jcols(*cols))
from pyspark.sql.group import GroupedData
return GroupedData(jgd, self.sql_ctx)
@since(1.3)
def agg(self, *exprs):
""" Aggregate on the entire :class:`DataFrame` without groups
(shorthand for ``df.groupBy.agg()``).
>>> df.agg({"age": "max"}).collect()
[Row(max(age)=5)]
>>> from pyspark.sql import functions as F
>>> df.agg(F.min(df.age)).collect()
[Row(min(age)=2)]
"""
return self.groupBy().agg(*exprs)
@since(1.3)
def unionAll(self, other):
""" Return a new :class:`DataFrame` containing union of rows in this
frame and another frame.
This is equivalent to `UNION ALL` in SQL.
"""
return DataFrame(self._jdf.unionAll(other._jdf), self.sql_ctx)
@since(1.3)
def intersect(self, other):
""" Return a new :class:`DataFrame` containing rows only in
both this frame and another frame.
This is equivalent to `INTERSECT` in SQL.
"""
return DataFrame(self._jdf.intersect(other._jdf), self.sql_ctx)
@since(1.3)
def subtract(self, other):
""" Return a new :class:`DataFrame` containing rows in this frame
but not in another frame.
This is equivalent to `EXCEPT` in SQL.
"""
return DataFrame(getattr(self._jdf, "except")(other._jdf), self.sql_ctx)
@since(1.4)
def dropDuplicates(self, subset=None):
"""Return a new :class:`DataFrame` with duplicate rows removed,
optionally only considering certain columns.
:func:`drop_duplicates` is an alias for :func:`dropDuplicates`.
>>> from pyspark.sql import Row
>>> df = sc.parallelize([ \
Row(name='Alice', age=5, height=80), \
Row(name='Alice', age=5, height=80), \
Row(name='Alice', age=10, height=80)]).toDF()
>>> df.dropDuplicates().show()
+---+------+-----+
|age|height| name|
+---+------+-----+
| 5| 80|Alice|
| 10| 80|Alice|
+---+------+-----+