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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
|
#
# 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.
#
"""
A collections of builtin functions
"""
import math
import sys
import functools
if sys.version < "3":
from itertools import imap as map
from pyspark import since, SparkContext
from pyspark.rdd import _prepare_for_python_RDD, ignore_unicode_prefix
from pyspark.serializers import PickleSerializer, AutoBatchedSerializer
from pyspark.sql.types import StringType, DataType, _parse_datatype_string
from pyspark.sql.column import Column, _to_java_column, _to_seq
from pyspark.sql.dataframe import DataFrame
def _create_function(name, doc=""):
""" Create a function for aggregator by name"""
def _(col):
sc = SparkContext._active_spark_context
jc = getattr(sc._jvm.functions, name)(col._jc if isinstance(col, Column) else col)
return Column(jc)
_.__name__ = name
_.__doc__ = doc
return _
def _create_binary_mathfunction(name, doc=""):
""" Create a binary mathfunction by name"""
def _(col1, col2):
sc = SparkContext._active_spark_context
# users might write ints for simplicity. This would throw an error on the JVM side.
jc = getattr(sc._jvm.functions, name)(col1._jc if isinstance(col1, Column) else float(col1),
col2._jc if isinstance(col2, Column) else float(col2))
return Column(jc)
_.__name__ = name
_.__doc__ = doc
return _
def _create_window_function(name, doc=''):
""" Create a window function by name """
def _():
sc = SparkContext._active_spark_context
jc = getattr(sc._jvm.functions, name)()
return Column(jc)
_.__name__ = name
_.__doc__ = 'Window function: ' + doc
return _
_functions = {
'lit': 'Creates a :class:`Column` of literal value.',
'col': 'Returns a :class:`Column` based on the given column name.',
'column': 'Returns a :class:`Column` based on the given column name.',
'asc': 'Returns a sort expression based on the ascending order of the given column name.',
'desc': 'Returns a sort expression based on the descending order of the given column name.',
'upper': 'Converts a string expression to upper case.',
'lower': 'Converts a string expression to upper case.',
'sqrt': 'Computes the square root of the specified float value.',
'abs': 'Computes the absolute value.',
'max': 'Aggregate function: returns the maximum value of the expression in a group.',
'min': 'Aggregate function: returns the minimum value of the expression in a group.',
'count': 'Aggregate function: returns the number of items in a group.',
'sum': 'Aggregate function: returns the sum of all values in the expression.',
'avg': 'Aggregate function: returns the average of the values in a group.',
'mean': 'Aggregate function: returns the average of the values in a group.',
'sumDistinct': 'Aggregate function: returns the sum of distinct values in the expression.',
}
_functions_1_4 = {
# unary math functions
'acos': 'Computes the cosine inverse of the given value; the returned angle is in the range' +
'0.0 through pi.',
'asin': 'Computes the sine inverse of the given value; the returned angle is in the range' +
'-pi/2 through pi/2.',
'atan': 'Computes the tangent inverse of the given value.',
'cbrt': 'Computes the cube-root of the given value.',
'ceil': 'Computes the ceiling of the given value.',
'cos': 'Computes the cosine of the given value.',
'cosh': 'Computes the hyperbolic cosine of the given value.',
'exp': 'Computes the exponential of the given value.',
'expm1': 'Computes the exponential of the given value minus one.',
'floor': 'Computes the floor of the given value.',
'log': 'Computes the natural logarithm of the given value.',
'log10': 'Computes the logarithm of the given value in Base 10.',
'log1p': 'Computes the natural logarithm of the given value plus one.',
'rint': 'Returns the double value that is closest in value to the argument and' +
' is equal to a mathematical integer.',
'signum': 'Computes the signum of the given value.',
'sin': 'Computes the sine of the given value.',
'sinh': 'Computes the hyperbolic sine of the given value.',
'tan': 'Computes the tangent of the given value.',
'tanh': 'Computes the hyperbolic tangent of the given value.',
'toDegrees': '.. note:: Deprecated in 2.1, use degrees instead.',
'toRadians': '.. note:: Deprecated in 2.1, use radians instead.',
'bitwiseNOT': 'Computes bitwise not.',
}
_functions_1_6 = {
# unary math functions
'stddev': 'Aggregate function: returns the unbiased sample standard deviation of' +
' the expression in a group.',
'stddev_samp': 'Aggregate function: returns the unbiased sample standard deviation of' +
' the expression in a group.',
'stddev_pop': 'Aggregate function: returns population standard deviation of' +
' the expression in a group.',
'variance': 'Aggregate function: returns the population variance of the values in a group.',
'var_samp': 'Aggregate function: returns the unbiased variance of the values in a group.',
'var_pop': 'Aggregate function: returns the population variance of the values in a group.',
'skewness': 'Aggregate function: returns the skewness of the values in a group.',
'kurtosis': 'Aggregate function: returns the kurtosis of the values in a group.',
'collect_list': 'Aggregate function: returns a list of objects with duplicates.',
'collect_set': 'Aggregate function: returns a set of objects with duplicate elements' +
' eliminated.',
}
_functions_2_1 = {
# unary math functions
'degrees': 'Converts an angle measured in radians to an approximately equivalent angle ' +
'measured in degrees.',
'radians': 'Converts an angle measured in degrees to an approximately equivalent angle ' +
'measured in radians.',
}
_functions_2_2 = {
'to_date': 'Converts a string date into a DateType using the (optionally) specified format.',
'to_timestamp': 'Converts a string timestamp into a timestamp type using the ' +
'(optionally) specified format.',
}
# math functions that take two arguments as input
_binary_mathfunctions = {
'atan2': 'Returns the angle theta from the conversion of rectangular coordinates (x, y) to' +
'polar coordinates (r, theta).',
'hypot': 'Computes ``sqrt(a^2 + b^2)`` without intermediate overflow or underflow.',
'pow': 'Returns the value of the first argument raised to the power of the second argument.',
}
_window_functions = {
'row_number':
"""returns a sequential number starting at 1 within a window partition.""",
'dense_rank':
"""returns the rank of rows within a window partition, without any gaps.
The difference between rank and dense_rank is that dense_rank leaves no gaps in ranking
sequence when there are ties. That is, if you were ranking a competition using dense_rank
and had three people tie for second place, you would say that all three were in second
place and that the next person came in third. Rank would give me sequential numbers, making
the person that came in third place (after the ties) would register as coming in fifth.
This is equivalent to the DENSE_RANK function in SQL.""",
'rank':
"""returns the rank of rows within a window partition.
The difference between rank and dense_rank is that dense_rank leaves no gaps in ranking
sequence when there are ties. That is, if you were ranking a competition using dense_rank
and had three people tie for second place, you would say that all three were in second
place and that the next person came in third. Rank would give me sequential numbers, making
the person that came in third place (after the ties) would register as coming in fifth.
This is equivalent to the RANK function in SQL.""",
'cume_dist':
"""returns the cumulative distribution of values within a window partition,
i.e. the fraction of rows that are below the current row.""",
'percent_rank':
"""returns the relative rank (i.e. percentile) of rows within a window partition.""",
}
for _name, _doc in _functions.items():
globals()[_name] = since(1.3)(_create_function(_name, _doc))
for _name, _doc in _functions_1_4.items():
globals()[_name] = since(1.4)(_create_function(_name, _doc))
for _name, _doc in _binary_mathfunctions.items():
globals()[_name] = since(1.4)(_create_binary_mathfunction(_name, _doc))
for _name, _doc in _window_functions.items():
globals()[_name] = since(1.6)(_create_window_function(_name, _doc))
for _name, _doc in _functions_1_6.items():
globals()[_name] = since(1.6)(_create_function(_name, _doc))
for _name, _doc in _functions_2_1.items():
globals()[_name] = since(2.1)(_create_function(_name, _doc))
del _name, _doc
@since(1.3)
def approxCountDistinct(col, rsd=None):
"""
.. note:: Deprecated in 2.1, use approx_count_distinct instead.
"""
return approx_count_distinct(col, rsd)
@since(2.1)
def approx_count_distinct(col, rsd=None):
"""Returns a new :class:`Column` for approximate distinct count of ``col``.
>>> df.agg(approx_count_distinct(df.age).alias('c')).collect()
[Row(c=2)]
"""
sc = SparkContext._active_spark_context
if rsd is None:
jc = sc._jvm.functions.approx_count_distinct(_to_java_column(col))
else:
jc = sc._jvm.functions.approx_count_distinct(_to_java_column(col), rsd)
return Column(jc)
@since(1.6)
def broadcast(df):
"""Marks a DataFrame as small enough for use in broadcast joins."""
sc = SparkContext._active_spark_context
return DataFrame(sc._jvm.functions.broadcast(df._jdf), df.sql_ctx)
@since(1.4)
def coalesce(*cols):
"""Returns the first column that is not null.
>>> cDf = spark.createDataFrame([(None, None), (1, None), (None, 2)], ("a", "b"))
>>> cDf.show()
+----+----+
| a| b|
+----+----+
|null|null|
| 1|null|
|null| 2|
+----+----+
>>> cDf.select(coalesce(cDf["a"], cDf["b"])).show()
+--------------+
|coalesce(a, b)|
+--------------+
| null|
| 1|
| 2|
+--------------+
>>> cDf.select('*', coalesce(cDf["a"], lit(0.0))).show()
+----+----+----------------+
| a| b|coalesce(a, 0.0)|
+----+----+----------------+
|null|null| 0.0|
| 1|null| 1.0|
|null| 2| 0.0|
+----+----+----------------+
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.coalesce(_to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.6)
def corr(col1, col2):
"""Returns a new :class:`Column` for the Pearson Correlation Coefficient for ``col1``
and ``col2``.
>>> a = range(20)
>>> b = [2 * x for x in range(20)]
>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])
>>> df.agg(corr("a", "b").alias('c')).collect()
[Row(c=1.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.corr(_to_java_column(col1), _to_java_column(col2)))
@since(2.0)
def covar_pop(col1, col2):
"""Returns a new :class:`Column` for the population covariance of ``col1``
and ``col2``.
>>> a = [1] * 10
>>> b = [1] * 10
>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])
>>> df.agg(covar_pop("a", "b").alias('c')).collect()
[Row(c=0.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.covar_pop(_to_java_column(col1), _to_java_column(col2)))
@since(2.0)
def covar_samp(col1, col2):
"""Returns a new :class:`Column` for the sample covariance of ``col1``
and ``col2``.
>>> a = [1] * 10
>>> b = [1] * 10
>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])
>>> df.agg(covar_samp("a", "b").alias('c')).collect()
[Row(c=0.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.covar_samp(_to_java_column(col1), _to_java_column(col2)))
@since(1.3)
def countDistinct(col, *cols):
"""Returns a new :class:`Column` for distinct count of ``col`` or ``cols``.
>>> df.agg(countDistinct(df.age, df.name).alias('c')).collect()
[Row(c=2)]
>>> df.agg(countDistinct("age", "name").alias('c')).collect()
[Row(c=2)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.countDistinct(_to_java_column(col), _to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.3)
def first(col, ignorenulls=False):
"""Aggregate function: returns the first value in a group.
The function by default returns the first values it sees. It will return the first non-null
value it sees when ignoreNulls is set to true. If all values are null, then null is returned.
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.first(_to_java_column(col), ignorenulls)
return Column(jc)
@since(2.0)
def grouping(col):
"""
Aggregate function: indicates whether a specified column in a GROUP BY list is aggregated
or not, returns 1 for aggregated or 0 for not aggregated in the result set.
>>> df.cube("name").agg(grouping("name"), sum("age")).orderBy("name").show()
+-----+--------------+--------+
| name|grouping(name)|sum(age)|
+-----+--------------+--------+
| null| 1| 7|
|Alice| 0| 2|
| Bob| 0| 5|
+-----+--------------+--------+
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.grouping(_to_java_column(col))
return Column(jc)
@since(2.0)
def grouping_id(*cols):
"""
Aggregate function: returns the level of grouping, equals to
(grouping(c1) << (n-1)) + (grouping(c2) << (n-2)) + ... + grouping(cn)
.. note:: The list of columns should match with grouping columns exactly, or empty (means all
the grouping columns).
>>> df.cube("name").agg(grouping_id(), sum("age")).orderBy("name").show()
+-----+-------------+--------+
| name|grouping_id()|sum(age)|
+-----+-------------+--------+
| null| 1| 7|
|Alice| 0| 2|
| Bob| 0| 5|
+-----+-------------+--------+
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.grouping_id(_to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.6)
def input_file_name():
"""Creates a string column for the file name of the current Spark task.
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.input_file_name())
@since(1.6)
def isnan(col):
"""An expression that returns true iff the column is NaN.
>>> df = spark.createDataFrame([(1.0, float('nan')), (float('nan'), 2.0)], ("a", "b"))
>>> df.select(isnan("a").alias("r1"), isnan(df.a).alias("r2")).collect()
[Row(r1=False, r2=False), Row(r1=True, r2=True)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.isnan(_to_java_column(col)))
@since(1.6)
def isnull(col):
"""An expression that returns true iff the column is null.
>>> df = spark.createDataFrame([(1, None), (None, 2)], ("a", "b"))
>>> df.select(isnull("a").alias("r1"), isnull(df.a).alias("r2")).collect()
[Row(r1=False, r2=False), Row(r1=True, r2=True)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.isnull(_to_java_column(col)))
@since(1.3)
def last(col, ignorenulls=False):
"""Aggregate function: returns the last value in a group.
The function by default returns the last values it sees. It will return the last non-null
value it sees when ignoreNulls is set to true. If all values are null, then null is returned.
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.last(_to_java_column(col), ignorenulls)
return Column(jc)
@since(1.6)
def monotonically_increasing_id():
"""A column that generates monotonically increasing 64-bit integers.
The generated ID is guaranteed to be monotonically increasing and unique, but not consecutive.
The current implementation puts the partition ID in the upper 31 bits, and the record number
within each partition in the lower 33 bits. The assumption is that the data frame has
less than 1 billion partitions, and each partition has less than 8 billion records.
As an example, consider a :class:`DataFrame` with two partitions, each with 3 records.
This expression would return the following IDs:
0, 1, 2, 8589934592 (1L << 33), 8589934593, 8589934594.
>>> df0 = sc.parallelize(range(2), 2).mapPartitions(lambda x: [(1,), (2,), (3,)]).toDF(['col1'])
>>> df0.select(monotonically_increasing_id().alias('id')).collect()
[Row(id=0), Row(id=1), Row(id=2), Row(id=8589934592), Row(id=8589934593), Row(id=8589934594)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.monotonically_increasing_id())
@since(1.6)
def nanvl(col1, col2):
"""Returns col1 if it is not NaN, or col2 if col1 is NaN.
Both inputs should be floating point columns (DoubleType or FloatType).
>>> df = spark.createDataFrame([(1.0, float('nan')), (float('nan'), 2.0)], ("a", "b"))
>>> df.select(nanvl("a", "b").alias("r1"), nanvl(df.a, df.b).alias("r2")).collect()
[Row(r1=1.0, r2=1.0), Row(r1=2.0, r2=2.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.nanvl(_to_java_column(col1), _to_java_column(col2)))
@since(1.4)
def rand(seed=None):
"""Generates a random column with independent and identically distributed (i.i.d.) samples
from U[0.0, 1.0].
"""
sc = SparkContext._active_spark_context
if seed is not None:
jc = sc._jvm.functions.rand(seed)
else:
jc = sc._jvm.functions.rand()
return Column(jc)
@since(1.4)
def randn(seed=None):
"""Generates a column with independent and identically distributed (i.i.d.) samples from
the standard normal distribution.
"""
sc = SparkContext._active_spark_context
if seed is not None:
jc = sc._jvm.functions.randn(seed)
else:
jc = sc._jvm.functions.randn()
return Column(jc)
@since(1.5)
def round(col, scale=0):
"""
Round the given value to `scale` decimal places using HALF_UP rounding mode if `scale` >= 0
or at integral part when `scale` < 0.
>>> spark.createDataFrame([(2.5,)], ['a']).select(round('a', 0).alias('r')).collect()
[Row(r=3.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.round(_to_java_column(col), scale))
@since(2.0)
def bround(col, scale=0):
"""
Round the given value to `scale` decimal places using HALF_EVEN rounding mode if `scale` >= 0
or at integral part when `scale` < 0.
>>> spark.createDataFrame([(2.5,)], ['a']).select(bround('a', 0).alias('r')).collect()
[Row(r=2.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.bround(_to_java_column(col), scale))
@since(1.5)
def shiftLeft(col, numBits):
"""Shift the given value numBits left.
>>> spark.createDataFrame([(21,)], ['a']).select(shiftLeft('a', 1).alias('r')).collect()
[Row(r=42)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.shiftLeft(_to_java_column(col), numBits))
@since(1.5)
def shiftRight(col, numBits):
"""(Signed) shift the given value numBits right.
>>> spark.createDataFrame([(42,)], ['a']).select(shiftRight('a', 1).alias('r')).collect()
[Row(r=21)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.shiftRight(_to_java_column(col), numBits)
return Column(jc)
@since(1.5)
def shiftRightUnsigned(col, numBits):
"""Unsigned shift the given value numBits right.
>>> df = spark.createDataFrame([(-42,)], ['a'])
>>> df.select(shiftRightUnsigned('a', 1).alias('r')).collect()
[Row(r=9223372036854775787)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.shiftRightUnsigned(_to_java_column(col), numBits)
return Column(jc)
@since(1.6)
def spark_partition_id():
"""A column for partition ID.
.. note:: This is indeterministic because it depends on data partitioning and task scheduling.
>>> df.repartition(1).select(spark_partition_id().alias("pid")).collect()
[Row(pid=0), Row(pid=0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.spark_partition_id())
@since(1.5)
def expr(str):
"""Parses the expression string into the column that it represents
>>> df.select(expr("length(name)")).collect()
[Row(length(name)=5), Row(length(name)=3)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.expr(str))
@ignore_unicode_prefix
@since(1.4)
def struct(*cols):
"""Creates a new struct column.
:param cols: list of column names (string) or list of :class:`Column` expressions
>>> df.select(struct('age', 'name').alias("struct")).collect()
[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]
>>> df.select(struct([df.age, df.name]).alias("struct")).collect()
[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]
"""
sc = SparkContext._active_spark_context
if len(cols) == 1 and isinstance(cols[0], (list, set)):
cols = cols[0]
jc = sc._jvm.functions.struct(_to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.5)
def greatest(*cols):
"""
Returns the greatest value of the list of column names, skipping null values.
This function takes at least 2 parameters. It will return null iff all parameters are null.
>>> df = spark.createDataFrame([(1, 4, 3)], ['a', 'b', 'c'])
>>> df.select(greatest(df.a, df.b, df.c).alias("greatest")).collect()
[Row(greatest=4)]
"""
if len(cols) < 2:
raise ValueError("greatest should take at least two columns")
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.greatest(_to_seq(sc, cols, _to_java_column)))
@since(1.5)
def least(*cols):
"""
Returns the least value of the list of column names, skipping null values.
This function takes at least 2 parameters. It will return null iff all parameters are null.
>>> df = spark.createDataFrame([(1, 4, 3)], ['a', 'b', 'c'])
>>> df.select(least(df.a, df.b, df.c).alias("least")).collect()
[Row(least=1)]
"""
if len(cols) < 2:
raise ValueError("least should take at least two columns")
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.least(_to_seq(sc, cols, _to_java_column)))
@since(1.4)
def when(condition, value):
"""Evaluates a list of conditions and returns one of multiple possible result expressions.
If :func:`Column.otherwise` is not invoked, None is returned for unmatched conditions.
:param condition: a boolean :class:`Column` expression.
:param value: a literal value, or a :class:`Column` expression.
>>> df.select(when(df['age'] == 2, 3).otherwise(4).alias("age")).collect()
[Row(age=3), Row(age=4)]
>>> df.select(when(df.age == 2, df.age + 1).alias("age")).collect()
[Row(age=3), Row(age=None)]
"""
sc = SparkContext._active_spark_context
if not isinstance(condition, Column):
raise TypeError("condition should be a Column")
v = value._jc if isinstance(value, Column) else value
jc = sc._jvm.functions.when(condition._jc, v)
return Column(jc)
@since(1.5)
def log(arg1, arg2=None):
"""Returns the first argument-based logarithm of the second argument.
If there is only one argument, then this takes the natural logarithm of the argument.
>>> df.select(log(10.0, df.age).alias('ten')).rdd.map(lambda l: str(l.ten)[:7]).collect()
['0.30102', '0.69897']
>>> df.select(log(df.age).alias('e')).rdd.map(lambda l: str(l.e)[:7]).collect()
['0.69314', '1.60943']
"""
sc = SparkContext._active_spark_context
if arg2 is None:
jc = sc._jvm.functions.log(_to_java_column(arg1))
else:
jc = sc._jvm.functions.log(arg1, _to_java_column(arg2))
return Column(jc)
@since(1.5)
def log2(col):
"""Returns the base-2 logarithm of the argument.
>>> spark.createDataFrame([(4,)], ['a']).select(log2('a').alias('log2')).collect()
[Row(log2=2.0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.log2(_to_java_column(col)))
@since(1.5)
@ignore_unicode_prefix
def conv(col, fromBase, toBase):
"""
Convert a number in a string column from one base to another.
>>> df = spark.createDataFrame([("010101",)], ['n'])
>>> df.select(conv(df.n, 2, 16).alias('hex')).collect()
[Row(hex=u'15')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.conv(_to_java_column(col), fromBase, toBase))
@since(1.5)
def factorial(col):
"""
Computes the factorial of the given value.
>>> df = spark.createDataFrame([(5,)], ['n'])
>>> df.select(factorial(df.n).alias('f')).collect()
[Row(f=120)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.factorial(_to_java_column(col)))
# --------------- Window functions ------------------------
@since(1.4)
def lag(col, count=1, default=None):
"""
Window function: returns the value that is `offset` rows before the current row, and
`defaultValue` if there is less than `offset` rows before the current row. For example,
an `offset` of one will return the previous row at any given point in the window partition.
This is equivalent to the LAG function in SQL.
:param col: name of column or expression
:param count: number of row to extend
:param default: default value
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.lag(_to_java_column(col), count, default))
@since(1.4)
def lead(col, count=1, default=None):
"""
Window function: returns the value that is `offset` rows after the current row, and
`defaultValue` if there is less than `offset` rows after the current row. For example,
an `offset` of one will return the next row at any given point in the window partition.
This is equivalent to the LEAD function in SQL.
:param col: name of column or expression
:param count: number of row to extend
:param default: default value
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.lead(_to_java_column(col), count, default))
@since(1.4)
def ntile(n):
"""
Window function: returns the ntile group id (from 1 to `n` inclusive)
in an ordered window partition. For example, if `n` is 4, the first
quarter of the rows will get value 1, the second quarter will get 2,
the third quarter will get 3, and the last quarter will get 4.
This is equivalent to the NTILE function in SQL.
:param n: an integer
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.ntile(int(n)))
# ---------------------- Date/Timestamp functions ------------------------------
@since(1.5)
def current_date():
"""
Returns the current date as a date column.
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.current_date())
def current_timestamp():
"""
Returns the current timestamp as a timestamp column.
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.current_timestamp())
@ignore_unicode_prefix
@since(1.5)
def date_format(date, format):
"""
Converts a date/timestamp/string to a value of string in the format specified by the date
format given by the second argument.
A pattern could be for instance `dd.MM.yyyy` and could return a string like '18.03.1993'. All
pattern letters of the Java class `java.text.SimpleDateFormat` can be used.
.. note:: Use when ever possible specialized functions like `year`. These benefit from a
specialized implementation.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(date_format('a', 'MM/dd/yyy').alias('date')).collect()
[Row(date=u'04/08/2015')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.date_format(_to_java_column(date), format))
@since(1.5)
def year(col):
"""
Extract the year of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(year('a').alias('year')).collect()
[Row(year=2015)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.year(_to_java_column(col)))
@since(1.5)
def quarter(col):
"""
Extract the quarter of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(quarter('a').alias('quarter')).collect()
[Row(quarter=2)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.quarter(_to_java_column(col)))
@since(1.5)
def month(col):
"""
Extract the month of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(month('a').alias('month')).collect()
[Row(month=4)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.month(_to_java_column(col)))
@since(1.5)
def dayofmonth(col):
"""
Extract the day of the month of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(dayofmonth('a').alias('day')).collect()
[Row(day=8)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.dayofmonth(_to_java_column(col)))
@since(1.5)
def dayofyear(col):
"""
Extract the day of the year of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(dayofyear('a').alias('day')).collect()
[Row(day=98)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.dayofyear(_to_java_column(col)))
@since(1.5)
def hour(col):
"""
Extract the hours of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])
>>> df.select(hour('a').alias('hour')).collect()
[Row(hour=13)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.hour(_to_java_column(col)))
@since(1.5)
def minute(col):
"""
Extract the minutes of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])
>>> df.select(minute('a').alias('minute')).collect()
[Row(minute=8)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.minute(_to_java_column(col)))
@since(1.5)
def second(col):
"""
Extract the seconds of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])
>>> df.select(second('a').alias('second')).collect()
[Row(second=15)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.second(_to_java_column(col)))
@since(1.5)
def weekofyear(col):
"""
Extract the week number of a given date as integer.
>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])
>>> df.select(weekofyear(df.a).alias('week')).collect()
[Row(week=15)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.weekofyear(_to_java_column(col)))
@since(1.5)
def date_add(start, days):
"""
Returns the date that is `days` days after `start`
>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])
>>> df.select(date_add(df.d, 1).alias('d')).collect()
[Row(d=datetime.date(2015, 4, 9))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.date_add(_to_java_column(start), days))
@since(1.5)
def date_sub(start, days):
"""
Returns the date that is `days` days before `start`
>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])
>>> df.select(date_sub(df.d, 1).alias('d')).collect()
[Row(d=datetime.date(2015, 4, 7))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.date_sub(_to_java_column(start), days))
@since(1.5)
def datediff(end, start):
"""
Returns the number of days from `start` to `end`.
>>> df = spark.createDataFrame([('2015-04-08','2015-05-10')], ['d1', 'd2'])
>>> df.select(datediff(df.d2, df.d1).alias('diff')).collect()
[Row(diff=32)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.datediff(_to_java_column(end), _to_java_column(start)))
@since(1.5)
def add_months(start, months):
"""
Returns the date that is `months` months after `start`
>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])
>>> df.select(add_months(df.d, 1).alias('d')).collect()
[Row(d=datetime.date(2015, 5, 8))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.add_months(_to_java_column(start), months))
@since(1.5)
def months_between(date1, date2):
"""
Returns the number of months between date1 and date2.
>>> df = spark.createDataFrame([('1997-02-28 10:30:00', '1996-10-30')], ['t', 'd'])
>>> df.select(months_between(df.t, df.d).alias('months')).collect()
[Row(months=3.9495967...)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.months_between(_to_java_column(date1), _to_java_column(date2)))
@since(2.2)
def to_date(col, format=None):
"""Converts a :class:`Column` of :class:`pyspark.sql.types.StringType` or
:class:`pyspark.sql.types.TimestampType` into :class:`pyspark.sql.types.DateType`
using the optionally specified format. Default format is 'yyyy-MM-dd'.
Specify formats according to
`SimpleDateFormats <http://docs.oracle.com/javase/tutorial/i18n/format/simpleDateFormat.html>`_.
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(to_date(df.t).alias('date')).collect()
[Row(date=datetime.date(1997, 2, 28))]
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(to_date(df.t, 'yyyy-MM-dd HH:mm:ss').alias('date')).collect()
[Row(date=datetime.date(1997, 2, 28))]
"""
sc = SparkContext._active_spark_context
if format is None:
jc = sc._jvm.functions.to_date(_to_java_column(col))
else:
jc = sc._jvm.functions.to_date(_to_java_column(col), format)
return Column(jc)
@since(2.2)
def to_timestamp(col, format=None):
"""Converts a :class:`Column` of :class:`pyspark.sql.types.StringType` or
:class:`pyspark.sql.types.TimestampType` into :class:`pyspark.sql.types.DateType`
using the optionally specified format. Default format is 'yyyy-MM-dd HH:mm:ss'. Specify
formats according to
`SimpleDateFormats <http://docs.oracle.com/javase/tutorial/i18n/format/simpleDateFormat.html>`_.
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(to_timestamp(df.t).alias('dt')).collect()
[Row(dt=datetime.datetime(1997, 2, 28, 10, 30))]
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(to_timestamp(df.t, 'yyyy-MM-dd HH:mm:ss').alias('dt')).collect()
[Row(dt=datetime.datetime(1997, 2, 28, 10, 30))]
"""
sc = SparkContext._active_spark_context
if format is None:
jc = sc._jvm.functions.to_timestamp(_to_java_column(col))
else:
jc = sc._jvm.functions.to_timestamp(_to_java_column(col), format)
return Column(jc)
@since(1.5)
def trunc(date, format):
"""
Returns date truncated to the unit specified by the format.
:param format: 'year', 'YYYY', 'yy' or 'month', 'mon', 'mm'
>>> df = spark.createDataFrame([('1997-02-28',)], ['d'])
>>> df.select(trunc(df.d, 'year').alias('year')).collect()
[Row(year=datetime.date(1997, 1, 1))]
>>> df.select(trunc(df.d, 'mon').alias('month')).collect()
[Row(month=datetime.date(1997, 2, 1))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.trunc(_to_java_column(date), format))
@since(1.5)
def next_day(date, dayOfWeek):
"""
Returns the first date which is later than the value of the date column.
Day of the week parameter is case insensitive, and accepts:
"Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun".
>>> df = spark.createDataFrame([('2015-07-27',)], ['d'])
>>> df.select(next_day(df.d, 'Sun').alias('date')).collect()
[Row(date=datetime.date(2015, 8, 2))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.next_day(_to_java_column(date), dayOfWeek))
@since(1.5)
def last_day(date):
"""
Returns the last day of the month which the given date belongs to.
>>> df = spark.createDataFrame([('1997-02-10',)], ['d'])
>>> df.select(last_day(df.d).alias('date')).collect()
[Row(date=datetime.date(1997, 2, 28))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.last_day(_to_java_column(date)))
@since(1.5)
def from_unixtime(timestamp, format="yyyy-MM-dd HH:mm:ss"):
"""
Converts the number of seconds from unix epoch (1970-01-01 00:00:00 UTC) to a string
representing the timestamp of that moment in the current system time zone in the given
format.
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.from_unixtime(_to_java_column(timestamp), format))
@since(1.5)
def unix_timestamp(timestamp=None, format='yyyy-MM-dd HH:mm:ss'):
"""
Convert time string with given pattern ('yyyy-MM-dd HH:mm:ss', by default)
to Unix time stamp (in seconds), using the default timezone and the default
locale, return null if fail.
if `timestamp` is None, then it returns current timestamp.
"""
sc = SparkContext._active_spark_context
if timestamp is None:
return Column(sc._jvm.functions.unix_timestamp())
return Column(sc._jvm.functions.unix_timestamp(_to_java_column(timestamp), format))
@since(1.5)
def from_utc_timestamp(timestamp, tz):
"""
Given a timestamp, which corresponds to a certain time of day in UTC, returns another timestamp
that corresponds to the same time of day in the given timezone.
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(from_utc_timestamp(df.t, "PST").alias('t')).collect()
[Row(t=datetime.datetime(1997, 2, 28, 2, 30))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.from_utc_timestamp(_to_java_column(timestamp), tz))
@since(1.5)
def to_utc_timestamp(timestamp, tz):
"""
Given a timestamp, which corresponds to a certain time of day in the given timezone, returns
another timestamp that corresponds to the same time of day in UTC.
>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])
>>> df.select(to_utc_timestamp(df.t, "PST").alias('t')).collect()
[Row(t=datetime.datetime(1997, 2, 28, 18, 30))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.to_utc_timestamp(_to_java_column(timestamp), tz))
@since(2.0)
@ignore_unicode_prefix
def window(timeColumn, windowDuration, slideDuration=None, startTime=None):
"""Bucketize rows into one or more time windows given a timestamp specifying column. Window
starts are inclusive but the window ends are exclusive, e.g. 12:05 will be in the window
[12:05,12:10) but not in [12:00,12:05). Windows can support microsecond precision. Windows in
the order of months are not supported.
The time column must be of :class:`pyspark.sql.types.TimestampType`.
Durations are provided as strings, e.g. '1 second', '1 day 12 hours', '2 minutes'. Valid
interval strings are 'week', 'day', 'hour', 'minute', 'second', 'millisecond', 'microsecond'.
If the ``slideDuration`` is not provided, the windows will be tumbling windows.
The startTime is the offset with respect to 1970-01-01 00:00:00 UTC with which to start
window intervals. For example, in order to have hourly tumbling windows that start 15 minutes
past the hour, e.g. 12:15-13:15, 13:15-14:15... provide `startTime` as `15 minutes`.
The output column will be a struct called 'window' by default with the nested columns 'start'
and 'end', where 'start' and 'end' will be of :class:`pyspark.sql.types.TimestampType`.
>>> df = spark.createDataFrame([("2016-03-11 09:00:07", 1)]).toDF("date", "val")
>>> w = df.groupBy(window("date", "5 seconds")).agg(sum("val").alias("sum"))
>>> w.select(w.window.start.cast("string").alias("start"),
... w.window.end.cast("string").alias("end"), "sum").collect()
[Row(start=u'2016-03-11 09:00:05', end=u'2016-03-11 09:00:10', sum=1)]
"""
def check_string_field(field, fieldName):
if not field or type(field) is not str:
raise TypeError("%s should be provided as a string" % fieldName)
sc = SparkContext._active_spark_context
time_col = _to_java_column(timeColumn)
check_string_field(windowDuration, "windowDuration")
if slideDuration and startTime:
check_string_field(slideDuration, "slideDuration")
check_string_field(startTime, "startTime")
res = sc._jvm.functions.window(time_col, windowDuration, slideDuration, startTime)
elif slideDuration:
check_string_field(slideDuration, "slideDuration")
res = sc._jvm.functions.window(time_col, windowDuration, slideDuration)
elif startTime:
check_string_field(startTime, "startTime")
res = sc._jvm.functions.window(time_col, windowDuration, windowDuration, startTime)
else:
res = sc._jvm.functions.window(time_col, windowDuration)
return Column(res)
# ---------------------------- misc functions ----------------------------------
@since(1.5)
@ignore_unicode_prefix
def crc32(col):
"""
Calculates the cyclic redundancy check value (CRC32) of a binary column and
returns the value as a bigint.
>>> spark.createDataFrame([('ABC',)], ['a']).select(crc32('a').alias('crc32')).collect()
[Row(crc32=2743272264)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.crc32(_to_java_column(col)))
@ignore_unicode_prefix
@since(1.5)
def md5(col):
"""Calculates the MD5 digest and returns the value as a 32 character hex string.
>>> spark.createDataFrame([('ABC',)], ['a']).select(md5('a').alias('hash')).collect()
[Row(hash=u'902fbdd2b1df0c4f70b4a5d23525e932')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.md5(_to_java_column(col))
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def sha1(col):
"""Returns the hex string result of SHA-1.
>>> spark.createDataFrame([('ABC',)], ['a']).select(sha1('a').alias('hash')).collect()
[Row(hash=u'3c01bdbb26f358bab27f267924aa2c9a03fcfdb8')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.sha1(_to_java_column(col))
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def sha2(col, numBits):
"""Returns the hex string result of SHA-2 family of hash functions (SHA-224, SHA-256, SHA-384,
and SHA-512). The numBits indicates the desired bit length of the result, which must have a
value of 224, 256, 384, 512, or 0 (which is equivalent to 256).
>>> digests = df.select(sha2(df.name, 256).alias('s')).collect()
>>> digests[0]
Row(s=u'3bc51062973c458d5a6f2d8d64a023246354ad7e064b1e4e009ec8a0699a3043')
>>> digests[1]
Row(s=u'cd9fb1e148ccd8442e5aa74904cc73bf6fb54d1d54d333bd596aa9bb4bb4e961')
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.sha2(_to_java_column(col), numBits)
return Column(jc)
@since(2.0)
def hash(*cols):
"""Calculates the hash code of given columns, and returns the result as an int column.
>>> spark.createDataFrame([('ABC',)], ['a']).select(hash('a').alias('hash')).collect()
[Row(hash=-757602832)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.hash(_to_seq(sc, cols, _to_java_column))
return Column(jc)
# ---------------------- String/Binary functions ------------------------------
_string_functions = {
'ascii': 'Computes the numeric value of the first character of the string column.',
'base64': 'Computes the BASE64 encoding of a binary column and returns it as a string column.',
'unbase64': 'Decodes a BASE64 encoded string column and returns it as a binary column.',
'initcap': 'Returns a new string column by converting the first letter of each word to ' +
'uppercase. Words are delimited by whitespace.',
'lower': 'Converts a string column to lower case.',
'upper': 'Converts a string column to upper case.',
'reverse': 'Reverses the string column and returns it as a new string column.',
'ltrim': 'Trim the spaces from left end for the specified string value.',
'rtrim': 'Trim the spaces from right end for the specified string value.',
'trim': 'Trim the spaces from both ends for the specified string column.',
}
for _name, _doc in _string_functions.items():
globals()[_name] = since(1.5)(_create_function(_name, _doc))
del _name, _doc
@since(1.5)
@ignore_unicode_prefix
def concat(*cols):
"""
Concatenates multiple input string columns together into a single string column.
>>> df = spark.createDataFrame([('abcd','123')], ['s', 'd'])
>>> df.select(concat(df.s, df.d).alias('s')).collect()
[Row(s=u'abcd123')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.concat(_to_seq(sc, cols, _to_java_column)))
@since(1.5)
@ignore_unicode_prefix
def concat_ws(sep, *cols):
"""
Concatenates multiple input string columns together into a single string column,
using the given separator.
>>> df = spark.createDataFrame([('abcd','123')], ['s', 'd'])
>>> df.select(concat_ws('-', df.s, df.d).alias('s')).collect()
[Row(s=u'abcd-123')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.concat_ws(sep, _to_seq(sc, cols, _to_java_column)))
@since(1.5)
def decode(col, charset):
"""
Computes the first argument into a string from a binary using the provided character set
(one of 'US-ASCII', 'ISO-8859-1', 'UTF-8', 'UTF-16BE', 'UTF-16LE', 'UTF-16').
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.decode(_to_java_column(col), charset))
@since(1.5)
def encode(col, charset):
"""
Computes the first argument into a binary from a string using the provided character set
(one of 'US-ASCII', 'ISO-8859-1', 'UTF-8', 'UTF-16BE', 'UTF-16LE', 'UTF-16').
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.encode(_to_java_column(col), charset))
@ignore_unicode_prefix
@since(1.5)
def format_number(col, d):
"""
Formats the number X to a format like '#,--#,--#.--', rounded to d decimal places
with HALF_EVEN round mode, and returns the result as a string.
:param col: the column name of the numeric value to be formatted
:param d: the N decimal places
>>> spark.createDataFrame([(5,)], ['a']).select(format_number('a', 4).alias('v')).collect()
[Row(v=u'5.0000')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.format_number(_to_java_column(col), d))
@ignore_unicode_prefix
@since(1.5)
def format_string(format, *cols):
"""
Formats the arguments in printf-style and returns the result as a string column.
:param col: the column name of the numeric value to be formatted
:param d: the N decimal places
>>> df = spark.createDataFrame([(5, "hello")], ['a', 'b'])
>>> df.select(format_string('%d %s', df.a, df.b).alias('v')).collect()
[Row(v=u'5 hello')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.format_string(format, _to_seq(sc, cols, _to_java_column)))
@since(1.5)
def instr(str, substr):
"""
Locate the position of the first occurrence of substr column in the given string.
Returns null if either of the arguments are null.
.. note:: The position is not zero based, but 1 based index. Returns 0 if substr
could not be found in str.
>>> df = spark.createDataFrame([('abcd',)], ['s',])
>>> df.select(instr(df.s, 'b').alias('s')).collect()
[Row(s=2)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.instr(_to_java_column(str), substr))
@since(1.5)
@ignore_unicode_prefix
def substring(str, pos, len):
"""
Substring starts at `pos` and is of length `len` when str is String type or
returns the slice of byte array that starts at `pos` in byte and is of length `len`
when str is Binary type
>>> df = spark.createDataFrame([('abcd',)], ['s',])
>>> df.select(substring(df.s, 1, 2).alias('s')).collect()
[Row(s=u'ab')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.substring(_to_java_column(str), pos, len))
@since(1.5)
@ignore_unicode_prefix
def substring_index(str, delim, count):
"""
Returns the substring from string str before count occurrences of the delimiter delim.
If count is positive, everything the left of the final delimiter (counting from left) is
returned. If count is negative, every to the right of the final delimiter (counting from the
right) is returned. substring_index performs a case-sensitive match when searching for delim.
>>> df = spark.createDataFrame([('a.b.c.d',)], ['s'])
>>> df.select(substring_index(df.s, '.', 2).alias('s')).collect()
[Row(s=u'a.b')]
>>> df.select(substring_index(df.s, '.', -3).alias('s')).collect()
[Row(s=u'b.c.d')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.substring_index(_to_java_column(str), delim, count))
@ignore_unicode_prefix
@since(1.5)
def levenshtein(left, right):
"""Computes the Levenshtein distance of the two given strings.
>>> df0 = spark.createDataFrame([('kitten', 'sitting',)], ['l', 'r'])
>>> df0.select(levenshtein('l', 'r').alias('d')).collect()
[Row(d=3)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.levenshtein(_to_java_column(left), _to_java_column(right))
return Column(jc)
@since(1.5)
def locate(substr, str, pos=1):
"""
Locate the position of the first occurrence of substr in a string column, after position pos.
.. note:: The position is not zero based, but 1 based index. Returns 0 if substr
could not be found in str.
:param substr: a string
:param str: a Column of :class:`pyspark.sql.types.StringType`
:param pos: start position (zero based)
>>> df = spark.createDataFrame([('abcd',)], ['s',])
>>> df.select(locate('b', df.s, 1).alias('s')).collect()
[Row(s=2)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.locate(substr, _to_java_column(str), pos))
@since(1.5)
@ignore_unicode_prefix
def lpad(col, len, pad):
"""
Left-pad the string column to width `len` with `pad`.
>>> df = spark.createDataFrame([('abcd',)], ['s',])
>>> df.select(lpad(df.s, 6, '#').alias('s')).collect()
[Row(s=u'##abcd')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.lpad(_to_java_column(col), len, pad))
@since(1.5)
@ignore_unicode_prefix
def rpad(col, len, pad):
"""
Right-pad the string column to width `len` with `pad`.
>>> df = spark.createDataFrame([('abcd',)], ['s',])
>>> df.select(rpad(df.s, 6, '#').alias('s')).collect()
[Row(s=u'abcd##')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.rpad(_to_java_column(col), len, pad))
@since(1.5)
@ignore_unicode_prefix
def repeat(col, n):
"""
Repeats a string column n times, and returns it as a new string column.
>>> df = spark.createDataFrame([('ab',)], ['s',])
>>> df.select(repeat(df.s, 3).alias('s')).collect()
[Row(s=u'ababab')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.repeat(_to_java_column(col), n))
@since(1.5)
@ignore_unicode_prefix
def split(str, pattern):
"""
Splits str around pattern (pattern is a regular expression).
.. note:: pattern is a string represent the regular expression.
>>> df = spark.createDataFrame([('ab12cd',)], ['s',])
>>> df.select(split(df.s, '[0-9]+').alias('s')).collect()
[Row(s=[u'ab', u'cd'])]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.split(_to_java_column(str), pattern))
@ignore_unicode_prefix
@since(1.5)
def regexp_extract(str, pattern, idx):
"""Extract a specific group matched by a Java regex, from the specified string column.
If the regex did not match, or the specified group did not match, an empty string is returned.
>>> df = spark.createDataFrame([('100-200',)], ['str'])
>>> df.select(regexp_extract('str', '(\d+)-(\d+)', 1).alias('d')).collect()
[Row(d=u'100')]
>>> df = spark.createDataFrame([('foo',)], ['str'])
>>> df.select(regexp_extract('str', '(\d+)', 1).alias('d')).collect()
[Row(d=u'')]
>>> df = spark.createDataFrame([('aaaac',)], ['str'])
>>> df.select(regexp_extract('str', '(a+)(b)?(c)', 2).alias('d')).collect()
[Row(d=u'')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.regexp_extract(_to_java_column(str), pattern, idx)
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def regexp_replace(str, pattern, replacement):
"""Replace all substrings of the specified string value that match regexp with rep.
>>> df = spark.createDataFrame([('100-200',)], ['str'])
>>> df.select(regexp_replace('str', '(\\d+)', '--').alias('d')).collect()
[Row(d=u'-----')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.regexp_replace(_to_java_column(str), pattern, replacement)
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def initcap(col):
"""Translate the first letter of each word to upper case in the sentence.
>>> spark.createDataFrame([('ab cd',)], ['a']).select(initcap("a").alias('v')).collect()
[Row(v=u'Ab Cd')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.initcap(_to_java_column(col)))
@since(1.5)
@ignore_unicode_prefix
def soundex(col):
"""
Returns the SoundEx encoding for a string
>>> df = spark.createDataFrame([("Peters",),("Uhrbach",)], ['name'])
>>> df.select(soundex(df.name).alias("soundex")).collect()
[Row(soundex=u'P362'), Row(soundex=u'U612')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.soundex(_to_java_column(col)))
@ignore_unicode_prefix
@since(1.5)
def bin(col):
"""Returns the string representation of the binary value of the given column.
>>> df.select(bin(df.age).alias('c')).collect()
[Row(c=u'10'), Row(c=u'101')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.bin(_to_java_column(col))
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def hex(col):
"""Computes hex value of the given column, which could be :class:`pyspark.sql.types.StringType`,
:class:`pyspark.sql.types.BinaryType`, :class:`pyspark.sql.types.IntegerType` or
:class:`pyspark.sql.types.LongType`.
>>> spark.createDataFrame([('ABC', 3)], ['a', 'b']).select(hex('a'), hex('b')).collect()
[Row(hex(a)=u'414243', hex(b)=u'3')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.hex(_to_java_column(col))
return Column(jc)
@ignore_unicode_prefix
@since(1.5)
def unhex(col):
"""Inverse of hex. Interprets each pair of characters as a hexadecimal number
and converts to the byte representation of number.
>>> spark.createDataFrame([('414243',)], ['a']).select(unhex('a')).collect()
[Row(unhex(a)=bytearray(b'ABC'))]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.unhex(_to_java_column(col)))
@ignore_unicode_prefix
@since(1.5)
def length(col):
"""Calculates the length of a string or binary expression.
>>> spark.createDataFrame([('ABC',)], ['a']).select(length('a').alias('length')).collect()
[Row(length=3)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.length(_to_java_column(col)))
@ignore_unicode_prefix
@since(1.5)
def translate(srcCol, matching, replace):
"""A function translate any character in the `srcCol` by a character in `matching`.
The characters in `replace` is corresponding to the characters in `matching`.
The translate will happen when any character in the string matching with the character
in the `matching`.
>>> spark.createDataFrame([('translate',)], ['a']).select(translate('a', "rnlt", "123") \\
... .alias('r')).collect()
[Row(r=u'1a2s3ae')]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.translate(_to_java_column(srcCol), matching, replace))
# ---------------------- Collection functions ------------------------------
@ignore_unicode_prefix
@since(2.0)
def create_map(*cols):
"""Creates a new map column.
:param cols: list of column names (string) or list of :class:`Column` expressions that grouped
as key-value pairs, e.g. (key1, value1, key2, value2, ...).
>>> df.select(create_map('name', 'age').alias("map")).collect()
[Row(map={u'Alice': 2}), Row(map={u'Bob': 5})]
>>> df.select(create_map([df.name, df.age]).alias("map")).collect()
[Row(map={u'Alice': 2}), Row(map={u'Bob': 5})]
"""
sc = SparkContext._active_spark_context
if len(cols) == 1 and isinstance(cols[0], (list, set)):
cols = cols[0]
jc = sc._jvm.functions.map(_to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.4)
def array(*cols):
"""Creates a new array column.
:param cols: list of column names (string) or list of :class:`Column` expressions that have
the same data type.
>>> df.select(array('age', 'age').alias("arr")).collect()
[Row(arr=[2, 2]), Row(arr=[5, 5])]
>>> df.select(array([df.age, df.age]).alias("arr")).collect()
[Row(arr=[2, 2]), Row(arr=[5, 5])]
"""
sc = SparkContext._active_spark_context
if len(cols) == 1 and isinstance(cols[0], (list, set)):
cols = cols[0]
jc = sc._jvm.functions.array(_to_seq(sc, cols, _to_java_column))
return Column(jc)
@since(1.5)
def array_contains(col, value):
"""
Collection function: returns null if the array is null, true if the array contains the
given value, and false otherwise.
:param col: name of column containing array
:param value: value to check for in array
>>> df = spark.createDataFrame([(["a", "b", "c"],), ([],)], ['data'])
>>> df.select(array_contains(df.data, "a")).collect()
[Row(array_contains(data, a)=True), Row(array_contains(data, a)=False)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.array_contains(_to_java_column(col), value))
@since(1.4)
def explode(col):
"""Returns a new row for each element in the given array or map.
>>> from pyspark.sql import Row
>>> eDF = spark.createDataFrame([Row(a=1, intlist=[1,2,3], mapfield={"a": "b"})])
>>> eDF.select(explode(eDF.intlist).alias("anInt")).collect()
[Row(anInt=1), Row(anInt=2), Row(anInt=3)]
>>> eDF.select(explode(eDF.mapfield).alias("key", "value")).show()
+---+-----+
|key|value|
+---+-----+
| a| b|
+---+-----+
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.explode(_to_java_column(col))
return Column(jc)
@since(2.1)
def posexplode(col):
"""Returns a new row for each element with position in the given array or map.
>>> from pyspark.sql import Row
>>> eDF = spark.createDataFrame([Row(a=1, intlist=[1,2,3], mapfield={"a": "b"})])
>>> eDF.select(posexplode(eDF.intlist)).collect()
[Row(pos=0, col=1), Row(pos=1, col=2), Row(pos=2, col=3)]
>>> eDF.select(posexplode(eDF.mapfield)).show()
+---+---+-----+
|pos|key|value|
+---+---+-----+
| 0| a| b|
+---+---+-----+
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.posexplode(_to_java_column(col))
return Column(jc)
@ignore_unicode_prefix
@since(1.6)
def get_json_object(col, path):
"""
Extracts json object from a json string based on json path specified, and returns json string
of the extracted json object. It will return null if the input json string is invalid.
:param col: string column in json format
:param path: path to the json object to extract
>>> data = [("1", '''{"f1": "value1", "f2": "value2"}'''), ("2", '''{"f1": "value12"}''')]
>>> df = spark.createDataFrame(data, ("key", "jstring"))
>>> df.select(df.key, get_json_object(df.jstring, '$.f1').alias("c0"), \\
... get_json_object(df.jstring, '$.f2').alias("c1") ).collect()
[Row(key=u'1', c0=u'value1', c1=u'value2'), Row(key=u'2', c0=u'value12', c1=None)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.get_json_object(_to_java_column(col), path)
return Column(jc)
@ignore_unicode_prefix
@since(1.6)
def json_tuple(col, *fields):
"""Creates a new row for a json column according to the given field names.
:param col: string column in json format
:param fields: list of fields to extract
>>> data = [("1", '''{"f1": "value1", "f2": "value2"}'''), ("2", '''{"f1": "value12"}''')]
>>> df = spark.createDataFrame(data, ("key", "jstring"))
>>> df.select(df.key, json_tuple(df.jstring, 'f1', 'f2')).collect()
[Row(key=u'1', c0=u'value1', c1=u'value2'), Row(key=u'2', c0=u'value12', c1=None)]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.json_tuple(_to_java_column(col), _to_seq(sc, fields))
return Column(jc)
@since(2.1)
def from_json(col, schema, options={}):
"""
Parses a column containing a JSON string into a [[StructType]] or [[ArrayType]]
of [[StructType]]s with the specified schema. Returns `null`, in the case of an unparseable
string.
:param col: string column in json format
:param schema: a StructType or ArrayType of StructType to use when parsing the json column
:param options: options to control parsing. accepts the same options as the json datasource
>>> from pyspark.sql.types import *
>>> data = [(1, '''{"a": 1}''')]
>>> schema = StructType([StructField("a", IntegerType())])
>>> df = spark.createDataFrame(data, ("key", "value"))
>>> df.select(from_json(df.value, schema).alias("json")).collect()
[Row(json=Row(a=1))]
>>> data = [(1, '''[{"a": 1}]''')]
>>> schema = ArrayType(StructType([StructField("a", IntegerType())]))
>>> df = spark.createDataFrame(data, ("key", "value"))
>>> df.select(from_json(df.value, schema).alias("json")).collect()
[Row(json=[Row(a=1)])]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.from_json(_to_java_column(col), schema.json(), options)
return Column(jc)
@ignore_unicode_prefix
@since(2.1)
def to_json(col, options={}):
"""
Converts a column containing a [[StructType]] or [[ArrayType]] of [[StructType]]s into a
JSON string. Throws an exception, in the case of an unsupported type.
:param col: name of column containing the struct or array of the structs
:param options: options to control converting. accepts the same options as the json datasource
>>> from pyspark.sql import Row
>>> from pyspark.sql.types import *
>>> data = [(1, Row(name='Alice', age=2))]
>>> df = spark.createDataFrame(data, ("key", "value"))
>>> df.select(to_json(df.value).alias("json")).collect()
[Row(json=u'{"age":2,"name":"Alice"}')]
>>> data = [(1, [Row(name='Alice', age=2), Row(name='Bob', age=3)])]
>>> df = spark.createDataFrame(data, ("key", "value"))
>>> df.select(to_json(df.value).alias("json")).collect()
[Row(json=u'[{"age":2,"name":"Alice"},{"age":3,"name":"Bob"}]')]
"""
sc = SparkContext._active_spark_context
jc = sc._jvm.functions.to_json(_to_java_column(col), options)
return Column(jc)
@since(1.5)
def size(col):
"""
Collection function: returns the length of the array or map stored in the column.
:param col: name of column or expression
>>> df = spark.createDataFrame([([1, 2, 3],),([1],),([],)], ['data'])
>>> df.select(size(df.data)).collect()
[Row(size(data)=3), Row(size(data)=1), Row(size(data)=0)]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.size(_to_java_column(col)))
@since(1.5)
def sort_array(col, asc=True):
"""
Collection function: sorts the input array in ascending or descending order according
to the natural ordering of the array elements.
:param col: name of column or expression
>>> df = spark.createDataFrame([([2, 1, 3],),([1],),([],)], ['data'])
>>> df.select(sort_array(df.data).alias('r')).collect()
[Row(r=[1, 2, 3]), Row(r=[1]), Row(r=[])]
>>> df.select(sort_array(df.data, asc=False).alias('r')).collect()
[Row(r=[3, 2, 1]), Row(r=[1]), Row(r=[])]
"""
sc = SparkContext._active_spark_context
return Column(sc._jvm.functions.sort_array(_to_java_column(col), asc))
# ---------------------------- User Defined Function ----------------------------------
def _wrap_function(sc, func, returnType):
command = (func, returnType)
pickled_command, broadcast_vars, env, includes = _prepare_for_python_RDD(sc, command)
return sc._jvm.PythonFunction(bytearray(pickled_command), env, includes, sc.pythonExec,
sc.pythonVer, broadcast_vars, sc._javaAccumulator)
class UserDefinedFunction(object):
"""
User defined function in Python
.. versionadded:: 1.3
"""
def __init__(self, func, returnType, name=None):
if not callable(func):
raise TypeError(
"Not a function or callable (__call__ is not defined): "
"{0}".format(type(func)))
self.func = func
self.returnType = (
returnType if isinstance(returnType, DataType)
else _parse_datatype_string(returnType))
# Stores UserDefinedPythonFunctions jobj, once initialized
self._judf_placeholder = None
self._name = name or (
func.__name__ if hasattr(func, '__name__')
else func.__class__.__name__)
@property
def _judf(self):
# It is possible that concurrent access, to newly created UDF,
# will initialize multiple UserDefinedPythonFunctions.
# This is unlikely, doesn't affect correctness,
# and should have a minimal performance impact.
if self._judf_placeholder is None:
self._judf_placeholder = self._create_judf()
return self._judf_placeholder
def _create_judf(self):
from pyspark.sql import SparkSession
spark = SparkSession.builder.getOrCreate()
sc = spark.sparkContext
wrapped_func = _wrap_function(sc, self.func, self.returnType)
jdt = spark._jsparkSession.parseDataType(self.returnType.json())
judf = sc._jvm.org.apache.spark.sql.execution.python.UserDefinedPythonFunction(
self._name, wrapped_func, jdt)
return judf
def __call__(self, *cols):
judf = self._judf
sc = SparkContext._active_spark_context
return Column(judf.apply(_to_seq(sc, cols, _to_java_column)))
@since(1.3)
def udf(f=None, returnType=StringType()):
"""Creates a :class:`Column` expression representing a user defined function (UDF).
.. note:: The user-defined functions must be deterministic. Due to optimization,
duplicate invocations may be eliminated or the function may even be invoked more times than
it is present in the query.
:param f: python function if used as a standalone function
:param returnType: a :class:`pyspark.sql.types.DataType` object
>>> from pyspark.sql.types import IntegerType
>>> slen = udf(lambda s: len(s), IntegerType())
>>> @udf
... def to_upper(s):
... if s is not None:
... return s.upper()
...
>>> @udf(returnType=IntegerType())
... def add_one(x):
... if x is not None:
... return x + 1
...
>>> df = spark.createDataFrame([(1, "John Doe", 21)], ("id", "name", "age"))
>>> df.select(slen("name").alias("slen(name)"), to_upper("name"), add_one("age")).show()
+----------+--------------+------------+
|slen(name)|to_upper(name)|add_one(age)|
+----------+--------------+------------+
| 8| JOHN DOE| 22|
+----------+--------------+------------+
"""
def _udf(f, returnType=StringType()):
udf_obj = UserDefinedFunction(f, returnType)
@functools.wraps(f)
def wrapper(*args):
return udf_obj(*args)
wrapper.func = udf_obj.func
wrapper.returnType = udf_obj.returnType
return wrapper
# decorator @udf, @udf() or @udf(dataType())
if f is None or isinstance(f, (str, DataType)):
# If DataType has been passed as a positional argument
# for decorator use it as a returnType
return_type = f or returnType
return functools.partial(_udf, returnType=return_type)
else:
return _udf(f=f, returnType=returnType)
blacklist = ['map', 'since', 'ignore_unicode_prefix']
__all__ = [k for k, v in globals().items()
if not k.startswith('_') and k[0].islower() and callable(v) and k not in blacklist]
__all__.sort()
def _test():
import doctest
from pyspark.sql import Row, SparkSession
import pyspark.sql.functions
globs = pyspark.sql.functions.__dict__.copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("sql.functions tests")\
.getOrCreate()
sc = spark.sparkContext
globs['sc'] = sc
globs['spark'] = spark
globs['df'] = sc.parallelize([Row(name='Alice', age=2), Row(name='Bob', age=5)]).toDF()
(failure_count, test_count) = doctest.testmod(
pyspark.sql.functions, globs=globs,
optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE)
spark.stop()
if failure_count:
exit(-1)
if __name__ == "__main__":
_test()
|