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
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>pyspark.sql.context — PySpark master documentation</title>
<link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../../',
VERSION: 'master',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<link rel="top" title="PySpark master documentation" href="../../../index.html" />
<link rel="up" title="Module code" href="../../index.html" />
</head>
<body role="document">
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> »</li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for pyspark.sql.context</h1><div class="highlight"><pre>
<span class="c">#</span>
<span class="c"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c"># this work for additional information regarding copyright ownership.</span>
<span class="c"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c"># (the "License"); you may not use this file except in compliance with</span>
<span class="c"># the License. You may obtain a copy of the License at</span>
<span class="c">#</span>
<span class="c"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c">#</span>
<span class="c"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c"># distributed under the License is distributed on an "AS IS" BASIS,</span>
<span class="c"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c"># See the License for the specific language governing permissions and</span>
<span class="c"># limitations under the License.</span>
<span class="c">#</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version</span> <span class="o">>=</span> <span class="s">'3'</span><span class="p">:</span>
<span class="nb">basestring</span> <span class="o">=</span> <span class="nb">unicode</span> <span class="o">=</span> <span class="nb">str</span>
<span class="k">else</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">itertools</span> <span class="kn">import</span> <span class="n">imap</span> <span class="k">as</span> <span class="nb">map</span>
<span class="kn">from</span> <span class="nn">py4j.protocol</span> <span class="kn">import</span> <span class="n">Py4JError</span>
<span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">RDD</span><span class="p">,</span> <span class="n">_prepare_for_python_RDD</span><span class="p">,</span> <span class="n">ignore_unicode_prefix</span>
<span class="kn">from</span> <span class="nn">pyspark.serializers</span> <span class="kn">import</span> <span class="n">AutoBatchedSerializer</span><span class="p">,</span> <span class="n">PickleSerializer</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">since</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">Row</span><span class="p">,</span> <span class="n">StringType</span><span class="p">,</span> <span class="n">StructType</span><span class="p">,</span> <span class="n">_verify_type</span><span class="p">,</span> \
<span class="n">_infer_schema</span><span class="p">,</span> <span class="n">_has_nulltype</span><span class="p">,</span> <span class="n">_merge_type</span><span class="p">,</span> <span class="n">_create_converter</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.readwriter</span> <span class="kn">import</span> <span class="n">DataFrameReader</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.utils</span> <span class="kn">import</span> <span class="n">install_exception_handler</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">UserDefinedFunction</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">pandas</span>
<span class="n">has_pandas</span> <span class="o">=</span> <span class="bp">True</span>
<span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span>
<span class="n">has_pandas</span> <span class="o">=</span> <span class="bp">False</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">"SQLContext"</span><span class="p">,</span> <span class="s">"HiveContext"</span><span class="p">,</span> <span class="s">"UDFRegistration"</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">_monkey_patch_RDD</span><span class="p">(</span><span class="n">sqlContext</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">toDF</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">sampleRatio</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Converts current :class:`RDD` into a :class:`DataFrame`</span>
<span class="sd"> This is a shorthand for ``sqlContext.createDataFrame(rdd, schema, sampleRatio)``</span>
<span class="sd"> :param schema: a StructType or list of names of columns</span>
<span class="sd"> :param samplingRatio: the sample ratio of rows used for inferring</span>
<span class="sd"> :return: a DataFrame</span>
<span class="sd"> >>> rdd.toDF().collect()</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">sampleRatio</span><span class="p">)</span>
<span class="n">RDD</span><span class="o">.</span><span class="n">toDF</span> <span class="o">=</span> <span class="n">toDF</span>
<div class="viewcode-block" id="SQLContext"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext">[docs]</a><span class="k">class</span> <span class="nc">SQLContext</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Main entry point for Spark SQL functionality.</span>
<span class="sd"> A SQLContext can be used create :class:`DataFrame`, register :class:`DataFrame` as</span>
<span class="sd"> tables, execute SQL over tables, cache tables, and read parquet files.</span>
<span class="sd"> :param sparkContext: The :class:`SparkContext` backing this SQLContext.</span>
<span class="sd"> :param sqlContext: An optional JVM Scala SQLContext. If set, we do not instantiate a new</span>
<span class="sd"> SQLContext in the JVM, instead we make all calls to this object.</span>
<span class="sd"> """</span>
<span class="nd">@ignore_unicode_prefix</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sparkContext</span><span class="p">,</span> <span class="n">sqlContext</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Creates a new SQLContext.</span>
<span class="sd"> >>> from datetime import datetime</span>
<span class="sd"> >>> sqlContext = SQLContext(sc)</span>
<span class="sd"> >>> allTypes = sc.parallelize([Row(i=1, s="string", d=1.0, l=1,</span>
<span class="sd"> ... b=True, list=[1, 2, 3], dict={"s": 0}, row=Row(a=1),</span>
<span class="sd"> ... time=datetime(2014, 8, 1, 14, 1, 5))])</span>
<span class="sd"> >>> df = allTypes.toDF()</span>
<span class="sd"> >>> df.registerTempTable("allTypes")</span>
<span class="sd"> >>> sqlContext.sql('select i+1, d+1, not b, list[1], dict["s"], time, row.a '</span>
<span class="sd"> ... 'from allTypes where b and i > 0').collect()</span>
<span class="sd"> [Row(_c0=2, _c1=2.0, _c2=False, _c3=2, _c4=0, \</span>
<span class="sd"> time=datetime.datetime(2014, 8, 1, 14, 1, 5), a=1)]</span>
<span class="sd"> >>> df.map(lambda x: (x.i, x.s, x.d, x.l, x.b, x.time, x.row.a, x.list)).collect()</span>
<span class="sd"> [(1, u'string', 1.0, 1, True, datetime.datetime(2014, 8, 1, 14, 1, 5), 1, [1, 2, 3])]</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sc</span> <span class="o">=</span> <span class="n">sparkContext</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_jsc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jsc</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_jvm</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scala_SQLContext</span> <span class="o">=</span> <span class="n">sqlContext</span>
<span class="n">_monkey_patch_RDD</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
<span class="n">install_exception_handler</span><span class="p">()</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">_ssql_ctx</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Accessor for the JVM Spark SQL context.</span>
<span class="sd"> Subclasses can override this property to provide their own</span>
<span class="sd"> JVM Contexts.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scala_SQLContext</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scala_SQLContext</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">SQLContext</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">())</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scala_SQLContext</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.setConf"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.setConf">[docs]</a> <span class="k">def</span> <span class="nf">setConf</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""Sets the given Spark SQL configuration property.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">setConf</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.getConf"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.getConf">[docs]</a> <span class="k">def</span> <span class="nf">getConf</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">defaultValue</span><span class="p">):</span>
<span class="sd">"""Returns the value of Spark SQL configuration property for the given key.</span>
<span class="sd"> If the key is not set, returns defaultValue.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">getConf</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">defaultValue</span><span class="p">)</span>
</div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s">"1.3.1"</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">udf</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Returns a :class:`UDFRegistration` for UDF registration.</span>
<span class="sd"> :return: :class:`UDFRegistration`</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">UDFRegistration</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.range"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.range">[docs]</a> <span class="k">def</span> <span class="nf">range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start</span><span class="p">,</span> <span class="n">end</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">step</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Create a :class:`DataFrame` with single LongType column named `id`,</span>
<span class="sd"> containing elements in a range from `start` to `end` (exclusive) with</span>
<span class="sd"> step value `step`.</span>
<span class="sd"> :param start: the start value</span>
<span class="sd"> :param end: the end value (exclusive)</span>
<span class="sd"> :param step: the incremental step (default: 1)</span>
<span class="sd"> :param numPartitions: the number of partitions of the DataFrame</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> >>> sqlContext.range(1, 7, 2).collect()</span>
<span class="sd"> [Row(id=1), Row(id=3), Row(id=5)]</span>
<span class="sd"> If only one argument is specified, it will be used as the end value.</span>
<span class="sd"> >>> sqlContext.range(3).collect()</span>
<span class="sd"> [Row(id=0), Row(id=1), Row(id=2)]</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">numPartitions</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">numPartitions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">defaultParallelism</span>
<span class="k">if</span> <span class="n">end</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">jdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">start</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numPartitions</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">jdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">range</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">start</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">end</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numPartitions</span><span class="p">))</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jdf</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@ignore_unicode_prefix</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.2</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.registerFunction"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.registerFunction">[docs]</a> <span class="k">def</span> <span class="nf">registerFunction</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">returnType</span><span class="o">=</span><span class="n">StringType</span><span class="p">()):</span>
<span class="sd">"""Registers a lambda function as a UDF so it can be used in SQL statements.</span>
<span class="sd"> In addition to a name and the function itself, the return type can be optionally specified.</span>
<span class="sd"> When the return type is not given it default to a string and conversion will automatically</span>
<span class="sd"> be done. For any other return type, the produced object must match the specified type.</span>
<span class="sd"> :param name: name of the UDF</span>
<span class="sd"> :param samplingRatio: lambda function</span>
<span class="sd"> :param returnType: a :class:`DataType` object</span>
<span class="sd"> >>> sqlContext.registerFunction("stringLengthString", lambda x: len(x))</span>
<span class="sd"> >>> sqlContext.sql("SELECT stringLengthString('test')").collect()</span>
<span class="sd"> [Row(_c0=u'4')]</span>
<span class="sd"> >>> from pyspark.sql.types import IntegerType</span>
<span class="sd"> >>> sqlContext.registerFunction("stringLengthInt", lambda x: len(x), IntegerType())</span>
<span class="sd"> >>> sqlContext.sql("SELECT stringLengthInt('test')").collect()</span>
<span class="sd"> [Row(_c0=4)]</span>
<span class="sd"> >>> from pyspark.sql.types import IntegerType</span>
<span class="sd"> >>> sqlContext.udf.register("stringLengthInt", lambda x: len(x), IntegerType())</span>
<span class="sd"> >>> sqlContext.sql("SELECT stringLengthInt('test')").collect()</span>
<span class="sd"> [Row(_c0=4)]</span>
<span class="sd"> """</span>
<span class="n">udf</span> <span class="o">=</span> <span class="n">UserDefinedFunction</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">returnType</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">udf</span><span class="p">()</span><span class="o">.</span><span class="n">registerPython</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">udf</span><span class="o">.</span><span class="n">_judf</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_inferSchemaFromList</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Infer schema from list of Row or tuple.</span>
<span class="sd"> :param data: list of Row or tuple</span>
<span class="sd"> :return: StructType</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">data</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"can not infer schema from empty dataset"</span><span class="p">)</span>
<span class="n">first</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">first</span><span class="p">)</span> <span class="ow">is</span> <span class="nb">dict</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"inferring schema from dict is deprecated,"</span>
<span class="s">"please use pyspark.sql.Row instead"</span><span class="p">)</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">_infer_schema</span><span class="p">(</span><span class="n">first</span><span class="p">)</span>
<span class="k">if</span> <span class="n">_has_nulltype</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">data</span><span class="p">:</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">_merge_type</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">_infer_schema</span><span class="p">(</span><span class="n">r</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">_has_nulltype</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="k">break</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Some of types cannot be determined after inferring"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">schema</span>
<span class="k">def</span> <span class="nf">_inferSchema</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Infer schema from an RDD of Row or tuple.</span>
<span class="sd"> :param rdd: an RDD of Row or tuple</span>
<span class="sd"> :param samplingRatio: sampling ratio, or no sampling (default)</span>
<span class="sd"> :return: StructType</span>
<span class="sd"> """</span>
<span class="n">first</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">first</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"The first row in RDD is empty, "</span>
<span class="s">"can not infer schema"</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">first</span><span class="p">)</span> <span class="ow">is</span> <span class="nb">dict</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"Using RDD of dict to inferSchema is deprecated. "</span>
<span class="s">"Use pyspark.sql.Row instead"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">samplingRatio</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">_infer_schema</span><span class="p">(</span><span class="n">first</span><span class="p">)</span>
<span class="k">if</span> <span class="n">_has_nulltype</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">rdd</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">100</span><span class="p">)[</span><span class="mi">1</span><span class="p">:]:</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">_merge_type</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">_infer_schema</span><span class="p">(</span><span class="n">row</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">_has_nulltype</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="k">break</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Some of types cannot be determined by the "</span>
<span class="s">"first 100 rows, please try again with sampling"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">samplingRatio</span> <span class="o"><</span> <span class="mf">0.99</span><span class="p">:</span>
<span class="n">rdd</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="bp">False</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">samplingRatio</span><span class="p">))</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_infer_schema</span><span class="p">)</span><span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="n">_merge_type</span><span class="p">)</span>
<span class="k">return</span> <span class="n">schema</span>
<span class="nd">@ignore_unicode_prefix</span>
<div class="viewcode-block" id="SQLContext.inferSchema"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.inferSchema">[docs]</a> <span class="k">def</span> <span class="nf">inferSchema</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Deprecated in 1.3, use :func:`createDataFrame` instead.</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"inferSchema is deprecated, please use createDataFrame instead."</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"Cannot apply schema to DataFrame"</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="bp">None</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="p">)</span>
</div>
<span class="nd">@ignore_unicode_prefix</span>
<div class="viewcode-block" id="SQLContext.applySchema"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.applySchema">[docs]</a> <span class="k">def</span> <span class="nf">applySchema</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Deprecated in 1.3, use :func:`createDataFrame` instead.</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"applySchema is deprecated, please use createDataFrame instead"</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"Cannot apply schema to DataFrame"</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"schema should be StructType, but got </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">schema</span><span class="p">))</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_createFromRDD</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Create an RDD for DataFrame from an existing RDD, returns the RDD and schema.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="n">struct</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_inferSchema</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="p">)</span>
<span class="n">converter</span> <span class="o">=</span> <span class="n">_create_converter</span><span class="p">(</span><span class="n">struct</span><span class="p">)</span>
<span class="n">rdd</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">converter</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="n">struct</span><span class="o">.</span><span class="n">fields</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span>
<span class="n">struct</span><span class="o">.</span><span class="n">names</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">struct</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span>
<span class="c"># take the first few rows to verify schema</span>
<span class="n">rows</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
<span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">:</span>
<span class="n">_verify_type</span><span class="p">(</span><span class="n">row</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"schema should be StructType or list or None, but got: </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="n">schema</span><span class="p">)</span>
<span class="c"># convert python objects to sql data</span>
<span class="n">rdd</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">toInternal</span><span class="p">)</span>
<span class="k">return</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span>
<span class="k">def</span> <span class="nf">_createFromLocal</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Create an RDD for DataFrame from an list or pandas.DataFrame, returns</span>
<span class="sd"> the RDD and schema.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">has_pandas</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">):</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">schema</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">data</span><span class="o">.</span><span class="n">columns</span><span class="p">]</span>
<span class="n">data</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">data</span><span class="o">.</span><span class="n">to_records</span><span class="p">(</span><span class="n">index</span><span class="o">=</span><span class="bp">False</span><span class="p">)]</span>
<span class="c"># make sure data could consumed multiple times</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="n">struct</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_inferSchemaFromList</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span>
<span class="n">struct</span><span class="o">.</span><span class="n">fields</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span>
<span class="n">struct</span><span class="o">.</span><span class="n">names</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">struct</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span>
<span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">data</span><span class="p">:</span>
<span class="n">_verify_type</span><span class="p">(</span><span class="n">row</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"schema should be StructType or list or None, but got: </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="n">schema</span><span class="p">)</span>
<span class="c"># convert python objects to sql data</span>
<span class="n">data</span> <span class="o">=</span> <span class="p">[</span><span class="n">schema</span><span class="o">.</span><span class="n">toInternal</span><span class="p">(</span><span class="n">row</span><span class="p">)</span> <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">data</span><span class="p">]</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">data</span><span class="p">),</span> <span class="n">schema</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<span class="nd">@ignore_unicode_prefix</span>
<div class="viewcode-block" id="SQLContext.createDataFrame"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.createDataFrame">[docs]</a> <span class="k">def</span> <span class="nf">createDataFrame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Creates a :class:`DataFrame` from an :class:`RDD` of :class:`tuple`/:class:`list`,</span>
<span class="sd"> list or :class:`pandas.DataFrame`.</span>
<span class="sd"> When ``schema`` is a list of column names, the type of each column</span>
<span class="sd"> will be inferred from ``data``.</span>
<span class="sd"> When ``schema`` is ``None``, it will try to infer the schema (column names and types)</span>
<span class="sd"> from ``data``, which should be an RDD of :class:`Row`,</span>
<span class="sd"> or :class:`namedtuple`, or :class:`dict`.</span>
<span class="sd"> If schema inference is needed, ``samplingRatio`` is used to determined the ratio of</span>
<span class="sd"> rows used for schema inference. The first row will be used if ``samplingRatio`` is ``None``.</span>
<span class="sd"> :param data: an RDD of :class:`Row`/:class:`tuple`/:class:`list`/:class:`dict`,</span>
<span class="sd"> :class:`list`, or :class:`pandas.DataFrame`.</span>
<span class="sd"> :param schema: a :class:`StructType` or list of column names. default None.</span>
<span class="sd"> :param samplingRatio: the sample ratio of rows used for inferring</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> >>> l = [('Alice', 1)]</span>
<span class="sd"> >>> sqlContext.createDataFrame(l).collect()</span>
<span class="sd"> [Row(_1=u'Alice', _2=1)]</span>
<span class="sd"> >>> sqlContext.createDataFrame(l, ['name', 'age']).collect()</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> >>> d = [{'name': 'Alice', 'age': 1}]</span>
<span class="sd"> >>> sqlContext.createDataFrame(d).collect()</span>
<span class="sd"> [Row(age=1, name=u'Alice')]</span>
<span class="sd"> >>> rdd = sc.parallelize(l)</span>
<span class="sd"> >>> sqlContext.createDataFrame(rdd).collect()</span>
<span class="sd"> [Row(_1=u'Alice', _2=1)]</span>
<span class="sd"> >>> df = sqlContext.createDataFrame(rdd, ['name', 'age'])</span>
<span class="sd"> >>> df.collect()</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> >>> from pyspark.sql import Row</span>
<span class="sd"> >>> Person = Row('name', 'age')</span>
<span class="sd"> >>> person = rdd.map(lambda r: Person(*r))</span>
<span class="sd"> >>> df2 = sqlContext.createDataFrame(person)</span>
<span class="sd"> >>> df2.collect()</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> >>> from pyspark.sql.types import *</span>
<span class="sd"> >>> schema = StructType([</span>
<span class="sd"> ... StructField("name", StringType(), True),</span>
<span class="sd"> ... StructField("age", IntegerType(), True)])</span>
<span class="sd"> >>> df3 = sqlContext.createDataFrame(rdd, schema)</span>
<span class="sd"> >>> df3.collect()</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> >>> sqlContext.createDataFrame(df.toPandas()).collect() # doctest: +SKIP</span>
<span class="sd"> [Row(name=u'Alice', age=1)]</span>
<span class="sd"> >>> sqlContext.createDataFrame(pandas.DataFrame([[1, 2]]).collect()) # doctest: +SKIP</span>
<span class="sd"> [Row(0=1, 1=2)]</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"data is already a DataFrame"</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_createFromRDD</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_createFromLocal</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
<span class="n">jrdd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">SerDeUtil</span><span class="o">.</span><span class="n">toJavaArray</span><span class="p">(</span><span class="n">rdd</span><span class="o">.</span><span class="n">_to_java_object_rdd</span><span class="p">())</span>
<span class="n">jdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">applySchemaToPythonRDD</span><span class="p">(</span><span class="n">jrdd</span><span class="o">.</span><span class="n">rdd</span><span class="p">(),</span> <span class="n">schema</span><span class="o">.</span><span class="n">json</span><span class="p">())</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jdf</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
<span class="n">df</span><span class="o">.</span><span class="n">_schema</span> <span class="o">=</span> <span class="n">schema</span>
<span class="k">return</span> <span class="n">df</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.registerDataFrameAsTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.registerDataFrameAsTable">[docs]</a> <span class="k">def</span> <span class="nf">registerDataFrameAsTable</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">,</span> <span class="n">tableName</span><span class="p">):</span>
<span class="sd">"""Registers the given :class:`DataFrame` as a temporary table in the catalog.</span>
<span class="sd"> Temporary tables exist only during the lifetime of this instance of :class:`SQLContext`.</span>
<span class="sd"> >>> sqlContext.registerDataFrameAsTable(df, "table1")</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">__class__</span> <span class="ow">is</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">registerDataFrameAsTable</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">,</span> <span class="n">tableName</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Can only register DataFrame as table"</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="SQLContext.parquetFile"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.parquetFile">[docs]</a> <span class="k">def</span> <span class="nf">parquetFile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">paths</span><span class="p">):</span>
<span class="sd">"""Loads a Parquet file, returning the result as a :class:`DataFrame`.</span>
<span class="sd"> .. note:: Deprecated in 1.4, use :func:`DataFrameReader.parquet` instead.</span>
<span class="sd"> >>> sqlContext.parquetFile('python/test_support/sql/parquet_partitioned').dtypes</span>
<span class="sd"> [('name', 'string'), ('year', 'int'), ('month', 'int'), ('day', 'int')]</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"parquetFile is deprecated. Use read.parquet() instead."</span><span class="p">)</span>
<span class="n">gateway</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span>
<span class="n">jpaths</span> <span class="o">=</span> <span class="n">gateway</span><span class="o">.</span><span class="n">new_array</span><span class="p">(</span><span class="n">gateway</span><span class="o">.</span><span class="n">jvm</span><span class="o">.</span><span class="n">java</span><span class="o">.</span><span class="n">lang</span><span class="o">.</span><span class="n">String</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">paths</span><span class="p">))</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">paths</span><span class="p">)):</span>
<span class="n">jpaths</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">paths</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
<span class="n">jdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">parquetFile</span><span class="p">(</span><span class="n">jpaths</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jdf</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="SQLContext.jsonFile"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.jsonFile">[docs]</a> <span class="k">def</span> <span class="nf">jsonFile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="sd">"""Loads a text file storing one JSON object per line as a :class:`DataFrame`.</span>
<span class="sd"> .. note:: Deprecated in 1.4, use :func:`DataFrameReader.json` instead.</span>
<span class="sd"> >>> sqlContext.jsonFile('python/test_support/sql/people.json').dtypes</span>
<span class="sd"> [('age', 'bigint'), ('name', 'string')]</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"jsonFile is deprecated. Use read.json() instead."</span><span class="p">)</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">jsonFile</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">scala_datatype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">parseDataType</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">json</span><span class="p">())</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">jsonFile</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">scala_datatype</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@ignore_unicode_prefix</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.jsonRDD"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.jsonRDD">[docs]</a> <span class="k">def</span> <span class="nf">jsonRDD</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">samplingRatio</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="sd">"""Loads an RDD storing one JSON object per string as a :class:`DataFrame`.</span>
<span class="sd"> If the schema is provided, applies the given schema to this JSON dataset.</span>
<span class="sd"> Otherwise, it samples the dataset with ratio ``samplingRatio`` to determine the schema.</span>
<span class="sd"> >>> df1 = sqlContext.jsonRDD(json)</span>
<span class="sd"> >>> df1.first()</span>
<span class="sd"> Row(field1=1, field2=u'row1', field3=Row(field4=11, field5=None), field6=None)</span>
<span class="sd"> >>> df2 = sqlContext.jsonRDD(json, df1.schema)</span>
<span class="sd"> >>> df2.first()</span>
<span class="sd"> Row(field1=1, field2=u'row1', field3=Row(field4=11, field5=None), field6=None)</span>
<span class="sd"> >>> from pyspark.sql.types import *</span>
<span class="sd"> >>> schema = StructType([</span>
<span class="sd"> ... StructField("field2", StringType()),</span>
<span class="sd"> ... StructField("field3",</span>
<span class="sd"> ... StructType([StructField("field5", ArrayType(IntegerType()))]))</span>
<span class="sd"> ... ])</span>
<span class="sd"> >>> df3 = sqlContext.jsonRDD(json, schema)</span>
<span class="sd"> >>> df3.first()</span>
<span class="sd"> Row(field2=u'row1', field3=Row(field5=None))</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="n">iterator</span><span class="p">):</span>
<span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
<span class="n">x</span> <span class="o">=</span> <span class="nb">unicode</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">unicode</span><span class="p">):</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s">"utf-8"</span><span class="p">)</span>
<span class="k">yield</span> <span class="n">x</span>
<span class="n">keyed</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">mapPartitions</span><span class="p">(</span><span class="n">func</span><span class="p">)</span>
<span class="n">keyed</span><span class="o">.</span><span class="n">_bypass_serializer</span> <span class="o">=</span> <span class="bp">True</span>
<span class="n">jrdd</span> <span class="o">=</span> <span class="n">keyed</span><span class="o">.</span><span class="n">_jrdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">BytesToString</span><span class="p">())</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">jsonRDD</span><span class="p">(</span><span class="n">jrdd</span><span class="o">.</span><span class="n">rdd</span><span class="p">(),</span> <span class="n">samplingRatio</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">scala_datatype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">parseDataType</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">json</span><span class="p">())</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">jsonRDD</span><span class="p">(</span><span class="n">jrdd</span><span class="o">.</span><span class="n">rdd</span><span class="p">(),</span> <span class="n">scala_datatype</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="SQLContext.load"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">):</span>
<span class="sd">"""Returns the dataset in a data source as a :class:`DataFrame`.</span>
<span class="sd"> .. note:: Deprecated in 1.4, use :func:`DataFrameReader.load` instead.</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"load is deprecated. Use read.load() instead."</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">read</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.createExternalTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.createExternalTable">[docs]</a> <span class="k">def</span> <span class="nf">createExternalTable</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">,</span> <span class="n">path</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">):</span>
<span class="sd">"""Creates an external table based on the dataset in a data source.</span>
<span class="sd"> It returns the DataFrame associated with the external table.</span>
<span class="sd"> The data source is specified by the ``source`` and a set of ``options``.</span>
<span class="sd"> If ``source`` is not specified, the default data source configured by</span>
<span class="sd"> ``spark.sql.sources.default`` will be used.</span>
<span class="sd"> Optionally, a schema can be provided as the schema of the returned :class:`DataFrame` and</span>
<span class="sd"> created external table.</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">path</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">options</span><span class="p">[</span><span class="s">"path"</span><span class="p">]</span> <span class="o">=</span> <span class="n">path</span>
<span class="k">if</span> <span class="n">source</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">source</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getConf</span><span class="p">(</span><span class="s">"spark.sql.sources.default"</span><span class="p">,</span>
<span class="s">"org.apache.spark.sql.parquet"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">createExternalTable</span><span class="p">(</span><span class="n">tableName</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"schema should be StructType"</span><span class="p">)</span>
<span class="n">scala_datatype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">parseDataType</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">json</span><span class="p">())</span>
<span class="n">df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">createExternalTable</span><span class="p">(</span><span class="n">tableName</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">scala_datatype</span><span class="p">,</span>
<span class="n">options</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@ignore_unicode_prefix</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.sql"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.sql">[docs]</a> <span class="k">def</span> <span class="nf">sql</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sqlQuery</span><span class="p">):</span>
<span class="sd">"""Returns a :class:`DataFrame` representing the result of the given query.</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> >>> sqlContext.registerDataFrameAsTable(df, "table1")</span>
<span class="sd"> >>> df2 = sqlContext.sql("SELECT field1 AS f1, field2 as f2 from table1")</span>
<span class="sd"> >>> df2.collect()</span>
<span class="sd"> [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="n">sqlQuery</span><span class="p">),</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.table"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.table">[docs]</a> <span class="k">def</span> <span class="nf">table</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">):</span>
<span class="sd">"""Returns the specified table as a :class:`DataFrame`.</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> >>> sqlContext.registerDataFrameAsTable(df, "table1")</span>
<span class="sd"> >>> df2 = sqlContext.table("table1")</span>
<span class="sd"> >>> sorted(df.collect()) == sorted(df2.collect())</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="n">tableName</span><span class="p">),</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@ignore_unicode_prefix</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.tables"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.tables">[docs]</a> <span class="k">def</span> <span class="nf">tables</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dbName</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Returns a :class:`DataFrame` containing names of tables in the given database.</span>
<span class="sd"> If ``dbName`` is not specified, the current database will be used.</span>
<span class="sd"> The returned DataFrame has two columns: ``tableName`` and ``isTemporary``</span>
<span class="sd"> (a column with :class:`BooleanType` indicating if a table is a temporary one or not).</span>
<span class="sd"> :param dbName: string, name of the database to use.</span>
<span class="sd"> :return: :class:`DataFrame`</span>
<span class="sd"> >>> sqlContext.registerDataFrameAsTable(df, "table1")</span>
<span class="sd"> >>> df2 = sqlContext.tables()</span>
<span class="sd"> >>> df2.filter("tableName = 'table1'").first()</span>
<span class="sd"> Row(tableName=u'table1', isTemporary=True)</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">dbName</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">tables</span><span class="p">(),</span> <span class="bp">self</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">tables</span><span class="p">(</span><span class="n">dbName</span><span class="p">),</span> <span class="bp">self</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.tableNames"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.tableNames">[docs]</a> <span class="k">def</span> <span class="nf">tableNames</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dbName</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Returns a list of names of tables in the database ``dbName``.</span>
<span class="sd"> :param dbName: string, name of the database to use. Default to the current database.</span>
<span class="sd"> :return: list of table names, in string</span>
<span class="sd"> >>> sqlContext.registerDataFrameAsTable(df, "table1")</span>
<span class="sd"> >>> "table1" in sqlContext.tableNames()</span>
<span class="sd"> True</span>
<span class="sd"> >>> "table1" in sqlContext.tableNames("db")</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">dbName</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="p">[</span><span class="n">name</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">tableNames</span><span class="p">()]</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="p">[</span><span class="n">name</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">tableNames</span><span class="p">(</span><span class="n">dbName</span><span class="p">)]</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.cacheTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.cacheTable">[docs]</a> <span class="k">def</span> <span class="nf">cacheTable</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">):</span>
<span class="sd">"""Caches the specified table in-memory."""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">cacheTable</span><span class="p">(</span><span class="n">tableName</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.uncacheTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.uncacheTable">[docs]</a> <span class="k">def</span> <span class="nf">uncacheTable</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">):</span>
<span class="sd">"""Removes the specified table from the in-memory cache."""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">uncacheTable</span><span class="p">(</span><span class="n">tableName</span><span class="p">)</span>
</div>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.3</span><span class="p">)</span>
<div class="viewcode-block" id="SQLContext.clearCache"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.SQLContext.clearCache">[docs]</a> <span class="k">def</span> <span class="nf">clearCache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Removes all cached tables from the in-memory cache. """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">clearCache</span><span class="p">()</span>
</div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns a :class:`DataFrameReader` that can be used to read data</span>
<span class="sd"> in as a :class:`DataFrame`.</span>
<span class="sd"> :return: :class:`DataFrameReader`</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">DataFrameReader</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="HiveContext"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.HiveContext">[docs]</a><span class="k">class</span> <span class="nc">HiveContext</span><span class="p">(</span><span class="n">SQLContext</span><span class="p">):</span>
<span class="sd">"""A variant of Spark SQL that integrates with data stored in Hive.</span>
<span class="sd"> Configuration for Hive is read from ``hive-site.xml`` on the classpath.</span>
<span class="sd"> It supports running both SQL and HiveQL commands.</span>
<span class="sd"> :param sparkContext: The SparkContext to wrap.</span>
<span class="sd"> :param hiveContext: An optional JVM Scala HiveContext. If set, we do not instantiate a new</span>
<span class="sd"> :class:`HiveContext` in the JVM, instead we make all calls to this object.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sparkContext</span><span class="p">,</span> <span class="n">hiveContext</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="n">SQLContext</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sparkContext</span><span class="p">)</span>
<span class="k">if</span> <span class="n">hiveContext</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scala_HiveContext</span> <span class="o">=</span> <span class="n">hiveContext</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">_ssql_ctx</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">'_scala_HiveContext'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scala_HiveContext</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_hive_ctx</span><span class="p">()</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scala_HiveContext</span>
<span class="k">except</span> <span class="n">Py4JError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s">"You must build Spark with Hive. "</span>
<span class="s">"Export 'SPARK_HIVE=true' and run "</span>
<span class="s">"build/sbt assembly"</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_get_hive_ctx</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">HiveContext</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">())</span>
<div class="viewcode-block" id="HiveContext.refreshTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.HiveContext.refreshTable">[docs]</a> <span class="k">def</span> <span class="nf">refreshTable</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">):</span>
<span class="sd">"""Invalidate and refresh all the cached the metadata of the given</span>
<span class="sd"> table. For performance reasons, Spark SQL or the external data source</span>
<span class="sd"> library it uses might cache certain metadata about a table, such as the</span>
<span class="sd"> location of blocks. When those change outside of Spark SQL, users should</span>
<span class="sd"> call this function to invalidate the cache.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">refreshTable</span><span class="p">(</span><span class="n">tableName</span><span class="p">)</span>
</div></div>
<span class="k">class</span> <span class="nc">UDFRegistration</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Wrapper for user-defined function registration."""</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sqlContext</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sqlContext</span> <span class="o">=</span> <span class="n">sqlContext</span>
<span class="k">def</span> <span class="nf">register</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">returnType</span><span class="o">=</span><span class="n">StringType</span><span class="p">()):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">sqlContext</span><span class="o">.</span><span class="n">registerFunction</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">returnType</span><span class="p">)</span>
<span class="n">register</span><span class="o">.</span><span class="n">__doc__</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">registerFunction</span><span class="o">.</span><span class="n">__doc__</span>
<span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">doctest</span>
<span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">Row</span><span class="p">,</span> <span class="n">SQLContext</span>
<span class="kn">import</span> <span class="nn">pyspark.sql.context</span>
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s">"SPARK_HOME"</span><span class="p">])</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">'local[4]'</span><span class="p">,</span> <span class="s">'PythonTest'</span><span class="p">)</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">sc</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sqlContext'</span><span class="p">]</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'rdd'</span><span class="p">]</span> <span class="o">=</span> <span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span>
<span class="p">[</span><span class="n">Row</span><span class="p">(</span><span class="n">field1</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">field2</span><span class="o">=</span><span class="s">"row1"</span><span class="p">),</span>
<span class="n">Row</span><span class="p">(</span><span class="n">field1</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">field2</span><span class="o">=</span><span class="s">"row2"</span><span class="p">),</span>
<span class="n">Row</span><span class="p">(</span><span class="n">field1</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">field2</span><span class="o">=</span><span class="s">"row3"</span><span class="p">)]</span>
<span class="p">)</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'df'</span><span class="p">]</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span>
<span class="n">jsonStrings</span> <span class="o">=</span> <span class="p">[</span>
<span class="s">'{"field1": 1, "field2": "row1", "field3":{"field4":11}}'</span><span class="p">,</span>
<span class="s">'{"field1" : 2, "field3":{"field4":22, "field5": [10, 11]},'</span>
<span class="s">'"field6":[{"field7": "row2"}]}'</span><span class="p">,</span>
<span class="s">'{"field1" : null, "field2": "row3", '</span>
<span class="s">'"field3":{"field4":33, "field5": []}}'</span>
<span class="p">]</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'jsonStrings'</span><span class="p">]</span> <span class="o">=</span> <span class="n">jsonStrings</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'json'</span><span class="p">]</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">jsonStrings</span><span class="p">)</span>
<span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span>
<span class="n">pyspark</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">context</span><span class="p">,</span> <span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span>
<span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span> <span class="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</span><span class="p">)</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sc'</span><span class="p">]</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
<span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
<span class="nb">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="n">__name__</span> <span class="o">==</span> <span class="s">"__main__"</span><span class="p">:</span>
<span class="n">_test</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../../index.html">
<img class="logo" src="../../../_static/spark-logo-hd.png" alt="Logo"/>
</a></p>
<div id="searchbox" style="display: none" role="search">
<h3>Quick search</h3>
<form class="search" action="../../../search.html" method="get">
<input type="text" name="q" />
<input type="submit" value="Go" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
<p class="searchtip" style="font-size: 90%">
Enter search terms or a module, class or function name.
</p>
</div>
<script type="text/javascript">$('#searchbox').show(0);</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
</ul>
</div>
<div class="footer" role="contentinfo">
© Copyright .
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
</div>
</body>
</html>
|
