site/docs/1.5.0/api/python/_modules/pyspark/sql/readwriter.html


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

<!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.readwriter &mdash; PySpark 1.5.0 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:     '1.5.0',
        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 1.5.0 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 1.5.0 documentation</a> &raquo;</li>
          <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &raquo;</li> 
      </ul>
    </div>  

    <div class="document">
      <div class="documentwrapper">
        <div class="bodywrapper">
          <div class="body" role="main">
            
  <h1>Source code for pyspark.sql.readwriter</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaClass</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.column</span> <span class="kn">import</span> <span class="n">_to_seq</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="o">*</span>

<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">&quot;DataFrameReader&quot;</span><span class="p">,</span> <span class="s">&quot;DataFrameWriter&quot;</span><span class="p">]</span>


<span class="k">def</span> <span class="nf">to_str</span><span class="p">(</span><span class="n">value</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    A wrapper over str(), but convert bool values to lower case string</span>
<span class="sd">    &quot;&quot;&quot;</span>
    <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="nb">bool</span><span class="p">):</span>
        <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
    <span class="k">else</span><span class="p">:</span>
        <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>


<div class="viewcode-block" id="DataFrameReader"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader">[docs]</a><span class="k">class</span> <span class="nc">DataFrameReader</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Interface used to load a :class:`DataFrame` from external storage systems</span>
<span class="sd">    (e.g. file systems, key-value stores, etc). Use :func:`SQLContext.read`</span>
<span class="sd">    to access this.</span>

<span class="sd">    ::Note: Experimental</span>

<span class="sd">    .. versionadded:: 1.4</span>
<span class="sd">    &quot;&quot;&quot;</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">_jreader</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">_ssql_ctx</span><span class="o">.</span><span class="n">read</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">_df</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jdf</span><span class="p">):</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="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="o">.</span><span class="n">_sqlContext</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="DataFrameReader.format"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.format">[docs]</a>    <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Specifies the input data source format.</span>

<span class="sd">        :param source: string, name of the data source, e.g. &#39;json&#39;, &#39;parquet&#39;.</span>

<span class="sd">        &gt;&gt;&gt; df = sqlContext.read.format(&#39;json&#39;).load(&#39;python/test_support/sql/people.json&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.dtypes</span>
<span class="sd">        [(&#39;age&#39;, &#39;bigint&#39;), (&#39;name&#39;, &#39;string&#39;)]</span>

<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">source</span><span class="p">)</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.schema"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.schema">[docs]</a>    <span class="k">def</span> <span class="nf">schema</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="sd">&quot;&quot;&quot;Specifies the input schema.</span>

<span class="sd">        Some data sources (e.g. JSON) can infer the input schema automatically from data.</span>
<span class="sd">        By specifying the schema here, the underlying data source can skip the schema</span>
<span class="sd">        inference step, and thus speed up data loading.</span>

<span class="sd">        :param schema: a StructType object</span>
<span class="sd">        &quot;&quot;&quot;</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">&quot;schema should be StructType&quot;</span><span class="p">)</span>
        <span class="n">jschema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sqlContext</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="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">jschema</span><span class="p">)</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.5</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.option"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.option">[docs]</a>    <span class="k">def</span> <span class="nf">option</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">&quot;&quot;&quot;Adds an input option for the underlying data source.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">value</span><span class="p">))</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.options"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.options">[docs]</a>    <span class="k">def</span> <span class="nf">options</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Adds input options for the underlying data source.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">options</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">options</span><span class="p">[</span><span class="n">k</span><span class="p">]))</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.load"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.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">format</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">&quot;&quot;&quot;Loads data from a data source and returns it as a :class`DataFrame`.</span>

<span class="sd">        :param path: optional string for file-system backed data sources.</span>
<span class="sd">        :param format: optional string for format of the data source. Default to &#39;parquet&#39;.</span>
<span class="sd">        :param schema: optional :class:`StructType` for the input schema.</span>
<span class="sd">        :param options: all other string options</span>

<span class="sd">        &gt;&gt;&gt; df = sqlContext.read.load(&#39;python/test_support/sql/parquet_partitioned&#39;, opt1=True,</span>
<span class="sd">        ...     opt2=1, opt3=&#39;str&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.dtypes</span>
<span class="sd">        [(&#39;name&#39;, &#39;string&#39;), (&#39;year&#39;, &#39;int&#39;), (&#39;month&#39;, &#39;int&#39;), (&#39;day&#39;, &#39;int&#39;)]</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="n">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">format</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</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="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</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="k">else</span><span class="p">:</span>
            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">load</span><span class="p">())</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.json"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.json">[docs]</a>    <span class="k">def</span> <span class="nf">json</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="sd">&quot;&quot;&quot;</span>
<span class="sd">        Loads a JSON file (one object per line) and returns the result as</span>
<span class="sd">        a :class`DataFrame`.</span>

<span class="sd">        If the ``schema`` parameter is not specified, this function goes</span>
<span class="sd">        through the input once to determine the input schema.</span>

<span class="sd">        :param path: string, path to the JSON dataset.</span>
<span class="sd">        :param schema: an optional :class:`StructType` for the input schema.</span>

<span class="sd">        &gt;&gt;&gt; df = sqlContext.read.json(&#39;python/test_support/sql/people.json&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.dtypes</span>
<span class="sd">        [(&#39;age&#39;, &#39;bigint&#39;), (&#39;name&#39;, &#39;string&#39;)]</span>

<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">schema</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">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">json</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.table"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.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">&quot;&quot;&quot;Returns the specified table as a :class:`DataFrame`.</span>

<span class="sd">        :param tableName: string, name of the table.</span>

<span class="sd">        &gt;&gt;&gt; df = sqlContext.read.parquet(&#39;python/test_support/sql/parquet_partitioned&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.registerTempTable(&#39;tmpTable&#39;)</span>
<span class="sd">        &gt;&gt;&gt; sqlContext.read.table(&#39;tmpTable&#39;).dtypes</span>
<span class="sd">        [(&#39;name&#39;, &#39;string&#39;), (&#39;year&#39;, &#39;int&#39;), (&#39;month&#39;, &#39;int&#39;), (&#39;day&#39;, &#39;int&#39;)]</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">table</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">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.parquet"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.parquet">[docs]</a>    <span class="k">def</span> <span class="nf">parquet</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">&quot;&quot;&quot;Loads a Parquet file, returning the result as a :class:`DataFrame`.</span>

<span class="sd">        &gt;&gt;&gt; df = sqlContext.read.parquet(&#39;python/test_support/sql/parquet_partitioned&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.dtypes</span>
<span class="sd">        [(&#39;name&#39;, &#39;string&#39;), (&#39;year&#39;, &#39;int&#39;), (&#39;month&#39;, &#39;int&#39;), (&#39;day&#39;, &#39;int&#39;)]</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">parquet</span><span class="p">(</span><span class="n">_to_seq</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">_sc</span><span class="p">,</span> <span class="n">paths</span><span class="p">)))</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.5</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.orc"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.orc">[docs]</a>    <span class="k">def</span> <span class="nf">orc</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="sd">&quot;&quot;&quot;</span>
<span class="sd">        Loads an ORC file, returning the result as a :class:`DataFrame`.</span>

<span class="sd">        ::Note: Currently ORC support is only available together with</span>
<span class="sd">        :class:`HiveContext`.</span>

<span class="sd">        &gt;&gt;&gt; df = hiveContext.read.orc(&#39;python/test_support/sql/orc_partitioned&#39;)</span>
<span class="sd">        &gt;&gt;&gt; df.dtypes</span>
<span class="sd">        [(&#39;a&#39;, &#39;bigint&#39;), (&#39;b&#39;, &#39;int&#39;), (&#39;c&#39;, &#39;int&#39;)]</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">orc</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameReader.jdbc"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameReader.jdbc">[docs]</a>    <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">column</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">lowerBound</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">upperBound</span><span class="o">=</span><span class="bp">None</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="n">predicates</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">properties</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Construct a :class:`DataFrame` representing the database table accessible</span>
<span class="sd">        via JDBC URL `url` named `table` and connection `properties`.</span>

<span class="sd">        The `column` parameter could be used to partition the table, then it will</span>
<span class="sd">        be retrieved in parallel based on the parameters passed to this function.</span>

<span class="sd">        The `predicates` parameter gives a list expressions suitable for inclusion</span>
<span class="sd">        in WHERE clauses; each one defines one partition of the :class:`DataFrame`.</span>

<span class="sd">        ::Note: Don&#39;t create too many partitions in parallel on a large cluster;</span>
<span class="sd">        otherwise Spark might crash your external database systems.</span>

<span class="sd">        :param url: a JDBC URL</span>
<span class="sd">        :param table: name of table</span>
<span class="sd">        :param column: the column used to partition</span>
<span class="sd">        :param lowerBound: the lower bound of partition column</span>
<span class="sd">        :param upperBound: the upper bound of the partition column</span>
<span class="sd">        :param numPartitions: the number of partitions</span>
<span class="sd">        :param predicates: a list of expressions</span>
<span class="sd">        :param properties: JDBC database connection arguments, a list of arbitrary string</span>
<span class="sd">                           tag/value. Normally at least a &quot;user&quot; and &quot;password&quot; property</span>
<span class="sd">                           should be included.</span>
<span class="sd">        :return: a DataFrame</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="n">properties</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
            <span class="n">properties</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
        <span class="n">jprop</span> <span class="o">=</span> <span class="n">JavaClass</span><span class="p">(</span><span class="s">&quot;java.util.Properties&quot;</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">_sc</span><span class="o">.</span><span class="n">_gateway</span><span class="o">.</span><span class="n">_gateway_client</span><span class="p">)()</span>
        <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">properties</span><span class="p">:</span>
            <span class="n">jprop</span><span class="o">.</span><span class="n">setProperty</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">properties</span><span class="p">[</span><span class="n">k</span><span class="p">])</span>
        <span class="k">if</span> <span class="n">column</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</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">_sqlContext</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">defaultParallelism</span>
            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">lowerBound</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">upperBound</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="n">jprop</span><span class="p">))</span>
        <span class="k">if</span> <span class="n">predicates</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="n">arr</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sqlContext</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toArray</span><span class="p">(</span><span class="n">predicates</span><span class="p">)</span>
            <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">arr</span><span class="p">,</span> <span class="n">jprop</span><span class="p">))</span>
        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">jprop</span><span class="p">))</span>

</div></div>
<div class="viewcode-block" id="DataFrameWriter"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter">[docs]</a><span class="k">class</span> <span class="nc">DataFrameWriter</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Interface used to write a [[DataFrame]] to external storage systems</span>
<span class="sd">    (e.g. file systems, key-value stores, etc). Use :func:`DataFrame.write`</span>
<span class="sd">    to access this.</span>

<span class="sd">    ::Note: Experimental</span>

<span class="sd">    .. versionadded:: 1.4</span>
<span class="sd">    &quot;&quot;&quot;</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">df</span><span class="p">):</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_df</span> <span class="o">=</span> <span class="n">df</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_sqlContext</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">sql_ctx</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="o">.</span><span class="n">write</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="DataFrameWriter.mode"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.mode">[docs]</a>    <span class="k">def</span> <span class="nf">mode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">saveMode</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Specifies the behavior when data or table already exists.</span>

<span class="sd">        Options include:</span>

<span class="sd">        * `append`: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">        * `overwrite`: Overwrite existing data.</span>
<span class="sd">        * `error`: Throw an exception if data already exists.</span>
<span class="sd">        * `ignore`: Silently ignore this operation if data already exists.</span>

<span class="sd">        &gt;&gt;&gt; df.write.mode(&#39;append&#39;).parquet(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="c"># At the JVM side, the default value of mode is already set to &quot;error&quot;.</span>
        <span class="c"># So, if the given saveMode is None, we will not call JVM-side&#39;s mode method.</span>
        <span class="k">if</span> <span class="n">saveMode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">saveMode</span><span class="p">)</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.format"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.format">[docs]</a>    <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Specifies the underlying output data source.</span>

<span class="sd">        :param source: string, name of the data source, e.g. &#39;json&#39;, &#39;parquet&#39;.</span>

<span class="sd">        &gt;&gt;&gt; df.write.format(&#39;json&#39;).save(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">source</span><span class="p">)</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.5</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.option"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.option">[docs]</a>    <span class="k">def</span> <span class="nf">option</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">&quot;&quot;&quot;Adds an output option for the underlying data source.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">option</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="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.options"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.options">[docs]</a>    <span class="k">def</span> <span class="nf">options</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Adds output options for the underlying data source.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">options</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">options</span><span class="p">[</span><span class="n">k</span><span class="p">])</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.partitionBy"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.partitionBy">[docs]</a>    <span class="k">def</span> <span class="nf">partitionBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Partitions the output by the given columns on the file system.</span>

<span class="sd">        If specified, the output is laid out on the file system similar</span>
<span class="sd">        to Hive&#39;s partitioning scheme.</span>

<span class="sd">        :param cols: name of columns</span>

<span class="sd">        &gt;&gt;&gt; df.write.partitionBy(&#39;year&#39;, &#39;month&#39;).parquet(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">cols</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cols</span><span class="p">[</span><span class="mi">0</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">cols</span> <span class="o">=</span> <span class="n">cols</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">_to_seq</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">_sc</span><span class="p">,</span> <span class="n">cols</span><span class="p">))</span>
        <span class="k">return</span> <span class="bp">self</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.save"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.save">[docs]</a>    <span class="k">def</span> <span class="nf">save</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">format</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">partitionBy</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">&quot;&quot;&quot;Saves the contents of the :class:`DataFrame` to a data source.</span>

<span class="sd">        The data source is specified by the ``format`` and a set of ``options``.</span>
<span class="sd">        If ``format`` is not specified, the default data source configured by</span>
<span class="sd">        ``spark.sql.sources.default`` will be used.</span>

<span class="sd">        :param path: the path in a Hadoop supported file system</span>
<span class="sd">        :param format: the format used to save</span>
<span class="sd">        :param mode: specifies the behavior of the save operation when data already exists.</span>

<span class="sd">            * ``append``: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">            * ``overwrite``: Overwrite existing data.</span>
<span class="sd">            * ``ignore``: Silently ignore this operation if data already exists.</span>
<span class="sd">            * ``error`` (default case): Throw an exception if data already exists.</span>
<span class="sd">        :param partitionBy: names of partitioning columns</span>
<span class="sd">        :param options: all other string options</span>

<span class="sd">        &gt;&gt;&gt; df.write.mode(&#39;append&#39;).parquet(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">format</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">path</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">_jwrite</span><span class="o">.</span><span class="n">save</span><span class="p">()</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.insertInto"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.insertInto">[docs]</a>    <span class="k">def</span> <span class="nf">insertInto</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">overwrite</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Inserts the content of the :class:`DataFrame` to the specified table.</span>

<span class="sd">        It requires that the schema of the class:`DataFrame` is the same as the</span>
<span class="sd">        schema of the table.</span>

<span class="sd">        Optionally overwriting any existing data.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="s">&quot;overwrite&quot;</span> <span class="k">if</span> <span class="n">overwrite</span> <span class="k">else</span> <span class="s">&quot;append&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">insertInto</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">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.saveAsTable"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.saveAsTable">[docs]</a>    <span class="k">def</span> <span class="nf">saveAsTable</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">format</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">partitionBy</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">&quot;&quot;&quot;Saves the content of the :class:`DataFrame` as the specified table.</span>

<span class="sd">        In the case the table already exists, behavior of this function depends on the</span>
<span class="sd">        save mode, specified by the `mode` function (default to throwing an exception).</span>
<span class="sd">        When `mode` is `Overwrite`, the schema of the [[DataFrame]] does not need to be</span>
<span class="sd">        the same as that of the existing table.</span>

<span class="sd">        * `append`: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">        * `overwrite`: Overwrite existing data.</span>
<span class="sd">        * `error`: Throw an exception if data already exists.</span>
<span class="sd">        * `ignore`: Silently ignore this operation if data already exists.</span>

<span class="sd">        :param name: the table name</span>
<span class="sd">        :param format: the format used to save</span>
<span class="sd">        :param mode: one of `append`, `overwrite`, `error`, `ignore` (default: error)</span>
<span class="sd">        :param partitionBy: names of partitioning columns</span>
<span class="sd">        :param options: all other string options</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">format</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">saveAsTable</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.json"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.json">[docs]</a>    <span class="k">def</span> <span class="nf">json</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">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Saves the content of the :class:`DataFrame` in JSON format at the specified path.</span>

<span class="sd">        :param path: the path in any Hadoop supported file system</span>
<span class="sd">        :param mode: specifies the behavior of the save operation when data already exists.</span>

<span class="sd">            * ``append``: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">            * ``overwrite``: Overwrite existing data.</span>
<span class="sd">            * ``ignore``: Silently ignore this operation if data already exists.</span>
<span class="sd">            * ``error`` (default case): Throw an exception if data already exists.</span>

<span class="sd">        &gt;&gt;&gt; df.write.json(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">json</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.parquet"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.parquet">[docs]</a>    <span class="k">def</span> <span class="nf">parquet</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">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">partitionBy</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Saves the content of the :class:`DataFrame` in Parquet format at the specified path.</span>

<span class="sd">        :param path: the path in any Hadoop supported file system</span>
<span class="sd">        :param mode: specifies the behavior of the save operation when data already exists.</span>

<span class="sd">            * ``append``: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">            * ``overwrite``: Overwrite existing data.</span>
<span class="sd">            * ``ignore``: Silently ignore this operation if data already exists.</span>
<span class="sd">            * ``error`` (default case): Throw an exception if data already exists.</span>
<span class="sd">        :param partitionBy: names of partitioning columns</span>

<span class="sd">        &gt;&gt;&gt; df.write.parquet(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">parquet</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="DataFrameWriter.orc"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.orc">[docs]</a>    <span class="k">def</span> <span class="nf">orc</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">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">partitionBy</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Saves the content of the :class:`DataFrame` in ORC format at the specified path.</span>

<span class="sd">        ::Note: Currently ORC support is only available together with</span>
<span class="sd">        :class:`HiveContext`.</span>

<span class="sd">        :param path: the path in any Hadoop supported file system</span>
<span class="sd">        :param mode: specifies the behavior of the save operation when data already exists.</span>

<span class="sd">            * ``append``: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">            * ``overwrite``: Overwrite existing data.</span>
<span class="sd">            * ``ignore``: Silently ignore this operation if data already exists.</span>
<span class="sd">            * ``error`` (default case): Throw an exception if data already exists.</span>
<span class="sd">        :param partitionBy: names of partitioning columns</span>

<span class="sd">        &gt;&gt;&gt; orc_df = hiveContext.read.orc(&#39;python/test_support/sql/orc_partitioned&#39;)</span>
<span class="sd">        &gt;&gt;&gt; orc_df.write.orc(os.path.join(tempfile.mkdtemp(), &#39;data&#39;))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">orc</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
</div>
    <span class="nd">@since</span><span class="p">(</span><span class="mf">1.4</span><span class="p">)</span>
<div class="viewcode-block" id="DataFrameWriter.jdbc"><a class="viewcode-back" href="../../../pyspark.sql.html#pyspark.sql.DataFrameWriter.jdbc">[docs]</a>    <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">properties</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Saves the content of the :class:`DataFrame` to a external database table via JDBC.</span>

<span class="sd">        .. note:: Don&#39;t create too many partitions in parallel on a large cluster;\</span>
<span class="sd">        otherwise Spark might crash your external database systems.</span>

<span class="sd">        :param url: a JDBC URL of the form ``jdbc:subprotocol:subname``</span>
<span class="sd">        :param table: Name of the table in the external database.</span>
<span class="sd">        :param mode: specifies the behavior of the save operation when data already exists.</span>

<span class="sd">            * ``append``: Append contents of this :class:`DataFrame` to existing data.</span>
<span class="sd">            * ``overwrite``: Overwrite existing data.</span>
<span class="sd">            * ``ignore``: Silently ignore this operation if data already exists.</span>
<span class="sd">            * ``error`` (default case): Throw an exception if data already exists.</span>
<span class="sd">        :param properties: JDBC database connection arguments, a list of</span>
<span class="sd">                           arbitrary string tag/value. Normally at least a</span>
<span class="sd">                           &quot;user&quot; and &quot;password&quot; property should be included.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="n">properties</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
            <span class="n">properties</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
        <span class="n">jprop</span> <span class="o">=</span> <span class="n">JavaClass</span><span class="p">(</span><span class="s">&quot;java.util.Properties&quot;</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">_sc</span><span class="o">.</span><span class="n">_gateway</span><span class="o">.</span><span class="n">_gateway_client</span><span class="p">)()</span>
        <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">properties</span><span class="p">:</span>
            <span class="n">jprop</span><span class="o">.</span><span class="n">setProperty</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">properties</span><span class="p">[</span><span class="n">k</span><span class="p">])</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">jprop</span><span class="p">)</span>

</div></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
    <span class="kn">import</span> <span class="nn">doctest</span>
    <span class="kn">import</span> <span class="nn">os</span>
    <span class="kn">import</span> <span class="nn">tempfile</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="p">,</span> <span class="n">HiveContext</span>
    <span class="kn">import</span> <span class="nn">pyspark.sql.readwriter</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">&quot;SPARK_HOME&quot;</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">readwriter</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">&#39;local[4]&#39;</span><span class="p">,</span> <span class="s">&#39;PythonTest&#39;</span><span class="p">)</span>

    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;tempfile&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">tempfile</span>
    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;os&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">os</span>
    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;sc&#39;</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">&#39;sqlContext&#39;</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">&#39;hiveContext&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">HiveContext</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">&#39;df&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">globs</span><span class="p">[</span><span class="s">&#39;sqlContext&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">read</span><span class="o">.</span><span class="n">parquet</span><span class="p">(</span><span class="s">&#39;python/test_support/sql/parquet_partitioned&#39;</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">readwriter</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="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">REPORT_NDIFF</span><span class="p">)</span>
    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;sc&#39;</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">&quot;__main__&quot;</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 1.5.0 documentation</a> &raquo;</li>
          <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &raquo;</li> 
      </ul>
    </div>
    <div class="footer" role="contentinfo">
        &copy; Copyright .
      Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
    </div>
  </body>
</html>