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
|
<!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.ml.recommendation — 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> »</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.ml.recommendation</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">from</span> <span class="nn">pyspark.ml.util</span> <span class="kn">import</span> <span class="n">keyword_only</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">JavaModel</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.param.shared</span> <span class="kn">import</span> <span class="o">*</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'ALS'</span><span class="p">,</span> <span class="s">'ALSModel'</span><span class="p">]</span>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="ALS"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS">[docs]</a><span class="k">class</span> <span class="nc">ALS</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasCheckpointInterval</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasRegParam</span><span class="p">,</span> <span class="n">HasSeed</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Alternating Least Squares (ALS) matrix factorization.</span>
<span class="sd"> ALS attempts to estimate the ratings matrix `R` as the product of</span>
<span class="sd"> two lower-rank matrices, `X` and `Y`, i.e. `X * Yt = R`. Typically</span>
<span class="sd"> these approximations are called 'factor' matrices. The general</span>
<span class="sd"> approach is iterative. During each iteration, one of the factor</span>
<span class="sd"> matrices is held constant, while the other is solved for using least</span>
<span class="sd"> squares. The newly-solved factor matrix is then held constant while</span>
<span class="sd"> solving for the other factor matrix.</span>
<span class="sd"> This is a blocked implementation of the ALS factorization algorithm</span>
<span class="sd"> that groups the two sets of factors (referred to as "users" and</span>
<span class="sd"> "products") into blocks and reduces communication by only sending</span>
<span class="sd"> one copy of each user vector to each product block on each</span>
<span class="sd"> iteration, and only for the product blocks that need that user's</span>
<span class="sd"> feature vector. This is achieved by pre-computing some information</span>
<span class="sd"> about the ratings matrix to determine the "out-links" of each user</span>
<span class="sd"> (which blocks of products it will contribute to) and "in-link"</span>
<span class="sd"> information for each product (which of the feature vectors it</span>
<span class="sd"> receives from each user block it will depend on). This allows us to</span>
<span class="sd"> send only an array of feature vectors between each user block and</span>
<span class="sd"> product block, and have the product block find the users' ratings</span>
<span class="sd"> and update the products based on these messages.</span>
<span class="sd"> For implicit preference data, the algorithm used is based on</span>
<span class="sd"> "Collaborative Filtering for Implicit Feedback Datasets", available</span>
<span class="sd"> at `http://dx.doi.org/10.1109/ICDM.2008.22`, adapted for the blocked</span>
<span class="sd"> approach used here.</span>
<span class="sd"> Essentially instead of finding the low-rank approximations to the</span>
<span class="sd"> rating matrix `R`, this finds the approximations for a preference</span>
<span class="sd"> matrix `P` where the elements of `P` are 1 if r > 0 and 0 if r <= 0.</span>
<span class="sd"> The ratings then act as 'confidence' values related to strength of</span>
<span class="sd"> indicated user preferences rather than explicit ratings given to</span>
<span class="sd"> items.</span>
<span class="sd"> >>> df = sqlContext.createDataFrame(</span>
<span class="sd"> ... [(0, 0, 4.0), (0, 1, 2.0), (1, 1, 3.0), (1, 2, 4.0), (2, 1, 1.0), (2, 2, 5.0)],</span>
<span class="sd"> ... ["user", "item", "rating"])</span>
<span class="sd"> >>> als = ALS(rank=10, maxIter=5)</span>
<span class="sd"> >>> model = als.fit(df)</span>
<span class="sd"> >>> model.rank</span>
<span class="sd"> 10</span>
<span class="sd"> >>> model.userFactors.orderBy("id").collect()</span>
<span class="sd"> [Row(id=0, features=[...]), Row(id=1, ...), Row(id=2, ...)]</span>
<span class="sd"> >>> test = sqlContext.createDataFrame([(0, 2), (1, 0), (2, 0)], ["user", "item"])</span>
<span class="sd"> >>> predictions = sorted(model.transform(test).collect(), key=lambda r: r[0])</span>
<span class="sd"> >>> predictions[0]</span>
<span class="sd"> Row(user=0, item=2, prediction=0.39...)</span>
<span class="sd"> >>> predictions[1]</span>
<span class="sd"> Row(user=1, item=0, prediction=3.19...)</span>
<span class="sd"> >>> predictions[2]</span>
<span class="sd"> Row(user=2, item=0, prediction=-1.15...)</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">rank</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"rank"</span><span class="p">,</span> <span class="s">"rank of the factorization"</span><span class="p">)</span>
<span class="n">numUserBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"numUserBlocks"</span><span class="p">,</span> <span class="s">"number of user blocks"</span><span class="p">)</span>
<span class="n">numItemBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"numItemBlocks"</span><span class="p">,</span> <span class="s">"number of item blocks"</span><span class="p">)</span>
<span class="n">implicitPrefs</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"implicitPrefs"</span><span class="p">,</span> <span class="s">"whether to use implicit preference"</span><span class="p">)</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"alpha"</span><span class="p">,</span> <span class="s">"alpha for implicit preference"</span><span class="p">)</span>
<span class="n">userCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"userCol"</span><span class="p">,</span> <span class="s">"column name for user ids"</span><span class="p">)</span>
<span class="n">itemCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"itemCol"</span><span class="p">,</span> <span class="s">"column name for item ids"</span><span class="p">)</span>
<span class="n">ratingCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"ratingCol"</span><span class="p">,</span> <span class="s">"column name for ratings"</span><span class="p">)</span>
<span class="n">nonnegative</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"nonnegative"</span><span class="p">,</span>
<span class="s">"whether to use nonnegative constraint for least squares"</span><span class="p">)</span>
<span class="nd">@keyword_only</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">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">implicitPrefs</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s">"item"</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">ratingCol</span><span class="o">=</span><span class="s">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \</span>
<span class="sd"> implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=None, \</span>
<span class="sd"> ratingCol="rating", nonnegative=false, checkpointInterval=10)</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ALS</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s">"org.apache.spark.ml.recommendation.ALS"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">rank</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"rank"</span><span class="p">,</span> <span class="s">"rank of the factorization"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numUserBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"numUserBlocks"</span><span class="p">,</span> <span class="s">"number of user blocks"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numItemBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"numItemBlocks"</span><span class="p">,</span> <span class="s">"number of item blocks"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">implicitPrefs</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"implicitPrefs"</span><span class="p">,</span> <span class="s">"whether to use implicit preference"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"alpha"</span><span class="p">,</span> <span class="s">"alpha for implicit preference"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">userCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"userCol"</span><span class="p">,</span> <span class="s">"column name for user ids"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">itemCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"itemCol"</span><span class="p">,</span> <span class="s">"column name for item ids"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ratingCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"ratingCol"</span><span class="p">,</span> <span class="s">"column name for ratings"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">nonnegative</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"nonnegative"</span><span class="p">,</span>
<span class="s">"whether to use nonnegative constraint for least squares"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">implicitPrefs</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s">"item"</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">ratingCol</span><span class="o">=</span><span class="s">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="ALS.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">implicitPrefs</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s">"item"</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">ratingCol</span><span class="o">=</span><span class="s">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \</span>
<span class="sd"> implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None, \</span>
<span class="sd"> ratingCol="rating", nonnegative=False, checkpointInterval=10)</span>
<span class="sd"> Sets params for ALS.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">ALSModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="ALS.setRank"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setRank">[docs]</a> <span class="k">def</span> <span class="nf">setRank</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`rank`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">rank</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getRank"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getRank">[docs]</a> <span class="k">def</span> <span class="nf">getRank</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of rank or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rank</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setNumUserBlocks"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setNumUserBlocks">[docs]</a> <span class="k">def</span> <span class="nf">setNumUserBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`numUserBlocks`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">numUserBlocks</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getNumUserBlocks"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getNumUserBlocks">[docs]</a> <span class="k">def</span> <span class="nf">getNumUserBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of numUserBlocks or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numUserBlocks</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setNumItemBlocks"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setNumItemBlocks">[docs]</a> <span class="k">def</span> <span class="nf">setNumItemBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`numItemBlocks`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">numItemBlocks</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getNumItemBlocks"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getNumItemBlocks">[docs]</a> <span class="k">def</span> <span class="nf">getNumItemBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of numItemBlocks or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numItemBlocks</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setNumBlocks"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setNumBlocks">[docs]</a> <span class="k">def</span> <span class="nf">setNumBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets both :py:attr:`numUserBlocks` and :py:attr:`numItemBlocks` to the specific value.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">numUserBlocks</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">numItemBlocks</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
</div>
<div class="viewcode-block" id="ALS.setImplicitPrefs"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setImplicitPrefs">[docs]</a> <span class="k">def</span> <span class="nf">setImplicitPrefs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`implicitPrefs`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">implicitPrefs</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getImplicitPrefs"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getImplicitPrefs">[docs]</a> <span class="k">def</span> <span class="nf">getImplicitPrefs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of implicitPrefs or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">implicitPrefs</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setAlpha"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setAlpha">[docs]</a> <span class="k">def</span> <span class="nf">setAlpha</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`alpha`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getAlpha"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getAlpha">[docs]</a> <span class="k">def</span> <span class="nf">getAlpha</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of alpha or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setUserCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setUserCol">[docs]</a> <span class="k">def</span> <span class="nf">setUserCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`userCol`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">userCol</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getUserCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getUserCol">[docs]</a> <span class="k">def</span> <span class="nf">getUserCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of userCol or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">userCol</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setItemCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setItemCol">[docs]</a> <span class="k">def</span> <span class="nf">setItemCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`itemCol`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">itemCol</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getItemCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getItemCol">[docs]</a> <span class="k">def</span> <span class="nf">getItemCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of itemCol or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">itemCol</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setRatingCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setRatingCol">[docs]</a> <span class="k">def</span> <span class="nf">setRatingCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`ratingCol`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">ratingCol</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getRatingCol"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getRatingCol">[docs]</a> <span class="k">def</span> <span class="nf">getRatingCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of ratingCol or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ratingCol</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="ALS.setNonnegative"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.setNonnegative">[docs]</a> <span class="k">def</span> <span class="nf">setNonnegative</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets the value of :py:attr:`nonnegative`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">nonnegative</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="ALS.getNonnegative"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALS.getNonnegative">[docs]</a> <span class="k">def</span> <span class="nf">getNonnegative</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of nonnegative or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">nonnegative</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="ALSModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.recommendation.ALSModel">[docs]</a><span class="k">class</span> <span class="nc">ALSModel</span><span class="p">(</span><span class="n">JavaModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by ALS.</span>
<span class="sd"> """</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">rank</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""rank of the matrix factorization model"""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"rank"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">userFactors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> a DataFrame that stores user factors in two columns: `id` and</span>
<span class="sd"> `features`</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"userFactors"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">itemFactors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> a DataFrame that stores item factors in two columns: `id` and</span>
<span class="sd"> `features`</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"itemFactors"</span><span class="p">)</span>
</div>
<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="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">SQLContext</span>
<span class="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="c"># The small batch size here ensures that we see multiple batches,</span>
<span class="c"># even in these small test examples:</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">"local[2]"</span><span class="p">,</span> <span class="s">"ml.recommendation tests"</span><span class="p">)</span>
<span class="n">sqlContext</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">'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">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">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="p">)</span>
<span class="n">sc</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>
</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> »</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>
|
