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
|
<!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.pipeline — PySpark master documentation</title>
<link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../../',
VERSION: 'master',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<link rel="top" title="PySpark master documentation" href="../../../index.html" />
<link rel="up" title="Module code" href="../../index.html" />
</head>
<body role="document">
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> »</li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for pyspark.ml.pipeline</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">abc</span> <span class="kn">import</span> <span class="n">ABCMeta</span><span class="p">,</span> <span class="n">abstractmethod</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.param</span> <span class="kn">import</span> <span class="n">Param</span><span class="p">,</span> <span class="n">Params</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.mllib.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="Estimator"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Estimator">[docs]</a><span class="k">class</span> <span class="nc">Estimator</span><span class="p">(</span><span class="n">Params</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Abstract class for estimators that fit models to data.</span>
<span class="sd"> """</span>
<span class="n">__metaclass__</span> <span class="o">=</span> <span class="n">ABCMeta</span>
<span class="nd">@abstractmethod</span>
<span class="k">def</span> <span class="nf">_fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Fits a model to the input dataset. This is called by the</span>
<span class="sd"> default implementation of fit.</span>
<span class="sd"> :param dataset: input dataset, which is an instance of</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> :returns: fitted model</span>
<span class="sd"> """</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span>
<div class="viewcode-block" id="Estimator.fit"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Estimator.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Fits a model to the input dataset with optional parameters.</span>
<span class="sd"> :param dataset: input dataset, which is an instance of</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> :param params: an optional param map that overrides embedded</span>
<span class="sd"> params. If a list/tuple of param maps is given,</span>
<span class="sd"> this calls fit on each param map and returns a</span>
<span class="sd"> list of models.</span>
<span class="sd"> :returns: fitted model(s)</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">params</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="k">return</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">paramMap</span><span class="p">)</span> <span class="k">for</span> <span class="n">paramMap</span> <span class="ow">in</span> <span class="n">params</span><span class="p">]</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
<span class="k">if</span> <span class="n">params</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">params</span><span class="p">)</span><span class="o">.</span><span class="n">_fit</span><span class="p">(</span><span class="n">dataset</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">_fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Params must be either a param map or a list/tuple of param maps, "</span>
<span class="s">"but got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">))</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="Transformer"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Transformer">[docs]</a><span class="k">class</span> <span class="nc">Transformer</span><span class="p">(</span><span class="n">Params</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Abstract class for transformers that transform one dataset into</span>
<span class="sd"> another.</span>
<span class="sd"> """</span>
<span class="n">__metaclass__</span> <span class="o">=</span> <span class="n">ABCMeta</span>
<span class="nd">@abstractmethod</span>
<span class="k">def</span> <span class="nf">_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Transforms the input dataset with optional parameters.</span>
<span class="sd"> :param dataset: input dataset, which is an instance of</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> :returns: transformed dataset</span>
<span class="sd"> """</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span>
<div class="viewcode-block" id="Transformer.transform"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Transformer.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Transforms the input dataset with optional parameters.</span>
<span class="sd"> :param dataset: input dataset, which is an instance of</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> :param params: an optional param map that overrides embedded</span>
<span class="sd"> params.</span>
<span class="sd"> :returns: transformed dataset</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">params</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
<span class="k">if</span> <span class="n">params</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">params</span><span class="p">,)</span><span class="o">.</span><span class="n">_transform</span><span class="p">(</span><span class="n">dataset</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">_transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Params must be either a param map but got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">))</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="Model"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Model">[docs]</a><span class="k">class</span> <span class="nc">Model</span><span class="p">(</span><span class="n">Transformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Abstract class for models that are fitted by estimators.</span>
<span class="sd"> """</span>
<span class="n">__metaclass__</span> <span class="o">=</span> <span class="n">ABCMeta</span>
</div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="Pipeline"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Pipeline">[docs]</a><span class="k">class</span> <span class="nc">Pipeline</span><span class="p">(</span><span class="n">Estimator</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A simple pipeline, which acts as an estimator. A Pipeline consists</span>
<span class="sd"> of a sequence of stages, each of which is either an</span>
<span class="sd"> :py:class:`Estimator` or a :py:class:`Transformer`. When</span>
<span class="sd"> :py:meth:`Pipeline.fit` is called, the stages are executed in</span>
<span class="sd"> order. If a stage is an :py:class:`Estimator`, its</span>
<span class="sd"> :py:meth:`Estimator.fit` method will be called on the input</span>
<span class="sd"> dataset to fit a model. Then the model, which is a transformer,</span>
<span class="sd"> will be used to transform the dataset as the input to the next</span>
<span class="sd"> stage. If a stage is a :py:class:`Transformer`, its</span>
<span class="sd"> :py:meth:`Transformer.transform` method will be called to produce</span>
<span class="sd"> the dataset for the next stage. The fitted model from a</span>
<span class="sd"> :py:class:`Pipeline` is an :py:class:`PipelineModel`, which</span>
<span class="sd"> consists of fitted models and transformers, corresponding to the</span>
<span class="sd"> pipeline stages. If there are no stages, the pipeline acts as an</span>
<span class="sd"> identity transformer.</span>
<span class="sd"> """</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">stages</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, stages=None)</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">stages</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">stages</span> <span class="o">=</span> <span class="p">[]</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Pipeline</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="c">#: Param for pipeline stages.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stages</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">"stages"</span><span class="p">,</span> <span class="s">"pipeline stages"</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>
<div class="viewcode-block" id="Pipeline.setStages"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Pipeline.setStages">[docs]</a> <span class="k">def</span> <span class="nf">setStages</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"> Set pipeline stages.</span>
<span class="sd"> :param value: a list of transformers or estimators</span>
<span class="sd"> :return: the pipeline instance</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">stages</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="Pipeline.getStages"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Pipeline.getStages">[docs]</a> <span class="k">def</span> <span class="nf">getStages</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Get pipeline stages.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">stages</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">:</span>
<span class="k">return</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">stages</span><span class="p">]</span>
</div>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="Pipeline.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Pipeline.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">stages</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, stages=None)</span>
<span class="sd"> Sets params for Pipeline.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">stages</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">stages</span> <span class="o">=</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">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">_fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="n">stages</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getStages</span><span class="p">()</span>
<span class="k">for</span> <span class="n">stage</span> <span class="ow">in</span> <span class="n">stages</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">stage</span><span class="p">,</span> <span class="n">Estimator</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">stage</span><span class="p">,</span> <span class="n">Transformer</span><span class="p">)):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="s">"Cannot recognize a pipeline stage of type </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">stage</span><span class="p">))</span>
<span class="n">indexOfLastEstimator</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">stage</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">stages</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">stage</span><span class="p">,</span> <span class="n">Estimator</span><span class="p">):</span>
<span class="n">indexOfLastEstimator</span> <span class="o">=</span> <span class="n">i</span>
<span class="n">transformers</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">stage</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">stages</span><span class="p">):</span>
<span class="k">if</span> <span class="n">i</span> <span class="o"><=</span> <span class="n">indexOfLastEstimator</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">stage</span><span class="p">,</span> <span class="n">Transformer</span><span class="p">):</span>
<span class="n">transformers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">stage</span><span class="p">)</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">stage</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span> <span class="c"># must be an Estimator</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">stage</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="n">transformers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
<span class="k">if</span> <span class="n">i</span> <span class="o"><</span> <span class="n">indexOfLastEstimator</span><span class="p">:</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">transformers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">stage</span><span class="p">)</span>
<span class="k">return</span> <span class="n">PipelineModel</span><span class="p">(</span><span class="n">transformers</span><span class="p">)</span>
<div class="viewcode-block" id="Pipeline.copy"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.Pipeline.copy">[docs]</a> <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">extra</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">extra</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">extra</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="n">that</span> <span class="o">=</span> <span class="n">Params</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">extra</span><span class="p">)</span>
<span class="n">stages</span> <span class="o">=</span> <span class="p">[</span><span class="n">stage</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">extra</span><span class="p">)</span> <span class="k">for</span> <span class="n">stage</span> <span class="ow">in</span> <span class="n">that</span><span class="o">.</span><span class="n">getStages</span><span class="p">()]</span>
<span class="k">return</span> <span class="n">that</span><span class="o">.</span><span class="n">setStages</span><span class="p">(</span><span class="n">stages</span><span class="p">)</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="PipelineModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.PipelineModel">[docs]</a><span class="k">class</span> <span class="nc">PipelineModel</span><span class="p">(</span><span class="n">Model</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Represents a compiled pipeline with transformers and fitted models.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">stages</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">PipelineModel</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">stages</span> <span class="o">=</span> <span class="n">stages</span>
<span class="k">def</span> <span class="nf">_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">stages</span><span class="p">:</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dataset</span>
<div class="viewcode-block" id="PipelineModel.copy"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.PipelineModel.copy">[docs]</a> <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">extra</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">extra</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">extra</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="n">stages</span> <span class="o">=</span> <span class="p">[</span><span class="n">stage</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">extra</span><span class="p">)</span> <span class="k">for</span> <span class="n">stage</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">stages</span><span class="p">]</span>
<span class="k">return</span> <span class="n">PipelineModel</span><span class="p">(</span><span class="n">stages</span><span class="p">)</span></div></div>
</pre></div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../../index.html">
<img class="logo" src="../../../_static/spark-logo-hd.png" alt="Logo"/>
</a></p>
<div id="searchbox" style="display: none" role="search">
<h3>Quick search</h3>
<form class="search" action="../../../search.html" method="get">
<input type="text" name="q" />
<input type="submit" value="Go" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
<p class="searchtip" style="font-size: 90%">
Enter search terms or a module, class or function name.
</p>
</div>
<script type="text/javascript">$('#searchbox').show(0);</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
</ul>
</div>
<div class="footer" role="contentinfo">
© Copyright .
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
</div>
</body>
</html>
|
