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
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import sys
if sys.version > '3':
basestring = str
from pyspark import SparkContext
from pyspark import since
from pyspark.ml import Estimator, Model, Transformer
from pyspark.ml.param import Param, Params
from pyspark.ml.util import keyword_only, JavaMLWriter, JavaMLReader, MLReadable, MLWritable
from pyspark.ml.wrapper import JavaParams
from pyspark.mllib.common import inherit_doc
@inherit_doc
class PipelineMLWriter(JavaMLWriter):
"""
Private Pipeline utility class that can save ML instances through their Scala implementation.
We can currently use JavaMLWriter, rather than MLWriter, since Pipeline implements _to_java.
"""
@inherit_doc
class PipelineMLReader(JavaMLReader):
"""
Private utility class that can load Pipeline instances through their Scala implementation.
We can currently use JavaMLReader, rather than MLReader, since Pipeline implements _from_java.
"""
@inherit_doc
class Pipeline(Estimator, MLReadable, MLWritable):
"""
A simple pipeline, which acts as an estimator. A Pipeline consists
of a sequence of stages, each of which is either an
:py:class:`Estimator` or a :py:class:`Transformer`. When
:py:meth:`Pipeline.fit` is called, the stages are executed in
order. If a stage is an :py:class:`Estimator`, its
:py:meth:`Estimator.fit` method will be called on the input
dataset to fit a model. Then the model, which is a transformer,
will be used to transform the dataset as the input to the next
stage. If a stage is a :py:class:`Transformer`, its
:py:meth:`Transformer.transform` method will be called to produce
the dataset for the next stage. The fitted model from a
:py:class:`Pipeline` is an :py:class:`PipelineModel`, which
consists of fitted models and transformers, corresponding to the
pipeline stages. If there are no stages, the pipeline acts as an
identity transformer.
.. versionadded:: 1.3.0
"""
stages = Param(Params._dummy(), "stages", "pipeline stages")
@keyword_only
def __init__(self, stages=None):
"""
__init__(self, stages=None)
"""
if stages is None:
stages = []
super(Pipeline, self).__init__()
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
@since("1.3.0")
def setStages(self, value):
"""
Set pipeline stages.
:param value: a list of transformers or estimators
:return: the pipeline instance
"""
self._set(stages=value)
return self
@since("1.3.0")
def getStages(self):
"""
Get pipeline stages.
"""
if self.stages in self._paramMap:
return self._paramMap[self.stages]
@keyword_only
@since("1.3.0")
def setParams(self, stages=None):
"""
setParams(self, stages=None)
Sets params for Pipeline.
"""
if stages is None:
stages = []
kwargs = self.setParams._input_kwargs
return self._set(**kwargs)
def _fit(self, dataset):
stages = self.getStages()
for stage in stages:
if not (isinstance(stage, Estimator) or isinstance(stage, Transformer)):
raise TypeError(
"Cannot recognize a pipeline stage of type %s." % type(stage))
indexOfLastEstimator = -1
for i, stage in enumerate(stages):
if isinstance(stage, Estimator):
indexOfLastEstimator = i
transformers = []
for i, stage in enumerate(stages):
if i <= indexOfLastEstimator:
if isinstance(stage, Transformer):
transformers.append(stage)
dataset = stage.transform(dataset)
else: # must be an Estimator
model = stage.fit(dataset)
transformers.append(model)
if i < indexOfLastEstimator:
dataset = model.transform(dataset)
else:
transformers.append(stage)
return PipelineModel(transformers)
@since("1.4.0")
def copy(self, extra=None):
"""
Creates a copy of this instance.
:param extra: extra parameters
:returns: new instance
"""
if extra is None:
extra = dict()
that = Params.copy(self, extra)
stages = [stage.copy(extra) for stage in that.getStages()]
return that.setStages(stages)
@since("2.0.0")
def write(self):
"""Returns an JavaMLWriter instance for this ML instance."""
return PipelineMLWriter(self)
@since("2.0.0")
def save(self, path):
"""Save this ML instance to the given path, a shortcut of `write().save(path)`."""
self.write().save(path)
@classmethod
@since("2.0.0")
def read(cls):
"""Returns an MLReader instance for this class."""
return PipelineMLReader(cls)
@classmethod
def _from_java(cls, java_stage):
"""
Given a Java Pipeline, create and return a Python wrapper of it.
Used for ML persistence.
"""
# Create a new instance of this stage.
py_stage = cls()
# Load information from java_stage to the instance.
py_stages = [JavaParams._from_java(s) for s in java_stage.getStages()]
py_stage.setStages(py_stages)
py_stage._resetUid(java_stage.uid())
return py_stage
def _to_java(self):
"""
Transfer this instance to a Java Pipeline. Used for ML persistence.
:return: Java object equivalent to this instance.
"""
gateway = SparkContext._gateway
cls = SparkContext._jvm.org.apache.spark.ml.PipelineStage
java_stages = gateway.new_array(cls, len(self.getStages()))
for idx, stage in enumerate(self.getStages()):
java_stages[idx] = stage._to_java()
_java_obj = JavaParams._new_java_obj("org.apache.spark.ml.Pipeline", self.uid)
_java_obj.setStages(java_stages)
return _java_obj
@inherit_doc
class PipelineModelMLWriter(JavaMLWriter):
"""
Private PipelineModel utility class that can save ML instances through their Scala
implementation.
We can (currently) use JavaMLWriter, rather than MLWriter, since PipelineModel implements
_to_java.
"""
@inherit_doc
class PipelineModelMLReader(JavaMLReader):
"""
Private utility class that can load PipelineModel instances through their Scala implementation.
We can currently use JavaMLReader, rather than MLReader, since PipelineModel implements
_from_java.
"""
@inherit_doc
class PipelineModel(Model, MLReadable, MLWritable):
"""
Represents a compiled pipeline with transformers and fitted models.
.. versionadded:: 1.3.0
"""
def __init__(self, stages):
super(PipelineModel, self).__init__()
self.stages = stages
def _transform(self, dataset):
for t in self.stages:
dataset = t.transform(dataset)
return dataset
@since("1.4.0")
def copy(self, extra=None):
"""
Creates a copy of this instance.
:param extra: extra parameters
:returns: new instance
"""
if extra is None:
extra = dict()
stages = [stage.copy(extra) for stage in self.stages]
return PipelineModel(stages)
@since("2.0.0")
def write(self):
"""Returns an JavaMLWriter instance for this ML instance."""
return PipelineModelMLWriter(self)
@since("2.0.0")
def save(self, path):
"""Save this ML instance to the given path, a shortcut of `write().save(path)`."""
self.write().save(path)
@classmethod
@since("2.0.0")
def read(cls):
"""Returns an JavaMLReader instance for this class."""
return PipelineModelMLReader(cls)
@classmethod
def _from_java(cls, java_stage):
"""
Given a Java PipelineModel, create and return a Python wrapper of it.
Used for ML persistence.
"""
# Load information from java_stage to the instance.
py_stages = [JavaParams._from_java(s) for s in java_stage.stages()]
# Create a new instance of this stage.
py_stage = cls(py_stages)
py_stage._resetUid(java_stage.uid())
return py_stage
def _to_java(self):
"""
Transfer this instance to a Java PipelineModel. Used for ML persistence.
:return: Java object equivalent to this instance.
"""
gateway = SparkContext._gateway
cls = SparkContext._jvm.org.apache.spark.ml.Transformer
java_stages = gateway.new_array(cls, len(self.stages))
for idx, stage in enumerate(self.stages):
java_stages[idx] = stage._to_java()
_java_obj =\
JavaParams._new_java_obj("org.apache.spark.ml.PipelineModel", self.uid, java_stages)
return _java_obj
|