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
|
#
# 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.
#
"""
Unit tests for Spark ML Python APIs.
"""
import sys
try:
import xmlrunner
except ImportError:
xmlrunner = None
if sys.version_info[:2] <= (2, 6):
try:
import unittest2 as unittest
except ImportError:
sys.stderr.write('Please install unittest2 to test with Python 2.6 or earlier')
sys.exit(1)
else:
import unittest
from pyspark.tests import ReusedPySparkTestCase as PySparkTestCase
from pyspark.sql import DataFrame, SQLContext, Row
from pyspark.sql.functions import rand
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml.param import Param, Params
from pyspark.ml.param.shared import HasMaxIter, HasInputCol, HasSeed
from pyspark.ml.util import keyword_only
from pyspark.ml import Estimator, Model, Pipeline, Transformer
from pyspark.ml.feature import *
from pyspark.ml.tuning import ParamGridBuilder, CrossValidator, CrossValidatorModel
from pyspark.mllib.linalg import DenseVector
class MockDataset(DataFrame):
def __init__(self):
self.index = 0
class HasFake(Params):
def __init__(self):
super(HasFake, self).__init__()
self.fake = Param(self, "fake", "fake param")
def getFake(self):
return self.getOrDefault(self.fake)
class MockTransformer(Transformer, HasFake):
def __init__(self):
super(MockTransformer, self).__init__()
self.dataset_index = None
def _transform(self, dataset):
self.dataset_index = dataset.index
dataset.index += 1
return dataset
class MockEstimator(Estimator, HasFake):
def __init__(self):
super(MockEstimator, self).__init__()
self.dataset_index = None
def _fit(self, dataset):
self.dataset_index = dataset.index
model = MockModel()
self._copyValues(model)
return model
class MockModel(MockTransformer, Model, HasFake):
pass
class PipelineTests(PySparkTestCase):
def test_pipeline(self):
dataset = MockDataset()
estimator0 = MockEstimator()
transformer1 = MockTransformer()
estimator2 = MockEstimator()
transformer3 = MockTransformer()
pipeline = Pipeline(stages=[estimator0, transformer1, estimator2, transformer3])
pipeline_model = pipeline.fit(dataset, {estimator0.fake: 0, transformer1.fake: 1})
model0, transformer1, model2, transformer3 = pipeline_model.stages
self.assertEqual(0, model0.dataset_index)
self.assertEqual(0, model0.getFake())
self.assertEqual(1, transformer1.dataset_index)
self.assertEqual(1, transformer1.getFake())
self.assertEqual(2, dataset.index)
self.assertIsNone(model2.dataset_index, "The last model shouldn't be called in fit.")
self.assertIsNone(transformer3.dataset_index,
"The last transformer shouldn't be called in fit.")
dataset = pipeline_model.transform(dataset)
self.assertEqual(2, model0.dataset_index)
self.assertEqual(3, transformer1.dataset_index)
self.assertEqual(4, model2.dataset_index)
self.assertEqual(5, transformer3.dataset_index)
self.assertEqual(6, dataset.index)
class TestParams(HasMaxIter, HasInputCol, HasSeed):
"""
A subclass of Params mixed with HasMaxIter, HasInputCol and HasSeed.
"""
@keyword_only
def __init__(self, seed=None):
super(TestParams, self).__init__()
self._setDefault(maxIter=10)
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
@keyword_only
def setParams(self, seed=None):
"""
setParams(self, seed=None)
Sets params for this test.
"""
kwargs = self.setParams._input_kwargs
return self._set(**kwargs)
class OtherTestParams(HasMaxIter, HasInputCol, HasSeed):
"""
A subclass of Params mixed with HasMaxIter, HasInputCol and HasSeed.
"""
@keyword_only
def __init__(self, seed=None):
super(OtherTestParams, self).__init__()
self._setDefault(maxIter=10)
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
@keyword_only
def setParams(self, seed=None):
"""
setParams(self, seed=None)
Sets params for this test.
"""
kwargs = self.setParams._input_kwargs
return self._set(**kwargs)
class ParamTests(PySparkTestCase):
def test_param(self):
testParams = TestParams()
maxIter = testParams.maxIter
self.assertEqual(maxIter.name, "maxIter")
self.assertEqual(maxIter.doc, "max number of iterations (>= 0).")
self.assertTrue(maxIter.parent == testParams.uid)
def test_params(self):
testParams = TestParams()
maxIter = testParams.maxIter
inputCol = testParams.inputCol
seed = testParams.seed
params = testParams.params
self.assertEqual(params, [inputCol, maxIter, seed])
self.assertTrue(testParams.hasParam(maxIter))
self.assertTrue(testParams.hasDefault(maxIter))
self.assertFalse(testParams.isSet(maxIter))
self.assertTrue(testParams.isDefined(maxIter))
self.assertEqual(testParams.getMaxIter(), 10)
testParams.setMaxIter(100)
self.assertTrue(testParams.isSet(maxIter))
self.assertEqual(testParams.getMaxIter(), 100)
self.assertTrue(testParams.hasParam(inputCol))
self.assertFalse(testParams.hasDefault(inputCol))
self.assertFalse(testParams.isSet(inputCol))
self.assertFalse(testParams.isDefined(inputCol))
with self.assertRaises(KeyError):
testParams.getInputCol()
# Since the default is normally random, set it to a known number for debug str
testParams._setDefault(seed=41)
testParams.setSeed(43)
self.assertEqual(
testParams.explainParams(),
"\n".join(["inputCol: input column name. (undefined)",
"maxIter: max number of iterations (>= 0). (default: 10, current: 100)",
"seed: random seed. (default: 41, current: 43)"]))
def test_hasseed(self):
noSeedSpecd = TestParams()
withSeedSpecd = TestParams(seed=42)
other = OtherTestParams()
# Check that we no longer use 42 as the magic number
self.assertNotEqual(noSeedSpecd.getSeed(), 42)
origSeed = noSeedSpecd.getSeed()
# Check that we only compute the seed once
self.assertEqual(noSeedSpecd.getSeed(), origSeed)
# Check that a specified seed is honored
self.assertEqual(withSeedSpecd.getSeed(), 42)
# Check that a different class has a different seed
self.assertNotEqual(other.getSeed(), noSeedSpecd.getSeed())
class FeatureTests(PySparkTestCase):
def test_binarizer(self):
b0 = Binarizer()
self.assertListEqual(b0.params, [b0.inputCol, b0.outputCol, b0.threshold])
self.assertTrue(all([~b0.isSet(p) for p in b0.params]))
self.assertTrue(b0.hasDefault(b0.threshold))
self.assertEqual(b0.getThreshold(), 0.0)
b0.setParams(inputCol="input", outputCol="output").setThreshold(1.0)
self.assertTrue(all([b0.isSet(p) for p in b0.params]))
self.assertEqual(b0.getThreshold(), 1.0)
self.assertEqual(b0.getInputCol(), "input")
self.assertEqual(b0.getOutputCol(), "output")
b0c = b0.copy({b0.threshold: 2.0})
self.assertEqual(b0c.uid, b0.uid)
self.assertListEqual(b0c.params, b0.params)
self.assertEqual(b0c.getThreshold(), 2.0)
b1 = Binarizer(threshold=2.0, inputCol="input", outputCol="output")
self.assertNotEqual(b1.uid, b0.uid)
self.assertEqual(b1.getThreshold(), 2.0)
self.assertEqual(b1.getInputCol(), "input")
self.assertEqual(b1.getOutputCol(), "output")
def test_idf(self):
sqlContext = SQLContext(self.sc)
dataset = sqlContext.createDataFrame([
(DenseVector([1.0, 2.0]),),
(DenseVector([0.0, 1.0]),),
(DenseVector([3.0, 0.2]),)], ["tf"])
idf0 = IDF(inputCol="tf")
self.assertListEqual(idf0.params, [idf0.inputCol, idf0.minDocFreq, idf0.outputCol])
idf0m = idf0.fit(dataset, {idf0.outputCol: "idf"})
self.assertEqual(idf0m.uid, idf0.uid,
"Model should inherit the UID from its parent estimator.")
output = idf0m.transform(dataset)
self.assertIsNotNone(output.head().idf)
def test_ngram(self):
sqlContext = SQLContext(self.sc)
dataset = sqlContext.createDataFrame([
Row(input=["a", "b", "c", "d", "e"])])
ngram0 = NGram(n=4, inputCol="input", outputCol="output")
self.assertEqual(ngram0.getN(), 4)
self.assertEqual(ngram0.getInputCol(), "input")
self.assertEqual(ngram0.getOutputCol(), "output")
transformedDF = ngram0.transform(dataset)
self.assertEqual(transformedDF.head().output, ["a b c d", "b c d e"])
def test_stopwordsremover(self):
sqlContext = SQLContext(self.sc)
dataset = sqlContext.createDataFrame([Row(input=["a", "panda"])])
stopWordRemover = StopWordsRemover(inputCol="input", outputCol="output")
# Default
self.assertEqual(stopWordRemover.getInputCol(), "input")
transformedDF = stopWordRemover.transform(dataset)
self.assertEqual(transformedDF.head().output, ["panda"])
# Custom
stopwords = ["panda"]
stopWordRemover.setStopWords(stopwords)
self.assertEqual(stopWordRemover.getInputCol(), "input")
self.assertEqual(stopWordRemover.getStopWords(), stopwords)
transformedDF = stopWordRemover.transform(dataset)
self.assertEqual(transformedDF.head().output, ["a"])
class HasInducedError(Params):
def __init__(self):
super(HasInducedError, self).__init__()
self.inducedError = Param(self, "inducedError",
"Uniformly-distributed error added to feature")
def getInducedError(self):
return self.getOrDefault(self.inducedError)
class InducedErrorModel(Model, HasInducedError):
def __init__(self):
super(InducedErrorModel, self).__init__()
def _transform(self, dataset):
return dataset.withColumn("prediction",
dataset.feature + (rand(0) * self.getInducedError()))
class InducedErrorEstimator(Estimator, HasInducedError):
def __init__(self, inducedError=1.0):
super(InducedErrorEstimator, self).__init__()
self._set(inducedError=inducedError)
def _fit(self, dataset):
model = InducedErrorModel()
self._copyValues(model)
return model
class CrossValidatorTests(PySparkTestCase):
def test_fit_minimize_metric(self):
sqlContext = SQLContext(self.sc)
dataset = sqlContext.createDataFrame([
(10, 10.0),
(50, 50.0),
(100, 100.0),
(500, 500.0)] * 10,
["feature", "label"])
iee = InducedErrorEstimator()
evaluator = RegressionEvaluator(metricName="rmse")
grid = (ParamGridBuilder()
.addGrid(iee.inducedError, [100.0, 0.0, 10000.0])
.build())
cv = CrossValidator(estimator=iee, estimatorParamMaps=grid, evaluator=evaluator)
cvModel = cv.fit(dataset)
bestModel = cvModel.bestModel
bestModelMetric = evaluator.evaluate(bestModel.transform(dataset))
self.assertEqual(0.0, bestModel.getOrDefault('inducedError'),
"Best model should have zero induced error")
self.assertEqual(0.0, bestModelMetric, "Best model has RMSE of 0")
def test_fit_maximize_metric(self):
sqlContext = SQLContext(self.sc)
dataset = sqlContext.createDataFrame([
(10, 10.0),
(50, 50.0),
(100, 100.0),
(500, 500.0)] * 10,
["feature", "label"])
iee = InducedErrorEstimator()
evaluator = RegressionEvaluator(metricName="r2")
grid = (ParamGridBuilder()
.addGrid(iee.inducedError, [100.0, 0.0, 10000.0])
.build())
cv = CrossValidator(estimator=iee, estimatorParamMaps=grid, evaluator=evaluator)
cvModel = cv.fit(dataset)
bestModel = cvModel.bestModel
bestModelMetric = evaluator.evaluate(bestModel.transform(dataset))
self.assertEqual(0.0, bestModel.getOrDefault('inducedError'),
"Best model should have zero induced error")
self.assertEqual(1.0, bestModelMetric, "Best model has R-squared of 1")
if __name__ == "__main__":
if xmlrunner:
unittest.main(testRunner=xmlrunner.XMLTestRunner(output='target/test-reports'))
else:
unittest.main()
|