1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
|
#
# 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.
#
from math import exp
import numpy
from numpy import array
from pyspark import RDD
from pyspark.streaming import DStream
from pyspark.mllib.common import callMLlibFunc, _py2java, _java2py
from pyspark.mllib.linalg import DenseVector, SparseVector, _convert_to_vector
from pyspark.mllib.regression import LabeledPoint, LinearModel, _regression_train_wrapper
from pyspark.mllib.util import Saveable, Loader, inherit_doc
__all__ = ['LogisticRegressionModel', 'LogisticRegressionWithSGD', 'LogisticRegressionWithLBFGS',
'SVMModel', 'SVMWithSGD', 'NaiveBayesModel', 'NaiveBayes',
'StreamingLogisticRegressionWithSGD']
class LinearClassificationModel(LinearModel):
"""
A private abstract class representing a multiclass classification
model. The categories are represented by int values: 0, 1, 2, etc.
"""
def __init__(self, weights, intercept):
super(LinearClassificationModel, self).__init__(weights, intercept)
self._threshold = None
def setThreshold(self, value):
"""
.. note:: Experimental
Sets the threshold that separates positive predictions from
negative predictions. An example with prediction score greater
than or equal to this threshold is identified as an positive,
and negative otherwise. It is used for binary classification
only.
"""
self._threshold = value
@property
def threshold(self):
"""
.. note:: Experimental
Returns the threshold (if any) used for converting raw
prediction scores into 0/1 predictions. It is used for
binary classification only.
"""
return self._threshold
def clearThreshold(self):
"""
.. note:: Experimental
Clears the threshold so that `predict` will output raw
prediction scores. It is used for binary classification only.
"""
self._threshold = None
def predict(self, test):
"""
Predict values for a single data point or an RDD of points
using the model trained.
"""
raise NotImplementedError
class LogisticRegressionModel(LinearClassificationModel):
"""
Classification model trained using Multinomial/Binary Logistic
Regression.
:param weights: Weights computed for every feature.
:param intercept: Intercept computed for this model. (Only used
in Binary Logistic Regression. In Multinomial Logistic
Regression, the intercepts will not be a single value,
so the intercepts will be part of the weights.)
:param numFeatures: the dimension of the features.
:param numClasses: the number of possible outcomes for k classes
classification problem in Multinomial Logistic Regression.
By default, it is binary logistic regression so numClasses
will be set to 2.
>>> data = [
... LabeledPoint(0.0, [0.0, 1.0]),
... LabeledPoint(1.0, [1.0, 0.0]),
... ]
>>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(data), iterations=10)
>>> lrm.predict([1.0, 0.0])
1
>>> lrm.predict([0.0, 1.0])
0
>>> lrm.predict(sc.parallelize([[1.0, 0.0], [0.0, 1.0]])).collect()
[1, 0]
>>> lrm.clearThreshold()
>>> lrm.predict([0.0, 1.0])
0.279...
>>> sparse_data = [
... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),
... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),
... LabeledPoint(0.0, SparseVector(2, {0: 1.0})),
... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))
... ]
>>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(sparse_data), iterations=10)
>>> lrm.predict(array([0.0, 1.0]))
1
>>> lrm.predict(array([1.0, 0.0]))
0
>>> lrm.predict(SparseVector(2, {1: 1.0}))
1
>>> lrm.predict(SparseVector(2, {0: 1.0}))
0
>>> import os, tempfile
>>> path = tempfile.mkdtemp()
>>> lrm.save(sc, path)
>>> sameModel = LogisticRegressionModel.load(sc, path)
>>> sameModel.predict(array([0.0, 1.0]))
1
>>> sameModel.predict(SparseVector(2, {0: 1.0}))
0
>>> from shutil import rmtree
>>> try:
... rmtree(path)
... except:
... pass
>>> multi_class_data = [
... LabeledPoint(0.0, [0.0, 1.0, 0.0]),
... LabeledPoint(1.0, [1.0, 0.0, 0.0]),
... LabeledPoint(2.0, [0.0, 0.0, 1.0])
... ]
>>> data = sc.parallelize(multi_class_data)
>>> mcm = LogisticRegressionWithLBFGS.train(data, iterations=10, numClasses=3)
>>> mcm.predict([0.0, 0.5, 0.0])
0
>>> mcm.predict([0.8, 0.0, 0.0])
1
>>> mcm.predict([0.0, 0.0, 0.3])
2
"""
def __init__(self, weights, intercept, numFeatures, numClasses):
super(LogisticRegressionModel, self).__init__(weights, intercept)
self._numFeatures = int(numFeatures)
self._numClasses = int(numClasses)
self._threshold = 0.5
if self._numClasses == 2:
self._dataWithBiasSize = None
self._weightsMatrix = None
else:
self._dataWithBiasSize = self._coeff.size / (self._numClasses - 1)
self._weightsMatrix = self._coeff.toArray().reshape(self._numClasses - 1,
self._dataWithBiasSize)
@property
def numFeatures(self):
return self._numFeatures
@property
def numClasses(self):
return self._numClasses
def predict(self, x):
"""
Predict values for a single data point or an RDD of points
using the model trained.
"""
if isinstance(x, RDD):
return x.map(lambda v: self.predict(v))
x = _convert_to_vector(x)
if self.numClasses == 2:
margin = self.weights.dot(x) + self._intercept
if margin > 0:
prob = 1 / (1 + exp(-margin))
else:
exp_margin = exp(margin)
prob = exp_margin / (1 + exp_margin)
if self._threshold is None:
return prob
else:
return 1 if prob > self._threshold else 0
else:
best_class = 0
max_margin = 0.0
if x.size + 1 == self._dataWithBiasSize:
for i in range(0, self._numClasses - 1):
margin = x.dot(self._weightsMatrix[i][0:x.size]) + \
self._weightsMatrix[i][x.size]
if margin > max_margin:
max_margin = margin
best_class = i + 1
else:
for i in range(0, self._numClasses - 1):
margin = x.dot(self._weightsMatrix[i])
if margin > max_margin:
max_margin = margin
best_class = i + 1
return best_class
def save(self, sc, path):
java_model = sc._jvm.org.apache.spark.mllib.classification.LogisticRegressionModel(
_py2java(sc, self._coeff), self.intercept, self.numFeatures, self.numClasses)
java_model.save(sc._jsc.sc(), path)
@classmethod
def load(cls, sc, path):
java_model = sc._jvm.org.apache.spark.mllib.classification.LogisticRegressionModel.load(
sc._jsc.sc(), path)
weights = _java2py(sc, java_model.weights())
intercept = java_model.intercept()
numFeatures = java_model.numFeatures()
numClasses = java_model.numClasses()
threshold = java_model.getThreshold().get()
model = LogisticRegressionModel(weights, intercept, numFeatures, numClasses)
model.setThreshold(threshold)
return model
class LogisticRegressionWithSGD(object):
@classmethod
def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0,
initialWeights=None, regParam=0.01, regType="l2", intercept=False,
validateData=True):
"""
Train a logistic regression model on the given data.
:param data: The training data, an RDD of
LabeledPoint.
:param iterations: The number of iterations
(default: 100).
:param step: The step parameter used in SGD
(default: 1.0).
:param miniBatchFraction: Fraction of data to be used for each
SGD iteration (default: 1.0).
:param initialWeights: The initial weights (default: None).
:param regParam: The regularizer parameter
(default: 0.01).
:param regType: The type of regularizer used for
training our model.
:Allowed values:
- "l1" for using L1 regularization
- "l2" for using L2 regularization
- None for no regularization
(default: "l2")
:param intercept: Boolean parameter which indicates the
use or not of the augmented representation
for training data (i.e. whether bias
features are activated or not,
default: False).
:param validateData: Boolean parameter which indicates if
the algorithm should validate data
before training. (default: True)
"""
def train(rdd, i):
return callMLlibFunc("trainLogisticRegressionModelWithSGD", rdd, int(iterations),
float(step), float(miniBatchFraction), i, float(regParam), regType,
bool(intercept), bool(validateData))
return _regression_train_wrapper(train, LogisticRegressionModel, data, initialWeights)
class LogisticRegressionWithLBFGS(object):
@classmethod
def train(cls, data, iterations=100, initialWeights=None, regParam=0.01, regType="l2",
intercept=False, corrections=10, tolerance=1e-4, validateData=True, numClasses=2):
"""
Train a logistic regression model on the given data.
:param data: The training data, an RDD of
LabeledPoint.
:param iterations: The number of iterations
(default: 100).
:param initialWeights: The initial weights (default: None).
:param regParam: The regularizer parameter
(default: 0.01).
:param regType: The type of regularizer used for
training our model.
:Allowed values:
- "l1" for using L1 regularization
- "l2" for using L2 regularization
- None for no regularization
(default: "l2")
:param intercept: Boolean parameter which indicates the
use or not of the augmented representation
for training data (i.e. whether bias
features are activated or not,
default: False).
:param corrections: The number of corrections used in the
LBFGS update (default: 10).
:param tolerance: The convergence tolerance of iterations
for L-BFGS (default: 1e-4).
:param validateData: Boolean parameter which indicates if the
algorithm should validate data before
training. (default: True)
:param numClasses: The number of classes (i.e., outcomes) a
label can take in Multinomial Logistic
Regression (default: 2).
>>> data = [
... LabeledPoint(0.0, [0.0, 1.0]),
... LabeledPoint(1.0, [1.0, 0.0]),
... ]
>>> lrm = LogisticRegressionWithLBFGS.train(sc.parallelize(data), iterations=10)
>>> lrm.predict([1.0, 0.0])
1
>>> lrm.predict([0.0, 1.0])
0
"""
def train(rdd, i):
return callMLlibFunc("trainLogisticRegressionModelWithLBFGS", rdd, int(iterations), i,
float(regParam), regType, bool(intercept), int(corrections),
float(tolerance), bool(validateData), int(numClasses))
if initialWeights is None:
if numClasses == 2:
initialWeights = [0.0] * len(data.first().features)
else:
if intercept:
initialWeights = [0.0] * (len(data.first().features) + 1) * (numClasses - 1)
else:
initialWeights = [0.0] * len(data.first().features) * (numClasses - 1)
return _regression_train_wrapper(train, LogisticRegressionModel, data, initialWeights)
class SVMModel(LinearClassificationModel):
"""
Model for Support Vector Machines (SVMs).
:param weights: Weights computed for every feature.
:param intercept: Intercept computed for this model.
>>> data = [
... LabeledPoint(0.0, [0.0]),
... LabeledPoint(1.0, [1.0]),
... LabeledPoint(1.0, [2.0]),
... LabeledPoint(1.0, [3.0])
... ]
>>> svm = SVMWithSGD.train(sc.parallelize(data), iterations=10)
>>> svm.predict([1.0])
1
>>> svm.predict(sc.parallelize([[1.0]])).collect()
[1]
>>> svm.clearThreshold()
>>> svm.predict(array([1.0]))
1.44...
>>> sparse_data = [
... LabeledPoint(0.0, SparseVector(2, {0: -1.0})),
... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),
... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),
... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))
... ]
>>> svm = SVMWithSGD.train(sc.parallelize(sparse_data), iterations=10)
>>> svm.predict(SparseVector(2, {1: 1.0}))
1
>>> svm.predict(SparseVector(2, {0: -1.0}))
0
>>> import os, tempfile
>>> path = tempfile.mkdtemp()
>>> svm.save(sc, path)
>>> sameModel = SVMModel.load(sc, path)
>>> sameModel.predict(SparseVector(2, {1: 1.0}))
1
>>> sameModel.predict(SparseVector(2, {0: -1.0}))
0
>>> from shutil import rmtree
>>> try:
... rmtree(path)
... except:
... pass
"""
def __init__(self, weights, intercept):
super(SVMModel, self).__init__(weights, intercept)
self._threshold = 0.0
def predict(self, x):
"""
Predict values for a single data point or an RDD of points
using the model trained.
"""
if isinstance(x, RDD):
return x.map(lambda v: self.predict(v))
x = _convert_to_vector(x)
margin = self.weights.dot(x) + self.intercept
if self._threshold is None:
return margin
else:
return 1 if margin > self._threshold else 0
def save(self, sc, path):
java_model = sc._jvm.org.apache.spark.mllib.classification.SVMModel(
_py2java(sc, self._coeff), self.intercept)
java_model.save(sc._jsc.sc(), path)
@classmethod
def load(cls, sc, path):
java_model = sc._jvm.org.apache.spark.mllib.classification.SVMModel.load(
sc._jsc.sc(), path)
weights = _java2py(sc, java_model.weights())
intercept = java_model.intercept()
threshold = java_model.getThreshold().get()
model = SVMModel(weights, intercept)
model.setThreshold(threshold)
return model
class SVMWithSGD(object):
@classmethod
def train(cls, data, iterations=100, step=1.0, regParam=0.01,
miniBatchFraction=1.0, initialWeights=None, regType="l2",
intercept=False, validateData=True):
"""
Train a support vector machine on the given data.
:param data: The training data, an RDD of
LabeledPoint.
:param iterations: The number of iterations
(default: 100).
:param step: The step parameter used in SGD
(default: 1.0).
:param regParam: The regularizer parameter
(default: 0.01).
:param miniBatchFraction: Fraction of data to be used for each
SGD iteration (default: 1.0).
:param initialWeights: The initial weights (default: None).
:param regType: The type of regularizer used for
training our model.
:Allowed values:
- "l1" for using L1 regularization
- "l2" for using L2 regularization
- None for no regularization
(default: "l2")
:param intercept: Boolean parameter which indicates the
use or not of the augmented representation
for training data (i.e. whether bias
features are activated or not,
default: False).
:param validateData: Boolean parameter which indicates if
the algorithm should validate data
before training. (default: True)
"""
def train(rdd, i):
return callMLlibFunc("trainSVMModelWithSGD", rdd, int(iterations), float(step),
float(regParam), float(miniBatchFraction), i, regType,
bool(intercept), bool(validateData))
return _regression_train_wrapper(train, SVMModel, data, initialWeights)
@inherit_doc
class NaiveBayesModel(Saveable, Loader):
"""
Model for Naive Bayes classifiers.
:param labels: list of labels.
:param pi: log of class priors, whose dimension is C,
number of labels.
:param theta: log of class conditional probabilities, whose
dimension is C-by-D, where D is number of features.
>>> data = [
... LabeledPoint(0.0, [0.0, 0.0]),
... LabeledPoint(0.0, [0.0, 1.0]),
... LabeledPoint(1.0, [1.0, 0.0]),
... ]
>>> model = NaiveBayes.train(sc.parallelize(data))
>>> model.predict(array([0.0, 1.0]))
0.0
>>> model.predict(array([1.0, 0.0]))
1.0
>>> model.predict(sc.parallelize([[1.0, 0.0]])).collect()
[1.0]
>>> sparse_data = [
... LabeledPoint(0.0, SparseVector(2, {1: 0.0})),
... LabeledPoint(0.0, SparseVector(2, {1: 1.0})),
... LabeledPoint(1.0, SparseVector(2, {0: 1.0}))
... ]
>>> model = NaiveBayes.train(sc.parallelize(sparse_data))
>>> model.predict(SparseVector(2, {1: 1.0}))
0.0
>>> model.predict(SparseVector(2, {0: 1.0}))
1.0
>>> import os, tempfile
>>> path = tempfile.mkdtemp()
>>> model.save(sc, path)
>>> sameModel = NaiveBayesModel.load(sc, path)
>>> sameModel.predict(SparseVector(2, {0: 1.0})) == model.predict(SparseVector(2, {0: 1.0}))
True
>>> from shutil import rmtree
>>> try:
... rmtree(path)
... except OSError:
... pass
"""
def __init__(self, labels, pi, theta):
self.labels = labels
self.pi = pi
self.theta = theta
def predict(self, x):
"""
Return the most likely class for a data vector
or an RDD of vectors
"""
if isinstance(x, RDD):
return x.map(lambda v: self.predict(v))
x = _convert_to_vector(x)
return self.labels[numpy.argmax(self.pi + x.dot(self.theta.transpose()))]
def save(self, sc, path):
java_labels = _py2java(sc, self.labels.tolist())
java_pi = _py2java(sc, self.pi.tolist())
java_theta = _py2java(sc, self.theta.tolist())
java_model = sc._jvm.org.apache.spark.mllib.classification.NaiveBayesModel(
java_labels, java_pi, java_theta)
java_model.save(sc._jsc.sc(), path)
@classmethod
def load(cls, sc, path):
java_model = sc._jvm.org.apache.spark.mllib.classification.NaiveBayesModel.load(
sc._jsc.sc(), path)
# Can not unpickle array.array from Pyrolite in Python3 with "bytes"
py_labels = _java2py(sc, java_model.labels(), "latin1")
py_pi = _java2py(sc, java_model.pi(), "latin1")
py_theta = _java2py(sc, java_model.theta(), "latin1")
return NaiveBayesModel(py_labels, py_pi, numpy.array(py_theta))
class NaiveBayes(object):
@classmethod
def train(cls, data, lambda_=1.0):
"""
Train a Naive Bayes model given an RDD of (label, features)
vectors.
This is the Multinomial NB (U{http://tinyurl.com/lsdw6p}) which
can handle all kinds of discrete data. For example, by
converting documents into TF-IDF vectors, it can be used for
document classification. By making every vector a 0-1 vector,
it can also be used as Bernoulli NB (U{http://tinyurl.com/p7c96j6}).
The input feature values must be nonnegative.
:param data: RDD of LabeledPoint.
:param lambda_: The smoothing parameter (default: 1.0).
"""
first = data.first()
if not isinstance(first, LabeledPoint):
raise ValueError("`data` should be an RDD of LabeledPoint")
labels, pi, theta = callMLlibFunc("trainNaiveBayes", data, lambda_)
return NaiveBayesModel(labels.toArray(), pi.toArray(), numpy.array(theta))
class StreamingLinearAlgorithm(object):
"""
Base class that has to be inherited by any StreamingLinearAlgorithm.
Prevents reimplementation of methods predictOn and predictOnValues.
"""
def __init__(self, model):
self._model = model
def latestModel(self):
"""
Returns the latest model.
"""
return self._model
def _validate(self, dstream):
if not isinstance(dstream, DStream):
raise TypeError(
"dstream should be a DStream object, got %s" % type(dstream))
if not self._model:
raise ValueError(
"Model must be intialized using setInitialWeights")
def predictOn(self, dstream):
"""
Make predictions on a dstream.
:return: Transformed dstream object.
"""
self._validate(dstream)
return dstream.map(lambda x: self._model.predict(x))
def predictOnValues(self, dstream):
"""
Make predictions on a keyed dstream.
:return: Transformed dstream object.
"""
self._validate(dstream)
return dstream.mapValues(lambda x: self._model.predict(x))
@inherit_doc
class StreamingLogisticRegressionWithSGD(StreamingLinearAlgorithm):
"""
Run LogisticRegression with SGD on a stream of data.
The weights obtained at the end of training a stream are used as initial
weights for the next stream.
:param stepSize: Step size for each iteration of gradient descent.
:param numIterations: Number of iterations run for each batch of data.
:param miniBatchFraction: Fraction of data on which SGD is run for each
iteration.
:param regParam: L2 Regularization parameter.
"""
def __init__(self, stepSize=0.1, numIterations=50, miniBatchFraction=1.0, regParam=0.01):
self.stepSize = stepSize
self.numIterations = numIterations
self.regParam = regParam
self.miniBatchFraction = miniBatchFraction
self._model = None
super(StreamingLogisticRegressionWithSGD, self).__init__(
model=self._model)
def setInitialWeights(self, initialWeights):
"""
Set the initial value of weights.
This must be set before running trainOn and predictOn.
"""
initialWeights = _convert_to_vector(initialWeights)
# LogisticRegressionWithSGD does only binary classification.
self._model = LogisticRegressionModel(
initialWeights, 0, initialWeights.size, 2)
return self
def trainOn(self, dstream):
"""Train the model on the incoming dstream."""
self._validate(dstream)
def update(rdd):
# LogisticRegressionWithSGD.train raises an error for an empty RDD.
if not rdd.isEmpty():
self._model = LogisticRegressionWithSGD.train(
rdd, self.numIterations, self.stepSize,
self.miniBatchFraction, self._model.weights)
dstream.foreachRDD(update)
def _test():
import doctest
from pyspark import SparkContext
import pyspark.mllib.classification
globs = pyspark.mllib.classification.__dict__.copy()
globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2)
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
exit(-1)
if __name__ == "__main__":
_test()
|