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
|
#
# 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.
#
"""
Python package for random data generation.
"""
from functools import wraps
from pyspark import since
from pyspark.mllib.common import callMLlibFunc
__all__ = ['RandomRDDs', ]
def toArray(f):
@wraps(f)
def func(sc, *a, **kw):
rdd = f(sc, *a, **kw)
return rdd.map(lambda vec: vec.toArray())
return func
class RandomRDDs(object):
"""
Generator methods for creating RDDs comprised of i.i.d samples from
some distribution.
.. addedversion:: 1.1.0
"""
@staticmethod
@since("1.1.0")
def uniformRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the
uniform distribution U(0.0, 1.0).
To transform the distribution in the generated RDD from U(0.0, 1.0)
to U(a, b), use
C{RandomRDDs.uniformRDD(sc, n, p, seed)\
.map(lambda v: a + (b - a) * v)}
:param sc: SparkContext used to create the RDD.
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ `U(0.0, 1.0)`.
>>> x = RandomRDDs.uniformRDD(sc, 100).collect()
>>> len(x)
100
>>> max(x) <= 1.0 and min(x) >= 0.0
True
>>> RandomRDDs.uniformRDD(sc, 100, 4).getNumPartitions()
4
>>> parts = RandomRDDs.uniformRDD(sc, 100, seed=4).getNumPartitions()
>>> parts == sc.defaultParallelism
True
"""
return callMLlibFunc("uniformRDD", sc._jsc, size, numPartitions, seed)
@staticmethod
@since("1.1.0")
def normalRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the standard normal
distribution.
To transform the distribution in the generated RDD from standard normal
to some other normal N(mean, sigma^2), use
C{RandomRDDs.normal(sc, n, p, seed)\
.map(lambda v: mean + sigma * v)}
:param sc: SparkContext used to create the RDD.
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ N(0.0, 1.0).
>>> x = RandomRDDs.normalRDD(sc, 1000, seed=1)
>>> stats = x.stats()
>>> stats.count()
1000
>>> abs(stats.mean() - 0.0) < 0.1
True
>>> abs(stats.stdev() - 1.0) < 0.1
True
"""
return callMLlibFunc("normalRDD", sc._jsc, size, numPartitions, seed)
@staticmethod
@since("1.3.0")
def logNormalRDD(sc, mean, std, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the log normal
distribution with the input mean and standard distribution.
:param sc: SparkContext used to create the RDD.
:param mean: mean for the log Normal distribution
:param std: std for the log Normal distribution
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ log N(mean, std).
>>> from math import sqrt, exp
>>> mean = 0.0
>>> std = 1.0
>>> expMean = exp(mean + 0.5 * std * std)
>>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))
>>> x = RandomRDDs.logNormalRDD(sc, mean, std, 1000, seed=2)
>>> stats = x.stats()
>>> stats.count()
1000
>>> abs(stats.mean() - expMean) < 0.5
True
>>> from math import sqrt
>>> abs(stats.stdev() - expStd) < 0.5
True
"""
return callMLlibFunc("logNormalRDD", sc._jsc, float(mean), float(std),
size, numPartitions, seed)
@staticmethod
@since("1.1.0")
def poissonRDD(sc, mean, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the Poisson
distribution with the input mean.
:param sc: SparkContext used to create the RDD.
:param mean: Mean, or lambda, for the Poisson distribution.
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ Pois(mean).
>>> mean = 100.0
>>> x = RandomRDDs.poissonRDD(sc, mean, 1000, seed=2)
>>> stats = x.stats()
>>> stats.count()
1000
>>> abs(stats.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(stats.stdev() - sqrt(mean)) < 0.5
True
"""
return callMLlibFunc("poissonRDD", sc._jsc, float(mean), size, numPartitions, seed)
@staticmethod
@since("1.3.0")
def exponentialRDD(sc, mean, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the Exponential
distribution with the input mean.
:param sc: SparkContext used to create the RDD.
:param mean: Mean, or 1 / lambda, for the Exponential distribution.
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ Exp(mean).
>>> mean = 2.0
>>> x = RandomRDDs.exponentialRDD(sc, mean, 1000, seed=2)
>>> stats = x.stats()
>>> stats.count()
1000
>>> abs(stats.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(stats.stdev() - sqrt(mean)) < 0.5
True
"""
return callMLlibFunc("exponentialRDD", sc._jsc, float(mean), size, numPartitions, seed)
@staticmethod
@since("1.3.0")
def gammaRDD(sc, shape, scale, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the Gamma
distribution with the input shape and scale.
:param sc: SparkContext used to create the RDD.
:param shape: shape (> 0) parameter for the Gamma distribution
:param scale: scale (> 0) parameter for the Gamma distribution
:param size: Size of the RDD.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of float comprised of i.i.d. samples ~ Gamma(shape, scale).
>>> from math import sqrt
>>> shape = 1.0
>>> scale = 2.0
>>> expMean = shape * scale
>>> expStd = sqrt(shape * scale * scale)
>>> x = RandomRDDs.gammaRDD(sc, shape, scale, 1000, seed=2)
>>> stats = x.stats()
>>> stats.count()
1000
>>> abs(stats.mean() - expMean) < 0.5
True
>>> abs(stats.stdev() - expStd) < 0.5
True
"""
return callMLlibFunc("gammaRDD", sc._jsc, float(shape),
float(scale), size, numPartitions, seed)
@staticmethod
@toArray
@since("1.1.0")
def uniformVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the uniform distribution U(0.0, 1.0).
:param sc: SparkContext used to create the RDD.
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD.
:param seed: Seed for the RNG that generates the seed for the generator in each partition.
:return: RDD of Vector with vectors containing i.i.d samples ~ `U(0.0, 1.0)`.
>>> import numpy as np
>>> mat = np.matrix(RandomRDDs.uniformVectorRDD(sc, 10, 10).collect())
>>> mat.shape
(10, 10)
>>> mat.max() <= 1.0 and mat.min() >= 0.0
True
>>> RandomRDDs.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions()
4
"""
return callMLlibFunc("uniformVectorRDD", sc._jsc, numRows, numCols, numPartitions, seed)
@staticmethod
@toArray
@since("1.1.0")
def normalVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the standard normal distribution.
:param sc: SparkContext used to create the RDD.
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of Vector with vectors containing i.i.d. samples ~ `N(0.0, 1.0)`.
>>> import numpy as np
>>> mat = np.matrix(RandomRDDs.normalVectorRDD(sc, 100, 100, seed=1).collect())
>>> mat.shape
(100, 100)
>>> abs(mat.mean() - 0.0) < 0.1
True
>>> abs(mat.std() - 1.0) < 0.1
True
"""
return callMLlibFunc("normalVectorRDD", sc._jsc, numRows, numCols, numPartitions, seed)
@staticmethod
@toArray
@since("1.3.0")
def logNormalVectorRDD(sc, mean, std, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the log normal distribution.
:param sc: SparkContext used to create the RDD.
:param mean: Mean of the log normal distribution
:param std: Standard Deviation of the log normal distribution
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of Vector with vectors containing i.i.d. samples ~ log `N(mean, std)`.
>>> import numpy as np
>>> from math import sqrt, exp
>>> mean = 0.0
>>> std = 1.0
>>> expMean = exp(mean + 0.5 * std * std)
>>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))
>>> m = RandomRDDs.logNormalVectorRDD(sc, mean, std, 100, 100, seed=1).collect()
>>> mat = np.matrix(m)
>>> mat.shape
(100, 100)
>>> abs(mat.mean() - expMean) < 0.1
True
>>> abs(mat.std() - expStd) < 0.1
True
"""
return callMLlibFunc("logNormalVectorRDD", sc._jsc, float(mean), float(std),
numRows, numCols, numPartitions, seed)
@staticmethod
@toArray
@since("1.1.0")
def poissonVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the Poisson distribution with the input mean.
:param sc: SparkContext used to create the RDD.
:param mean: Mean, or lambda, for the Poisson distribution.
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`)
:param seed: Random seed (default: a random long integer).
:return: RDD of Vector with vectors containing i.i.d. samples ~ Pois(mean).
>>> import numpy as np
>>> mean = 100.0
>>> rdd = RandomRDDs.poissonVectorRDD(sc, mean, 100, 100, seed=1)
>>> mat = np.mat(rdd.collect())
>>> mat.shape
(100, 100)
>>> abs(mat.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(mat.std() - sqrt(mean)) < 0.5
True
"""
return callMLlibFunc("poissonVectorRDD", sc._jsc, float(mean), numRows, numCols,
numPartitions, seed)
@staticmethod
@toArray
@since("1.3.0")
def exponentialVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the Exponential distribution with the input mean.
:param sc: SparkContext used to create the RDD.
:param mean: Mean, or 1 / lambda, for the Exponential distribution.
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`)
:param seed: Random seed (default: a random long integer).
:return: RDD of Vector with vectors containing i.i.d. samples ~ Exp(mean).
>>> import numpy as np
>>> mean = 0.5
>>> rdd = RandomRDDs.exponentialVectorRDD(sc, mean, 100, 100, seed=1)
>>> mat = np.mat(rdd.collect())
>>> mat.shape
(100, 100)
>>> abs(mat.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(mat.std() - sqrt(mean)) < 0.5
True
"""
return callMLlibFunc("exponentialVectorRDD", sc._jsc, float(mean), numRows, numCols,
numPartitions, seed)
@staticmethod
@toArray
@since("1.3.0")
def gammaVectorRDD(sc, shape, scale, numRows, numCols, numPartitions=None, seed=None):
"""
Generates an RDD comprised of vectors containing i.i.d. samples drawn
from the Gamma distribution.
:param sc: SparkContext used to create the RDD.
:param shape: Shape (> 0) of the Gamma distribution
:param scale: Scale (> 0) of the Gamma distribution
:param numRows: Number of Vectors in the RDD.
:param numCols: Number of elements in each Vector.
:param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).
:param seed: Random seed (default: a random long integer).
:return: RDD of Vector with vectors containing i.i.d. samples ~ Gamma(shape, scale).
>>> import numpy as np
>>> from math import sqrt
>>> shape = 1.0
>>> scale = 2.0
>>> expMean = shape * scale
>>> expStd = sqrt(shape * scale * scale)
>>> mat = np.matrix(RandomRDDs.gammaVectorRDD(sc, shape, scale, 100, 100, seed=1).collect())
>>> mat.shape
(100, 100)
>>> abs(mat.mean() - expMean) < 0.1
True
>>> abs(mat.std() - expStd) < 0.1
True
"""
return callMLlibFunc("gammaVectorRDD", sc._jsc, float(shape), float(scale),
numRows, numCols, numPartitions, seed)
def _test():
import doctest
from pyspark.context import SparkContext
globs = globals().copy()
# The small batch size here ensures that we see multiple batches,
# even in these small test examples:
globs['sc'] = SparkContext('local[2]', '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()
|