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
|
#
# 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 numpy
from numpy import array
from collections import namedtuple
from pyspark import SparkContext, since
from pyspark.rdd import ignore_unicode_prefix
from pyspark.mllib.common import JavaModelWrapper, callMLlibFunc, inherit_doc
__all__ = ['FPGrowth', 'FPGrowthModel', 'PrefixSpan', 'PrefixSpanModel']
@inherit_doc
@ignore_unicode_prefix
class FPGrowthModel(JavaModelWrapper):
"""
.. note:: Experimental
A FP-Growth model for mining frequent itemsets
using the Parallel FP-Growth algorithm.
>>> data = [["a", "b", "c"], ["a", "b", "d", "e"], ["a", "c", "e"], ["a", "c", "f"]]
>>> rdd = sc.parallelize(data, 2)
>>> model = FPGrowth.train(rdd, 0.6, 2)
>>> sorted(model.freqItemsets().collect())
[FreqItemset(items=[u'a'], freq=4), FreqItemset(items=[u'c'], freq=3), ...
.. versionadded:: 1.4.0
"""
@since("1.4.0")
def freqItemsets(self):
"""
Returns the frequent itemsets of this model.
"""
return self.call("getFreqItemsets").map(lambda x: (FPGrowth.FreqItemset(x[0], x[1])))
class FPGrowth(object):
"""
.. note:: Experimental
A Parallel FP-growth algorithm to mine frequent itemsets.
.. versionadded:: 1.4.0
"""
@classmethod
@since("1.4.0")
def train(cls, data, minSupport=0.3, numPartitions=-1):
"""
Computes an FP-Growth model that contains frequent itemsets.
:param data: The input data set, each element contains a
transaction.
:param minSupport: The minimal support level (default: `0.3`).
:param numPartitions: The number of partitions used by
parallel FP-growth (default: same as input data).
"""
model = callMLlibFunc("trainFPGrowthModel", data, float(minSupport), int(numPartitions))
return FPGrowthModel(model)
class FreqItemset(namedtuple("FreqItemset", ["items", "freq"])):
"""
Represents an (items, freq) tuple.
.. versionadded:: 1.4.0
"""
@inherit_doc
@ignore_unicode_prefix
class PrefixSpanModel(JavaModelWrapper):
"""
.. note:: Experimental
Model fitted by PrefixSpan
>>> data = [
... [["a", "b"], ["c"]],
... [["a"], ["c", "b"], ["a", "b"]],
... [["a", "b"], ["e"]],
... [["f"]]]
>>> rdd = sc.parallelize(data, 2)
>>> model = PrefixSpan.train(rdd)
>>> sorted(model.freqSequences().collect())
[FreqSequence(sequence=[[u'a']], freq=3), FreqSequence(sequence=[[u'a'], [u'a']], freq=1), ...
.. versionadded:: 1.6.0
"""
@since("1.6.0")
def freqSequences(self):
"""Gets frequence sequences"""
return self.call("getFreqSequences").map(lambda x: PrefixSpan.FreqSequence(x[0], x[1]))
class PrefixSpan(object):
"""
.. note:: Experimental
A parallel PrefixSpan algorithm to mine frequent sequential patterns.
The PrefixSpan algorithm is described in J. Pei, et al., PrefixSpan:
Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth
([[http://doi.org/10.1109/ICDE.2001.914830]]).
.. versionadded:: 1.6.0
"""
@classmethod
@since("1.6.0")
def train(cls, data, minSupport=0.1, maxPatternLength=10, maxLocalProjDBSize=32000000):
"""
Finds the complete set of frequent sequential patterns in the input sequences of itemsets.
:param data: The input data set, each element contains a sequnce of itemsets.
:param minSupport: the minimal support level of the sequential pattern, any pattern appears
more than (minSupport * size-of-the-dataset) times will be output (default: `0.1`)
:param maxPatternLength: the maximal length of the sequential pattern, any pattern appears
less than maxPatternLength will be output. (default: `10`)
:param maxLocalProjDBSize: The maximum number of items (including delimiters used in
the internal storage format) allowed in a projected database before local
processing. If a projected database exceeds this size, another
iteration of distributed prefix growth is run. (default: `32000000`)
"""
model = callMLlibFunc("trainPrefixSpanModel",
data, minSupport, maxPatternLength, maxLocalProjDBSize)
return PrefixSpanModel(model)
class FreqSequence(namedtuple("FreqSequence", ["sequence", "freq"])):
"""
Represents a (sequence, freq) tuple.
.. versionadded:: 1.6.0
"""
def _test():
import doctest
import pyspark.mllib.fpm
globs = pyspark.mllib.fpm.__dict__.copy()
globs['sc'] = SparkContext('local[4]', 'PythonTest')
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
exit(-1)
if __name__ == "__main__":
_test()
|
