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
|
#
# 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':
xrange = range
import numpy as np
from pyspark.mllib.common import callMLlibFunc
from pyspark.rdd import RDD
class KernelDensity(object):
"""
.. note:: Experimental
Estimate probability density at required points given a RDD of samples
from the population.
>>> kd = KernelDensity()
>>> sample = sc.parallelize([0.0, 1.0])
>>> kd.setSample(sample)
>>> kd.estimate([0.0, 1.0])
array([ 0.12938758, 0.12938758])
"""
def __init__(self):
self._bandwidth = 1.0
self._sample = None
def setBandwidth(self, bandwidth):
"""Set bandwidth of each sample. Defaults to 1.0"""
self._bandwidth = bandwidth
def setSample(self, sample):
"""Set sample points from the population. Should be a RDD"""
if not isinstance(sample, RDD):
raise TypeError("samples should be a RDD, received %s" % type(sample))
self._sample = sample
def estimate(self, points):
"""Estimate the probability density at points"""
points = list(points)
densities = callMLlibFunc(
"estimateKernelDensity", self._sample, self._bandwidth, points)
return np.asarray(densities)
|
