01f09b1612
## What changes were proposed in this pull request? General decisions to follow, except where noted: * spark.mllib, pyspark.mllib: Remove all Experimental annotations. Leave DeveloperApi annotations alone. * spark.ml, pyspark.ml ** Annotate Estimator-Model pairs of classes and companion objects the same way. ** For all algorithms marked Experimental with Since tag <= 1.6, remove Experimental annotation. ** For all algorithms marked Experimental with Since tag = 2.0, leave Experimental annotation. * DeveloperApi annotations are left alone, except where noted. * No changes to which types are sealed. Exceptions where I am leaving items Experimental in spark.ml, pyspark.ml, mainly because the items are new: * Model Summary classes * MLWriter, MLReader, MLWritable, MLReadable * Evaluator and subclasses: There is discussion of changes around evaluating multiple metrics at once for efficiency. * RFormula: Its behavior may need to change slightly to match R in edge cases. * AFTSurvivalRegression * MultilayerPerceptronClassifier DeveloperApi changes: * ml.tree.Node, ml.tree.Split, and subclasses should no longer be DeveloperApi ## How was this patch tested? N/A Note to reviewers: * spark.ml.clustering.LDA underwent significant changes (additional methods), so let me know if you want me to leave it Experimental. * Be careful to check for cases where a class should no longer be Experimental but has an Experimental method, val, or other feature. I did not find such cases, but please verify. Author: Joseph K. Bradley <joseph@databricks.com> Closes #14147 from jkbradley/experimental-audit.
60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
#
|
|
# 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):
|
|
"""
|
|
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)
|