4ad9bfd53b
### What changes were proposed in this pull request? This PR aims to drop Python 2.7, 3.4 and 3.5. Roughly speaking, it removes all the widely known Python 2 compatibility workarounds such as `sys.version` comparison, `__future__`. Also, it removes the Python 2 dedicated codes such as `ArrayConstructor` in Spark. ### Why are the changes needed? 1. Unsupport EOL Python versions 2. Reduce maintenance overhead and remove a bit of legacy codes and hacks for Python 2. 3. PyPy2 has a critical bug that causes a flaky test, SPARK-28358 given my testing and investigation. 4. Users can use Python type hints with Pandas UDFs without thinking about Python version 5. Users can leverage one latest cloudpickle, https://github.com/apache/spark/pull/28950. With Python 3.8+ it can also leverage C pickle. ### Does this PR introduce _any_ user-facing change? Yes, users cannot use Python 2.7, 3.4 and 3.5 in the upcoming Spark version. ### How was this patch tested? Manually tested and also tested in Jenkins. Closes #28957 from HyukjinKwon/SPARK-32138. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
55 lines
1.9 KiB
Python
55 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 numpy as np
|
|
|
|
from pyspark.mllib.common import callMLlibFunc
|
|
from pyspark.rdd import RDD
|
|
|
|
|
|
class KernelDensity(object):
|
|
"""
|
|
Estimate probability density at required points given an 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)
|