#!/usr/bin/env python # Licensed to Cloudera, Inc. under one # or more contributor license agreements. See the NOTICE file # distributed with this work for additional information # regarding copyright ownership. Cloudera, Inc. 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 pyspark import random if not 'sc' in globals(): sc = pyspark.SparkContext() NUM_SAMPLES = 1000 def sample(p): x,y = random.random(),random.random() return 1 if x*x + y*y < 1 else 0 count = sc.parallelize(xrange(0, NUM_SAMPLES)) \ .map(sample) \ .reduce(lambda a, b: a + b) print "Pi is roughly %f" % (4.0 * count / NUM_SAMPLES)