Source code for tests.system.providers.google.cloud.dataplex.resources.spark_example_pi

# 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.

from __future__ import annotations

import sys
from operator import add
from random import random

from pyspark.sql import SparkSession

if __name__ == "__main__":
    """
    Usage: pi [partitions]
    """

[docs]    spark = SparkSession.builder.appName("PythonPi").getOrCreate()


    partitions = int(sys.argv[1]) if len(sys.argv) > 1 else 2
    n = 100000 * partitions

    def f(_: int) -> float:
        x = random() * 2 - 1
        y = random() * 2 - 1
        return 1 if x**2 + y**2 <= 1 else 0

    count = spark.sparkContext.parallelize(range(1, n + 1), partitions).map(f).reduce(add)
    print(f"Pi is roughly {4.0 * count / n:f}")

    spark.stop()

Was this entry helpful?