# -*- coding: utf-8 -*-
"""
author SparkByExamples.com
"""

import pyspark
from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('SparkByExamples.com') \
        .master("local[5]").getOrCreate()

df = spark.range(0,20)
print(df.rdd.getNumPartitions())

spark.conf.set("spark.sql.shuffle.partitions", "500")

rdd = spark.sparkContext.parallelize((0,20))
print("From local[5]"+str(rdd.getNumPartitions()))

rdd1 = spark.sparkContext.parallelize((0,25), 6)
print("parallelize : "+str(rdd1.getNumPartitions()))

"""rddFromFile = spark.sparkContext.textFile("src/main/resources/test.txt",10)
print("TextFile : "+str(rddFromFile.getNumPartitions())) """

rdd1.saveAsTextFile("c://tmp/partition2")

rdd2 = rdd1.repartition(4)
print("Repartition size : "+str(rdd2.getNumPartitions()))
rdd2.saveAsTextFile("c://tmp/re-partition2")

rdd3 = rdd1.coalesce(4)
print("Repartition size : "+str(rdd3.getNumPartitions()))
rdd3.saveAsTextFile("c:/tmp/coalesce2")