test1.py

import sys
from operator import add

from pyspark.sql import SparkSession


if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("PythonWordCount")\
        .getOrCreate()
    sc=spark.sparkContext

    words = 'the quick brown fox jumps over the\
        lazy dog the quick brown fox jumps over the lazy dog'

    seq = words.split()
    # sc is SparkContext that is created with pyspark
    data = sc.parallelize(seq)
    counts = data.map(lambda word: (word, 1)).reduceByKey(lambda a, b: a + b).collect()
    dict(counts)
    sc.stop()