导包

from pyspark import SparkConf, SparkContext
import os

os.environ["PYSPARK_PYTHON"] = "D:/dev/python/python3.10.4/python.exe"
conf = SparkConf().setMaster("local[*]").setAppName("test_spark")
sc = SparkContext(conf=conf)

创建RDD

rdd = sc.parallelize([1, 2, 3, 4, 5, 6, 7])

collect算子

rdd_list: list = rdd.collect()
print(rdd_list)
print(type(rdd_list))

reduce算子

num = rdd.reduce(lambda a, b: a + b)
print(num)

take算子，取出前n个元素，返回list

take_list = rdd.take(3)
print(take_list)

count算子，计数

num_count = rdd.count()
print(num_count)

saveAsTextFile算子

环境配置

os.environ["HADOOP_HOME"] = "D:/dev/hadoop-3.0.0"
conf.set("spark.default.parallelism", "1")

rdd.saveAsTextFile("D:/output")