93、python-第三阶段-3-数据输入

from pyspark import SparkConf,SparkContext
conf = SparkConf().setMaster("local[*]").setAppName("test_spark_app")
sc = SparkContext(conf=conf)

rdd1 = sc.parallelize([1,2,3,4,5])
rdd2 = sc.parallelize((1,2,3,4,5))
rdd3 = sc.parallelize("bdsdfsdfsdf")
rdd4 = sc.parallelize({1,2,3,4,5})
rdd5 = sc.parallelize({"key1":"value1","key2":"value2"})
print(rdd1.collect())
print(rdd2.collect())
print(rdd3.collect())
print(rdd4.collect())
print(rdd5.collect())
sc.stop()

转成rdd对象，里面会有很多的方法供我们使用

from pyspark import SparkConf,SparkContext
conf = SparkConf().setMaster("local[*]").setAppName("test_spark_app")
sc = SparkContext(conf=conf)
rdd=sc.textFile("d:/hello.txt")
print(rdd.collect())
sc.stop()