pyspark之DataFrame學習（1）

from pyspark.sql import SparkSessionspark= SparkSession\                .builder \                .appName("dataFrame") \                .getOrCreate()#1產生JSON資料stringJSONRDD = spark.sparkContext.parallelize(('''{    "id":"123",    "name":"Katie",    "age":19,    "eyeColor":"brown"}''','''{    "id":"234",    "name":"Michael",    "age":22,    "eyeColor":"green"}''','''{    "id":"345",    "name":"Simone",    "age":23,    "eyeColor":"blue"}'''))#2建立DataFrameswimmersJSON = spark.read.json(stringJSONRDD)#3建立一個暫存資料表swimmersJSON.createOrReplaceGlobalTempView("swimmersJSON")#4查看前幾行print swimmersJSON.show()#預設是10行

#5可以通過編寫sql語句查詢print spark.sql("select * from swimmersJSON").collect()

#6列印模式print swimmersJSON.printSchema()