[Spark][Python][RDD][DataFrame]从 RDD 构造 DataFrame 例子
from pyspark.sql.types import *
schema = StructType( [ StructField("age",IntegerType(),True),
StructField("name",StringType(),True),
StructField("pcode",StringType(),True) ] )
myrdd = sc.parallelize([(40,"Abram","01601"),(16,"Lucia","87501")])
mydf = sqlContext.createDataFrame(myrdd,schema)
mydf.limit(5).show()
+---+-----+-----+
|age| name|pcode|
+---+-----+-----+
| 40|Abram|01601|
| 16|Lucia|87501|
+---+-----+-----+
