📄 220120_(65) spark_sql
data1 = ['홍길동,1000','이순신,2000','임꺽정,3000',
'김철수,4000','이황,5000','이이,6000']
yeje=sc.parallelize(data1)
yeje=yeje.map(lambda v:v.split(','))
yeje
PythonRDD[56] at RDD at PythonRDD.scala:53
yeje.collect()
[['홍길동', '1000'],
['이순신', '2000'],
['임꺽정', '3000'],
['김철수', '4000'],
['이황', '5000'],
['이이', '6000']]
yejedf=sqlCtx.createDataFrame(yeje, ['name','salary'])
yejedf.show()
+------+------+
| name|salary|
+------+------+
|홍길동| 1000|
|이순신| 2000|
|임꺽정| 3000|
|김철수| 4000|
| 이황| 5000|
| 이이| 6000|
+------+------+
yejedf.createOrReplaceTempView('my2')