[
https://issues.apache.org/jira/browse/SPARK-15404?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
郭同 updated SPARK-15404:
-----------------------
Description:
import os
import sys
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql.types import Row, StructField, StructType, StringType,
IntegerType
if __name__ == "__main__":
sc = SparkContext(appName="PythonSQL")
sqlContext = SQLContext(sc)
schema = StructType([StructField("person_name", StringType(), False),
StructField("person_age", IntegerType(), False)])
some_rdd = sc.parallelize([Row(person_name="John", person_age=19),
Row(person_name="Smith", person_age=23),
Row(person_name="Sarah", person_age=18)])
some_df = sqlContext.createDataFrame(some_rdd, schema)
some_df.printSchema()
some_df.registerAsTable("people")
teenagers = sqlContext.sql("SELECT * FROM people ")
for each in teenagers.collect():
print(each)
sc.stop()
was:
from __future__ import print_function
import os
import sys
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql.types import Row, StructField, StructType, StringType,
IntegerType
if __name__ == "__main__":
sc = SparkContext(appName="PythonSQL")
sqlContext = SQLContext(sc)
schema = StructType([StructField("person_name", StringType(), False),
StructField("person_age", IntegerType(), False)])
some_rdd = sc.parallelize([Row(person_name="John", person_age=19),
Row(person_name="Smith", person_age=23),
Row(person_name="Sarah", person_age=18)])
some_df = sqlContext.createDataFrame(some_rdd, schema)
some_df.printSchema()
some_df.registerAsTable("people")
teenagers = sqlContext.sql("SELECT * FROM people ")
for each in teenagers.collect():
print(each)
sc.stop()
> pyspark sql bug ,here is the testcase
> -------------------------------------
>
> Key: SPARK-15404
> URL: https://issues.apache.org/jira/browse/SPARK-15404
> Project: Spark
> Issue Type: Bug
> Environment: 1.6
> Reporter: 郭同
>
> import os
> import sys
> from pyspark import SparkContext
> from pyspark.sql import SQLContext
> from pyspark.sql.types import Row, StructField, StructType, StringType,
> IntegerType
> if __name__ == "__main__":
> sc = SparkContext(appName="PythonSQL")
> sqlContext = SQLContext(sc)
> schema = StructType([StructField("person_name", StringType(), False),
> StructField("person_age", IntegerType(), False)])
> some_rdd = sc.parallelize([Row(person_name="John", person_age=19),
> Row(person_name="Smith", person_age=23),
> Row(person_name="Sarah", person_age=18)])
> some_df = sqlContext.createDataFrame(some_rdd, schema)
> some_df.printSchema()
> some_df.registerAsTable("people")
> teenagers = sqlContext.sql("SELECT * FROM people ")
> for each in teenagers.collect():
> print(each)
> sc.stop()
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
