[
https://issues.apache.org/jira/browse/SPARK-16720?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15393069#comment-15393069
]
Hyukjin Kwon commented on SPARK-16720:
--------------------------------------
Hi [~holdenk], this part seems familiar to me. Do you mind if i look into this
and work on this?
> Loading CSV file with 2k+ columns fails during attribute resolution on action
> -----------------------------------------------------------------------------
>
> Key: SPARK-16720
> URL: https://issues.apache.org/jira/browse/SPARK-16720
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.0.0
> Reporter: holdenk
>
> Example shell for repro:
> {quote}
> scala> val df =spark.read.format("csv").option("header",
> "true").option("inferSchema", "true").load("/home/holden/Downloads/ex*.csv")
> df: org.apache.spark.sql.DataFrame = [Date: string, Lifetime Total Likes: int
> ... 2125 more fields]
> scala> df.schema
> res0: org.apache.spark.sql.types.StructType =
> StructType(StructField(Date,StringType,true), StructField(Lifetime Total
> Likes,IntegerType,true), StructField(Daily New Likes,IntegerType,true),
> StructField(Daily Unlikes,IntegerType,true), StructField(Daily Page Engaged
> Users,IntegerType,true), StructField(Weekly Page Engaged
> Users,IntegerType,true), StructField(28 Days Page Engaged
> Users,IntegerType,true), StructField(Daily Like Sources - On Your
> Page,IntegerType,true), StructField(Daily Total Reach,IntegerType,true),
> StructField(Weekly Total Reach,IntegerType,true), StructField(28 Days Total
> Reach,IntegerType,true), StructField(Daily Organic Reach,IntegerType,true),
> StructField(Weekly Organic Reach,IntegerType,true), StructField(28 Days
> Organic Reach,IntegerType,true), StructField(Daily T...
> scala> df.take(1)
> [GIANT LIST OF COLUMNS]
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolve$1$$anonfun$apply$5.apply(LogicalPlan.scala:134)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolve$1$$anonfun$apply$5.apply(LogicalPlan.scala:134)
> at scala.Option.getOrElse(Option.scala:121)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolve$1.apply(LogicalPlan.scala:133)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolve$1.apply(LogicalPlan.scala:129)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.Iterator$class.foreach(Iterator.scala:893)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> at org.apache.spark.sql.types.StructType.foreach(StructType.scala:95)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at org.apache.spark.sql.types.StructType.map(StructType.scala:95)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolve(LogicalPlan.scala:129)
> at
> org.apache.spark.sql.execution.datasources.FileSourceStrategy$.apply(FileSourceStrategy.scala:87)
> at
> org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:60)
> at
> org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:60)
> at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
> at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
> at
> org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:61)
> at org.apache.spark.sql.execution.SparkPlanner.plan(SparkPlanner.scala:47)
> at
> org.apache.spark.sql.execution.SparkPlanner$$anonfun$plan$1$$anonfun$apply$1.applyOrElse(SparkPlanner.scala:51)
> at
> org.apache.spark.sql.execution.SparkPlanner$$anonfun$plan$1$$anonfun$apply$1.applyOrElse(SparkPlanner.scala:48)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:300)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:298)
> at
> org.apache.spark.sql.execution.SparkPlanner$$anonfun$plan$1.apply(SparkPlanner.scala:48)
> at
> org.apache.spark.sql.execution.SparkPlanner$$anonfun$plan$1.apply(SparkPlanner.scala:48)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
> at
> org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:78)
> at
> org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:76)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:83)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:83)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2558)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:1924)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2139)
> ... 48 elided
> {quote}
> Interestingly enough attempting to access row by index also fails in column
> resolution phase or converting to an RDD also fails.
> Loading without header on succeeds.
> csv file for repro (on dropbox):
> https://www.dropbox.com/s/f8453txcej43mz4/example_facebook.csv?dl=0
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
