0
將火花數據幀寫入csv和實木複合地板時發生錯誤。我已經嘗試安裝winutil,但仍未解決錯誤。SparkR將數據幀寫入csv和實木複合地時發生錯誤
我的代碼
INVALID_IMEI <- c("","000000000000000")
setwd("D:/Revas/Jatim Old")
fileList <- list.files()
cdrSchema <- structType(structField("date","string"),
structField("time","string"),
structField("a_number","string"),
structField("b_number", "string"),
structField("duration","integer"),
structField("lac_cid","string"),
structField("imei","string"))
file <- fileList[1]
filePath <- paste0("D:/Revas/Jatim Old/",file)
dataset <- read.df(filePath, header="false",source="csv",delimiter="|",schema=cdrSchema)
dataset <- filter(dataset, ifelse(dataset$imei %in% INVALID_IMEI,FALSE,TRUE))
dataset <- filter(dataset, ifelse(isnan(dataset$imei),FALSE,TRUE))
dataset <- filter(dataset, ifelse(isNull(dataset$imei),FALSE,TRUE))
要導出數據框,我嘗試下面的代碼
write.df(dataset, "D:/spark/dataset",mode="overwrite")
write.parquet(dataset, "D:/spark/dataset",mode="overwrite")
,我得到以下錯誤
Error: Error in save : org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:215)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:173)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:173)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:173)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:145)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.comma