我正在尝试应用MLlib中提供的ALS矩阵分解。以下是我的代码
from pyspark.sql.types import StringType
from pyspark import SQLContext
sqlContext = SQLContext(sc)
t1 =
sqlContext.read.csv("/user/hadoop/personalization/test1.csv",header=False)
from pyspark.mllib.recommendation\
import ALS,MatrixFactorizationModel, Rating
model=ALS.train(t1,rank=2,iterations=20,seed=0)
products_for_users = model.recommendProductsForUsers(2).collect()
l2=sqlContext.createDataFrame(products_for_users)
l2.show()
l2.write.csv('l2.csv')
在最后一步,执行write.csv()后,我收到以下错误:有人可以确定错误的来源
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/lib/spark/python/pyspark/sql/readwriter.py", line 674, in csv
self._jwrite.csv(path)
File "/usr/lib/spark/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py",
lin
e 933, in __call__
File "/usr/lib/spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/usr/lib/spark/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py",
line 31
2, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o140.csv.
: java.lang.UnsupportedOperationException: CSV data source does not support struct<_1:struct<user:bigint,product:bigint,rating:double>,_2:struct<user:bigint,pro duct:bigint,rating:double>> data type.
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anonfun $verifySchema$1.apply(CSVFileFormat.scala:186)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anonfun $verifySchema$1.apply(CSVFileFormat.scala:183)
at scala.collection.Iterator$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 org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.verifySc hema(CSVFileFormat.scala:183)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.prepareW rite(CSVFileFormat.scala:87)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command$$anonfun$run$1$$anonfun$4.apply(InsertIntoHadoopFsRelationCommand.scala: 121)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command$$anonfun$run$1$$anonfun$4.apply(InsertIntoHadoopFsRelationCommand.scala: 121)
at org.apache.spark.sql.execution.datasources.BaseWriterContainer.driver SideSetup(WriterContainer.scala:105)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelationCommand.scala:140)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLEx ecution.scala:57)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation Command.run(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffect Result$lzycompute(commands.scala:60)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffect Result(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute( commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(Spa rkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(Spa rkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.appl y(SparkPlan.scala:136)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.s cala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala :133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryE xecution.scala:86)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.sc ala:86)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSourc e.scala:487)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:211)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:194)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:551)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl. java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAcces sorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
答案 0 :(得分:0)
在将带有可能性的数据帧写入CSV时,我遇到了类似的错误。你可能想尝试下面的,这对我有用。
l2.toPandas().to_csv('l2.csv')