Ниже приведен код, который я использовал для импорта таблицы bigquery в мой кластер PySpark (dataproc), а затем запускал на нем алгоритм fp-growth. Но сегодня, когда я запускал тот же код, он выдавал ошибку. Он возвращает схему импортированного df с .printSchema (), но когда я пытаюсь запустить .show () или .fit (), он выдает следующую ошибку.
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, split
from pyspark.sql.types import ArrayType, IntegerType
from pyspark.ml.fpm import FPGrowth
from pyspark.sql.functions import concat_ws
spark = SparkSession.builder.appName('Jupyter BigQuery Storage').config('spark.jars','gs://spark-lib/bigquery/spark-bigquery-latest.jar').getOrCreate()
table = "project_name.dataset_name.test_table"
df = spark.read.format("bigquery").option("table",table).load()
df.printSchema()
df = df.withColumn(
"item",
split(col("item"), ",").cast(ArrayType(IntegerType())).alias("item")
)
df.printSchema()
df.show(2)
fpGrowth = FPGrowth(itemsCol="item", minSupport=0.01, minConfidence=0.01)
model = fpGrowth.fit(df)
Ниже я получаю ошибку:
Py4JJavaError Traceback (most recent call last)
<ipython-input-10-74ec76b0ec20> in <module>
14 df.printSchema()
15
---> 16 df.show(2)
17
18 fpGrowth = FPGrowth(itemsCol="item", minSupport=0.01, minConfidence=0.01)
/usr/lib/spark/python/pyspark/sql/dataframe.py in show(self, n, truncate, vertical)
378 """
379 if isinstance(truncate, bool) and truncate:
--> 380 print(self._jdf.showString(n, 20, vertical))
381 else:
382 print(self._jdf.showString(n, int(truncate), vertical))
/opt/conda/anaconda/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
/usr/lib/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/opt/conda/anaconda/lib/python3.6/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o377.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 3.0 failed 4 times, most recent failure: Lost task 0.3 in stage 3.0 (TID 18, cluster-we8z-x-0.c.project_name.dataset_name, executor 1): java.lang.NoClassDefFoundError: Could not initialize class com.google.cloud.spark.bigquery.SparkBigQueryConnectorUserAgentProvider
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$.headerProvider(DirectBigQueryRelation.scala:356)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$.createReadClient(DirectBigQueryRelation.scala:333)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$$anonfun$$lessinit$greater$default$3$1.apply(DirectBigQueryRelation.scala:42)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$$anonfun$$lessinit$greater$default$3$1.apply(DirectBigQueryRelation.scala:42)
at com.google.cloud.spark.bigquery.direct.BigQueryRDD.compute(BigQueryRDD.scala:46)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1892)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1880)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1879)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2113)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2062)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2051)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3389)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3370)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3369)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2550)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2764)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:254)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:291)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NoClassDefFoundError: Could not initialize class com.google.cloud.spark.bigquery.SparkBigQueryConnectorUserAgentProvider
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$.headerProvider(DirectBigQueryRelation.scala:356)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$.createReadClient(DirectBigQueryRelation.scala:333)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$$anonfun$$lessinit$greater$default$3$1.apply(DirectBigQueryRelation.scala:42)
at com.google.cloud.spark.bigquery.direct.DirectBigQueryRelation$$anonfun$$lessinit$greater$default$3$1.apply(DirectBigQueryRelation.scala:42)
at com.google.cloud.spark.bigquery.direct.BigQueryRDD.compute(BigQueryRDD.scala:46)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
