我正在学习spark流媒体，当我执行下面的代码时，我得到了一个错误，这是为了执行tweet分析。
### May cause deprecation warnings, safe to ignore, they aren't errors
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.sql import SQLContext
from pyspark.sql.functions import desc
ssc = StreamingContext(sc, 10 )
sqlContext = SQLContext(sc)
socket_stream = ssc.socketTextStream("127.0.0.1", 5557)
lines = socket_stream.window( 20 )
from collections import namedtuple
fields = ("tag", "count" )
Tweet = namedtuple( 'Tweet', fields )
# Use Parenthesis for multiple lines or use \.
( lines.flatMap( lambda text: text.split( " " ) ) #Splits to a list
.filter( lambda word: word.lower().startswith("#") ) # Checks for hashtag calls
.map( lambda word: ( word.lower(), 1 ) ) # Lower cases the word
.reduceByKey( lambda a, b: a + b ) # Reduces
.map( lambda rec: Tweet( rec[0], rec[1] ) ) # Stores in a Tweet Object
.foreachRDD( lambda rdd: rdd.toDF().sort( desc("count") ) # Sorts Them in a DF
.limit(10).registerTempTable("tweets") ) ) # Registers to a table.
import time
from IPython import display
import matplotlib.pyplot as plt
import seaborn as sns
import pandas
# Only works for Jupyter Notebooks!
%matplotlib inline
ssc.start()
count = 0
while count < 10:
time.sleep( 3 )
top_10_tweets = sqlContext.sql( 'Select tag, count from tweets' )
top_10_df = top_10_tweets.toPandas()
display.clear_output(wait=True)
plt.figure( figsize = ( 8, 5 ) )
sns.barplot( x="count", y="tag", data=top_10_df)
plt.show()
count = count + 1
我使用的是jupyter -notebook. 这是它给出的错误。
Py4JJavaError Traceback (most recent call last)
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
62 try:
---> 63 return f(*a, **kw)`enter code here`
64 except py4j.protocol.Py4JJavaError as e:
/usr/local/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
Py4JJavaError: An error occurred while calling o25.sql.
: org.apache.spark.sql.AnalysisException: Table or view not found: tweets; line 1 pos 23
at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:47)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveRelations$$lookupTableFromCatalog(Analyzer.scala:733)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:685)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:715)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:708)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:89)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:326)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:324)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:708)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:654)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.sql.catalyst.analysis.NoSuchTableException: Table or view 'tweets' not found in database 'default';
at org.apache.spark.sql.hive.client.HiveClient$$anonfun$getTable$1.apply(HiveClient.scala:81)
at org.apache.spark.sql.hive.client.HiveClient$$anonfun$getTable$1.apply(HiveClient.scala:81)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.hive.client.HiveClient$class.getTable(HiveClient.scala:81)
at org.apache.spark.sql.hive.client.HiveClientImpl.getTable(HiveClientImpl.scala:83)
at org.apache.spark.sql.hive.HiveExternalCatalog.getRawTable(HiveExternalCatalog.scala:118)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:700)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$getTable$1.apply(HiveExternalCatalog.scala:700)
at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
at org.apache.spark.sql.hive.HiveExternalCatalog.getTable(HiveExternalCatalog.scala:699)
at org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.getTable(ExternalCatalogWithListener.scala:138)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.lookupRelation(SessionCatalog.scala:706)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveRelations$$lookupTableFromCatalog(Analyzer.scala:730)
... 53 more
During handling of the above exception, another exception occurred:
AnalysisException Traceback (most recent call last)
<ipython-input-10-68a0b51a5ce9> in <module>()
3
4 time.sleep( 3 )
----> 5 top_10_tweets = sqlContext.sql( 'Select tag, count from tweets' )
6 top_10_df = top_10_tweets.toPandas()
7 display.clear_output(wait=True)
/usr/local/spark/python/pyspark/sql/context.py in sql(self, sqlQuery)
356 [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
357 """
--> 358 return self.sparkSession.sql(sqlQuery)
359
360 @since(1.0)
/usr/local/spark/python/pyspark/sql/session.py in sql(self, sqlQuery)
765 [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
766 """
--> 767 return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
768
769 @since(2.0)
/usr/local/spark/python/lib/py4j-0.10.7-src.zip/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/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
67 e.java_exception.getStackTrace()))
68 if s.startswith('org.apache.spark.sql.AnalysisException: '):
---> 69 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
70 if s.startswith('org.apache.spark.sql.catalyst.analysis'):
71 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
AnalysisException: 'Table or view not found: tweets; line 1 pos 23'