, когда я запускаю в py spark streaming на ноутбуке jupyter, получая следующую ошибку, любая помощь очень ценится, большое спасибо ....
# 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(5).createOrReplaceTempView("tweets") ) ) # Registers to a table.
import time
from IPython import display
import matplotlib.pyplot as plt
import seaborn as sns
# Only works for Jupyter Notebooks!
get_ipython().magic('matplotlib inline')
count = 0
while count < 10:
time.sleep( 3 )
print(lines)
top_10_tweets = spark.sql( 'Select tag, count from tweets' )
top_10_df = top_10_tweets.toPandas()
display.clear_output(wait=True)
plt.figure( figsize = ( 10, 8 ) )
sns.barplot( x="count", y="tag", data=top_10_df)
plt.show()
count = count + 1
Когда я запускаю этот код:
<pyspark.streaming.dstream.DStream object at 0x7fc74c57c550>
Py4JJavaError Traceback (most recent call last)
~/spark-2.1.1-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
spark-2.1.1-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
Py4JJavaError: An error occurred while calling o60.sql.
: org.apache.spark.sql.AnalysisException: Table or view not found: tweets; line 1 pos 23
at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveRelations$$lookupTableFromCatalog(Analyzer.scala:460)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:479)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:464)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:60)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:58)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:58)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:307)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:305)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:58)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:464)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:454)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
at scala.collection.immutable.List.foreach(List.scala:381)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:69)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:67)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:50)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:63)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
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:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
During handling of the above exception, another exception occurred:
AnalysisException Traceback (most recent call last)
<ipython-input-14-126bd83d3cd6> in <module>()
3 time.sleep( 3 )
4 print(lines)
----> 5 top_10_tweets = spark.sql( 'Select tag, count from tweets' )
6 top_10_df = top_10_tweets.toPandas()
7 display.clear_output(wait=True)
~/spark-2.1.1-bin-hadoop2.7/python/pyspark/sql/session.py in sql(self, sqlQuery)
543 [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
544 """
--> 545 return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
546
547 @since(2.0)
spark-2.1.1-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
~/spark-2.1.1-bin-hadoop2.7/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 повысить AnalysisException (s.split (':', 1) [1], stackTrace)
AnalysisException: 'Таблица или представление не найдены: твиты;строка 1 поз 23 '
показывает, что "не получаются временные таблицы Tweets" [AnalysisException]