我想使用Pyspark将DataFrames写入HBase。我正在尝试运行此answer中的代码。
from pyspark import SparkContext
from pyspark.sql import SQLContext
sc = SparkContext()
sqlc = SQLContext(sc)
data_source_format = 'org.apache.spark.sql.execution.datasources.hbase'
df = sc.parallelize([('a', '1.0'), ('b', '2.0')]).toDF(schema=['col0', 'col1'])
catalog = ''.join("""{
"table":{"namespace":"default", "name":"testtable"},
"rowkey":"key",
"columns":{
"col0":{"cf":"rowkey", "col":"key", "type":"string"},
"col1":{"cf":"cf", "col":"col1", "type":"string"}
}
}""".split())
df.write.options(catalog=catalog).format(data_source_format).save()
按以下格式执行命令：
sudo spark-submit --packages com.hortonworks:shc:1.0.0-1.6-s_2.10 --repositories http://repo.hortonworks.com/content/groups/public/ --files /home/chenxx/hbase/conf/hbase-site.xml sogou4.py
Spark版本：2.3.0 Hadoop版本：2.7.6 HBase版本：1.5 Scala版本：2.11.6 Python版本：2.7
错误：
Traceback (most recent call last):
File "/home/chenxx/PycharmProjects/SoGou/sogou4.py", line 48, in <module>
df.write.options(catalog = catalog1).format(data_source_format).save()
File "/usr/local/lib/python2.7/dist-packages/pyspark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 701, in save
File "/usr/local/lib/python2.7/dist-packages/pyspark/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py", line 1160, in __call__
File "/usr/local/lib/python2.7/dist-packages/pyspark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
File "/usr/local/lib/python2.7/dist-packages/pyspark/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py", line 320, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o61.save.
: java.lang.NoClassDefFoundError: org/apache/spark/Logging
at java.lang.ClassLoader.defineClass1(Native Method)
at java.lang.ClassLoader.defineClass(ClassLoader.java:763)
at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
at java.net.URLClassLoader.defineClass(URLClassLoader.java:467)
at java.net.URLClassLoader.access$100(URLClassLoader.java:73)
at java.net.URLClassLoader$1.run(URLClassLoader.java:368)
at java.net.URLClassLoader$1.run(URLClassLoader.java:362)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:361)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.getDeclaredConstructors0(Native Method)
at java.lang.Class.privateGetDeclaredConstructors(Class.java:2671)
at java.lang.Class.getConstructor0(Class.java:3075)
at java.lang.Class.newInstance(Class.java:412)
at org.apache.spark.sql.execution.datasources.DataSource.planForWriting(DataSource.scala:544)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:278)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:267)
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:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.Logging
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 29 more
如果有任何建议，我将不胜感激！