Я запускаю следующую программу в оболочке pyspark
из pyspark. sql import SparkSession
spark = SparkSession \ .builder \ .appName("Python Spark SQL basic example") \ .config("spark.jars", "/home/airflow/postgresql-42.2.10.jar") \ .getOrCreate()
df = spark.read \ .format("jdbc") \ .option("url", "jdbc:postgresql://localhost:5432/testdb") \ .option("dbtable", "testdb.Customer") \ .option("user", "abc") \ .option("driver", "org.postgresql.Driver") \ .option("password", "xyz") \ .load()
выдает следующую ошибку
File "<stdin>", line 7, in <module>
File "/opt/spark/python/pyspark/sql/readwriter.py", line 172, in load
return self._df(self._jreader.load())
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/opt/spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o120.load.
: java.lang.ClassNotFoundException: org.postgresql/postgresql
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:45)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions$$anonfun$6.apply(JDBCOptions.scala:79)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions$$anonfun$6.apply(JDBCOptions.scala:79)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.<init>(JDBCOptions.scala:79)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.<init>(JDBCOptions.scala:35)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:34)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:341)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:164)
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)
Я использую свечи 2.3 и python 3.6, Как решить эту ошибку?