hi,
I am trying to connect to a mysql database on my machine.
But, I am getting some error
dataframe_mysql = sqlContext.read.format("jdbc").options(
url="jdbc:mysql://localhost:3306/my_db",
driver = "com.mysql.jdbc.Driver",
dbtable = "data1",
user="123").load()
below is the full trace -
---Py4JJavaError
Traceback (most recent call
last) in () 4 dbtable =
"data1", 5 user="root",> 6 password="123").load() 7
/Users/tejaV/Documents/My_Study_folder/spark-1.6.1/python/pyspark/sql/readwriter.pyc
in load(self, path, format, schema, **options)137
return self._df(self._jreader.load(path))138 else:--> 139
return self._df(self._jreader.load())140 141
@since(1.4)
/Users/tejaV/Documents/My_Study_folder/spark-1.6.1/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py
in __call__(self, *args)811 answer =
self.gateway_client.send_command(command)812 return_value
= get_return_value(--> 813 answer, self.gateway_client,
self.target_id, self.name)814 815 for temp_arg in
temp_args:
/Users/tejaV/Documents/My_Study_folder/spark-1.6.1/python/pyspark/sql/utils.pyc
in deco(*a, **kw) 43 def deco(*a, **kw): 44
try:---> 45 return f(*a, **kw) 46 except
py4j.protocol.Py4JJavaError as e: 47 s =
e.java_exception.toString()
/Users/tejaV/Documents/My_Study_folder/spark-1.6.1/python/lib/py4j-0.9-src.zip/py4j/protocol.py
in get_return_value(answer, gateway_client, target_id, name)306
raise Py4JJavaError(307 "An error
occurred while calling {0}{1}{2}.\n".--> 308
format(target_id, ".", name), value)309 else:310
raise Py4JError(
Py4JJavaError: An error occurred while calling o98.load.
: java.lang.ClassNotFoundException: com.mysql.jdbc.Driver
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
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:38)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:45)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:45)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.createConnectionFactory(JdbcUtils.scala:45)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:120)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.(JDBCRelation.scala:91)
at
org.apache.spark.sql.execution.datasources.jdbc.DefaultSource.createRelation(DefaultSource.scala:57)
at
org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
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:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)