In [2]:

    

from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession, SQLContext
from graphframes import *
spark = SparkSession.builder.appName("Python Spark SQL basic example").config("spark.some.config.option", "some-value").getOrCreate()


    

In [3]:

    

# Create DataFrames manually
v = spark.createDataFrame([
   ("A", "ARON"  ,350 ),
   ("B", "BILL"  ,360 ),
   ("C", "CLAIR" ,195 ),
   ("D", "DANIEL",90),
   ("E", "ERIC"  ,90),
   ("F", "FRANK" ,215 ),
   ("G", "GRAHAM",30 ),
   ("H", "HENRY" ,25 ),
   ("I", "INNA"  ,25 ),
   ("J", "JEN"   ,20 )
], ["id", "name", "total_seconds"])

e = spark.createDataFrame([
   ("A", "B", 60),
   ("B", "A", 50),
   ("A", "C", 50),
   ("C", "A", 100),
   ("A", "D", 90),
   ("C", "I", 25),
   ("C", "J", 20),
   ("B", "F", 50),
   ("F", "B", 110),
   ("F", "G", 30),
   ("F", "H", 25),
   ("B", "E", 90)
],["src","dst","relationship"])
# Now lets construct the graph
g = GraphFrame(v,e)


    

    




---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-3-ba13e9877bca> in <module>
     28 ],["src","dst","relationship"])
     29 # Now lets construct the graph
---> 30 g = GraphFrame(v,e)

c:\users\cmoha\appdata\local\programs\python\python37-32\lib\site-packages\graphframes\graphframe.py in __init__(self, v, e)
     63         self._sqlContext = v.sql_ctx
     64         self._sc = self._sqlContext._sc
---> 65         self._jvm_gf_api = _java_api(self._sc)
     66 
     67         self.ID = self._jvm_gf_api.ID()

c:\users\cmoha\appdata\local\programs\python\python37-32\lib\site-packages\graphframes\graphframe.py in _java_api(jsc)
     36 def _java_api(jsc):
     37     javaClassName = "org.graphframes.GraphFramePythonAPI"
---> 38     return jsc._jvm.Thread.currentThread().getContextClassLoader().loadClass(javaClassName) \
     39             .newInstance()
     40 

C:\Spark\spark-2.3.1-bin-hadoop2.7\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:

C:\Spark\spark-2.3.1-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

C:\Spark\spark-2.3.1-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o59.loadClass.
: java.lang.ClassNotFoundException: org.graphframes.GraphFramePythonAPI
	at java.net.URLClassLoader.findClass(Unknown Source)
	at java.lang.ClassLoader.loadClass(Unknown Source)
	at java.lang.ClassLoader.loadClass(Unknown Source)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
	at java.lang.reflect.Method.invoke(Unknown Source)
	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(Unknown Source)

In [ ]: