mllib KernelDensity error - python-3.x

Question

I'm trying to use pyspark.mllib.stat.KernelDensity this way:
data = sc.parallelize([0, 1, 2, 2, 1, 1, 1, 1, 1, 2, 0, 0])
kd = KernelDensity()
kd.setSample(data)
kd.setBandwidth(3)
densities = kd.estimate([-1.0, 2.0, 5.0])
but eventually get this error:
--------------------------------------------------------------------------- Py4JError Traceback (most recent call
last) in ()
8
9 # Find density estimates for the given values
---> 10 densities = kd.estimate([-1.0, 2.0, 5.0])
/home/user10215193/anaconda3/lib/python3.6/site-packages/pyspark/mllib/stat/KernelDensity.py
in estimate(self, points)
56 points = list(points)
57 densities = callMLlibFunc(
---> 58 "estimateKernelDensity", self._sample, self._bandwidth, points)
59 return np.asarray(densities)
/home/user10215193/anaconda3/lib/python3.6/site-packages/pyspark/mllib/common.py
in callMLlibFunc(name, *args)
129 api = getattr(sc._jvm.PythonMLLibAPI(), name)
130 print(api)
--> 131 return callJavaFunc(sc, api, *args)
132
133
/home/user10215193/anaconda3/lib/python3.6/site-packages/pyspark/mllib/common.py
in callJavaFunc(sc, func, *args)
121 """ Call Java Function """
122 args = [_py2java(sc, a) for a in args]
--> 123 return _java2py(sc, func(*args))
124
125
/home/user10215193/anaconda3/lib/python3.6/site-packages/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:
/home/user10215193/anaconda3/lib/python3.6/site-packages/py4j/protocol.py
in get_return_value(answer, gateway_client, target_id, name)
321 raise Py4JError(
322 "An error occurred while calling {0}{1}{2}. Trace:\n{3}\n".
--> 323 format(target_id, ".", name, value))
324 else:
325 raise Py4JError(
Py4JError: An error occurred while calling o19.estimateKernelDensity.
Trace: py4j.Py4JException: Method estimateKernelDensity([class
org.apache.spark.api.java.JavaRDD, class java.lang.Integer, class
java.util.ArrayList]) does not exist at
py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:318)
at
py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:326)
at py4j.Gateway.invoke(Gateway.java:272) 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)
I couldn't find anything similar here so if somebody can help me with this I would much appreciate it.

Answer 1

You have to be careful about the types:
bandwidth has to be float
sample has to be RDD[float]
So replace your code with:
kd.setSample(data.map(float))
kd.setBandwidth(3.0)
densities = kd.estimate([-1.0, 2.0, 5.0])
and you'll be fine.