Hi get the following error after trying to perform
gridsearch and crossvalidation on randomforst estimator for classificaiton
rf = RandomForestClassifier(labelCol="Labeld",featuresCol="features")
evaluator = BinaryClassificationEvaluator(metricName="F1 Score")
rf_cv = CrossValidator(estimator=rf,
estimatorParamMaps=gridS,evaluator=evaluator,numFolds=5)
(trainingData, testData) = transformed13.randomSplit([0.7, 0.3])
rfmodel = rf_cv.fit(trainingData)
---------------------------------------------------------------------------Py4JJavaError
Traceback (most recent call
last)<ipython-input-76-bdd59134bbe0> in <module>()----> 1 rfmodel =
rf_cv.fit(trainingData)
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/pipeline.py in
fit(self, dataset, params) 67 return
self.copy(params)._fit(dataset) 68 else:---> 69
return self._fit(dataset) 70 else: 71
raise ValueError("Params must be either a param map or a
list/tuple of param maps, "
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/tuning.py in
_fit(self, dataset) 237 train = df.filter(~condition)
238 for j in range(numModels):--> 239
model = est.fit(train, epm[j]) 240 # TODO:
duplicate evaluator to take extra params from input 241
metric = eva.evaluate(model.transform(validation, epm[j]))
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/pipeline.py in
fit(self, dataset, params) 65 elif isinstance(params,
dict): 66 if params:---> 67 return
self.copy(params)._fit(dataset) 68 else: 69
return self._fit(dataset)
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/wrapper.py in
_fit(self, dataset) 131 132 def _fit(self, dataset):--> 133
java_model = self._fit_java(dataset) 134 return
self._create_model(java_model) 135
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/wrapper.py in
_fit_java(self, dataset) 127 :return: fitted Java model
128 """--> 129 self._transfer_params_to_java() 130
return self._java_obj.fit(dataset._jdf) 131
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/wrapper.py in
_transfer_params_to_java(self) 80 for param in
self.params: 81 if param in paramMap:---> 82
pair = self._make_java_param_pair(param, paramMap[param]) 83
self._java_obj.set(pair) 84
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/ml/wrapper.py in
_make_java_param_pair(self, param, value) 71 java_param =
self._java_obj.getParam(param.name) 72 java_value =
_py2java(sc, value)---> 73 return java_param.w(java_value)
74 75 def _transfer_params_to_java(self):
/opt/cloudera/parcels/CDH/lib/spark/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:
/opt/cloudera/parcels/CDH/lib/spark/python/pyspark/sql/utils.py 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()
/opt/cloudera/parcels/CDH/lib/spark/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 o91602.w.
: java.lang.ClassCastException: java.lang.Integer cannot be cast to
java.lang.Double
at scala.runtime.BoxesRunTime.unboxToDouble(BoxesRunTime.java:119)
at org.apache.spark.ml.param.DoubleParam.w(params.scala:225)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
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)
