-
Notifications
You must be signed in to change notification settings - Fork 48
Closed
Description
Appears to have stopped working after 67108de
model = pipeline.fit(df_mask.filter(rf_tile_sum('label') > 0).cache())---------------------------------------------------------------------------Py4JJavaError Traceback (most recent call last)<ipython-input-1-04772a34de7f> in <module>()
----> 1 model = pipeline.fit(df_mask.filter(rf_tile_sum('label') > 0).cache())
/anaconda3/lib/python3.6/site-packages/pyspark/ml/base.py in fit(self, dataset, params)
130 return self.copy(params)._fit(dataset)
131 else:
--> 132 return self._fit(dataset)
133 else:
134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/anaconda3/lib/python3.6/site-packages/pyspark/ml/pipeline.py in _fit(self, dataset)
107 dataset = stage.transform(dataset)
108 else: # must be an Estimator
--> 109 model = stage.fit(dataset)
110 transformers.append(model)
111 if i < indexOfLastEstimator:
/anaconda3/lib/python3.6/site-packages/pyspark/ml/base.py in fit(self, dataset, params)
130 return self.copy(params)._fit(dataset)
131 else:
--> 132 return self._fit(dataset)
133 else:
134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/anaconda3/lib/python3.6/site-packages/pyspark/ml/wrapper.py in _fit(self, dataset)
286
287 def _fit(self, dataset):
--> 288 java_model = self._fit_java(dataset)
289 model = self._create_model(java_model)
290 return self._copyValues(model)
/anaconda3/lib/python3.6/site-packages/pyspark/ml/wrapper.py in _fit_java(self, dataset)
283 """
284 self._transfer_params_to_java()
--> 285 return self._java_obj.fit(dataset._jdf)
286
287 def _fit(self, dataset):
/anaconda3/lib/python3.6/site-packages/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:
/anaconda3/lib/python3.6/site-packages/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()
/anaconda3/lib/python3.6/site-packages/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 o638.fit.
: java.lang.NullPointerException: Value at index 0 is null
at org.apache.spark.sql.Row$class.getAnyValAs(Row.scala:472)
at org.apache.spark.sql.Row$class.getDouble(Row.scala:248)
at org.apache.spark.sql.catalyst.expressions.GenericRow.getDouble(rows.scala:166)
at org.apache.spark.ml.classification.Classifier.getNumClasses(Classifier.scala:115)
at org.apache.spark.ml.classification.DecisionTreeClassifier.train(DecisionTreeClassifier.scala:102)
at org.apache.spark.ml.classification.DecisionTreeClassifier.train(DecisionTreeClassifier.scala:45)
at org.apache.spark.ml.Predictor.fit(Predictor.scala:118)
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)
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels