Обучение pyspark xgboost4j не удалось - PullRequest
Новая
       10

Обучение pyspark xgboost4j не удалось

0 голосов
/ 27 мая 2020

Я использую python 3.7, java 8, pyspark 2.4.5, xgboost jars 0.72 и файл sparkxgb.zip. Я создал модель XGBoostEstimator без проблем, но когда я попытался уместить свои данные, я получил эту ошибку: 

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-10-2a9b2bf68c2c> in <module>
----> 1 model = pipeline.fit(data_train)

C:\spark\spark-2.4.5-bin-hadoop2.7\python\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, "

C:\spark\spark-2.4.5-bin-hadoop2.7\python\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:

C:\spark\spark-2.4.5-bin-hadoop2.7\python\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, "

C:\spark\spark-2.4.5-bin-hadoop2.7\python\pyspark\ml\wrapper.py in _fit(self, dataset)
    293 
    294     def _fit(self, dataset):
--> 295         java_model = self._fit_java(dataset)
    296         model = self._create_model(java_model)
    297         return self._copyValues(model)

C:\spark\spark-2.4.5-bin-hadoop2.7\python\pyspark\ml\wrapper.py in _fit_java(self, dataset)
    290         """
    291         self._transfer_params_to_java()
--> 292         return self._java_obj.fit(dataset._jdf)
    293 
    294     def _fit(self, dataset):

C:\spark\spark-2.4.5-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-2.4.5-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-2.4.5-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 o371.fit.
: ml.dmlc.xgboost4j.java.XGBoostError: XGBoostModel training failed
    at ml.dmlc.xgboost4j.scala.spark.XGBoost$.ml$dmlc$xgboost4j$scala$spark$XGBoost$$postTrackerReturnProcessing(XGBoost.scala:406)
    at ml.dmlc.xgboost4j.scala.spark.XGBoost$$anonfun$trainDistributed$4.apply(XGBoost.scala:356)
    at ml.dmlc.xgboost4j.scala.spark.XGBoost$$anonfun$trainDistributed$4.apply(XGBoost.scala:337)
    at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
    at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
    at scala.collection.immutable.List.foreach(List.scala:392)
    at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
    at scala.collection.immutable.List.map(List.scala:296)
    at ml.dmlc.xgboost4j.scala.spark.XGBoost$.trainDistributed(XGBoost.scala:336)
    at ml.dmlc.xgboost4j.scala.spark.XGBoostEstimator.train(XGBoostEstimator.scala:139)
    at ml.dmlc.xgboost4j.scala.spark.XGBoostEstimator.train(XGBoostEstimator.scala:36)
    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)

Я попытался изменить версию jars, но затем мне не удалось создать модель XGBoostEstimator. Есть какие идеи? Я видел, что у многих людей была такая же проблема, но кто-то еще ее решил.

...