У меня есть небольшая PySpark программа, которая использует xgboost4j и xgboost4j-spark для обучения данного набора данных в форме искрового фрейма данных.
Обучение завершено, но, похоже, я не могу сохранить модель.
Текущие версии библиотек:
- Pyspark 2.4.0
- xgboost4j 0.90
- xgboost4j-spark 0.90
Spark представить аргументы:
os.environ['PYSPARK_SUBMIT_ARGS'] = "--py-files dist/DNA-0.0.2-py3.6.egg " \
"--jars dna/resources/xgboost4j-spark-0.90.jar," \
"dna/resources/xgboost4j-0.90.jar pyspark-shell"
Процесс обучения выглядит следующим образом:
def spark_xgboost_train(spark=None, models_path='', train_df=None):
spark.sparkContext.addPyFile("dna/resources/xgboost4j-spark-0.90.jar")
spark.sparkContext.addPyFile("dna/resources/xgboost4j-0.90.jar")
spark.sparkContext.addPyFile('dna/resources/pyspark-xgboost_0.90_261ab52e07bec461c711d209b70428ab481db470.zip')
import sparkxgb as sxgb
from sparkxgb import XGBoostClassifier, XGBoostClassificationModel
# pre-process
train_df = train_df.drop('url')
train_df = train_df.na.fill(0)
x = train_df.columns
x.remove('label')
vectorAssembler = VectorAssembler() \
.setInputCols(x) \
.setOutputCol("features")
xgboost = XGBoostClassifier(
featuresCol="features",
labelCol="label",
predictionCol="prediction",
)
pipeline = Pipeline().setStages([vectorAssembler])
df = pipeline.fit(train_df).transform(train_df)
model = xgboost.fit(df)
# save
model.write().overwrite().save(models_path + "model.dat")
Я получаю ошибку:
Traceback (most recent call last):
File "/storage/env/DNAtestenv/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/storage/env/DNAtestenv/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/elad/DNA/dna/__main__.py", line 360, in <module>
main()
File "/home/elad/DNA/dna/__main__.py", line 325, in main
run_pipelines(config)
File "/home/elad/DNA/dna/__main__.py", line 311, in run_pipelines
objective=config['objective'], nthread=config['nthread'])
File "/home/elad/DNA/dna/__main__.py", line 234, in train_model
max_depth=max_depth, eta=eta, silent=silent, objective=objective, nthread=1)
File "/home/elad/DNA/dna/model/xgboost_train.py", line 82, in spark_xgboost_train
model.write().save(models_path + '/model.dat')
File "/storage/env/DNAtestenv/lib/python3.7/site-packages/pyspark/ml/util.py", line 183, in save
self._jwrite.save(path)
File "/storage/env/DNAtestenv/lib/python3.7/site-packages/py4j/java_gateway.py", line 1257, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/storage/env/DNAtestenv/lib/python3.7/site-packages/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/storage/env/DNAtestenv/lib/python3.7/site-packages/py4j/protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o484.save.
: java.lang.NoSuchMethodError: org.json4s.jackson.JsonMethods$.parse(Lorg/json4s/JsonInput;Z)Lorg/json4s/JsonAST$JValue;
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$$anonfun$1$$anonfun$3.apply(DefaultXGBoostParamsWriter.scala:73)
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$$anonfun$1$$anonfun$3.apply(DefaultXGBoostParamsWriter.scala:71)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$$anonfun$1.apply(DefaultXGBoostParamsWriter.scala:71)
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$$anonfun$1.apply(DefaultXGBoostParamsWriter.scala:69)
at scala.Option.getOrElse(Option.scala:121)
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$.getMetadataToSave(DefaultXGBoostParamsWriter.scala:69)
at ml.dmlc.xgboost4j.scala.spark.params.DefaultXGBoostParamsWriter$.saveMetadata(DefaultXGBoostParamsWriter.scala:51)
at ml.dmlc.xgboost4j.scala.spark.XGBoostModel$XGBoostModelModelWriter.saveImpl(XGBoostModel.scala:371)
at org.apache.spark.ml.util.MLWriter.save(ReadWrite.scala:180)
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:745)
Что бы я хотел сделать, это сохранить и загрузить модель, например:
# save
model.write().save(models_path + '/model.dat')
# load
model2 = sxgb.xgboost.XGBoostClassificationModel().load(models_path + '/model.dat')
Я также пытался использовать другие версии xgboost4j (0.80, 0.72). Не могу найти причину для этого, я даже пытался прочитать исходный код оболочки и исходный код jars, я ничего не смог найти.
заранее спасибо.