Я использую модель ALS (метод факторизации матрицы чередующихся наименьших квадратов) для механизма рекомендаций и получаю эту ошибку, которую я не могу устранить даже после нескольких часов работы. Типы данных и формат аргументов модели являются правильными в соответствии с определением функции модели
Пожалуйста, помогите
###Modeling codes
train_df = train_df.dropDuplicates()
als_model = ALS( implicitPrefs=True,coldStartStrategy="drop",userCol="userID_index", itemCol="itemID_index", ratingCol="rating")
als_model.setSeed(345)
grid = (ParamGridBuilder()
.addGrid(als_model.rank,[8,10])
.addGrid(als_model.regParam,[0.1,0.5])
.addGrid(als_model.alpha, [40])
.build()
)
als_eval = RegressionEvaluator(metricName='rmse', labelCol='rating')
cv = CrossValidator(estimator=als_model, estimatorParamMaps=grid, evaluator=als_eval,numFolds=1)
train_df.persist(StorageLevel.MEMORY_AND_DISK)
cv_model = cv.fit(train_df)
Ошибка здесь
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/utils.py in deco(*a, **kw)
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
/opt/cloudera/parcels/SPARK2/lib/spark2/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
Py4JJavaError: An error occurred while calling o4662.fit.
: java.lang.IllegalArgumentException: requirement failed: No ratings available from MapPartitionsRDD[3167] at map at ALS.scala:613
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.ml.recommendation.ALS$.train(ALS.scala:843)
at org.apache.spark.ml.recommendation.ALS.fit(ALS.scala:622)
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:280)
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)
During handling of the above exception, another exception occurred:
IllegalArgumentException Traceback (most recent call last)
<ipython-input-79-202a4259227e> in <module>
16 cv = CrossValidator(estimator=als_model, estimatorParamMaps=grid, evaluator=als_eval,numFolds=1)
17 train_df.persist(StorageLevel.MEMORY_AND_DISK)
---> 18 cv_model = cv.fit(train_df)
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/base.py in fit(self, dataset, params)
62 return self.copy(params)._fit(dataset)
63 else:
---> 64 return self._fit(dataset)
65 else:
66 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/tuning.py in _fit(self, dataset)
230 validation = df.filter(condition)
231 train = df.filter(~condition)
--> 232 models = est.fit(train, epm)
233 for j in range(numModels):
234 model = models[j]
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/base.py in fit(self, dataset, params)
57 params = dict()
58 if isinstance(params, (list, tuple)):
---> 59 return [self.fit(dataset, paramMap) for paramMap in params]
60 elif isinstance(params, dict):
61 if params:
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/base.py in <listcomp>(.0)
57 params = dict()
58 if isinstance(params, (list, tuple)):
---> 59 return [self.fit(dataset, paramMap) for paramMap in params]
60 elif isinstance(params, dict):
61 if params:
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/base.py in fit(self, dataset, params)
60 elif isinstance(params, dict):
61 if params:
---> 62 return self.copy(params)._fit(dataset)
63 else:
64 return self._fit(dataset)
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/wrapper.py in _fit(self, dataset)
263
264 def _fit(self, dataset):
--> 265 java_model = self._fit_java(dataset)
266 return self._create_model(java_model)
267
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/ml/wrapper.py in _fit_java(self, dataset)
260 """
261 self._transfer_params_to_java()
--> 262 return self._java_obj.fit(dataset._jdf)
263
264 def _fit(self, dataset):
/opt/cloudera/parcels/SPARK2/lib/spark2/python/lib/py4j-0.10.4-src.zip/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:
/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/utils.py in deco(*a, **kw)
77 raise QueryExecutionException(s.split(': ', 1)[1], stackTrace)
78 if s.startswith('java.lang.IllegalArgumentException: '):
---> 79 raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
80 raise
81 return deco
IllegalArgumentException: 'requirement failed: No ratings available from MapPartitionsRDD[3167] at map at ALS.scala:613'
Однако я не смог найти любую проблему с моим набором данных 'train_df' или синтаксисом кода. Любая помощь будет принята с благодарностью
