Thanks Irving, The problem was that I was using spark in cluster mode and had to resort to HDFS to properly save/load the model.
On Mon, Jul 31, 2017 at 9:09 AM Irving Duran <irving.du...@gmail.com> wrote: > I think the problem is because you are calling "model2 = > ALSModel.load("/models/als")" instead of "model2 = > *model*.load("/models/als")". > See my working sample below. > > >>> model.save('/models/als.test') > SLF4J: Failed to load class "org.slf4j.impl.StaticLoggerBinder". > SLF4J: Defaulting to no-operation (NOP) logger implementation > SLF4J: See http://www.slf4j.org/codes.html#StaticLoggerBinder for further > details. > >>> model2 = model.load('/models/als.test') > >>> model > ALS_4324a1082d889dd1f0e4 > >>> model2 > ALS_4324a1082d889dd1f0e4 > > > Thank You, > > Irving Duran > > On Sat, Jul 29, 2017 at 2:57 PM, Cristian Garcia <cgarcia....@gmail.com> > wrote: > >> This code is not working: >> >> ================ >> from pyspark.ml.evaluation import RegressionEvaluator >> from pyspark.ml.recommendation import ALS, ALSModel >> from pyspark.sql import Row >> >> als = ALS(maxIter=10, regParam=0.01, userCol="user_id", >> itemCol="movie_id", ratingCol="rating") >> model = als.fit(training) >> >> model.save("/models/als") >> >> model2 = ALSModel.load("/models/als") # <-- error here >> ================= >> >> >> >> Gives rise to this error: >> ================= >> >> ---------------------------------------------------------------------------Py4JJavaError >> Traceback (most recent call >> last)<ipython-input-24-c0454f47bb1d> in <module>()----> 1 m2 = >> ALSModel.load("/models/als") >> /usr/local/spark/python/pyspark/ml/util.py in load(cls, path) 251 def >> load(cls, path): 252 """Reads an ML instance from the input path, >> a shortcut of `read().load(path)`."""--> 253 return >> cls.read().load(path) 254 255 >> /usr/local/spark/python/pyspark/ml/util.py in load(self, path) 192 >> if not isinstance(path, basestring): 193 raise >> TypeError("path should be a basestring, got type %s" % type(path))--> 194 >> java_obj = self._jread.load(path) 195 if not >> hasattr(self._clazz, "_from_java"): 196 raise >> NotImplementedError("This Java ML type cannot be loaded into Python >> currently: %r" >> /usr/local/spark/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: >> /usr/local/spark/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() >> /usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in >> get_return_value(answer, gateway_client, target_id, name) 317 >> raise Py4JJavaError( 318 "An error occurred while >> calling {0}{1}{2}.\n".--> 319 format(target_id, ".", >> name), value) 320 else: 321 raise >> Py4JError( >> Py4JJavaError: An error occurred while calling o337.load. >> : java.lang.UnsupportedOperationException: empty collection >> at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1370) >> at >> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) >> at >> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) >> at org.apache.spark.rdd.RDD.withScope(RDD.scala:362) >> at org.apache.spark.rdd.RDD.first(RDD.scala:1367) >> at >> org.apache.spark.ml.util.DefaultParamsReader$.loadMetadata(ReadWrite.scala:379) >> at >> org.apache.spark.ml.recommendation.ALSModel$ALSModelReader.load(ALS.scala:317) >> 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) >> >> ================= >> > >