我是pyspark的新手，我只是将我的RandomForestRegressor模型保存在名为“模型”的文件夹中。我有3个文件夹：数据，元数据和treesMetadata。 每个人都包含一些文件。
现在，我正在尝试将模型加载到新的Jupiter Notebook中。这是我加载模型的代码：
from pyspark.sql import SparkSession
import pyspark
from pyspark.sql.types import FloatType,StructField,StringType,IntegerType,StructType
from pyspark.ml.regression import RandomForestRegressor
from pyspark.ml.linalg import Vectors
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml import Pipeline
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.sql.functions import *
import os
import sys
# I know I'm importing a bunch of useless things for just a load test...
spark = SparkSession.builder.appName('RForest_Regression').getOrCreate()
model_1 = RandomForestRegressor.load(os.path.join(sys.argv[1], 'model/'))
但是在加载模型时出现此错误：
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-22-5b0649952b0d> in <module>
----> 1 model_1 = RandomForestRegressor.load(os.path.join(sys.argv[1], 'model/'))
~/spark-2.4.3-bin-hadoop2.7/python/pyspark/ml/util.py in load(cls, path)
360 def load(cls, path):
361 """Reads an ML instance from the input path, a shortcut of `read().load(path)`."""
--> 362 return cls.read().load(path)
363
364
~/spark-2.4.3-bin-hadoop2.7/python/pyspark/ml/util.py in load(self, path)
298 if not isinstance(path, basestring):
299 raise TypeError("path should be a basestring, got type %s" % type(path))
--> 300 java_obj = self._jread.load(path)
301 if not hasattr(self._clazz, "_from_java"):
302 raise NotImplementedError("This Java ML type cannot be loaded into Python currently: %r"
~/spark-2.4.3-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:
~/spark-2.4.3-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()
~/spark-2.4.3-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 o320.load.
: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: file:/Volumes/FabioHDD1T/-f/model/metadata
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1343)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.take(RDD.scala:1337)
at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1378)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.first(RDD.scala:1377)
at org.apache.spark.ml.util.DefaultParamsReader$.loadMetadata(ReadWrite.scala:615)
at org.apache.spark.ml.util.DefaultParamsReader.load(ReadWrite.scala:493)
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)
我不确定这是什么意思，这是我第一次尝试保存和加载模型。我想知道我的加载方法是否有问题...：（
答案 0 :(得分：1)
您几乎拥有了它……这是如何将训练好的模型重新加载到dataframe中以对新数据进行预测的摘要。
print(spark.version)
2.4.3
# fit model
cvModel = cv_grid.fit(train_df)
# save best model to specified path
mPath = "/path/to/model/folder"
cvModel.bestModel.write().overwrite().save(mPath)
# read pickled model via pipeline api
from pyspark.ml.pipeline import PipelineModel
persistedModel = PipelineModel.load(mPath)
# predict
predictionsDF = persistedModel.transform(test_df)
答案 1 :(得分：0)
from pyspark.ml.regression import RandomForestRegressionModel
rfModel = RandomForestRegressionModel.load("Path_to_saved_model")