Question

我想使用pyspark运行PCA，但是它给出了这个奇怪的错误。我正在使用带有python 3.6.3和pyspark 2.3.1的MAC。我也尝试过使用虚拟环境，发生相同的错误。当我也进行随机森林模型拟合时，也会发生相同的错误。请让我知道如何解决！！

from pyspark.ml.feature import PCA
from pyspark.mllib.linalg import Vectors
from pyspark import SparkContext
from pyspark import SQLContext

sc = SparkContext()

sqlContext = SQLContext(sc)
data = [(Vectors.sparse(5, [(1,1.0), (3, 7.0)]),), 
    (Vectors.dense([2.0,0.0,3.0,4.0,5.0]),),
    (Vectors.dense([5.6,3.0,1.0,6.4,3.5]),),
    (Vectors.dense([3.4, 5.3, 0.0, 5.5, 6.6]),),
   (Vectors.dense([4.1,3.1,3.2,9.1,7.0]),),
   (Vectors.dense([3.6, 4.1, 4.2, 6.3, 7.0]),),]

df = sqlContext.createDataFrame(data, ['features'])

pca = PCA(k=3, inputCol='features', outputCol='pcaFeatures')
# Error Occurs on this line
modle = pca.fit(df)

ERROR:
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:

~/anaconda3/lib/python3.6/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:

Py4JJavaError: An error occurred while calling o35.fit.
: java.lang.IllegalArgumentException: requirement failed: Column features must be of type org.apache.spark.ml.linalg.VectorUDT@3bfc3ba7 but was actually org.apache.spark.mllib.linalg.VectorUDT@f71b0bce.
    at scala.Predef$.require(Predef.scala:224)
    at org.apache.spark.ml.util.SchemaUtils$.checkColumnType(SchemaUtils.scala:42)
    at org.apache.spark.ml.feature.PCAParams$class.validateAndTransformSchema(PCA.scala:56)
    at org.apache.spark.ml.feature.PCA.validateAndTransformSchema(PCA.scala:70)
    at org.apache.spark.ml.feature.PCA.transformSchema(PCA.scala:105)
    at org.apache.spark.ml.PipelineStage.transformSchema(Pipeline.scala:74)
    at org.apache.spark.ml.feature.PCA.fit(PCA.scala:94)
    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)


During handling of the above exception, another exception occurred:

IllegalArgumentException                  Traceback (most recent call last)
<ipython-input-11-cf9820b1adfc> in <module>()
----> 1 modle = pca.fit(df)

/usr/local/spark/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, "

/usr/local/spark/python/pyspark/ml/wrapper.py in _fit(self, dataset)
    286 
    287     def _fit(self, dataset):
--> 288         java_model = self._fit_java(dataset)
    289         model = self._create_model(java_model)
    290         return self._copyValues(model)

/usr/local/spark/python/pyspark/ml/wrapper.py in _fit_java(self, dataset)
    283         """
    284         self._transfer_params_to_java()
--> 285         return self._java_obj.fit(dataset._jdf)
    286 
    287     def _fit(self, dataset):

~/anaconda3/lib/python3.6/site-packages/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:

/usr/local/spark/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: Column features must be of type org.apache.spark.ml.linalg.VectorUDT@3bfc3ba7 but was actually org.apache.spark.mllib.linalg.VectorUDT@f71b0bce.'


1
sc.version
'2.3.1'

Answer 1

更改来自的导入
from pyspark.mllib.linalg import Vectors至
from pyspark.ml.linalg import Vectors

Py4JJavaError使用pyspark ml库时

1 个答案: