[
https://issues.apache.org/jira/browse/SPARK-15194?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15280563#comment-15280563
]
praveen dareddy commented on SPARK-15194:
-----------------------------------------
Hi All,
After going through ml and mllib api's,It seems MultivariateGaussian in scala
uses breeze library for linear algebra.
So, are we implementing the same in Python using numpy or using a wrapper to
Scala MultivariateGaussian?
I have tried using JavaWrapper class in
https://github.com/apache/spark/blob/master/python/pyspark/ml/wrapper.py
as wrapper solution. But I am getting constructor errors.( need to pass Vector
and DenseMatrix to MultivariateGaussian).
Are there any other Wrapper API's i am missing?
Kindly, help me out.
Thanks,
Praveen
Here is my code,
from pyspark.ml.wrapper import JavaWrapper
__all__ = ['MultivariateGaussian']
class MultivariateGaussian(JavaWrapper):
#@keyword_only
def __init__(self, mu,sigma):
super(MultivariateGaussian, self).__init__()
self._java_obj = self._new_java_obj(
"org.apache.spark.ml.stat.distribution.MultivariateGaussian",(mu,sigma) )
self.mu=mu
self.sigma=sigma
> Add Python ML API for MultivariateGaussian
> ------------------------------------------
>
> Key: SPARK-15194
> URL: https://issues.apache.org/jira/browse/SPARK-15194
> Project: Spark
> Issue Type: Improvement
> Components: ML, PySpark
> Reporter: holdenk
> Priority: Minor
>
> We have a PySpark API for the MLLib version but not the ML version. This
> would allow Python's `GaussianMixture` to more closely match the Scala API.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
