viirya commented on a change in pull request #30413:
URL: https://github.com/apache/spark/pull/30413#discussion_r529762661
##########
File path: python/pyspark/mllib/clustering.py
##########
@@ -499,32 +554,36 @@ class GaussianMixture(object):
.. versionadded:: 1.3.0
"""
+
@classmethod
- @since('1.3.0')
def train(cls, rdd, k, convergenceTol=1e-3, maxIterations=100, seed=None,
initialModel=None):
"""
Train a Gaussian Mixture clustering model.
- :param rdd:
- Training points as an `RDD` of `Vector` or convertible
- sequence types.
- :param k:
- Number of independent Gaussians in the mixture model.
- :param convergenceTol:
- Maximum change in log-likelihood at which convergence is
- considered to have occurred.
- (default: 1e-3)
- :param maxIterations:
- Maximum number of iterations allowed.
- (default: 100)
- :param seed:
- Random seed for initial Gaussian distribution. Set as None to
- generate seed based on system time.
- (default: None)
- :param initialModel:
- Initial GMM starting point, bypassing the random
- initialization.
- (default: None)
+ .. versionadded:: 1.3.0
+
+ Parameters
+ ----------
+ rdd : ::py:class:`pyspark.RDD`
+ Training points as an `RDD` of
:py:class:`pyspark.mllib.linalg.Vector`
+ or convertible sequence types.
+ param k : int
Review comment:
param is redundant.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
