Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4059#discussion_r23399900
--- Diff: python/pyspark/mllib/clustering.py ---
@@ -86,6 +86,68 @@ def train(cls, rdd, k, maxIterations=100, runs=1,
initializationMode="k-means||"
return KMeansModel([c.toArray() for c in centers])
+class GaussianMixtureModel(object):
+
+ """A clustering model derived from the Gaussian Mixture Model method.
+
+ >>> from numpy import array
+ >>> clusterdata_1 = sc.parallelize(array([-0.1,-0.05,-0.01,-0.1,
+ ... 0.9,0.8,0.75,0.935,
+ ... -0.83,-0.68,-0.91,-0.76
]).reshape(6,2))
+ >>> model = GaussianMixtureEM.train(clusterdata_1, 3, 0.0001, 3205, 10)
+ >>> labels = model.predictLabels(clusterdata_1).collect()
+ >>> labels[0]==labels[2]
+ True
+ >>> labels[3]==labels[4]
+ False
+ >>> labels[4]==labels[5]
+ True
+ >>> clusterdata_2 = sc.parallelize(array([-5.1971, -2.5359, -3.8220,
+ ... -5.2211, -5.0602, 4.7118,
+ ... 6.8989, 3.4592, 4.6322,
+ ... 5.7048, 4.6567, 5.5026,
+ ... 4.5605, 5.2043,
6.2734]).reshape(5,3))
+ >>> model = GaussianMixtureEM.train(clusterdata_2, 2, 0.0001, 150, 10)
+ >>> labels = model.predictLabels(clusterdata_2).collect()
+ >>> labels[0]==labels[1]==labels[2]
+ True
+ >>> labels[3]==labels[4]
+ True
+ """
+
+ def __init__(self, weight, mu, sigma):
+ self.weight = weight
+ self.mu = mu
+ self.sigma = sigma
+
+ def predictLabels(self, X):
+ """
+ Find the cluster to which the points in X has maximum membership
+ in this model.
+ """
+ cluster_labels = self.predictSoft(X).map(lambda x: x.index(max(x)))
+ return cluster_labels
+
+ def predictSoft(self, X):
+ """
+ Find the membership of each point in X to all clusters in this
model.
--- End diff --
What is the type of the return value? Is it a matrix or an array? This is
important for Python users.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
