Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4059#discussion_r23943651
--- Diff: python/pyspark/mllib/clustering.py ---
@@ -86,6 +89,98 @@ 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.
+
+ >>> 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 = GaussianMixture.train(clusterdata_1, 3,
convergenceTol=0.0001,
+ ... maxIterations=50, seed=10)
+ >>> labels = model.predict(clusterdata_1).collect()
+ >>> labels[0]==labels[1]
+ False
+ >>> labels[1]==labels[2]
+ True
+ >>> 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 = GaussianMixture.train(clusterdata_2, 2,
convergenceTol=0.0001,
+ ... maxIterations=150, seed=10)
+ >>> labels = model.predict(clusterdata_2).collect()
+ >>> labels[0]==labels[1]==labels[2]
+ True
+ >>> labels[3]==labels[4]
+ True
+ """
+
+ def __init__(self, weights, gaussians):
+ self.weights = weights
+ self.gaussians = gaussians
+ self.k = len(self.weights)
+
+ def predict(self, x):
+ """
+ Find the cluster to which the points in 'x' has maximum membership
+ in this model.
+
+ Parameters
+ ----------
+ x : RDD of data points
+
+ Returns
+ -------
+ cluster_labels : RDD of cluster labels.
+ """
+ if isinstance(x, RDD):
+ cluster_labels = self.predictSoft(x).map(lambda z:
z.index(max(z)))
+ return cluster_labels
+
+ def predictSoft(self, x):
+ """
+ Find the membership of each point in 'x' to all mixture components.
+
+ Parameters
+ ----------
+ x : RDD of data points
+
+ Returns
+ -------
+ membership_matrix : RDD of array of double values.
+ """
+ means, sigmas = zip(*[(g.mu, g.sigma) for g in self.gaussians])
--- End diff --
We didn't check whether `x` is an `RDD` or not here.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
