Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/6791#discussion_r33093432
--- Diff: python/pyspark/mllib/clustering.py ---
@@ -274,5 +276,63 @@ def _test():
exit(-1)
+class LDAModel(JavaModelWrapper):
+
+ """ A clustering model derived from the LDA method.
+
+ Latent Dirichlet Allocation (LDA), a topic model designed for text
documents.
+ Terminologyu
+ - "word" = "term": an element of the vocabulary
+ - "token": instance of a term appearing in a document
+ - "topic": multinomial distribution over words representing some
concept
+ References:
+ - Original LDA paper (journal version):
+ Blei, Ng, and Jordan. "Latent Dirichlet Allocation." JMLR, 2003.
+
+ >>> from pyspark.mllib.linalg import Vectors
+ >>> from collections import namedtuple
+ >>> from numpy.testing import assert_almost_equal
+ >>> data = [
+ ... [1, Vectors.dense([0.0, 1.0])],
+ ... [2, SparseVector(2, {0: 1.0})],
+ ... ]
+ >>> rdd = sc.parallelize(data)
+ >>> model = LDA.train(rdd, k=2)
+ >>> model.vocabSize()
+ 2
+ >>> topics = model.topicsMatrix()
+ >>> topics_expect = array([[0.5, 0.5], [0.5, 0.5]])
+ >>> assert_almost_equal(topics, topics_expect, 1)
+ """
+
+ def topicsMatrix(self):
+ """Inferred topics, where each topic is represented by a
distribution over terms."""
+ return self.call("topicsMatrix").toArray()
+
+ def vocabSize(self):
+ """Vocabulary size (number of terms or terms in the vocabulary)"""
+ return self.call("vocabSize")
+
+ def describeTopics(self, maxTermsPerTopic=None):
+ """Return the topics described by weighted terms.
+
+ TODO:
+ Implementing this method is a little hard. Since Scala's return
value consistes of tuples.
+ """
+ raise NotImplementedError("LDAModel.describeTopics() in Python
must be implemented.")
+
+
+class LDA():
+
+ @classmethod
+ def train(cls, rdd, k=10, maxIterations=20, docConcentration=-1.0,
+ topicConcentration=-1.0, seed=None, checkpointInterval=10,
optimizer="em"):
+ """Train a LDA model."""
--- End diff --
This should document the expected format of the rdd, plus other parameters.
Feel free to copy from Scala doc.
---
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]
