From 2519dcc33bde3a6d341790d73b5d292ea7af961a Mon Sep 17 00:00:00 2001
From: Yanbo Liang <ybliang8@gmail.com>
Date: Thu, 25 Jun 2015 08:13:17 -0700
Subject: [PATCH] [MINOR] [MLLIB] rename some functions of PythonMLLibAPI
Keep the same naming conventions for PythonMLLibAPI.
Only the following three functions is different from others
```scala
trainNaiveBayes
trainGaussianMixture
trainWord2Vec
```
So change them to
```scala
trainNaiveBayesModel
trainGaussianMixtureModel
trainWord2VecModel
```
It does not affect any users and public APIs, only to make better understand for developer and code hacker.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #7011 from yanboliang/py-mllib-api-rename and squashes the following commits:
771ffec [Yanbo Liang] rename some functions of PythonMLLibAPI
---
.../org/apache/spark/mllib/api/python/PythonMLLibAPI.scala | 6 +++---
python/pyspark/mllib/classification.py | 2 +-
python/pyspark/mllib/clustering.py | 6 +++---
python/pyspark/mllib/feature.py | 2 +-
4 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index c4bea7c2ca..b16903a8d5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -278,7 +278,7 @@ private[python] class PythonMLLibAPI extends Serializable {
/**
* Java stub for NaiveBayes.train()
*/
- def trainNaiveBayes(
+ def trainNaiveBayesModel(
data: JavaRDD[LabeledPoint],
lambda: Double): JList[Object] = {
val model = NaiveBayes.train(data.rdd, lambda)
@@ -346,7 +346,7 @@ private[python] class PythonMLLibAPI extends Serializable {
* Java stub for Python mllib GaussianMixture.run()
* Returns a list containing weights, mean and covariance of each mixture component.
*/
- def trainGaussianMixture(
+ def trainGaussianMixtureModel(
data: JavaRDD[Vector],
k: Int,
convergenceTol: Double,
@@ -553,7 +553,7 @@ private[python] class PythonMLLibAPI extends Serializable {
* @param seed initial seed for random generator
* @return A handle to java Word2VecModelWrapper instance at python side
*/
- def trainWord2Vec(
+ def trainWord2VecModel(
dataJRDD: JavaRDD[java.util.ArrayList[String]],
vectorSize: Int,
learningRate: Double,
diff --git a/python/pyspark/mllib/classification.py b/python/pyspark/mllib/classification.py
index 2698f10d06..735d45ba03 100644
--- a/python/pyspark/mllib/classification.py
+++ b/python/pyspark/mllib/classification.py
@@ -581,7 +581,7 @@ class NaiveBayes(object):
first = data.first()
if not isinstance(first, LabeledPoint):
raise ValueError("`data` should be an RDD of LabeledPoint")
- labels, pi, theta = callMLlibFunc("trainNaiveBayes", data, lambda_)
+ labels, pi, theta = callMLlibFunc("trainNaiveBayesModel", data, lambda_)
return NaiveBayesModel(labels.toArray(), pi.toArray(), numpy.array(theta))
diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py
index e6ef72942c..8bc0654c76 100644
--- a/python/pyspark/mllib/clustering.py
+++ b/python/pyspark/mllib/clustering.py
@@ -265,9 +265,9 @@ class GaussianMixture(object):
initialModelWeights = initialModel.weights
initialModelMu = [initialModel.gaussians[i].mu for i in range(initialModel.k)]
initialModelSigma = [initialModel.gaussians[i].sigma for i in range(initialModel.k)]
- weight, mu, sigma = callMLlibFunc("trainGaussianMixture", rdd.map(_convert_to_vector), k,
- convergenceTol, maxIterations, seed, initialModelWeights,
- initialModelMu, initialModelSigma)
+ weight, mu, sigma = callMLlibFunc("trainGaussianMixtureModel", rdd.map(_convert_to_vector),
+ k, convergenceTol, maxIterations, seed,
+ initialModelWeights, initialModelMu, initialModelSigma)
mvg_obj = [MultivariateGaussian(mu[i], sigma[i]) for i in range(k)]
return GaussianMixtureModel(weight, mvg_obj)
diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py
index 334f5b86cd..f00bb93b7b 100644
--- a/python/pyspark/mllib/feature.py
+++ b/python/pyspark/mllib/feature.py
@@ -549,7 +549,7 @@ class Word2Vec(object):
"""
if not isinstance(data, RDD):
raise TypeError("data should be an RDD of list of string")
- jmodel = callMLlibFunc("trainWord2Vec", data, int(self.vectorSize),
+ jmodel = callMLlibFunc("trainWord2VecModel", data, int(self.vectorSize),
float(self.learningRate), int(self.numPartitions),
int(self.numIterations), int(self.seed),
int(self.minCount))
--
GitLab