Repository: spark Updated Branches: refs/heads/master 4915e9e3b -> f9b6bf2f8
[SPARK-7667] [MLLIB] MLlib Python API consistency check MLlib Python API consistency check Author: Yanbo Liang <yblia...@gmail.com> Closes #6856 from yanboliang/spark-7667 and squashes the following commits: 21bae35 [Yanbo Liang] remove duplicate code eb12f95 [Yanbo Liang] fix doc inherit problem 9e7ec3c [Yanbo Liang] address comments e763d32 [Yanbo Liang] MLlib Python API consistency check Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f9b6bf2f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f9b6bf2f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f9b6bf2f Branch: refs/heads/master Commit: f9b6bf2f83d9dad273aa36d65d0560d35b941cc2 Parents: 4915e9e Author: Yanbo Liang <yblia...@gmail.com> Authored: Mon Jun 29 18:50:23 2015 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Mon Jun 29 18:50:23 2015 -0700 ---------------------------------------------------------------------- python/pyspark/mllib/feature.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/f9b6bf2f/python/pyspark/mllib/feature.py ---------------------------------------------------------------------- diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py index f00bb93..b513877 100644 --- a/python/pyspark/mllib/feature.py +++ b/python/pyspark/mllib/feature.py @@ -111,6 +111,15 @@ class JavaVectorTransformer(JavaModelWrapper, VectorTransformer): """ def transform(self, vector): + """ + Applies transformation on a vector or an RDD[Vector]. + + Note: In Python, transform cannot currently be used within + an RDD transformation or action. + Call transform directly on the RDD instead. + + :param vector: Vector or RDD of Vector to be transformed. + """ if isinstance(vector, RDD): vector = vector.map(_convert_to_vector) else: @@ -191,7 +200,7 @@ class StandardScaler(object): Computes the mean and variance and stores as a model to be used for later scaling. - :param data: The data used to compute the mean and variance + :param dataset: The data used to compute the mean and variance to build the transformation model. :return: a StandardScalarModel """ @@ -346,10 +355,6 @@ class IDFModel(JavaVectorTransformer): vector :return: an RDD of TF-IDF vectors or a TF-IDF vector """ - if isinstance(x, RDD): - return JavaVectorTransformer.transform(self, x) - - x = _convert_to_vector(x) return JavaVectorTransformer.transform(self, x) def idf(self): --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
