diff options
Diffstat (limited to 'python/pyspark/mllib/feature.py')
-rw-r--r-- | python/pyspark/mllib/feature.py | 37 |
1 files changed, 35 insertions, 2 deletions
diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py index da90554f41..cf5fdf2cf9 100644 --- a/python/pyspark/mllib/feature.py +++ b/python/pyspark/mllib/feature.py @@ -33,12 +33,13 @@ from py4j.protocol import Py4JJavaError from pyspark import SparkContext from pyspark.rdd import RDD, ignore_unicode_prefix from pyspark.mllib.common import callMLlibFunc, JavaModelWrapper -from pyspark.mllib.linalg import Vectors, DenseVector, SparseVector, _convert_to_vector +from pyspark.mllib.linalg import ( + Vector, Vectors, DenseVector, SparseVector, _convert_to_vector) from pyspark.mllib.regression import LabeledPoint __all__ = ['Normalizer', 'StandardScalerModel', 'StandardScaler', 'HashingTF', 'IDFModel', 'IDF', 'Word2Vec', 'Word2VecModel', - 'ChiSqSelector', 'ChiSqSelectorModel'] + 'ChiSqSelector', 'ChiSqSelectorModel', 'ElementwiseProduct'] class VectorTransformer(object): @@ -520,6 +521,38 @@ class Word2Vec(object): return Word2VecModel(jmodel) +class ElementwiseProduct(VectorTransformer): + """ + .. note:: Experimental + + Scales each column of the vector, with the supplied weight vector. + i.e the elementwise product. + + >>> weight = Vectors.dense([1.0, 2.0, 3.0]) + >>> eprod = ElementwiseProduct(weight) + >>> a = Vectors.dense([2.0, 1.0, 3.0]) + >>> eprod.transform(a) + DenseVector([2.0, 2.0, 9.0]) + >>> b = Vectors.dense([9.0, 3.0, 4.0]) + >>> rdd = sc.parallelize([a, b]) + >>> eprod.transform(rdd).collect() + [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])] + """ + def __init__(self, scalingVector): + self.scalingVector = _convert_to_vector(scalingVector) + + def transform(self, vector): + """ + Computes the Hadamard product of the vector. + """ + if isinstance(vector, RDD): + vector = vector.map(_convert_to_vector) + + else: + vector = _convert_to_vector(vector) + return callMLlibFunc("elementwiseProductVector", self.scalingVector, vector) + + def _test(): import doctest from pyspark import SparkContext |