From 32e3cdaa647722671adcb5068bd5ffbf2f157806 Mon Sep 17 00:00:00 2001 From: Yanbo Liang Date: Sun, 21 Jun 2015 12:04:20 -0700 Subject: [SPARK-7604] [MLLIB] Python API for PCA and PCAModel Python API for PCA and PCAModel Author: Yanbo Liang Closes #6315 from yanboliang/spark-7604 and squashes the following commits: 1d58734 [Yanbo Liang] remove transform() in PCAModel, use default behavior 4d9d121 [Yanbo Liang] Python API for PCA and PCAModel --- python/pyspark/mllib/feature.py | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'python/pyspark') diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py index cf5fdf2cf9..334f5b86cd 100644 --- a/python/pyspark/mllib/feature.py +++ b/python/pyspark/mllib/feature.py @@ -252,6 +252,41 @@ class ChiSqSelector(object): return ChiSqSelectorModel(jmodel) +class PCAModel(JavaVectorTransformer): + """ + Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA. + """ + + +class PCA(object): + """ + A feature transformer that projects vectors to a low-dimensional space using PCA. + + >>> data = [Vectors.sparse(5, [(1, 1.0), (3, 7.0)]), + ... Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]), + ... Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0])] + >>> model = PCA(2).fit(sc.parallelize(data)) + >>> pcArray = model.transform(Vectors.sparse(5, [(1, 1.0), (3, 7.0)])).toArray() + >>> pcArray[0] + 1.648... + >>> pcArray[1] + -4.013... + """ + def __init__(self, k): + """ + :param k: number of principal components. + """ + self.k = int(k) + + def fit(self, data): + """ + Computes a [[PCAModel]] that contains the principal components of the input vectors. + :param data: source vectors + """ + jmodel = callMLlibFunc("fitPCA", self.k, data) + return PCAModel(jmodel) + + class HashingTF(object): """ .. note:: Experimental -- cgit v1.2.3