From e43803b8f477b2c8d28836ac163cb54328d13f1a Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Thu, 7 May 2015 15:45:37 -0700 Subject: [SPARK-6948] [MLLIB] compress vectors in VectorAssembler The compression is based on storage. brkyvz Author: Xiangrui Meng Closes #5985 from mengxr/SPARK-6948 and squashes the following commits: df56a00 [Xiangrui Meng] update python tests 6d90d45 [Xiangrui Meng] compress vectors in VectorAssembler --- python/pyspark/ml/feature.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'python/pyspark/ml/feature.py') diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 8a0fdddd2d..705a368192 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -121,12 +121,12 @@ class VectorAssembler(JavaTransformer, HasInputCols, HasOutputCol): >>> df = sc.parallelize([Row(a=1, b=0, c=3)]).toDF() >>> vecAssembler = VectorAssembler(inputCols=["a", "b", "c"], outputCol="features") >>> vecAssembler.transform(df).head().features - SparseVector(3, {0: 1.0, 2: 3.0}) + DenseVector([1.0, 0.0, 3.0]) >>> vecAssembler.setParams(outputCol="freqs").transform(df).head().freqs - SparseVector(3, {0: 1.0, 2: 3.0}) + DenseVector([1.0, 0.0, 3.0]) >>> params = {vecAssembler.inputCols: ["b", "a"], vecAssembler.outputCol: "vector"} >>> vecAssembler.transform(df, params).head().vector - SparseVector(2, {1: 1.0}) + DenseVector([0.0, 1.0]) """ _java_class = "org.apache.spark.ml.feature.VectorAssembler" -- cgit v1.2.3