val rows: RDD[Vector] = sc.parallelize(Array(Vectors.dense(12.0, -51.0, 4.0), Vectors.dense(6.0, 167.0, -68.0), Vectors.dense(-4.0, 24.0, -41.0))) // an RDD of local vectors
rows: org.apache.spark.rdd.RDD[org.apache.spark.mllib.linalg.Vector] = ParallelCollectionRDD[10563] at parallelize at command-1805207615647079:1
// QR decomposition val qrResult = mat.tallSkinnyQR(true)
qrResult: org.apache.spark.mllib.linalg.QRDecomposition[org.apache.spark.mllib.linalg.distributed.RowMatrix,org.apache.spark.mllib.linalg.Matrix] =
QRDecomposition(org.apache.spark.mllib.linalg.distributed.RowMatrix@5a0eb9ce,14.0 21.0 -14.0
0.0 -174.99999999999997 70.00000000000001
0.0 0.0 -35.000000000000014 )
%py from pyspark.mllib.linalg.distributed import RowMatrix # Create an RDD of vectors. rows = sc.parallelize([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]) # Create a RowMatrix from an RDD of vectors. mat = RowMatrix(rows) # Get its size. m = mat.numRows() # 4 n = mat.numCols() # 3 print m,'x',n # Get the rows as an RDD of vectors again. rowsRDD = mat.rows
4 x 3
SDS-2.x, Scalable Data Engineering Science
Last refresh: Never