Data Types - MLlib

import org.apache.spark.mllib.linalg.{Vector, Vectors}

// Create a dense vector (1.0, 0.0, 3.0).
val dv: Vector = Vectors.dense(1.0, 0.0, 3.0)
// Create a sparse vector (1.0, 0.0, 3.0) by specifying its indices and values corresponding to nonzero entries.
val sv1: Vector = Vectors.sparse(3, Array(0, 2), Array(1.0, 3.0))
// Create a sparse vector (1.0, 0.0, 3.0) by specifying its nonzero entries.
val sv2: Vector = Vectors.sparse(3, Seq((0, 1.0), (2, 3.0)))

import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;

// Create a dense vector (1.0, 0.0, 3.0).
Vector dv = Vectors.dense(1.0, 0.0, 3.0);
// Create a sparse vector (1.0, 0.0, 3.0) by specifying its indices and values corresponding to nonzero entries.
Vector sv = Vectors.sparse(3, new int[] {0, 2}, new double[] {1.0, 3.0});

import numpy as np
import scipy.sparse as sps
from pyspark.mllib.linalg import Vectors

# Use a NumPy array as a dense vector.
dv1 = np.array([1.0, 0.0, 3.0])
# Use a Python list as a dense vector.
dv2 = [1.0, 0.0, 3.0]
# Create a SparseVector.
sv1 = Vectors.sparse(3, [0, 2], [1.0, 3.0])
# Use a single-column SciPy csc_matrix as a sparse vector.
sv2 = sps.csc_matrix((np.array([1.0, 3.0]), np.array([0, 2]), np.array([0, 2])), shape = (3, 1))

import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint

// Create a labeled point with a positive label and a dense feature vector.
val pos = LabeledPoint(1.0, Vectors.dense(1.0, 0.0, 3.0))

// Create a labeled point with a negative label and a sparse feature vector.
val neg = LabeledPoint(0.0, Vectors.sparse(3, Array(0, 2), Array(1.0, 3.0)))

import org.apache.spark.mllib.linalg.Vectors;
import org.apache.spark.mllib.regression.LabeledPoint;

// Create a labeled point with a positive label and a dense feature vector.
LabeledPoint pos = new LabeledPoint(1.0, Vectors.dense(1.0, 0.0, 3.0));

// Create a labeled point with a negative label and a sparse feature vector.
LabeledPoint neg = new LabeledPoint(0.0, Vectors.sparse(3, new int[] {0, 2}, new double[] {1.0, 3.0}));

from pyspark.mllib.linalg import SparseVector
from pyspark.mllib.regression import LabeledPoint

# Create a labeled point with a positive label and a dense feature vector.
pos = LabeledPoint(1.0, [1.0, 0.0, 3.0])

# Create a labeled point with a negative label and a sparse feature vector.
neg = LabeledPoint(0.0, SparseVector(3, [0, 2], [1.0, 3.0]))

import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
import org.apache.spark.rdd.RDD

val examples: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;
import org.apache.spark.api.java.JavaRDD;

JavaRDD<LabeledPoint> examples = 
  MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt").toJavaRDD();

from pyspark.mllib.util import MLUtils

examples = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

import org.apache.spark.mllib.linalg.{Matrix, Matrices}

// Create a dense matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0))
val dm: Matrix = Matrices.dense(3, 2, Array(1.0, 3.0, 5.0, 2.0, 4.0, 6.0))

// Create a sparse matrix ((9.0, 0.0), (0.0, 8.0), (0.0, 6.0))
val sm: Matrix = Matrices.sparse(3, 2, Array(0, 1, 3), Array(0, 2, 1), Array(9, 6, 8))

import org.apache.spark.mllib.linalg.Matrix;
import org.apache.spark.mllib.linalg.Matrices;

// Create a dense matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0))
Matrix dm = Matrices.dense(3, 2, new double[] {1.0, 3.0, 5.0, 2.0, 4.0, 6.0});

// Create a sparse matrix ((9.0, 0.0), (0.0, 8.0), (0.0, 6.0))
Matrix sm = Matrices.sparse(3, 2, new int[] {0, 1, 3}, new int[] {0, 2, 1}, new double[] {9, 6, 8});

import org.apache.spark.mllib.linalg.{Matrix, Matrices}

// Create a dense matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0))
dm2 = Matrices.dense(3, 2, [1, 2, 3, 4, 5, 6])

// Create a sparse matrix ((9.0, 0.0), (0.0, 8.0), (0.0, 6.0))
sm = Matrices.sparse(3, 2, [0, 1, 3], [0, 2, 1], [9, 6, 8])

import org.apache.spark.mllib.linalg.Vector
import org.apache.spark.mllib.linalg.distributed.RowMatrix

val rows: RDD[Vector] = ... // an RDD of local vectors
// Create a RowMatrix from an RDD[Vector].
val mat: RowMatrix = new RowMatrix(rows)

// Get its size.
val m = mat.numRows()
val n = mat.numCols()

// QR decomposition 
val qrResult = mat.tallSkinnyQR(true)

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.distributed.RowMatrix;

JavaRDD<Vector> rows = ... // a JavaRDD of local vectors
// Create a RowMatrix from an JavaRDD<Vector>.
RowMatrix mat = new RowMatrix(rows.rdd());

// Get its size.
long m = mat.numRows();
long n = mat.numCols();

// QR decomposition 
QRDecomposition<RowMatrix, Matrix> result = mat.tallSkinnyQR(true);

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

# Get the rows as an RDD of vectors again.
rowsRDD = mat.rows

import org.apache.spark.mllib.linalg.distributed.{IndexedRow, IndexedRowMatrix, RowMatrix}

val rows: RDD[IndexedRow] = ... // an RDD of indexed rows
// Create an IndexedRowMatrix from an RDD[IndexedRow].
val mat: IndexedRowMatrix = new IndexedRowMatrix(rows)

// Get its size.
val m = mat.numRows()
val n = mat.numCols()

// Drop its row indices.
val rowMat: RowMatrix = mat.toRowMatrix()

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.linalg.distributed.IndexedRow;
import org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix;
import org.apache.spark.mllib.linalg.distributed.RowMatrix;

JavaRDD<IndexedRow> rows = ... // a JavaRDD of indexed rows
// Create an IndexedRowMatrix from a JavaRDD<IndexedRow>.
IndexedRowMatrix mat = new IndexedRowMatrix(rows.rdd());

// Get its size.
long m = mat.numRows();
long n = mat.numCols();

// Drop its row indices.
RowMatrix rowMat = mat.toRowMatrix();

from pyspark.mllib.linalg.distributed import IndexedRow, IndexedRowMatrix

# Create an RDD of indexed rows.
#   - This can be done explicitly with the IndexedRow class:
indexedRows = sc.parallelize([IndexedRow(0, [1, 2, 3]), 
                              IndexedRow(1, [4, 5, 6]), 
                              IndexedRow(2, [7, 8, 9]), 
                              IndexedRow(3, [10, 11, 12])])
#   - or by using (long, vector) tuples:
indexedRows = sc.parallelize([(0, [1, 2, 3]), (1, [4, 5, 6]), 
                              (2, [7, 8, 9]), (3, [10, 11, 12])])

# Create an IndexedRowMatrix from an RDD of IndexedRows.
mat = IndexedRowMatrix(indexedRows)

# Get its size.
m = mat.numRows()  # 4
n = mat.numCols()  # 3

# Get the rows as an RDD of IndexedRows.
rowsRDD = mat.rows

# Convert to a RowMatrix by dropping the row indices.
rowMat = mat.toRowMatrix()

# Convert to a CoordinateMatrix.
coordinateMat = mat.toCoordinateMatrix()

# Convert to a BlockMatrix.
blockMat = mat.toBlockMatrix()

import org.apache.spark.mllib.linalg.distributed.{CoordinateMatrix, MatrixEntry}

val entries: RDD[MatrixEntry] = ... // an RDD of matrix entries
// Create a CoordinateMatrix from an RDD[MatrixEntry].
val mat: CoordinateMatrix = new CoordinateMatrix(entries)

// Get its size.
val m = mat.numRows()
val n = mat.numCols()

// Convert it to an IndexRowMatrix whose rows are sparse vectors.
val indexedRowMatrix = mat.toIndexedRowMatrix()

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.linalg.distributed.CoordinateMatrix;
import org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix;
import org.apache.spark.mllib.linalg.distributed.MatrixEntry;

JavaRDD<MatrixEntry> entries = ... // a JavaRDD of matrix entries
// Create a CoordinateMatrix from a JavaRDD<MatrixEntry>.
CoordinateMatrix mat = new CoordinateMatrix(entries.rdd());

// Get its size.
long m = mat.numRows();
long n = mat.numCols();

// Convert it to an IndexRowMatrix whose rows are sparse vectors.
IndexedRowMatrix indexedRowMatrix = mat.toIndexedRowMatrix();

from pyspark.mllib.linalg.distributed import CoordinateMatrix, MatrixEntry

# Create an RDD of coordinate entries.
#   - This can be done explicitly with the MatrixEntry class:
entries = sc.parallelize([MatrixEntry(0, 0, 1.2), MatrixEntry(1, 0, 2.1), MatrixEntry(6, 1, 3.7)])
#   - or using (long, long, float) tuples:
entries = sc.parallelize([(0, 0, 1.2), (1, 0, 2.1), (2, 1, 3.7)])

# Create an CoordinateMatrix from an RDD of MatrixEntries.
mat = CoordinateMatrix(entries)

# Get its size.
m = mat.numRows()  # 3
n = mat.numCols()  # 2

# Get the entries as an RDD of MatrixEntries.
entriesRDD = mat.entries

# Convert to a RowMatrix.
rowMat = mat.toRowMatrix()

# Convert to an IndexedRowMatrix.
indexedRowMat = mat.toIndexedRowMatrix()

# Convert to a BlockMatrix.
blockMat = mat.toBlockMatrix()

import org.apache.spark.mllib.linalg.distributed.{BlockMatrix, CoordinateMatrix, MatrixEntry}

val entries: RDD[MatrixEntry] = ... // an RDD of (i, j, v) matrix entries
// Create a CoordinateMatrix from an RDD[MatrixEntry].
val coordMat: CoordinateMatrix = new CoordinateMatrix(entries)
// Transform the CoordinateMatrix to a BlockMatrix
val matA: BlockMatrix = coordMat.toBlockMatrix().cache()

// Validate whether the BlockMatrix is set up properly. Throws an Exception when it is not valid.
// Nothing happens if it is valid.
matA.validate()

// Calculate A^T A.
val ata = matA.transpose.multiply(matA)

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.linalg.distributed.BlockMatrix;
import org.apache.spark.mllib.linalg.distributed.CoordinateMatrix;
import org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix;

JavaRDD<MatrixEntry> entries = ... // a JavaRDD of (i, j, v) Matrix Entries
// Create a CoordinateMatrix from a JavaRDD<MatrixEntry>.
CoordinateMatrix coordMat = new CoordinateMatrix(entries.rdd());
// Transform the CoordinateMatrix to a BlockMatrix
BlockMatrix matA = coordMat.toBlockMatrix().cache();

// Validate whether the BlockMatrix is set up properly. Throws an Exception when it is not valid.
// Nothing happens if it is valid.
matA.validate();

// Calculate A^T A.
BlockMatrix ata = matA.transpose().multiply(matA);

from pyspark.mllib.linalg import Matrices
from pyspark.mllib.linalg.distributed import BlockMatrix

# Create an RDD of sub-matrix blocks.
blocks = sc.parallelize([((0, 0), Matrices.dense(3, 2, [1, 2, 3, 4, 5, 6])), 
                         ((1, 0), Matrices.dense(3, 2, [7, 8, 9, 10, 11, 12]))])

# Create a BlockMatrix from an RDD of sub-matrix blocks.
mat = BlockMatrix(blocks, 3, 2)

# Get its size.
m = mat.numRows() # 6
n = mat.numCols() # 2

# Get the blocks as an RDD of sub-matrix blocks.
blocksRDD = mat.blocks

# Convert to a LocalMatrix.
localMat = mat.toLocalMatrix()

# Convert to an IndexedRowMatrix.
indexedRowMat = mat.toIndexedRowMatrix()

# Convert to a CoordinateMatrix.
coordinateMat = mat.toCoordinateMatrix()