A local matrix in Spark has integer-typed row and column indices. Values are double-typed. All the values are stored on a single machine. MLlib supports the following matrix types:
- Dense matrices: Matrices where entry values stored are in a single, double array in a column-major order.
- Sparse matrices: Matrices where non-zero entry values are stored in the CSC format in a column-major order. For example, the following dense matrix is stored in a one-dimensional array [2.0, 3.0, 4.0, 1.0, 4.0, 5.0] for the matrix size (3, 2):
This is an example of a dense and sparse matrix:
val dMatrix: Matrix = Matrices.dense(2, 2, Array(1.0, 2.0, 3.0, 4.0)) println("dMatrix: n" + dMatrix) val sMatrixOne: Matrix ...