mathjs/lib/type/matrix/utils/algorithm03.js

Math.js is an extensive math library for JavaScript and Node.js. It features a flexible expression parser with support for symbolic computation, comes with a large set of built-in functions and constants, and offers an integrated solution to work with dif

'use strict';

var DimensionError = require('../../../error/DimensionError');

function factory(type, config, load, typed) {
  var DenseMatrix = type.DenseMatrix;
  /**
   * Iterates over SparseMatrix items and invokes the callback function f(Dij, Sij).
   * Callback function invoked M*N times.
   *
   *
   *          ┌  f(Dij, Sij)  ; S(i,j) !== 0
   * C(i,j) = ┤
   *          └  f(Dij, 0)    ; otherwise
   *
   *
   * @param {Matrix}   denseMatrix       The DenseMatrix instance (D)
   * @param {Matrix}   sparseMatrix      The SparseMatrix instance (C)
   * @param {Function} callback          The f(Dij,Sij) operation to invoke, where Dij = DenseMatrix(i,j) and Sij = SparseMatrix(i,j)
   * @param {boolean}  inverse           A true value indicates callback should be invoked f(Sij,Dij)
   *
   * @return {Matrix}                    DenseMatrix (C)
   *
   * see https://github.com/josdejong/mathjs/pull/346#issuecomment-97477571
   */

  var algorithm03 = function algorithm03(denseMatrix, sparseMatrix, callback, inverse) {
    // dense matrix arrays
    var adata = denseMatrix._data;
    var asize = denseMatrix._size;
    var adt = denseMatrix._datatype; // sparse matrix arrays

    var bvalues = sparseMatrix._values;
    var bindex = sparseMatrix._index;
    var bptr = sparseMatrix._ptr;
    var bsize = sparseMatrix._size;
    var bdt = sparseMatrix._datatype; // validate dimensions

    if (asize.length !== bsize.length) {
      throw new DimensionError(asize.length, bsize.length);
    } // check rows & columns


    if (asize[0] !== bsize[0] || asize[1] !== bsize[1]) {
      throw new RangeError('Dimension mismatch. Matrix A (' + asize + ') must match Matrix B (' + bsize + ')');
    } // sparse matrix cannot be a Pattern matrix


    if (!bvalues) {
      throw new Error('Cannot perform operation on Dense Matrix and Pattern Sparse Matrix');
    } // rows & columns


    var rows = asize[0];
    var columns = asize[1]; // datatype

    var dt; // zero value

    var zero = 0; // callback signature to use

    var cf = callback; // process data types

    if (typeof adt === 'string' && adt === bdt) {
      // datatype
      dt = adt; // convert 0 to the same datatype

      zero = typed.convert(0, dt); // callback

      cf = typed.find(callback, [dt, dt]);
    } // result (DenseMatrix)


    var cdata = []; // initialize dense matrix

    for (var z = 0; z < rows; z++) {
      // initialize row
      cdata[z] = [];
    } // workspace


    var x = []; // marks indicating we have a value in x for a given column

    var w = []; // loop columns in b

    for (var j = 0; j < columns; j++) {
      // column mark
      var mark = j + 1; // values in column j

      for (var k0 = bptr[j], k1 = bptr[j + 1], k = k0; k < k1; k++) {
        // row
        var i = bindex[k]; // update workspace

        x[i] = inverse ? cf(bvalues[k], adata[i][j]) : cf(adata[i][j], bvalues[k]);
        w[i] = mark;
      } // process workspace


      for (var y = 0; y < rows; y++) {
        // check we have a calculated value for current row
        if (w[y] === mark) {
          // use calculated value
          cdata[y][j] = x[y];
        } else {
          // calculate value
          cdata[y][j] = inverse ? cf(zero, adata[y][j]) : cf(adata[y][j], zero);
        }
      }
    } // return dense matrix


    return new DenseMatrix({
      data: cdata,
      size: [rows, columns],
      datatype: dt
    });
  };

  return algorithm03;
}

exports.name = 'algorithm03';
exports.factory = factory;