ó î&]\c@`saddlmZmZmZddlmZddlmZmZm Z dgZ dd„Z dS(i(tdivisiontprint_functiontabsolute_importi(t_nnls(tasarray_chkfinitetzerostdoubletnnlsc C`sCtt||fƒ\}}t|jƒdkr?tdƒ‚nt|jƒdkrctdƒ‚n|j\}}||jdkr”tdƒ‚n|d krŚdn t|ƒ}t|fdtƒ}t|fdtƒ}t|fdtƒ}t j ||||||||ƒ\}} } | dkr9t d ƒ‚n|| fS( s2 Solve ``argmin_x || Ax - b ||_2`` for ``x>=0``. This is a wrapper for a FORTRAN non-negative least squares solver. Parameters ---------- A : ndarray Matrix ``A`` as shown above. b : ndarray Right-hand side vector. maxiter: int, optional Maximum number of iterations, optional. Default is ``3 * A.shape[1]``. Returns ------- x : ndarray Solution vector. rnorm : float The residual, ``|| Ax-b ||_2``. Notes ----- The FORTRAN code was published in the book below. The algorithm is an active set method. It solves the KKT (Karush-Kuhn-Tucker) conditions for the non-negative least squares problem. References ---------- Lawson C., Hanson R.J., (1987) Solving Least Squares Problems, SIAM isexpected matrixisexpected vectorisincompatible dimensionsi˙˙˙˙tdtypestoo many iterationsN( tmapRtlentshapet ValueErrortNonetintRRRRt RuntimeError( tAtbtmaxitertmtntwtzztindextxtrnormtmode((s2lib/python2.7/site-packages/scipy/optimize/nnls.pyR s "- N( t __future__RRRtRtnumpyRRRt__all__R R(((s2lib/python2.7/site-packages/scipy/optimize/nnls.pyts