ó ÚÆ÷Xc@`s^ddlmZmZmZddlmZddlmZmZm Z dgZ d„Z dS(i(tdivisiontprint_functiontabsolute_importi(t_nnls(tasarray_chkfinitetzerostdoubletnnlsc C`s"tt||fƒ\}}t|jƒdkr?tdƒ‚nt|jƒdkrctdƒ‚n|j\}}||jdkr”tdƒ‚nt|fdtƒ}t|fdtƒ}t|fdtƒ}tj |||||||ƒ\}}} | dkrt dƒ‚n||fS( sÀ 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. 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 dimensionstdtypestoo many iterations( tmapRtlentshapet ValueErrorRRtintRRt RuntimeError( tAtbtmtntwtzztindextxtrnormtmode((s2/tmp/pip-build-X4mzal/scipy/scipy/optimize/nnls.pyR s* N( t __future__RRRtRtnumpyRRRt__all__R(((s2/tmp/pip-build-X4mzal/scipy/scipy/optimize/nnls.pyts