a ja+@sdZddlZddlZddlZddlZddlmZm Z m Z m Z m Z ddl mZddlmZgZddZGd d d ZdddZdS)zTrust-region optimization.N)_check_unknown_options_status_messageOptimizeResult_prepare_scalar_function_call_callback_maybe_halt)HessianUpdateStrategy) FD_METHODScs.dgdurdfSfdd}|fS)Nrcs*dd7<t|g|RS)Nrr)npcopy)xZ wrapper_argsargsfunctionZncallsAE:\soccer\ml_env\Lib\site-packages\scipy/optimize/_trustregion.pyfunction_wrappersz(_wrap_function..function_wrapperr)rrrrr r_wrap_functions rc@sjeZdZdZdddZddZeddZed d Zed d Z d dZ eddZ ddZ ddZ dS)BaseQuadraticSubproblemaQ Base/abstract class defining the quadratic model for trust-region minimization. Child classes must implement the ``solve`` method. Values of the objective function, Jacobian and Hessian (if provided) at the current iterate ``x`` are evaluated on demand and then stored as attributes ``fun``, ``jac``, ``hess``. NcCsF||_d|_d|_d|_d|_d|_d|_||_||_||_ ||_ dSN) _x_f_g_h_g_magZ _cauchy_pointZ _newton_point_fun_jac_hess_hessp)selfr funjachesshessprrr__init__(sz BaseQuadraticSubproblem.__init__cCs*|jt|j|dt|||S)Ng?)r r dotr!r#rprrr__call__5sz BaseQuadraticSubproblem.__call__cCs|jdur||j|_|jS)z1Value of objective function at current iteration.N)rrrrrrrr 8s zBaseQuadraticSubproblem.funcCs|jdur||j|_|jS)z=Value of Jacobian of objective function at current iteration.N)rrrr)rrrr!?s zBaseQuadraticSubproblem.jaccCs|jdur||j|_|jS)zrrrrrs     rr?@@333333?-C6?FTc# szt||durtd|dur0|dur0td|dur@tdd| krTdks^ntd|dkrntd|dkr~td ||krtd t|}t|||||d j}j}t |rʈj }n6t |rn,|t vst |t rd}fd d }ntdt||\}}| dur$t|d} d}|}|}| r<|g}||||||}d}|j| krz||\}}Wn"tjjyd}YqYn0||}||}||||||}|j|j}|j|}|dkrd}q||}|dkr|d9}n|dkr|rtd||}|| kr&|}|}| r<|t||d7}t||jd} t|| rbq|j| krvd}q|| krPd}qqPtdtdddf}!| r|dkrt|!|ntj|!|tddtd|jtd|tdjtdjtdj |dt||dk||j|j!jjj |d||!|d }"|durh|j |"d<| rv||"d <|"S)!a Minimization of scalar function of one or more variables using a trust-region algorithm. Options for the trust-region algorithm are: initial_trust_radius : float Initial trust radius. max_trust_radius : float Never propose steps that are longer than this value. eta : float Trust region related acceptance stringency for proposed steps. gtol : float Gradient norm must be less than `gtol` before successful termination. maxiter : int Maximum number of iterations to perform. disp : bool If True, print convergence message. inexact : bool Accuracy to solve subproblems. If True requires less nonlinear iterations, but more vector products. Only effective for method trust-krylov. This function is called by the `minimize` function. It is not supposed to be called directly. Nz7Jacobian is currently required for trust-region methodsz_Either the Hessian or the Hessian-vector product is currently required for trust-region methodszBA subproblem solving strategy is required for trust-region methodsrg?zinvalid acceptance stringencyz%the max trust radius must be positivez)the initial trust radius must be positivez?the initial trust radius must be less than the max trust radius)r!r"rcs||Sr)r"r%)r r'rZsfrrr#sz%_minimize_trust_region..hesspr-g?r)r r successmaxiterz:A bad approximation caused failure to predict improvement.z3A linalg error occurred, such as a non-psd Hessian.) stacklevelz# Current function value: %fz Iterations: %dz! Function evaluations: %dz! Gradient evaluations: %dz Hessian evaluations: %d) r rKstatusr r!nfevZnjevnhevnitmessager"allvecs)"r ValueError Exceptionr Zasarrayflattenrr Zgradcallabler"r isinstancerrlenr,r>r+Z LinAlgErrorminappendr rrrprintwarningswarnRuntimeWarningrOZngevrPr!)#r Zx0rr!r"r#Z subproblemZinitial_trust_radiusZmax_trust_radiusetaZgtolrLZdispZ return_allcallbackZinexactZunknown_optionsZnhesspZwarnflagr6r rSmkr'Z hits_boundaryZpredicted_valueZ x_proposedZ m_proposedZactual_reductionZpredicted_reductionrhoZintermediate_resultZstatus_messagesresultrrHr_minimize_trust_regionvs                  rf)rNNNNrDrErFrGNFFNT)rBr0r]numpyr Z scipy.linalgr* _optimizerrrrrZ'scipy.optimize._hessian_update_strategyrZ(scipy.optimize._differentiable_functionsr __all__rrrfrrrrs   X