Package specific_analyses :: Package model_free :: Module optimisation :: Class MF_minimise_command
[hide private]
[frames] | no frames]

Class MF_minimise_command

source code


Command class for standard model-free minimisation.

Instance Methods [hide private]
 
__init__(self)
Initialise the base class.
source code
tuple of numpy array, float, int, int, int, int, str
optimise(self)
Model-free optimisation.
source code
 
run(self, processor, completed)
Setup and perform the model-free optimisation.
source code
 
store_data(self, data, opt_params)
Store all the data required for model-free optimisation.
source code

Inherited from multi.slave_commands.Slave_command: set_memo_id

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __str__, __subclasshook__

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self)
(Constructor)

source code 

Initialise the base class.

Overrides: object.__init__

optimise(self)

source code 

Model-free optimisation.

Returns: tuple of numpy array, float, int, int, int, int, str
The optimisation results consisting of the parameter vector, function value, iteration count, function count, gradient count, Hessian count, and warnings.

run(self, processor, completed)

source code 

Setup and perform the model-free optimisation.

Parameters:
  • processor - The slave processor the command is running on. Results from the command are returned via calls to processor.return_object.
  • completed - The flag used in batching result returns to indicate that the sequence of batched result commands has completed. This value should be returned via the last result object retuned by this method or methods it calls. All other Result_commands should be initialised with completed=False. This is an optimisation to prevent the sending an extra batched result queue completion result command being sent, it may be an over early optimisation.
Overrides: multi.slave_commands.Slave_command.run

store_data(self, data, opt_params)

source code 

Store all the data required for model-free optimisation.

Parameters:
  • data (class instance) - The data used to initialise the model-free target function class.
  • opt_params (class instance) - The parameters and data required for optimisation using minfx.