py4design.pyoptimise package

Module contents

Pyoptimise

Documentation is available in the docstrings and online at http://chenkianwee.github.io/py4design/

Submodules

analyse_xml                  --- Functions for analysing the generated xml from the optimisation.
                                 dependencies: scipy, numpy, scikit-learn, pymf
draw_graph                   --- Functions for drawing graphs.
                                 dependencies: matplotlib
nsga2                        --- Classes and functions for performing NSGA2 optimisation.
py4design.pyoptimise.empty_xml_files(xml_filelist)

This function empties all the xml files.

Parameters:

xml_filelist : list of str

The list of xml files to be emptied.
py4design.pyoptimise.create_nsga2_population_class(gene_dict_list, score_dict_list, mutation_rate, crossover_rate, init_population, live_file, dead_file)

This function creates a population class.

Parameters:

gene_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a Gene class instance. Each dictionay is in this format: {“type”: “int_range”, “range”: (0,4,1)}.

score_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a ScoreMeta class instance. Each dictionay is in this format: {“name”: “solar”, “minmax”: “min”}.

mutation_rate : float

The mutation probability, the probability is between 0 to 1. The usual mutation probability is about 0.01.

crossover_rate : float

The crossover rate, the rate is between 0 to 1. The usual crossover rate is about 0.8.

init_population : int

The population size. The usual size is about 100.

live_file : str

The file path of the XML file that documents all the living individuals.

dead_file : str

The file path of the XML file that documents all the dead individuals.
Returns:

population : Population class instance

The created population class instance.
py4design.pyoptimise.initialise_nsga2(gene_dict_list, score_dict_list, mutation_rate, crossover_rate, init_population, live_file, dead_file)

This function initialises the population and writes the xml files for an NSGA2 optimisation process.

Parameters:

gene_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a Gene class instance. Each dictionay is in this format: {“type”: “int_range”, “range”: (0,4,1)}.

score_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a ScoreMeta class instance. Each dictionay is in this format: {“name”: “solar”, “minmax”: “min”}.

mutation_rate : float

The mutation probability, the probability is between 0 to 1. The usual mutation probability is about 0.01.

crossover_rate : float

The crossover rate, the rate is between 0 to 1. The usual crossover rate is about 0.8.

init_population : int

The population size. The usual size is about 100.

live_file : str

The file path of the XML file that documents all the living individuals.

dead_file : str

The file path of the XML file that documents all the dead individuals.
Returns:

population : Population class instance

The created population class instance.
py4design.pyoptimise.resume_nsga2(gene_dict_list, score_dict_list, mutation_rate, crossover_rate, init_population, live_file, dead_file)

This function resumes a broken NSGA2 optimisation process based on the dead xml file.

Parameters:

gene_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a Gene class instance. Each dictionay is in this format: {“type”: “int_range”, “range”: (0,4,1)}.

score_dict_list : list of dictionaries

Each dictionary contains the parameters for creating a ScoreMeta class instance. Each dictionay is in this format: {“name”: “solar”, “minmax”: “min”}.

mutation_rate : float

The mutation probability, the probability is between 0 to 1. The usual mutation probability is about 0.01.

crossover_rate : float

The crossover rate, the rate is between 0 to 1. The usual crossover rate is about 0.8.

init_population : int

The population size. The usual size is about 100.

live_file : str

The file path of the XML file that documents all the living individuals.

dead_file : str

The file path of the XML file that documents all the dead individuals.
Returns:

population : Population class instance

The resumed population class instance.
py4design.pyoptimise.feedback_nsga2(population)

This function performs the feedback process of a population.

Parameters:

population : Population class instance

The function will perform the reproduction on this population and generate a new generation of individuals.