3. API pymetamodels (main class object)

Load main pymetamodels class as follow:

1import pymetamodels
2
3### Load main object
4mita = pymetamodels.metamodel()
5
6### Load main object (alternative)
7mita = pymetamodels.load()

and start building your metamodel and analysis

3.1. Class -> pymetamodels (functions)

pymetamodels.load()[source]
Synopsis:

  • Returns an empty metamodel() object

Args:

  • None

Optional parameters:

  • None

Returns:

  • Returns an empty metamodel() object

Note

  • Is equivalent to mita = pymetamodels.metamodel()


pymetamodels.newconf()[source]
Synopsis:

  • Returns an empty objconf() object

Args:

  • None

Optional parameters:

  • None

Returns:

  • Returns a new objconf() object

Note

  • Is equivalent to mita = pymetamodels.metamodel().objconf()


3.2. Class -> pymetamodels

class pymetamodels.metamodel[source]

Python class to perform design of experiments, analysis, metamodels and optimizations

Platform:

Windows

Synopsis:

object definition of optimization variables, read and save from Excel files, sensitivity analysis

Dependences:

numpy, SALib, sklearn, scipy, xlrd, xlwt

Variables:

  • case – global data object case

  • plt – object plot


logging_start(logging_path)[source]
Synopsis:

  • Initialize the logging to a external file named as logging_pymetamodels.log

Args:

  • logging_path: the output folder path to the logging

Optional parameters:

  • None

Returns:

  • If the path exists

Note


keys()[source]
Synopsis:

  • Return the list of names and id cases

Args:

  • None

Optional parameters:

  • None

Returns:

  • List of names and id cases

Note


objconf()[source]
Synopsis:

  • Return the objconf object for programatically build the configuration spreadsheet

Args:

  • None

Optional parameters:

  • None

Returns:

  • objconf object

Note


obj_samplig_sensi()[source]
Synopsis:

  • Return the objsamplingsensitivity object

Args:

  • None

Optional parameters:

  • None

Returns:

  • objsamplingsensitivity object

Note


sensitivity_type(case)[source]
Synopsis:

  • Returns the sensitivity type analysis

Args:

  • None

Optional parameters:

  • None

Returns:

  • sensitivity type analysis name string

Note


run_sampling_routine(case)[source]
Synopsis:

  • Execute the sampling routines to generate the DOEX for each case

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • None

Note


run_sensitivity_analisis(case)[source]
Synopsis:

  • Execute the sensitivity analysis routines to generate the sensitivity indexes S_i

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • None

Note


run_sensitivity_normalization()[source]
Synopsis:

  • Execute the normalization of the sensitivity indexes

Args:

  • None

Optional parameters:

  • None

Returns:

  • Adds to the metamodel data structure the sensitivity indexes normalize

Note

  • See tutorials Tutorials

  • This calculation is performed as described by Nguyen [NR15]


run_metamodel_construction(case, scheme=None, with_test=True)[source]
Synopsis:

  • Execute the metamodelling regression routines to generate a predictor of DOEY values

Args:

  • case: case name to be execute

Optional parameters:

  • scheme=None: designate the type of metamodel search scheme that will be carried out to find the most optimal ML metamolde. The available schemes are: None, general, general_fast, general_fast_nonpol, linear, gaussian, polynomial (see Section 2.3)

  • with_test = True: use doeX_test and doeY_test as test data, if not available split the train data into split and train data (by 0.35)

Returns:

  • None

Note


obj_metamodel(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the train metamodel object (see objmetamodel())

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

Note


save_metamodel(folder_path, case)[source]
Synopsis:

  • Save metamodels objects as a .metaita file which can be later read

  • .metaita files are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the files

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Path to the file

Note


load_metamodel(folder_path, case)[source]
Synopsis:

  • Load metamodels object as a .metaita file for each case with the function save_metamodel()

Args:

  • folder_path: path to the folder where to save the files

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • True if the metamodel was loaded

Note


obj_optimization(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the optimization object (see objoptimization())

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

Note


save_optimization(folder_path, case)[source]
Synopsis:

  • Save the optimization data as a .optita file which can be later read

  • .optita files are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the files

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Path to the file

Note


load_optimization(folder_path, case)[source]
Synopsis:

  • Load optimization object as a .optita file for each case

Args:

  • folder_path: path to the folder where to save the files

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • True if the optimization was loaded

Note


run_optimization_problem(case, scheme=None, max_size_grid_methods=None, rel_tol_val_grid_methods=None, verbose_testing=False)[source]
Synopsis:

  • Execute optimization problem routines for a case according the configuration spreadsheet

Args:

  • case: case name to be execute

Optional parameters:

  • scheme = None: designate the type of optimization solver scheme that will be carried out (see Section 2.4). The availables schemes are: “general”, “general_fast”, “general_with_constrains”, “global”, “minimize”, “grid_method”, “iter_grid_method”

  • max_size_grid_methods = None: value for max_size_grid_methods ivar, diemsion of the grid for grid methods

  • rel_tol_val_grid_methods = None: tolerance value for rel_tol_val_grid_methods ivar, tolerance of the iterative maximum error

  • verbose_testing = False: verbose routines messages

Returns:

  • None

Note


print_structure(case=None)[source]
Synopsis:

  • Recursively data object structure case and all the nested data objects dictionaries

Args:

  • dictionary: dictionary object to recursively be printed

Optional parameters:

  • case: case name to be execute, if None prints the full case object

Returns:

  • None

Note


vars_parameter_matrix(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the parameters values for each input variables from the metamodel configuration

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Pointer to data structure object correspoding to the parameters values for each input variable from the metamodel configuration

Note


vars_out_parameter_matrix(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the parameters values for each output variables from the metamodel configuration

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Pointer to data structure object correspoding to the parameters values for each output variable from the metamodel configuration

Note


doeX(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the DOEX inputs variable arrays

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Pointer to data structure object correspoding to the DOEX

Note


doeY(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the DOEY output variables arrays

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Pointer to data structure object correspoding to the DOEY

Note


SiY(case)[source]
Synopsis:

  • Returns a data structure object correspoding to the results for the sensitivity analysis values

Args:

  • case: case name to be execute

Optional parameters:

  • None

Returns:

  • Pointer to data structure object correspoding to the results for the sensitivity analysis values

Note


read_xls_case(folder_path, file_name, sheet='cases', col_start=0, row_start=1, tit_row=0)[source]
Synopsis:

  • Read metamodel configuration spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

  • sheet: sheet name with the cases description

Optional parameters:

  • col_start = 0: the columm number where the data starts

  • row_start = 1: the row number where the data starts

  • tit_row = 0: the row number where the titles start

Returns:

  • None

Note


output_xls(folder_path, file_name, col_start=0, tit_row=0)[source]
Synopsis:

  • Output DOEX, DOEY and analysis data into a spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

Optional parameters:

  • col_start = 0: the columm number where the data starts

  • row_start = 1: the row number where the data starts

Returns:

  • The path to the xls spreadsheet

Note

  • See tutorials Tutorials

  • It is limit to DOE with a maximun size of 65500 samples. For larger values save directly to csv


save_tofile_DOEX(folder_path, file_name)[source]
Synopsis:

  • Save DOEX into a spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

Optional parameters:

  • None

Returns:

  • The path to the xls spreadsheet

Note


read_fromfile_DOEX(folder_path, file_name)[source]
Synopsis:

  • Read DOEX from a spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

Optional parameters:

  • None

Returns:

  • The path to the xls spreadsheet

Note


save_tofile_DOEY(folder_path, file_name)[source]
Synopsis:

  • Save DOEY into a spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

Optional parameters:

  • None

Returns:

  • The path to the xls spreadsheet

Note


read_fromfile_DOEY(folder_path, file_name)[source]
Synopsis:

  • Read DOEY from a spreadsheet in xls format

Args:

  • folder_path: path to xls spreadsheet

  • file_name: xls spreadsheet file name

Optional parameters:

  • None

Returns:

  • The path to the xls spreadsheet

Note


output_plts_sensitivity(folder_path, case, use_alias_as_vars=False)[source]
Synopsis:

  • Plots all cross DOEX variable sampling combinations and sensitivity analisys

  • Plots sensitivity histograms for each case

  • Plots are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the plots images

  • case: case name to be execute

Optional parameters:

  • use_alias_as_vars: use alias names as variable names

Returns:

  • Saves in the folder_path location the plots regarding the sensitivity analysis

Note


output_plts_models_XY(folder_path, case, use_alias_as_vars=False)[source]
Synopsis:

  • XY 2D scatter plots of the DOEY variables versus DOEX variables

  • Plots are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the plots images

  • case: case name to be execute

Optional parameters:

  • use_alias_as_vars: use alias names as variable names

Returns:

  • Saves in the folder_path location the plots regarding the XY plots of the DOEY variables versus DOEX variables

Note


output_plts_models_XYZ(folder_path, case, default_other_vars_level=0.5, text_annotation=True, scatter=False, use_alias_as_vars=False)[source]
Synopsis:

  • XYZ 3D scatter plots of the DOEY variables versus DOEX variables

  • Plots are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the plots images

  • case: case name to be execute

Optional parameters:

  • default_other_vars_level = 0.5: range fraction for non doeX X,Y variables

  • text_annotation = True: switch on and off the text annotation regarding default_other_vars_level

  • scatter = True: show scatter plot

  • use_alias_as_vars: use alias names as variable names

Returns:

  • Saves in the folder_path location the plots regarding the XY plots of the DOEY variables versus DOEX variables

Note

  • Non X,Y plots variables values are compute according var default_other_vars_level

  • See tutorials Tutorials or Tutorial A03


output_plts_models_residuals_plot(folder_path, case, use_alias_as_vars=False)[source]
Synopsis:

  • XY 2D scatter plots of the residual values, DOEY varibles metamodel predictions ploted versus DOEY variable values

  • Plots are placed in a sub-folder of the output folder

Args:

  • folder_path: path to the folder where to save the plots images

  • case: case name to be execute

Optional parameters:

  • use_alias_as_vars: use alias names as variable names

Returns:

  • Saves in the folder_path location the residual values, DOEY varibles predictions ploted versus DOEY variable values

Note


print_dict(dictionary, ident='', braces=1)[source]
Synopsis:

  • Recursively prints nested dictionaries

Args:

  • dictionary: dictionary object to recursively be printed

Optional parameters:

  • ident: identificator string

  • braces: number of braces

Returns:

  • None

Note


3.3. Class -> objconf

Load the programmatically configuration spreadsheet builder as follows:

1import pymetamodels
2
3### Load main object (alternative)
4mita = pymetamodels.load()
5
6### Load objconf object
7conf = mita.objconf()

and start building your configuration spreadsheet

class obj_conf.objconf(model)[source]

Python class to build programatically the configuration spreadsheet

Platform:

Windows

Synopsis:

to build programatically the pymetamodels configuration spreadsheet

Dependences:

Excel©, xlrd, xlwt, numpy


start(folder_path, file_name)[source]
Synopsis:

  • Initialise the objconf with the file and path name

Args:

  • folder_path: folder path

  • file_name: conf file name without extension

Optional parameters:

  • None

Returns:

  • None

Note


add_case(case_name, vars_sheet, output_sheet, samples, sensitivity_method, comment=None, others={}, force_overwrite=False)[source]
Synopsis:

  • Adds a new entry to the cases sheet

Args:

  • case_name: name and id of the case, is a unique key value

  • vars_sheet: name and id of the sheet where are described the input vars for the given case

  • output_sheet: name and id of the sheet where are described the output vars for the given case

  • samples: number of samples for the sampling activities (\(2^N \ values\))

  • sensitivity_method: name and id of the sensitivity analysis method (see Section 2.2)

Optional parameters:

  • comment = None: comment for the given case

  • others = {}: dictionary with other variables

  • force_overwrite = False: force over writting case_name data

Returns:

  • True if the action was possible, False if the key case_name already exist

Note


add_vars_sheet_variable(vars_sheet, variable, value, min, max, distribution, is_range, cov_un, ud, alias, comment=None, others={}, force_overwrite=False)[source]
Synopsis:

  • Adds a new entry to the input variable to the vars_sheet

Args:

  • vars_sheet: name and id of the sheet where are described the input vars for the given case

  • variable: name and id of the input variable, is a unique key value

  • value: nominal value of the input variable, use in case is not considered a ranged variable in the DOEX

  • min: min value of the ranged variable in the DOEX

  • max: max value of the ranged variable in the DOEX

  • distribution: type of range distribution (unif, triang, norm, lognorm)

  • is_range: TRUE or FALSE value to choose if the variable is a range or a single value in the DOEX

  • cov_un: covariance used for the generation of the norm distributions

  • ud: units name for the variable (i.e. [m])

  • alias: alias name for the variable

Optional parameters:

  • comment = None: comment for the given case

  • others = {}: dictionary with other variables

  • force_overwrite = False: force over writting variable data

Returns:

  • None

Note


add_output_sheet(output_sheet, variable, value, ud, array, op_min, op_min_0, ineq_0, eq_0, alias, comment=None, others={}, force_overwrite=False)[source]
Synopsis:

  • Adds a new entry to the output vars case sheet

Args:

  • output_sheet: name and id of the sheet where are described the output vars for the given case

  • variable: name and id of the output variable, is a unique key value

  • value: nominal value of the output variable

  • ud: units name for the variable (i.e. [m])

  • array: TRUE or FALSE, is the output variable an array or single value

  • op_min: TRUE if variable is to be minimize, \(min(DOEY_{var})\)

  • op_min_0: TRUE if variable is to be optimize to 0, \(objective(DOEY_{var}=0)\)

  • ineq_0: TRUE if variables is consider for an inequality constrain, \(DOEY_{var}>=0\)

  • eq_0: TRUE if variables is consider for an equality constrain =0, \(DOEY_{var}=0\)

  • alias: alias name for the variable

Optional parameters:

  • comment = None: comment for the given case

  • others = {}: dictionary with other variables

  • force_overwrite = False: force over writting variable data

Returns:

  • None

Note


check_consistency()[source]
Synopsis:

  • Check consistency between cases, the input vars case sheet and the output vars case sheet

Args:

  • None

Optional parameters:

  • None

Returns:

  • True if pass or list of text messages

Note


save_conf()[source]
Synopsis:

  • Save the configuration to a file

Args:

  • None

Optional parameters:

  • None

Returns:

  • True or False if errors

Note


read_xls_sheet_to_dict(folder_path, file_name, sheet_name, col_start=0, row_title=0, units=False)[source]
Synopsis:

  • Load excel sheet (in .xls format) into a dictionary of arrays

  • The format is each column is a data channel or array of data

  • First row is the channel names

  • Second row is the units names

Args:

  • folder_path: the folder path name

  • file_name: file name of the coupons file (type xls)

  • sheet_name: sheet name with the channel list or array of data

Optional parameters:

  • col_start = 0: first column

  • row_title = 0: first row

  • units = False: does the sheet con tain a second row of units

Returns:

  • (dct, dct_units): (dictionary, dictionary of units)

Note

  • None


save_dict_to_xls_sheet(folder_path, file_name, sheet_name, data_dict, col_start=0, row_title=0, dict_units=None, add_row_under_units=None, overwrite=True)[source]
Synopsis:

  • Save a dictionary of arrays (see read_xls_sheet_to_dict()) into a excel sheet (in .xls format)

  • The format is each column is a data channel or array of data

  • First row is the channel names

  • Second row is the units names

Args:

  • folder_path: the folder path name

  • file_name: file name of the coupons file (type xls)

  • sheet_name: sheet name with the channel list or array of data

  • data_dict: dictionary of units per channel

Optional parameters:

  • col_start = 0: first column

  • row_title = 0: first row

  • dict_units = None:

  • add_row_under_units = None: value of a third row under the units

  • overwrite = True: overwrites the file creating a new one with the same name or updates the file if it exists

Returns:

  • None

Note

  • None


3.4. Class -> objsamplingsensitivity

Access to the sampling and sensitivity object:

1import pymetamodels
2
3### Load main object (alternative)
4mita = pymetamodels.load()
5
6### Load obj_samplig_sensi object
7conf = mita.obj_samplig_sensi()
class obj_sampling_sensitivity.objsamplingsensitivity(model)[source]

Python class representing the sampling and sensitivity analysis

Platform:

Windows

Synopsis:

object optimization calculation

Dependences:

SALib

Variables:

  • version – optimization model version

  • conf_level – the confidence interval level (default 0.95)

Note


3.5. Class -> objmetamodel

Represent the metamodel constructed with the DOEX and DOEY for each case and predict new values.

class obj_metamodel.objmetamodel(logging_path=None)[source]

Python class representing a metamodel object train with doeX and doeY data

Platform:

Windows

Synopsis:

object train with doeX and doeY data

Dependences:

numpy, sklearn

Variables:

  • tol – (default 0.0001) metamodel training tolerance

  • eps – (default 0.0001) metamodel training eps value for

  • n_alphas – (default 200) metamodel training eps value for

  • random_state – (default True) activate the random state generation (bool)

Note

  • The training is based on kriging, polynomial and regressor methods

  • See tutorials Tutorials and for example tutorial A3


save_to_file(folder, file_name)[source]
Synopsis:

  • Save the metamodel object to a file with .metaita extension

Args:

  • folder: folder path

  • file_name: file name

Optional parameters:

  • None

Returns:

  • The file path

Note


load_file(file_path)[source]
Synopsis:

  • Loads the metamodel object from a file with .metaita extension

Args:

  • file_path: path to the file

Optional parameters:

  • None

Returns:

  • None

Note


fit_model(doeX_train, doeY_train, var_keysX, var_keysY, doeX_test=None, doeY_test=None, scheme=None, with_test=True)[source]
Synopsis:

  • Execute the metamodelling regression fitting routines to generate a predictor of DOEY values choosing the best ME model

Args:

  • doeX_train: numpy array representing the doeX (nsamplesxnfeatures) for performing the training

  • doeY_train: numpy array representing the doeY (ntargetsxnfeatures) for performing the training

  • var_keysX: list of doeX variable names

  • var_keysY: list of doeY variable names

Optional parameters:

  • doeX_test = None: numpy array representing the doeX (nsamplesxnfeatures) for performing the evaluation

  • doeY_test = None: numpy array representing the doeY (ntargetsxnfeatures) for performing the evaluation

  • scheme: designate the type of metamodel search scheme that will be carried out to find the most optimal ML metamolde. The available schemes are: None, general, general_fast, general_fast_nonpol, linear, gaussian, polynomial (see Section 2.3)

  • with_test = True: use doeX_test and doeY_test as test data, if not available split the train data into split and train data (by 0.35)

Returns:

  • None

Note


predict(doeX_predict)[source]
Synopsis:

  • Execute the metamodelling regression fitting routines to generate a predictor of DOEY values choosing the best modelling strategy

Args:

  • doeX_predict: numpy array representing the doeY (ntargetsxnfeatures) for performing the prediction

Optional parameters:

  • None

Returns:

  • None

Note


predict_1D(var_target, lst_var_features)[source]
Synopsis:

  • Execute the metamodelling regression fitting routines to generate a predictor of DOEY values choosing the best modelling strategy

  • Data is input as a 1D list of varibles values

Args:

  • var_target: var name to predict the value

  • lst_var_features: list of values ordered as varX labels

Optional parameters:

  • None

Returns:

  • Prediction for var_target

Note


score_doeY_target(doeX_test, doeY_test, var_target)[source]
Synopsis:

  • Execute the regression of the origin values versus predicted ones

  • Obtains the regression score of the var_target prediction

Args:

  • doeX_test = None: numpy array representing the doeX (nsamplesxnfeatures) for performing the evaluation

  • doeY_test = None: numpy array representing the doeY (ntargetsxnfeatures) for performing the evaluation

  • var_target: var name to predict the value

Optional parameters:

  • None

Returns:

  • (varY_predict, varY_values, score, varY_predict_line)

  • varY_predict: var_target array predicted values

  • varY_values: var_target values

  • score: score of var_target array predicted values versus var_target values regression

  • varY_predict_line: var_target array predicted values with line regression

Note


property doeX_np_shape

Shape of the trained doeX

Getter:

Returns train doeX shape

Type:

tuple


property doeY_np_shape

Shape of the trained doeY

Getter:

Returns train doeY shape

Type:

tuple


property doeX_varX

List of var names corresponding to the trained doeX

Getter:

Returns list of var names corresponding to the trained doeX

Type:

tuple


property doeY_varY

List of var names corresponding to the trained doeY

Getter:

Returns list of var names corresponding to the trained doeY

Type:

tuple


property metamodel_score

Metamodel score value

Getter:

Returns the metamodel score value

Type:

float


3.6. Class -> objoptimization

Represent the optimization problem solution based on a constructed metamodel.

class obj_optimization.objoptimization(logging_path=None)[source]

Python class representing the optimization calculation

Platform:

Windows

Synopsis:

object optimization calculation

Dependences:

numpy, scipy

Variables:

  • version – optimization model version

  • tol – (default 1e-6) optimization methods tolerance value

  • rel_tol_val_grid_methods – (default 5e-4) optimization grid methods tolerance value

  • max_size_grid_methods – (default 5e-3) optimization grid methods max size of the grid

  • tolerance_check_bounds_constrains – (default 1e-3) tolerance to check bounds and contrains limits

Note


property min_fun

Min value of objective function found

Getter:

Returns Min value of objective function found

Type:

float


property DOEX_min_func

DOEX array of Min value of objective function

Getter:

Returns DOEX array of Min value of objective function

Type:

array


property min_func_model

Optimization model use for Min value of objective function

Getter:

Returns Optimization model

Type:

string


property DOEY_min_func

DOEY array of Min value of objective function

Getter:

Returns DOEY array of Min value of objective function

Type:

array


property doeX_varX

List of var names corresponding to the optimized doeX

Getter:

Returns list of var names corresponding to the optimized doeX

Type:

tuple


property doeY_varY

List of var names corresponding to the optimized doeY

Getter:

Returns list of var names corresponding to the optimized doeY

Type:

tuple


save_to_file(folder, file_name)[source]
Synopsis:

  • Save the optimization data to a file with .optita extension

Args:

  • folder: folder path

  • file_name: file name

Optional parameters:

  • None

Returns:

  • The file path

Note


load_file(file_path)[source]
Synopsis:

  • Loads the optimization data to a file with .optita extension

Args:

  • file_path: path to the file

Optional parameters:

  • None

Returns:

  • None

Note


run_optimization(obj_metamodel, min_vars, type_op_min, bounds, constrains_vars=None, scheme=None)[source]
Synopsis:

  • Execute the optimization routines to minimize a DOEY metamodel variable

Args:

  • obj_metamodel: metamodel object

  • min_var: variable to be minimize

  • type_op_min: type variable to be minimize 1: minimize 2:equal to zero

  • bounds: DOEX variables bounds

Optional parameters:

  • constrains_vars = None:

  • scheme=None: scheme method to be applied. The availables schemes are: “general”, “general_fast”, “general_with_constrains”, “global”, “minimize”, “grid_method”, “iter_grid_method”

Returns:

  • None

Note