nimo.ai_tools package

nimo.ai_tools.ai_tool_blox module

class nimo.ai_tools.ai_tool_blox.BLOX(input_file, output_file, num_objectives, num_proposals, output_res)

Bases: object

Class of BLOX

This class can select the next candidates by random exploration.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for BLOX. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_bomp module

class nimo.ai_tools.ai_tool_bomp.BOMP(input_file, output_file, num_objectives, num_proposals, physbo_score, minimization, process_X, output_res, training_res)

Bases: object

Class of BOMP

This class can select the next candidates by Bayesian optimization based on PHYSBO package.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for PHYSBO. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Main function to select the proposals by AI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_combi module

class nimo.ai_tools.ai_tool_combi.COMBI(input_file, output_file, num_objectives, num_proposals, physbo_score, minimization, combi_ranges, spread_elements)

Bases: object

Class of BOCOMBI

This class can select the next candidates by Bayesian optimization based on PHYSBO package.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for PHYSBO with inclination. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Main function to select the proposals by AI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_es module

class nimo.ai_tools.ai_tool_es.ES(input_file, output_file, num_objectives, num_proposals)

Bases: object

Class of ES

This class can select the next candidates by exhaustive search.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for RE. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_pdc module

class nimo.ai_tools.ai_tool_pdc.PDC(input_file, output_file, num_objectives, num_proposals, pdc_estimation, pdc_sampling, output_res)

Bases: object

Class of PDC

This class can select the next candidates by phase diagram construction.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for PDC. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_physbo module

class nimo.ai_tools.ai_tool_physbo.PHYSBO(input_file, output_file, num_objectives, num_proposals, physbo_score, minimization, output_res, training_res)

Bases: object

Class of PHYSBO

This class can select the next candidates by Bayesian optimization based on PHYSBO package.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for PHYSBO. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Main function to select the proposals by AI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_ptr module

class nimo.ai_tools.ai_tool_ptr.PTR(input_file, output_file, num_objectives, num_proposals, ptr_ranges, output_res)

Bases: object

Class of PTR

This class can select the next candidates by random exploration.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for BLOX. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_re module

class nimo.ai_tools.ai_tool_re.RE(input_file, output_file, num_objectives, num_proposals, process_X, re_seed)

Bases: object

Class of RE

This class can select the next candidates by random exploration.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for RE. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_rsvm module

class nimo.ai_tools.ai_tool_rsvm.RSVM(input_file, output_file, num_objectives, num_proposals, other_datasets, minimization, output_res)

Bases: object

Class of RSVM

This class can select the next candidates by rank SVM.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for RSVM. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.

nimo.ai_tools.ai_tool_slesa_WAM module

class nimo.ai_tools.ai_tool_slesa_WAM.SLESA_WAM(input_file, num_discretize=None, y_plot_range=None)

Bases: object

Class of SLESA WAM

This class can select the next candidates by random exploration.

calculation()

Calculation of WAM

Returns:: True (str) for success.

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

nimo.ai_tools.ai_tool_slesa module

class nimo.ai_tools.ai_tool_slesa.SLESA(input_file, output_file, num_objectives, num_proposals, slesa_beta_max, slesa_beta_num, re_seed, output_res)

Bases: object

Class of SLESA

This class can select the next candidates by random exploration.

calc_ai(t_train, X_all, train_actions, test_actions)

Calculating the proposals by AI algorithm

This function is for BLOX. This function do not depend on robot. If the new AI alborithm is developed, this function is only changed.

Parameters:

t_train (list[float]) – the list where observed objectives are stored
X_all (list[float]) – the list where all descriptors are stored
train_actions (list[float]) – the list where observed actions are stored
test_actions (list[float]) – the list where test actions are stored

Returns:

the list where the selected actions are stored

Return type:

actions (list[int])

load_data()

Loading candidates

This function do not depend on robot.

Returns:: the list where observed objectives are stored X_all (list[float]): the list where all descriptors are stored train_actions (list[float]): the list where observed actions are stored test_actions (list[float]): the list where test actions are stored
Return type:: t_train (list[float])

select()

Selecting the proposals by MI algorithm

This function do not depend on robot.

Returns:: True (str) for success.