CQERG

class pystoned.CQERG.CERG(y, x, tau, z=None, cet='addi', fun='prod', rts='vrs')[source]

Convex expectile regression (CER) with Genetic algorithm

__init__(y, x, tau, z=None, cet='addi', fun='prod', rts='vrs')[source]

CERG model

Parameters:
  • y (float) – output variable.

  • x (float) – input variables.

  • tau (float) – quantile.

  • z (float, optional) – Contextual variable(s). Defaults to None.

  • cet (String, optional) – CET_ADDI (additive composite error term) or CET_MULT (multiplicative composite error term). Defaults to CET_ADDI.

  • fun (String, optional) – FUN_PROD (production frontier) or FUN_COST (cost frontier). Defaults to FUN_PROD.

  • rts (String, optional) – RTS_VRS (variable returns to scale) or RTS_CRS (constant returns to scale). Defaults to RTS_VRS.

display_alpha()[source]

Display alpha value

display_beta()[source]

Display beta value

display_lamda()[source]

Display lamda value

display_negative_residual()[source]

Dispaly negative residual value

display_positive_residual()[source]

Dispaly positive residual value

display_residual()[source]

Dispaly residual value

display_status()[source]

Display the status of problem

get_alpha()[source]

Return alpha value by array

get_beta()[source]

Return beta value by array

get_blocks()[source]

Return the number of blocks

get_frontier()[source]

Return estimated frontier value by array

get_lamda()[source]

Return beta value by array

get_negative_residual()[source]

Return negative residual value by array

get_positive_residual()[source]

Return positive residual value by array

get_predict(x_test)[source]

Return the estimated function in testing sample

get_residual()[source]

Return residual value by array

get_runningtime()[source]

Return the running time

get_status()[source]

Return status

get_totalconstr()[source]

Return the number of total constraints

optimize(email='local', solver=None)[source]

Optimize the function by requested method

class pystoned.CQERG.CQRG(y, x, tau, z=None, cet='addi', fun='prod', rts='vrs')[source]

Convex quantile regression (CQR) with Genetic algorithm

__init__(y, x, tau, z=None, cet='addi', fun='prod', rts='vrs')[source]

CQRG model

Parameters:
  • y (float) – output variable.

  • x (float) – input variables.

  • tau (float) – quantile.

  • z (float, optional) – Contextual variable(s). Defaults to None.

  • cet (String, optional) – CET_ADDI (additive composite error term) or CET_MULT (multiplicative composite error term). Defaults to CET_ADDI.

  • fun (String, optional) – FUN_PROD (production frontier) or FUN_COST (cost frontier). Defaults to FUN_PROD.

  • rts (String, optional) – RTS_VRS (variable returns to scale) or RTS_CRS (constant returns to scale). Defaults to RTS_VRS.

display_alpha()[source]

Display alpha value

display_beta()[source]

Display beta value

display_lamda()[source]

Display lamda value

display_negative_residual()[source]

Dispaly negative residual value

display_positive_residual()[source]

Dispaly positive residual value

display_residual()[source]

Dispaly residual value

display_status()[source]

Display the status of problem

get_alpha()[source]

Return alpha value by array

get_beta()[source]

Return beta value by array

get_blocks()[source]

Return the number of blocks

get_frontier()[source]

Return estimated frontier value by array

get_lamda()[source]

Return beta value by array

get_negative_residual()[source]

Return negative residual value by array

get_positive_residual()[source]

Return positive residual value by array

get_predict(x_test)[source]

Return the estimated function in testing sample

get_residual()[source]

Return residual value by array

get_runningtime()[source]

Return the running time

get_status()[source]

Return status

get_totalconstr()[source]

Return the number of total constraints

optimize(email='local', solver=None)[source]

Optimize the function by requested method