def test_risk_slim(data_csv_file,
sample_weights_csv_file=None,
max_coefficient=5,
max_L0_value=5,
max_offset=50,
c0_value=1e-6,
w_pos=1.00,
settings=None):
# load dataset
data = load_data_from_csv(dataset_csv_file=data_csv_file,
sample_weights_csv_file=sample_weights_csv_file)
N, P = data['X'].shape
# offset value
coef_set = CoefficientSet(variable_names=data['variable_names'],
lb=-max_coefficient,
ub=max_coefficient,
sign=0)
conservative_offset = get_conservative_offset(data, coef_set, max_L0_value)
max_offset = min(max_offset, conservative_offset)
coef_set['(Intercept)'].ub = max_offset
coef_set['(Intercept)'].lb = -max_offset
# create constraint dictionary
trivial_L0_max = P - np.sum(coef_set.C_0j == 0)
max_L0_value = min(max_L0_value, trivial_L0_max)
constraints = {
'L0_min': 0,
'L0_max': max_L0_value,
'coef_set': coef_set,
}
# Train model using lattice_cpa
model_info, mip_info, lcpa_info = run_lattice_cpa(data, constraints,
settings)
#model info contains key results
pprint(model_info)
# lcpa_output contains detailed information about LCPA
pprint(lcpa_info)
# todo check solution
# mip_output contains information to access the MIP
mip_info['risk_slim_mip'] #CPLEX mip
mip_info['risk_slim_idx'] #indices of the relevant constraints
return True
#
'init_use_sequential_rounding': True, # use SeqRd in initialization procedure
'init_sequential_rounding_max_runtime': 10.0, # max runtime for SeqRd in initialization procedure
'init_sequential_rounding_max_solutions': 5, # max solutions to round using SeqRd
#
'init_polishing_after': True, # polish after rounding
'init_polishing_max_runtime': 30.0, # max runtime for polishing
'init_polishing_max_solutions': 5, # max solutions to polish
#
# CPLEX Solver Parameters
'cplex_randomseed': 0, # random seed
'cplex_mipemphasis': 0, # cplex MIP strategy
}
# train model using lattice_cpa
model_info, mip_info, lcpa_info = run_lattice_cpa(data, constraints, settings)
#model info contains key results
pprint(model_info)
print_model(model_info['solution'], data)
# mip_output contains information to access the MIP
mip_info['risk_slim_mip'] #CPLEX mip
mip_info['risk_slim_idx'] #indices of the relevant constraints
# lcpa_output contains detailed information about LCPA
pprint(lcpa_info)
def risk_slim(data, max_coefficient, max_L0_value, c0_value, max_offset, max_runtime = 120, w_pos = 1):
"""
@parameters:
max_coefficient: value of largest/smallest coefficient
max_L0_value: maximum model size (set as float(inf))
max_offset: maximum value of offset parameter (optional)
c0_value: L0-penalty parameter such that c0_value > 0; larger values ->
sparser models; we set to a small value (1e-6) so that we get a model with max_L0_value terms
max_runtime: max algorithm running time
w_pos: relative weight on examples with y = +1; w_neg = 1.00 (optional)
"""
# create coefficient set and set the value of the offset parameter
coef_set = CoefficientSet(variable_names = data['variable_names'], lb = -max_coefficient, ub = max_coefficient, sign = 0)
conservative_offset = get_conservative_offset(data, coef_set, max_L0_value)
max_offset = min(max_offset, conservative_offset)
coef_set['(Intercept)'].ub = max_offset
coef_set['(Intercept)'].lb = -max_offset
constraints = {
'L0_min': 0,
'L0_max': max_L0_value,
'coef_set':coef_set,
}
# Set parameters
settings = {
# Problem Parameters
'c0_value': c0_value,
'w_pos': w_pos,
# LCPA Settings
'max_runtime': max_runtime, # max runtime for LCPA
'max_tolerance': np.finfo('float').eps, # tolerance to stop LCPA (set to 0 to return provably optimal solution)
'display_cplex_progress': True, # print CPLEX progress on screen
'loss_computation': 'lookup', # how to compute the loss function ('normal','fast','lookup')
# LCPA Improvements
'round_flag': False, # round continuous solutions with SeqRd
'polish_flag': False, # polish integer feasible solutions with DCD
'chained_updates_flag': False, # use chained updates
'add_cuts_at_heuristic_solutions': True, # add cuts at integer feasible solutions found using polishing/rounding
# Initialization
'initialization_flag': True, # use initialization procedure
'init_max_runtime': 300.0, # max time to run CPA in initialization procedure
'init_max_coefficient_gap': 0.49,
# CPLEX Solver Parameters
'cplex_randomseed': 0, # random seed
'cplex_mipemphasis': 0, # cplex MIP strategy
}
# train model using lattice_cpa
model_info, mip_info, lcpa_info = run_lattice_cpa(data, constraints, settings)
return model_info, mip_info, lcpa_info