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
# data data_name = "breastcancer" # name of the data data_dir = os.getcwd() + '/examples/data/' # directory where datasets are stored data_csv_file = data_dir + data_name + '_data.csv' # csv file for the dataset sample_weights_csv_file = None # csv file of sample weights for the dataset (optional) # problem parameters max_coefficient = 5 # value of largest/smallest coefficient max_L0_value = 5 # maximum model size max_offset = 50 # maximum value of offset parameter (optional) c0_value = 1e-6 # 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 w_pos = 1.00 # relative weight on examples with y = +1; w_neg = 1.00 (optional) # load dataset data = load_data_from_csv(dataset_csv_file = data_csv_file, sample_weights_csv_file = sample_weights_csv_file) # coefficient set coef_set = CoefficientSet(variable_names = data['variable_names'], lb=-max_coefficient, ub=max_coefficient, sign=0) # offset value conservative_offset = get_conservative_offset(data, coef_set, max_L0_value) 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)
str(key): loaded_settings[key]
for key in loaded_settings if key in settings
}
settings.update(loaded_settings)
#overwrite parameters specified by the user
settings['max_runtime'] = float(
'inf') if parsed.timelimit == -1 else parsed.timelimit
settings['c0_value'] = parsed.c0_value
settings['w_pos'] = parsed.w_pos
# check if sample weights file was specified, if not set as None
logger.info("loading data and sample weights")
data = load_data_from_csv(dataset_csv_file=parsed.data,
sample_weights_csv_file=parsed.weights,
fold_csv_file=parsed.cvindices,
fold_num=parsed.fold)
N, P = data['X'].shape
# initialize coefficient set and offset parameter
logger.info("creating coefficient set and constraints")
max_coefficient = parsed.max_coef
max_model_size = parsed.max_size if parsed.max_size >= 0 else float('inf')
max_offset = parsed.max_offset if parsed.max_offset >= 0 else float('inf')
coef_set = CoefficientSet(variable_names=data['variable_names'],
lb=-max_coefficient,
ub=max_coefficient,
sign=0)
trivial_model_size = P - np.sum(coef_set.C_0j == 0)