# save labels in binary and one-hot representations
labels.dump(os.path.join(labels_train_folder, 'labels_bin.np'))
# remove redundant education-number and labels features
x = delete(x, (4, 14), 1)
# enumerate parameters
monotone = True
ratios = np.arange(0, .5, .1)
for ratio in ratios:
print '\nPerturbing {}% of data'.format(ratio)
if ratio > 0:
pert_data, _ = perturbate_data(x, adult_params['cat_cols'], ratio, monotone,
adult_params['miss_data_symbol'],
adult_params['mnar_values'])
else:
pert_data = x
print "\tRatio is {} of {}".format(
np.sum(pert_data == adult_params['miss_data_symbol']),
len(pert_data) * len(adult_params['cat_cols']))
path = os.path.join(perturb_folder,
'adult_train_pert_mono_{}_ratio_{}.csv'.format(monotone,
ratio))
# save perturbed data to disk as csv
print '\tSaving perturbed data to {}'.format(path)
np.savetxt(path, pert_data, delimiter=",", fmt="%s")
for imp_method in adult_params['imp_methods']:
# save votes training data
np.savetxt('data/votes_train.csv', votes_train, delimiter=",", fmt="%s")
# For training data
print 'Preparing train data for {}'.format(dataname)
# enumerate parameters
monotone = True
ratios = np.arange(0, .5, .1)
for ratio in ratios:
print '\nPerturbing {}% of data'.format(ratio)
if ratio > 0:
pert_data, _ = perturbate_data(
votes_train, votes_params['cat_cols'], ratio, monotone,
votes_params['miss_data_symbol'], votes_params['mnar_values'])
else:
pert_data = votes_train
path = os.path.join(perturb_folder,
'{}_train_pert_mono_{}_ratio_{}.csv'.format(dataname,
monotone,
ratio))
# save perturbed data to disk as csv
print '\tSaving perturbed data to {}'.format(path)
np.savetxt(path, pert_data, delimiter=",", fmt="%s")
# impute data given imp_methods in params.py
for imp_method in votes_params['imp_methods']:
print '\tImputing with {}'.format(imp_method)
imp = Imputer()
data = impute(pert_data, imp, imp_method, votes_params)
