models=[calibrated_pipeline],
model_names=model_names,
examples=examples,
targets=target_values,
)
# Load the permutation important results from the saved pickle file
with open(f'IMPORTANT_FEATURES_ALL_MODELS_{target}_{time}.pkl',
'rb') as pkl_file:
important_vars = pickle.load(pkl_file)
features = list(itertools.combinations(important_vars, r=2))
results = myInterpreter.calc_ale(
features=features,
n_bootstrap=n_bootstrap,
subsample=subsample,
n_jobs=njobs,
n_bins=n_bins,
)
results_fname = join(
ale_path,
f'ale_2d_results_{model_name}_{target}_{time}{drop_opt}{resample_method}.nc'
)
print(f'Saving {results_fname}...')
myInterpreter.save_results(fname=results_fname, data=results)
duration = datetime.datetime.now() - start_time
seconds = duration.total_seconds()
hours = seconds // 3600
model_names=[model_name],
examples=examples_transformed,
targets=target_values_transformed,
feature_names=feature_names)
njobs = 1 if model_name == 'XGBoost' else len(important_vars)
if normalize_method != None:
unnormalize_func = UnNormalize(model.steps[1][1], feature_names)
else:
unnormalize_func = None
result_dict = myInterpreter.calc_ale(
features=important_vars,
nbootstrap=100,
subsample=1.0,
njobs=njobs,
nbins=30,
)
ale_results.append(result_dict)
myInterpreter.model_names = model_set
ale_results = merge_nested_dict(ale_results)
myInterpreter.set_results(ale_results, option='ale')
fig, axes = myInterpreter.plot_ale(
display_feature_names=display_feature_names,
to_probability=True,
display_units=feature_units,
title=
f'{plt_config.title_dict[target]} {time.replace("_", " ").title()}',
parameters['model_name'] = model_name
calibrated_pipeline = _load_model(**parameters)
model = calibrated_pipeline.calibrated_classifiers_[0].base_estimator
examples_transformed, target_values_transformed = just_transforms(
model, examples, target_values)
myInterpreter = InterpretToolkit(model=[model.steps[-1][1]],
model_names=[model_name],
examples=examples_transformed,
targets=target_values_transformed,
feature_names=feature_names)
result_dict = myInterpreter.calc_ale(
features=feature_names,
nbootstrap=1,
subsample=0.6,
njobs=40,
nbins=30,
)
ale_std = []
for f in feature_names:
ale_std.append(np.std(result_dict[f][model_name]['values'],
ddof=1))
dropped_features = []
idx = np.argsort(ale_std)[::-1]
c = 0
# Drop a feature if its std(ALE) is an order of magnitude
# less than the max std(ALE)
for i in idx:
if c == 0: