estimators = load_models(time, target, drop_opt, model_names)
# Subsample time indices to reduce autocorrelations
X_subset, y_subset = get_independent_samples(X, y, info)
explainer = InterpretToolkit(estimators=estimators,
estimator_names=model_names,
X=X_subset.copy(),
y=y_subset.copy())
background_dataset = shap.sample(X, 100)
results = explainer.local_contributions(
method='shap',
background_dataset=background_dataset,
performance_based=True,
n_samples=n_samples)
results = explainer.save(fname=save_fname, data=results)
duration = datetime.datetime.now() - start_time
seconds = duration.total_seconds()
hours = seconds // 3600
minutes = (seconds % 3600) // 60
seconds = seconds % 60
message = f"""
SHAP Feature Contributions values for {target} {time} are done!
Started at {start_time.strftime("%I:%M %p")},
Duration : {hours:.2f} hours : {minutes:.2f} minutes : {seconds:.2f} seconds
"""
send_email(message)
message = 'SHAP value computation are done running!'
iterator = itertools.product(time_set, target_set)
for combo in iterator:
time, target = combo
parameters = {
'time': time,
'target': target,
'drop_opt': drop_opt,
}
X, y = _load_train_data(**parameters)
estimators = load_models(time, target, drop_opt, model_names)
explainer = InterpretToolkit(estimators=estimators,
estimator_names=model_names,
X=X,
y=y)
# ale_results_all_models_tornado_first_hourL1_based_feature_selection_aggressive.nc
fnames = join(ale_path,
f'ale_results_all_models_{target}_{time}{drop_opt}.nc')
ale = explainer.load(fnames=fnames)
results = explainer.interaction_strength(ale,
n_bootstrap=10,
subsample=0.1)
print(results)
explainer.save(fname=join(
ale_path, f'ias_score_all_models_{target}_{time}{drop_opt}.nc'),
data=results)
estimators = load_models(time, target, drop_opt, model_names)
explainer = InterpretToolkit(estimators=estimators,
estimator_names=model_names,
X=X,
y=y)
results = explainer.pd(
features='all',
n_bootstrap=n_bootstrap,
subsample=subsample,
n_jobs=njobs,
n_bins=n_bins,
)
print(f'Saving {results_fname}...')
explainer.save(fname=results_fname, data=results)
duration = datetime.datetime.now() - start_time
seconds = duration.total_seconds()
hours = seconds // 3600
minutes = (seconds % 3600) // 60
seconds = seconds % 60
message = f"""
PD computations are done running!
Started at {start_time.strftime("%I:%M %p")},
Duration : {hours:.2f} hours : {minutes:.2f} minutes : {seconds:.2f} seconds
"""
send_email(message)