def main_standard(dataset, subject, model, params, exp, eval_set, ph):
printd(dataset, subject, model, params, exp, eval_set, ph)
# retrieve model's parameters
params = locate_params(params)
model_class = locate_model(model)
# scale variables in minutes to the benchmark sampling frequency
ph_f = ph // cs.freq
hist_f = params["hist"] // cs.freq
day_len_f = cs.day_len // cs.freq
""" PREPROCESSING """
train, valid, test, scalers = preprocessing(dataset, subject, ph_f, hist_f,
day_len_f)
""" MODEL TRAINING """
raw_results = make_predictions_pclstm(subject,
model_class,
params,
ph_f,
train,
valid,
test,
scalers,
mode=eval_set)
""" POST-PROCESSING """
raw_results = postprocessing(raw_results, scalers, dataset)
""" EVALUATION """
ResultsSubject(model,
exp,
ph,
dataset,
subject,
params=params,
results=raw_results).save_raw_results()
def study(dataset, model, params, mode, ph, all_feat, patients, combs):
# retrieve model's parameters
params = locate_params(params)
model_class = locate_model(model)
# scale variables in minutes to the benchmark sampling frequency
ph_f = ph // cs.freq
hist_f = params["hist"] // cs.freq
day_len_f = cs.day_len // cs.freq
# full processing
for i in patients:
dir = os.path.join(cs.path, "study", dataset, model, mode,
"patient " + str(i))
""" PREPROCESSING ALL FEATURES"""
printd("Preprocessing patient " + str(i))
data = preprocessing_full(dataset, str(i), ph_f, hist_f, day_len_f,
all_feat)
for ele in combs:
printd("Preprocessing patient", str(i),
"with features glucose " + " + ".join(ele))
train, valid, test, scalers = preprocessing_select(
data, dataset, day_len_f, all_feat, ele)
for j in range(5):
torch.manual_seed(j)
""" MODEL TRAINING & TUNING """
if not ele:
file = os.path.join(dir, "reference", "seed " + str(j),
"weights", "weights")
else:
file = os.path.join(dir, " + ".join(ele), "seed " + str(j),
"weights", "weights")
raw_results = make_predictions(str(i),
model_class,
params,
ph_f,
train,
valid,
test,
mode=mode,
save_model_file=file)
""" POST-PROCESSING """
raw_results = postprocessing(raw_results, scalers, dataset)
""" EVALUATION """
if not ele:
file_save = os.path.join("reference", "seed " + str(j))
else:
file_save = os.path.join(" + ".join(ele), "seed " + str(j))
results = ResultsSubject(model,
file_save,
ph,
dataset,
str(i),
params=params,
results=raw_results,
study=True,
mode=mode)
printd(results.compute_mean_std_results())
def main(dataset, subject, model, params, exp, mode, log, ph, plot):
printd(dataset, subject, model, params, exp, mode, log, ph, plot)
# retrieve model's parameters
search = locate_search(params)
params = locate_params(params)
model_class = locate_model(model)
# scale variables in minutes to the benchmark sampling frequency
ph_f = ph // cs.freq
hist_f = params["hist"] // cs.freq
day_len_f = cs.day_len // cs.freq
""" PREPROCESSING """
train, valid, test, scalers = preprocessing(dataset, subject, ph_f, hist_f, day_len_f)
""" MODEL TRAINING & TUNING """
if search:
params = find_best_hyperparameters(subject, model_class, params, search, ph_f, train, valid, test)
raw_results = make_predictions(subject, model_class, params, ph_f, train, valid, test, mode=mode)
""" POST-PROCESSING """
raw_results = postprocessing(raw_results, scalers, dataset)
""" EVALUATION """
results = ResultsSubject(model, exp, ph, dataset, subject, params=params, results=raw_results)
printd(results.compute_results())
if plot:
results.plot(0)
def main_cgega_iterative_training(dataset,
subject,
model,
params1,
params2,
exp,
eval_set,
ph,
save_iter=False):
printd(dataset, subject, model, params1, params2, exp, eval_set, ph)
# retrieve model's parameters
params1 = locate_params(params1)
params2 = locate_params(params2)
model_class = locate_model(model)
# scale variables in minutes to the benchmark sampling frequency
ph_f = ph // cs.freq
hist_f = params1["hist"] // cs.freq
day_len_f = cs.day_len // cs.freq
freq_ds = misc.datasets.datasets[dataset]["glucose_freq"]
""" PREPROCESSING """
train, valid, test, scalers = preprocessing(dataset, subject, ph_f, hist_f,
day_len_f)
""" MODEL TRAINING """
dir = join(cs.path, "processing", "models", "weights", "cg_ega")
file = join(dir, exp, model_class.__name__ + "_" + dataset + subject)
results_test, results_valid_iter = progressive_improvement_clinical_acceptability(
subject, model_class, params1, params2, ph, freq_ds, train, valid,
test, scalers, file, eval_set)
results_test = postprocessing(results_test, scalers, dataset)
results_valid_iter = postprocessing_all_iter(results_valid_iter, scalers,
dataset)
ResultsSubject(model,
exp,
ph,
dataset,
subject,
params=[params1, params2],
results=results_test).save_raw_results()
if save_iter:
ResultsSubjectPICA(model,
exp,
ph,
dataset,
subject,
params=[params1, params2],
results=results_valid_iter).save_raw_results()
def process_main_args(args_):
model = locate_model(args_.model)
params = locate_params(args_.params)
# redirect the logs to a file if specified
if args_.log is not None:
log_file = args_.log
log_path = os.path.join(path, "logs", log_file)
sys.stdout = open(log_path, "w")
sbj_msg = args_.source_dataset + "_2_" + args_.target_dataset, " " + args_.target_subject
if args_.tl_mode == "source_training":
printd("source_training", sbj_msg)
main_source_training(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode)
elif args_.tl_mode == "source_training_test":
printd("source_training_test", sbj_msg)
main_source_training(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode)
main_target_global(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode, args_.exp, args_.plot)
elif args_.tl_mode == "end_to_end_0":
printd("end_to_end_0", sbj_msg)
end_to_end(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode, args_.exp, args_.plot)
elif args_.tl_mode == "target_training":
printd("target_training", sbj_msg)
main_target_training(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.eval_mode, args_.exp, args_.plot)
elif args_.tl_mode == "target_global":
printd("target_global", sbj_msg)
main_target_global(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode, args_.exp, args_.plot)
elif args_.tl_mode == "target_finetuning":
printd("target_finetuning", sbj_msg)
main_target_finetuning(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode, args_.exp, args_.plot)
elif args_.tl_mode == "end_to_end" and args_.params_ft is not None:
printd("end_to_end", sbj_msg)
params_ft = locate_params(args_.params_ft)
main_source_training(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params,
args_.weights, args_.eval_mode)
main_target_global(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params_ft,
args_.weights, args_.eval_mode, args_.exp, args_.plot)
main_target_finetuning(args_.source_dataset, args_.target_dataset, args_.target_subject, model, params_ft,
args_.weights, args_.eval_mode, args_.exp, args_.plot, args_.save)
def __init__(self, source_dataset, target_dataset, target_subject,
exp_name, model_name, params):
self.source_dataset = source_dataset
self.target_dataset = target_dataset
self.target_subject = target_subject
self.exp_name = exp_name
self.model_name = model_name
self.Model = locate_model(model_name)
self.params = locate_params(params)
self.ph = misc.constants.ph_f
self.hist = self.params["hist"] // misc.constants.freq
self.day_len = misc.constants.day_len_f
self.train, self.valid, self.test, _ = preprocessing_source_multi(
self.source_dataset, self.target_dataset, self.target_subject,
self.ph, self.hist, self.day_len)
def __init__(self, source_ds, target_ds, weights_name, model_name, params_name):
"""
Object that is used to analyze the features outputed by saved models pre-transfer
(models trained on the multi sources, before finetuning). Can be use to plot and save t-SNE representations,
and compute the local domain perplexity metric.
:param source_ds: source dataset (e.g., "idiab", "ohio", "idiab+t1dms", etc.)
:param target_ds: target dataset (i.e., "idiab" or "ohio")
:param weights_name: name of the weights
:param model_name: name of the model
:param params_name: name of the used parameters
"""
self.source_dataset = source_ds
self.target_dataset = target_ds
self.exp_name = weights_name
self.model_name = model_name
self.Model = locate_model(model_name)
self.params = locate_params(params_name)
self.target_subjects = misc.datasets.datasets[self.target_dataset]["subjects"]
self.ph = misc.constants.ph_f
self.hist = self.params["hist"] // misc.constants.freq
self.day_len = misc.constants.day_len_f
def main(dataset,
subject,
model,
params,
exp,
mode,
log,
ph,
plot,
save=False):
printd(dataset, subject, model, params, exp, mode, log, ph, plot)
# retrieve model's parameters
search = locate_search(params)
params = locate_params(params)
model_class = locate_model(model)
# scale variables in minutes to the benchmark sampling frequency
ph_f = ph // cs.freq
hist_f = params["hist"] // cs.freq
day_len_f = cs.day_len // cs.freq
""" PREPROCESSING """
train, valid, test, scalers = preprocessing(dataset, subject, ph_f, hist_f,
day_len_f)
start = time.time()
""" MODEL TRAINING & TUNING """
if search:
params = find_best_hyperparameters(subject, model_class, params,
search, ph_f, train, valid, test)
if save:
dir = os.path.join(cs.path, "processing", "models", "weights",
model_class.__name__, exp)
file = os.path.join(dir,
model_class.__name__ + "_" + dataset + subject)
else:
file = None
raw_results = make_predictions(subject,
model_class,
params,
ph_f,
train,
valid,
test,
mode=mode,
save_model_file=file)
""" POST-PROCESSING """
raw_results = postprocessing(raw_results, scalers, dataset)
""" EVALUATION """
results = ResultsSubject(model,
exp,
ph,
dataset,
subject,
params=params,
results=raw_results)
printd(results.compute_mean_std_results())
end = time.time()
printd("Time elapsed : " + str(end - start) + " seconds")
if plot:
results.plot(0)
