def parse_s(s):
fn_data = Name_functions.DS_file(s)
fn_subset = Name_functions.DS_reduced_ids_DSJ(s)
x, y = Di(fn_data).split_data(int(s), fn_subset_ids=fn_subset)
print('\tM^{}_j ... '.format(s), end='', flush=True)
good_splits = 0
for i in sorted(x):
fn_model = Name_functions.model_SJ(s, i)
c, cc = np.unique(y[i], return_counts=True)
if min(cc) < cv * 2:
index = np.where(cc == np.min(cc))
continue
if len(c) <= 1:
continue
if os.path.exists(fn_model):
good_splits += 1
continue
else:
generate_model(x[i], y[i], s, i)
good_splits += 1
continue
print('Done ({}/{} D^{}_j met requirements)'.format(
good_splits, len(x), s))
return good_splits, len(x), 100 * good_splits / len(x)
def parse_ms(s):
print('D^{} ... '.format(s), end='', flush=True)
if Filefunctions.exists(Name_functions.DS_train_ids(s)):
if Filefunctions.exists(Name_functions.DS_test_ids(s)):
print('Already done')
return
np.random.seed(0)
X, y, times, ids = DI(Name_functions.DS_file(s)).get_data(
Name_functions.DS_reduced_ids_DSJ(s), True, True)
if Parameters.take_test_split_chronological:
test_case_ids = []
train_case_ids = []
times_post_warm_up = [
t for t in times if t > Parameters.test_time_start
]
times_post_warm_up.sort()
train_start_index = int(
(1 - Parameters.assessment_test_split) * len(times_post_warm_up))
train_time_end = times_post_warm_up[train_start_index]
for case_start_time, case_id in zip(times, ids):
if case_start_time <= Parameters.test_time_start:
continue
if case_start_time < train_time_end:
train_case_ids.append(case_id)
else:
test_case_ids.append(case_id)
else:
indices = [
i for i in range(len(ids)) if times[i] > Parameters.test_time_start
]
test_indices = []
train_indices = []
c, cc = np.unique(y[indices], return_counts=True)
for label, label_count in zip(c, cc):
num_test = int(label_count * Parameters.assessment_test_split)
indices_c = [i for i in indices if y[i] == label]
indices_c_test = np.random.choice(indices_c,
num_test,
replace=False)
test_indices.extend(indices_c_test.tolist())
train_indices.extend(
[i for i in indices_c if i not in indices_c_test])
test_case_ids = ids[test_indices]
train_case_ids = ids[train_indices]
with open(Name_functions.DS_train_ids(s), 'w+') as wf:
for case_id in train_case_ids:
wf.write('{}\n'.format(case_id))
with open(Name_functions.DS_test_ids(s), 'w+') as wf:
for case_id in test_case_ids:
wf.write('{}\n'.format(case_id))
print('Done')
def run():
with open(Name_functions.best_graec(), 'r') as rf:
(S, B, T, P) = rf.readline()[:-1].split(';')[0:4]
CalculateDailyScores(single={'S': [int(S)],
'Tau': [float(T)],
'P': [float(P)],
'Beta': [float(B)]},
multi={'Beta': Parameters.GRAEC_beta,
'Tau': Parameters.GRAEC_tau,
'S': Parameters.S_values},
test_ids_fn=Name_functions.DS_reduced_ids_DSJ(S)).run()
def parse_naive(s):
print('\tM^{}_naive ... '.format(s), end='', flush=True)
fn_model = Name_functions.model_S_naive(s)
if os.path.exists(fn_model):
print("Already done")
return 1.0, 1.0, 100
fn_data = Name_functions.DS_file(s)
fn_subset = Name_functions.DS_reduced_ids_DSJ(s)
x, y, t = Di(fn_data).get_data(fn_subset, True, False)
y = y.ravel()
# Only take data that is in the first year
x = [
x[i] for i in range(len(t)) if t[i] < Parameters.train_time_naive_stop
]
y = [
y[i] for i in range(len(t)) if t[i] < Parameters.train_time_naive_stop
]
x_train, x_test, y_train, y_test = train_test_split(x,
y,
random_state=0,
test_size=0.2)
# Get the best model
best_model = None
best_score = -1
for c in used_models:
score, model = train_classifier(c, x_train, x_test, y_train, y_test)
if score > best_score:
best_score = score
best_model = model
# save the model
Model_Functions.saveModel(best_model, fn_model)
print("Done")
return 1.0, 1.0, 100
def parse_ms(s):
fn_target = Name_functions.DS_reduced_ids_DSJ(s)
# Check existence
print('\tD^S_j ... ', end='', flush=True)
if Filefunctions.exists(fn_target):
print('Already done')
return
fn_input = Name_functions.DS_file(s)
x, y, ids = DataImporter(fn_input).split_data(int(s),
return_identifiers=True)
ids_keep = []
for i in sorted(x):
xi, yi, indices = KMedoids.reduce_to_medoids(x[i],
y[i],
return_indices=True)
ids_keep.extend([ids[i][j] for j in indices])
with open(fn_target, 'w+') as wf:
for caseID in ids_keep:
wf.write('{}\n'.format(caseID))
print('Done')
