def parse_naive(s):
fn_target = Name_functions.DS_reduced_ids_naive(s)
print('\tD^S_naive ... ', end='', flush=True)
# Check existence
if Filefunctions.exists(fn_target):
print('Already done')
return
fn_input = Name_functions.DS_file(s)
x, y, timestamps, ids = DataImporter(fn_input).get_data(
return_identifiers=True, return_split_values=True)
first_year_indices = [
i for i in range(len(timestamps))
if timestamps[i] < Parameters.train_time_naive_stop
]
x = x[first_year_indices]
y = y[first_year_indices]
ids = ids[first_year_indices]
x, y, medoid_indices = KMedoids.reduce_to_medoids(
x, y, return_indices=True, factor=Parameters.LargeSmallFactor)
ids_keep = [ids[i] for i in medoid_indices]
with open(fn_target, 'w+') as wf:
for CaseID in ids_keep:
wf.write('{}\n'.format(CaseID))
print('Done')
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 _eval_previous(self):
print('Parsing Previous ... ', end='', flush=True)
fn_recent = Name_functions.parameter_evaluation_evaluation_metric_file('Previous')
if Filefunctions.exists(fn_recent):
print('Already done')
return
with open(fn_recent, 'w+') as wf:
wf.write('S;Day;NumEntries;accuracy;f1\n')
for S in self.Multi['S']:
predictor = Classifiers.PreviousClassifier(S)
fn = Name_functions.DS_file(S)
_, labels, times, ids = Di(fn).get_data(fn_subset_ids=self.test_ids_fn,
return_split_values=True,
return_identifiers=True)
data = pd.DataFrame(index=ids)
data['time'] = times
data['y_true'] = [l[0] for l in labels]
data['Day'] = np.floor(data['time'])
# Calculate the accuracy score for each day
for day in data['Day'].unique():
subset = data[data['Day'] == day]
acc_score, f1_score = self.get_scores(predictor=predictor,
true_labels=subset['y_true'],
times=subset['time'],
ids=subset.index
)
if not (acc_score is None or f1_score is None):
wf.write('{};{};{};{};{}\n'.format(S,
day,
len(subset),
acc_score,
f1_score))
print('Done')
def parse_ms(s):
fn_data = Name_functions.DS_file(s)
x, y, time, case_id = Di(fn_data).get_data(return_identifiers=True,
return_split_values=True)
print('\tM^{}_j ... '.format(s), end='', flush=True)
# S predictions
for i in sorted([int(i) for i in Name_functions.S_J_values(s)],
reverse=True):
if Filefunctions.exists(Name_functions.DSJ_probabilities(s, i)):
continue
model_i = Model_Functions.loadModel(Name_functions.model_SJ(s, i))
model_labels = model_i.classes_.tolist()
model_end_time = Name_functions.SJ_period_end_time(s, i)
with open(Name_functions.DSJ_probabilities(s, i), 'w+') as wf:
for dx, t, idn in zip(x, time, case_id):
if t < model_end_time:
# Only test if the model existed before the data point
continue
model_predictions = model_i.predict_proba(dx.reshape(1, -1))[0]
actual_predictions = [
(0 if (i not in model_labels) else
model_predictions[model_labels.index(i)])
for i in all_labels
]
wf.write('{};{};{}\n'.format(
idn, t,
';'.join(['{:4f}'.format(x) for x in actual_predictions])))
print('Done')
# Naive predictions
print('\tM^{}_naive ... '.format(s), end='', flush=True)
if Filefunctions.exists(Name_functions.DS_probabilities_naive(s)):
print('Already done')
return
model_naive = Model_Functions.loadModel(Name_functions.model_S_naive(s))
model_naive_labels = model_naive.classes_.tolist()
model_naive_end_time = Parameters.train_time_naive_stop
with open(Name_functions.DS_probabilities_naive(s), 'w+') as wf:
for dx, t, idn in zip(x, time, case_id):
if t < model_naive_end_time:
# Only test if the model existed before the data point
continue
model_predictions = model_naive.predict_proba(dx.reshape(1, -1))[0]
actual_predictions = [
(0 if (i not in model_naive_labels) else
model_predictions[model_naive_labels.index(i)])
for i in all_labels
]
wf.write('{};{};{}\n'.format(
idn, t,
';'.join(['{:4f}'.format(x) for x in actual_predictions])))
print('Done')
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 _eval_param(self, evaluated_parameter):
print('Parsing parameter {} ... '.format(evaluated_parameter), end='', flush=True)
fn = Name_functions.parameter_evaluation_evaluation_metric_file(evaluated_parameter)
if Filefunctions.exists(fn):
print('Already done')
return
with open(fn, 'w+') as wf:
wf.write('S;Beta;Tau;P;Day;NumEntries;accuracy;f1\n')
for S in self.values(evaluated_parameter, 'S'):
predictor = Classifiers.BPTSClassifier(s=S, score_function=None)
fn = Name_functions.DS_file(S)
_, labels, times, ids = Di(fn).get_data(fn_subset_ids=self.test_ids_fn, return_split_values=True,
return_identifiers=True)
data = pd.DataFrame(index=ids)
data['time'] = times
data['y_true'] = [l[0] for l in labels]
data['Day'] = np.floor(data['time'])
for beta in self.values(evaluated_parameter, 'Beta'):
for p in self.values(evaluated_parameter, 'P'):
for tau in self.values(evaluated_parameter, 'Tau'):
scoring_function = PeriodScoring(s=S, beta=beta, tau=tau, p=p)
predictor.set_scoring_function(scoring_function)
for day in data['Day'].unique():
subset = data[data['Day'] == day]
acc_score, f1_score = self.get_scores(predictor=predictor,
ids=subset.index,
times=subset['time'],
true_labels=subset['y_true'],
)
if not (acc_score is None or f1_score is None):
wf.write('{};{};{};{};{};{};{};{}\n'.format(S,
beta,
tau,
p,
day,
len(subset),
acc_score,
f1_score))
print('Done')
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')
def parse_ms(s):
print('\tGRAEC ... ', end='', flush=True)
if Filefunctions.exists(Name_functions.S_GRAEC_enumeration_dictionary(s)):
print('Already done')
return
enumeration_encoder = dict()
fn_data = Name_functions.DS_file(s)
fn_train_ids = Name_functions.DS_train_ids(s)
fn_test_ids = Name_functions.DS_test_ids(s)
x_train, labels_train, times_train, ids_train = DI(fn_data).get_data(
fn_subset_ids=fn_train_ids,
return_split_values=True,
return_identifiers=True)
x_test, labels_test, times_test, ids_test = DI(fn_data).get_data(
fn_subset_ids=fn_test_ids,
return_split_values=True,
return_identifiers=True)
enumeration = 0
predictor = Classifiers.BPTSClassifier(s=s, score_function=None)
for B in Parameters.GRAEC_beta:
for T in Parameters.GRAEC_tau:
for P in Parameters.GRAEC_p if not T == 0 else [
0
]: # P has no use for T == 0
enumeration_encoder[enumeration] = '{};{};{}'.format(B, T, P)
predictor.set_scoring_function(
score_function=PeriodScoring(beta=B, p=P, tau=T, s=s))
with open(
Name_functions.S_GRAEC_train_predictions(
s, enumeration), 'w+') as wf:
wf.write('SOID;time;True_label;Predicted_label\n')
for case_id, t, true_label in zip(ids_train, times_train,
labels_train):
predicted_label = predictor.predict(case_id=case_id,
time=t)
wf.write('{};{};{};{}\n'.format(
case_id, t, true_label[0], predicted_label))
with open(
Name_functions.S_GRAEC_test_predictions(
s, enumeration), 'w+') as wf:
wf.write('Case_id;time;True_label;Predicted_label\n')
for case_id, t, true_label in zip(ids_test, times_test,
labels_test):
predicted_label = predictor.predict(case_id=case_id,
time=t)
wf.write('{};{};{};{}\n'.format(
case_id, t, true_label[0], predicted_label))
enumeration += 1
Human_Functions.save_dict_to_csv(
enumeration_encoder, Name_functions.S_GRAEC_enumeration_dictionary(s))
fn_data = Name_functions.DS_file(s)
fn_ids = Name_functions.DS_test_ids(s)
x, labels, times, ids = DI(fn_data).get_data(fn_subset_ids=fn_ids,
return_split_values=True,
return_identifiers=True)
print('Done')
print('\tNaive and Previous ... ', end='', flush=True)
naive_predictor = Classifiers.NaiveClassifier(s)
previous_predictor = Classifiers.PreviousClassifier(s)
with open(Name_functions.S_naive_test_predictions(s), 'w+') as wf_naive:
with open(Name_functions.S_recent_test_predictions(s),
'w+') as wf_previous:
wf_naive.write('{};{};{};{}\n'.format('Case_id', 'time',
'True_label',
'Predicted_label'))
wf_previous.write('{};{};{};{}\n'.format('Case_id', 'time',
'True_label',
'Predicted_label'))
for case_id, t, true_label in zip(ids, times, labels):
predicted_label_naive = naive_predictor.predict(
case_id=case_id, time=t)
if predicted_label_naive is not None:
wf_naive.write('{};{};{};{}\n'.format(
case_id, t, true_label[0], predicted_label_naive))
predicted_label_previous = previous_predictor.predict(
case_id=case_id, time=t)
if predicted_label_previous is not None:
wf_previous.write('{};{};{};{}\n'.format(
case_id, t, true_label[0], predicted_label_previous))
print('Done')
def run():
for s in Parameters.S_values:
create_labelled_dataset(event_log=Name_functions.event_log(),
s=s,
feature_filename=Name_functions.cases_info(),
output_file=Name_functions.DS_file(s))