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 _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')
