def evaluate(self):
eers = []
if len(self.subjects) > 4:
for idx, subject in enumerate(self.subjects):
genuine_user_data = self.data.loc[self.data.subject == subject, \
"H.period":"H.Return"]
imposter_data = self.data.loc[self.data.subject != subject, :]
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:]
#self.test_imposter = imposter_data.groupby("subject"). \
# head(5).loc[:, "H.period":"H.Return"]
self.test_imposter = self.attacker[idx]
self.training()
self.testing()
eers.append(evaluateEERGMM(self.user_scores, \
self.imposter_scores))
else:
genuine_user_data = self.data.loc[self.data.subject == self.subjects, \
"H.period":"H.Return"]
imposter_data = self.data.loc[
self.data.subject != self.subjects, :]
# generated_data = attacker_data
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:]
self.test_imposter = imposter_data.groupby("subject"). \
head(6).loc[:, "H.period":"H.Return"]
self.test_imposter = self.attacker
self.training()
self.testing()
eers.append(evaluateEERGMM(self.user_scores, \
self.imposter_scores))
return np.mean(eers)
def evaluate(self):
eers = []
for subject in subjects: 000
genuine_user_data = data.loc[data.subject == "s002", \
"H.period":"UD.l.Return"]
imposter_data = data.loc[data.subject != subject, :]
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:]
self.test_imposter = imposter_data.groupby("subject"). \
head(5).loc[:, "H.period":"UD.l.Return"]
self.training()
self.testing()
eers.append(evaluateEERGMM(self.user_scores, \
self.imposter_scores))
def evaluate(self):
eers = []
for subject in subjects:
genuine_user_data = data.loc[data.subject == subject, \
"H.period":"H.Return"]
imposter_data = data.loc[data.subject != subject, :]
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:]
self.test_imposter = imposter_data.groupby("subject"). \
head(5).loc[:, "H.period":"H.Return"]
self.training()
self.testing()
if isinstance(self, GMMDetector):
eers.append(evaluateEERGMM(self.user_scores, \
self.imposter_scores))
else:
eers.append(evaluateEER(self.user_scores, \
self.imposter_scores))
return np.mean(eers), np.std(eers)
def evaluate(self):
fpr = []
if isinstance(self.subjects, list):
for idx, subject in enumerate(self.subjects):
genuine_user_data = self.data.loc[self.data.user_id == subject, \
["stroke duration", 'start $x$', 'start $y$', 'stop $x$', 'stop $y$',
'length of trajectory', 'mid-stroke pressure',
'mid-stroke area covered',
'20\%-perc. pairwise velocity', '50\%-perc. pairwise velocity',
'20\%-perc. dev. from end-to-end line',
'50\%-perc. dev. from end-to-end line',
'80\%-perc. dev. from end-to-end line']]
imposter_data = self.data.loc[self.data.user_id != subject, :]
# generated_data = attacker_data
genuine_user_data = normalize_df(genuine_user_data[:400])
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:400]
# self.test_imposter = normalize(imposter_data.groupby("user_id"). \
# tail(10).loc[:, ["stroke duration", 'start $x$', 'start $y$', 'stop $x$', 'stop $y$',
# 'length of trajectory', 'mid-stroke pressure', 'mid-stroke area covered',
# '20\%-perc. pairwise velocity', '50\%-perc. pairwise velocity',
# '20\%-perc. dev. from end-to-end line', '50\%-perc. dev. from end-to-end line',
# '80\%-perc. dev. from end-to-end line']])
# print(idx)
# self.test_imposter = normalize_np(self.attacker[idx])
self.test_imposter = self.attacker[idx]
self.training()
self.testing()
# eers.append(evaluateEER(self.u_scores, \
# self.i_scores))
fpr.append(
evaluateEERGMM(self.user_scores, self.imposter_scores))
# print(evaluateFAR(self.u_scores, self.i_scores))
else:
genuine_user_data = self.data.loc[self.data.user_id == self.subjects, \
["stroke duration", 'start $x$', 'start $y$', 'stop $x$', 'stop $y$',
'length of trajectory', 'mid-stroke pressure',
'mid-stroke area covered',
'20\%-perc. pairwise velocity', '50\%-perc. pairwise velocity',
'20\%-perc. dev. from end-to-end line',
'50\%-perc. dev. from end-to-end line',
'80\%-perc. dev. from end-to-end line']]
imposter_data = self.data.loc[
self.data.user_id != self.subjects, :]
# generated_data = attacker_data
genuine_user_data = normalize_df(genuine_user_data[:400])
self.train = genuine_user_data[:200]
self.test_genuine = genuine_user_data[200:400]
# self.test_imposter = imposter_data.groupby("subject"). \
# head(6).loc[:, "H.period":"H.Return"]
self.test_imposter = self.attacker
self.training()
self.testing()
fpr.append(evaluateEERGMM(self.user_scores, self.imposter_scores))
return np.mean(fpr)