class IABOD(ABOD):
# todo: refactor - avoid coping data from HullCluster to class
# (originally needed for superclass to access it)
data = []
__verbose = False
__test_offline = False
data_cluster = None
# todo: remove test online
def __init__(self, test_offline=False, cluster=None):
ABOD.__init__(self)
self.__test_offline = test_offline
if cluster is None:
self.data_cluster = MeanShiftCluster()
else:
assert issubclass(cluster, ClusterBase)
self.data_cluster = cluster
def fit(self, data, dim_reduction=False):
raise NotImplementedError("Use 'partial_fit' instead of 'fit'")
def partial_fit(self, samples):
if self.__test_offline is True:
if len(self.data) == 0:
self.data = samples
elif len(self.data) < 40:
self.data = np.concatenate((self.data, samples))
else:
self.data_cluster.update(samples)
self.data = self.data_cluster.get_data()
def mean_dist(self, samples, metric='cosine'):
return self.data_cluster.mean_dist(samples, metric)
def class_mean_dist(self, samples, metric='cosine'):
return self.data_cluster.class_mean_dist(samples, metric)
class ISVM:
__verbose = False
clf = None
uncertainty_thresh = 0.7
random_data = None
data_cluster = None
# prediction
prediction = None
probability = None
def __init__(self, random_data, cluster=None):
# load random data
self.random_data = random_data
self.clf = SVC(kernel='linear', probability=True, C=1)
if cluster is None:
self.data_cluster = MeanShiftCluster()
else:
assert issubclass(cluster, ClusterBase)
self.data_cluster = cluster
def decision_function(self, samples):
pass
def get_proba(self):
# probability that it is the class (uncertain samples not counted)
prob = 0
prob += np.sum(self.probability[:, 1][self.prediction == 1])
prob += np.sum(1 - self.probability[:, 1][self.prediction == -1])
prob /= len(self.probability[:, 1][self.prediction != 0])
return prob
def mean_dist(self, samples, metric='cosine'):
return self.data_cluster.mean_dist(samples, metric)
def class_mean_dist(self, samples, metric='cosine'):
return self.data_cluster.class_mean_dist(samples, metric)
def predict(self, samples):
proba = self.clf.predict_proba(samples)
self.probability = proba
mask_1 = np.sum(proba < self.uncertainty_thresh, axis=1) == 2
pred = np.array([-1 if r[0] > 0.5 else 1 for r in proba])
pred[mask_1] = 0
self.prediction = pred
return pred
def __fit_vs_random(self, class_data):
label_class = np.repeat(1, np.shape(class_data)[0])
label_unknown = np.repeat(-1, np.shape(self.random_data)[0])
training_embeddings = np.concatenate((class_data, self.random_data))
training_labels = np.concatenate((label_class, label_unknown))
self.clf.fit(training_embeddings, training_labels)
def partial_fit(self, samples):
self.data_cluster.update(samples)
reduced_data = self.data_cluster.get_data()
# refit SVM one vs random
self.__fit_vs_random(reduced_data)