def Cascade(trn, max_level):
if len(trn) > 2:
X = array([x for x, y in trn])
Y = array([y for x, y in trn])
else:
X, Y = trn
T = 512
classifiers = []
td = training_utils.TrainingData(X, Y)
SD = distance_utils.calcDistanceMatrix2([X])
trunk = td.trunk
sensitivity = 0.99
o = metric_learning.search_threshold(SD, trunk, sensitivity)
thres = o[0]
TP, FP = o[1]
num_FN = (1 - sensitivity) * (len(TP) / sensitivity)
pairs = TP, FP
MAX_NUM_POS = 2000
MAX_NUM_NEG = 4000
num_pos = min(len(pairs[0]), MAX_NUM_POS)
num_neg = min(len(pairs[1]), MAX_NUM_NEG)
print "TP vs FP: %d vs %d" % (len(TP), len(FP))
trunk = o[2]
classifiers.append((thres, (TP, FP)))
FPvsFN = len(FP) / num_FN
print "#FP/#FN = ", FPvsFN
#return classifiers
for level in range(1, max_level + 1):
print "level = %d" % level
random.shuffle(TP)
random.shuffle(FP)
pos = TP[-1:-num_pos - 1:-1]
neg = FP[0:num_neg]
pairs = pos, neg
print len(pairs[0]), len(pairs[1])
XX, yy = training_utils.create_training_sample(X, pairs)
classifier = adaboost.AdaBoost(rank1_metric.Rank1_Metric)
classifier.set_training_sample(XX, yy)
classifier.train(T, 1)
#classifier
VD, vy = training_utils.create_training_sample(
X, (TP, FP)) # for validation
SD = -classifier.predict(VD) # be careful about the sign!!!
sensitivity = 0.99
o = metric_learning.search_threshold(SD, trunk, sensitivity)
thres = o[0]
TP, FP = o[1]
num_FN = (1 - sensitivity) * (len(TP) / sensitivity)
print "TP vs FP: %d vs %d" % (len(TP), len(FP))
trunk = o[2]
classifiers.append((classifier, thres, (TP, FP)))
FPvsFN = len(FP) / num_FN
print "#FP/#FN = ", FPvsFN
if len(TP) == 0 or len(FP) == 0 or FPvsFN < 1.2: break
return classifiers
def Cascade(trn, max_level):
if len(trn)>2:
X = array([x for x,y in trn])
Y = array([y for x,y in trn])
else:
X,Y = trn
T = 512
classifiers = []
td = training_utils.TrainingData(X,Y)
SD = distance_utils.calcDistanceMatrix2([X])
trunk = td.trunk
sensitivity = 0.99
o = metric_learning.search_threshold(SD, trunk, sensitivity)
thres = o[0]
TP,FP = o[1]
num_FN = (1-sensitivity)*(len(TP)/sensitivity)
pairs = TP,FP
MAX_NUM_POS = 2000
MAX_NUM_NEG = 4000
num_pos = min(len(pairs[0]),MAX_NUM_POS)
num_neg = min(len(pairs[1]),MAX_NUM_NEG)
print "TP vs FP: %d vs %d"%(len(TP),len(FP))
trunk = o[2]
classifiers.append((thres, (TP,FP)))
FPvsFN = len(FP)/num_FN
print "#FP/#FN = ",FPvsFN
#return classifiers
for level in range(1,max_level+1):
print "level = %d"%level
random.shuffle(TP)
random.shuffle(FP)
pos = TP[-1:-num_pos-1:-1]
neg = FP[0:num_neg]
pairs = pos, neg
print len(pairs[0]), len(pairs[1])
XX,yy = training_utils.create_training_sample(X, pairs)
classifier = adaboost.AdaBoost(rank1_metric.Rank1_Metric)
classifier.set_training_sample(XX,yy)
classifier.train(T, 1)
#classifier
VD, vy = training_utils.create_training_sample(X, (TP,FP)) # for validation
SD = -classifier.predict(VD) # be careful about the sign!!!
sensitivity = 0.99
o = metric_learning.search_threshold(SD, trunk, sensitivity)
thres = o[0]
TP,FP = o[1]
num_FN = (1-sensitivity)*(len(TP)/sensitivity)
print "TP vs FP: %d vs %d"%(len(TP),len(FP))
trunk = o[2]
classifiers.append((classifier, thres, (TP,FP)))
FPvsFN = len(FP)/num_FN
print "#FP/#FN = ",FPvsFN
if len(TP)==0 or len(FP)==0 or FPvsFN < 1.2 : break
return classifiers
def compute_distance(self, X):
f = self.dist_func
X = numpy.array(X)
training_X = self.training_X
# compute the distance matrix from X to training_X
dist = distance_utils.calcDistanceMatrix2((X, training_X), distFunc=f)
## 'dist' is reshaped s.t. dist[i,j] = d(X[i],training_X[j])
labels = numpy.matlib.repmat(self.training_y, len(X), 1)
dist.setfield(labels, dtype=labels.dtype)
# for each x in X, sort the training samples w.r.t the distance to x
self.sorted_dist = numpy.sort(dist)
self.sorted_labels = self.sorted_dist.getfield(labels.dtype)
def compute_distance(self, X):
f = self.dist_func
X = numpy.array(X)
training_X = self.training_X
# compute the distance matrix from X to training_X
dist = distance_utils.calcDistanceMatrix2((X, training_X), distFunc = f)
## 'dist' is reshaped s.t. dist[i,j] = d(X[i],training_X[j])
labels = numpy.matlib.repmat(self.training_y, len(X), 1)
dist.setfield(labels, dtype=labels.dtype)
# for each x in X, sort the training samples w.r.t the distance to x
self.sorted_dist = numpy.sort(dist)
self.sorted_labels = self.sorted_dist.getfield(labels.dtype)
