def main():
input_dir = sys.argv[1]
num_samples_per_site = int(sys.argv[2])
target_sites = get_target_sites(input_dir)
labels = dict(map(lambda (i, s): (s, i), enumerate(target_sites)))
X, Y = load_feature_vectors(input_dir, num_samples_per_site, labels)
X, Y, testX, testY = select_test_set(X, Y, (num_samples_per_site / 2) * len(target_sites))
# X, testX = scale(X, testX)
X = [[0.0, 0.0], [0.01, 0.01], [1.0, 1.0], [1.1, 1.1], [2.0, 2.0], [2.1, 2.1], [2.05, 2.05]]#, [2.05, 2.05], [2.05, 2.07], [2.01, 2.01]]
Y=[0.0, 0.0, 1.0, 1.0, 2.0, 2.0, 1.0]#, 1.0, 2.0, 2.0]
labels = {0: 0, 1: 1, 2: 2}
thetas, bs, slacks = SVM_fit(X, Y, len(labels), 5.0)
print "thetas"
print thetas[0]
print thetas[1]
print thetas[2]
print "bs"
print bs
print "slacks"
print slacks
print "Should be class 0:"
print SVM_classify([0.05, 0.05], thetas, bs)
print "Should be class 1:"
print SVM_classify([1.05, 1.05], thetas, bs)
print "Should be class 2:"
print SVM_classify([1.98, 1.98], thetas, bs)
def run(input_dir, num_samples_per_site, onevone = True):
input_dir = sys.argv[1]
num_samples_per_site = int(sys.argv[2])
target_sites = get_target_sites(input_dir)
labels = dict(map(lambda (i, s): (s, i), enumerate(target_sites)))
X, Y = load_feature_vectors(input_dir, num_samples_per_site, labels)
#X, Y, testX, testY = select_test_set(X, Y, (num_samples_per_site / 2) * len(target_sites))
#X = [[100.0, 100.0], [101.0, 101.0], [200.0, 200.0], [201.0, 201.0], [300.0, 301.0], [300.0, 301.0]]
#Y = [0.0, 0.0, 1.0, 1.0, 2.0, 2.0]
iters = select_cross_validation_subsets(X, Y, 6)
#crange = map(lambda c: c/10.0, range(1, 11))
#crange = map(lambda c: c/1000.0, range(1, 11))
#crange.extend(map(lambda c: c/100.0, range(2, 11)))
#crange = [0.00001, 0.01, 1.0, 100.0, 10000.0]
crange = [1.0, 100.0]
for c in crange:
print "C=%f"%c
print "Linear kernel:"
for d in iters:
trainX, testX = scale(d["train"][0], d["test"][0])
classify(trainX, d["train"][1], testX, d["test"][1], onevone, c)
print "RBF kernel:"
for d in iters:
trainX, testX = scale(d["train"][0], d["test"][0])
classify(trainX, d["train"][1], testX, d["test"][1], onevone, c, 'rbf')
def main():
cmd = sys.argv[3]
input_dir = sys.argv[1]
num_samples_per_site = int(sys.argv[2])
target_sites = get_target_sites(input_dir)
labels = dict(map(lambda (i, s): (s, i), enumerate(target_sites)))
X, Y = load_feature_vectors(input_dir, num_samples_per_site, labels)
X, Y, testX, testY = select_test_set(X, Y,
(num_samples_per_site / 2) * len(target_sites))
Y = map(lambda v: v*1.0, Y)
testY = map(lambda v: v*1.0, testY)
pca = PCA(n_components = 50)
print "Fitting X"
pca.fit(X)
print "Transforming X and testX"
Xnew = pca.transform(X)
testXnew = pca.transform(testX)
del X
del testX
if cmd == "monb":
multiclass_on_binary_svms(Xnew, Y, testXnew, testY)
elif cmd == "multiclass":
multiclass_svm(Xnew, testXnew, Y, testY, labels)
elif cmd == "anomdet":
anomaly_detection(labels, Xnew, Y, testXnew, testY)
def main():
cmd = sys.argv[5]
sinput_dir = sys.argv[1]
minput_dir = sys.argv[2]
nssamples = int(sys.argv[3])
nmsamples = int(sys.argv[4])
target_sites = get_target_sites(sinput_dir)
labels = dict(map(lambda (i, s): (s, i), enumerate(target_sites)))
Xs, Ys = load_feature_vectors(sinput_dir, nssamples, labels)
Xm, Ym = load_feature_vectors(minput_dir, nmsamples, labels)
if cmd == "multiclass-crossvalidate":
d = 50
nb = 15
e = 100
c = 0.1
Xm = reduce(Xm, Xs, d, nb, e)
multiclass_svm_crossvalidate(Xm, Ym, labels, c)
elif cmd == "multiclass-test":
d = 50
nb = 15
e = 100
c = 0.1
Xm = reduce(Xm, Xs, d, nb, e)
multiclass_svm_test(Xm, Ym, labels, c, nmsamples*len(labels) / 2)
elif cmd == "onevone-test":
c = 1.0
print "Original dimensionality"
monb_test(Xm, Ym, c, True, nmsamples*len(labels) / 2)
d = 50
nb = 15
e = 100
print "Reduced dimensionality"
Xm = reduce(Xm, Xs, d, nb, e)
monb_test(Xm, Ym, c, True, nmsamples*len(labels) / 2)
elif cmd == "onevone-crossvalidate":
c = 1.0
d = 110
nb = 15
e = 100
Xm = reduce(Xm, Xs, d, nb, e)
monb_crossvalidate(Xm, Ym, c, True)
elif cmd == "onevall-crossvalidate":
c = 1.0
d = 50
nb = 15
e = 100
Xm = reduce(Xm, Xs, d, nb, e)
monb_crossvalidate(Xm, Ym, c, False)
elif cmd == "onevall-test":
c = 1.0
print "Original dimensionality"
monb_test(Xm, Ym, c, False, nmsamples*len(labels) / 2)
d = 50
nb = 15
e = 100
print "Reduced dimensionality"
Xm = reduce(Xm, Xs, d, nb, e)
monb_test(Xm, Ym, c, False, nmsamples*len(labels) / 2)
elif cmd == "anomdet-test":
v = .1
d = 50
nb = 15
e = 100
X = reduce(Xm, Xs, d, nb, e)
anom_det_test(labels, X, Ym, v, nmsamples*len(labels) / 2)
elif cmd == "anomdet-crossvalidate":
v = 0.1
d = 50
nb = 15
e = 100
X = reduce(Xm, Xs, d, nb, e)
anom_det_crossvalidate(labels, X, Ym, v)
