def prepareMusk2(path, name):
print("Prepare Musk2:")
fname = prepareLoading(name, path)
# Create MIL problem from Musk2 data
musk2_raw = np.array(pd.read_csv(fname, usecols=range(0,169), skip_blank_lines=True, header=None))
# Scale data by z-score normalization
features = musk2_raw[:, 2:-1].astype(np.float64)
features = scale(features)
keys = musk2_raw[:, 0]
labels = musk2_raw[:, -1]
musk2 = milData('musk2')
for i, row in enumerate(features):
key = keys[i]
x = features[i]
z = labels[i]
musk2.add_x(key, x, z, UPDATE=False )
musk2.save(path)
print("Bags: ", musk2.N_B, "(+: {p}, -: {n})".format(p=np.sum(musk2.z==1), n=np.sum(musk2.z==0)))
print("Instances: ", musk2.N_X, "(+: {p}, -: {n})".format(p=np.sum(musk2.y==1), n=np.sum(musk2.y==0)))
print ("Features: ", musk2.N_D)
print("\n")
return musk2
def prepareFox(path, name):
print("Prepare Fox:")
fname = prepareLoading(name, path)
# Create MIL problem from Fox data
features = loadmat(fname)["Data"]
features = scale(features)
keys = loadmat(fname)['bags']
labels = loadmat(fname)['labels']
b = 0
fox = milData('fox')
for i, row in enumerate(features):
x = row
key = keys[i][0]
z = labels[b][0]
fox.add_x(key, x, z, UPDATE=False)
if i < len(features) - 1 and key != keys[
i + 1]: # will the next key belong to the next bag?
b += 1
fox.save(path)
print(
"Bags: ", fox.N_B, "(+: {p}, -: {n})".format(p=np.sum(fox.z == 1),
n=np.sum(fox.z == 0)))
print(
"Instances: ", fox.N_X,
"(+: {p}, -: {n})".format(p=np.sum(fox.y == 1), n=np.sum(fox.y == 0)))
print("Features: ", fox.N_D)
print("\n")
return fox