def initialize_data(set_type, set_size, seed=None):
data_set = DataSet()
if (seed != None):
np.random.seed(seed)
for i in range(set_size):
if (set_type == "data_set_1"):
data_set.add(generateInstance_1(seed))
elif (set_type == "data_set_3a"):
data_set.add(generateInstance_3a(seed))
elif (set_type == "data_set_3b"):
data_set.add(generateInstance_3b(seed))
elif (set_type == "data_set_4"):
data_set.add(generateInstance_4(seed))
elif (set_type == "data_set_5"):
data_set.add(generateInstance_5(seed))
return data_set
