def __init__(self, k, datas):
self.datas = [Vec(data[:-1]) for data in datas]
self.lab = {self.datas[i]: datas[i][-1] for i in range(len(datas))}
Vec.sta(self.datas)
# ini_centers = [self.datas[random.randint(0,len(self.datas)-1)] for i in range(k)]
ini_centers = random.sample(self.datas, k)
while 1:
ini_cls = {cent: [] for cent in ini_centers}
for data in self.datas:
sho_dis, cls = float("inf"), None
for cent in ini_centers:
dis = data.distance(cent)
if dis < sho_dis:
sho_dis, cls = dis, cent
ini_cls[cls].append(data)
new_centers = [
Vec.get_clustercenter(ini_cls[key]) for key in ini_cls
]
if Vec.is_converg(ini_centers, new_centers, 1e-5):
self.cls = ini_cls
break
else:
ini_centers = new_centers
def __init__(self, datas: list, k: int):
self.datas = [Vec(data[:-1]) for data in datas]
Vec.sta(self.datas)
self.lab = {self.datas[i]: datas[i][-1] for i in range(len(datas))}
self.k = int(sqrt(len(datas))) if k > sqrt(len(datas)) else k