#調(diào)用科學計算包與繪圖包
import numpy as np
import random
import matplotlib.pyplot as plt

# 獲取數(shù)據(jù)
def loadDataSet(filename):
  dataSet=np.loadtxt(filename,dtype=np.float32,delimiter=',')
  return dataSet

#計算兩個向量之間的歐式距離
def calDist(X1 , X2 ):
  sum = 0
  for x1 , x2 in zip(X1 , X2):
    sum += (x1 - x2) ** 2
  return sum ** 0.5

#獲取一個點的ε-鄰域（記錄的是索引）
def getNeibor(data , dataSet , e):
  res = []
  for i in range(dataSet.shape[0]):
    if calDist(data , dataSet[i])<e:
      res.append(i)
  return res

#密度聚類算法
def DBSCAN(dataSet , e , minPts):
  coreObjs = {}#初始化核心對象集合
  C = {}
  n = dataSet.shape[0]
  #找出所有核心對象，key是核心對象的index，value是ε-鄰域中對象的index
  for i in range(n):
    neibor = getNeibor(dataSet[i] , dataSet , e)
    if len(neibor)>=minPts:
      coreObjs[i] = neibor
  oldCoreObjs = coreObjs.copy()
  k = 0#初始化聚類簇數(shù)
  notAccess = list(range(n))#初始化未訪問樣本集合（索引）
  while len(coreObjs)>0:
    OldNotAccess = []
    OldNotAccess.extend(notAccess)
    cores = coreObjs.keys()
    #隨機選取一個核心對象
    randNum = random.randint(0,len(cores)-1)
    cores=list(cores)
    core = cores[randNum]
    queue = []
    queue.append(core)
    notAccess.remove(core)
    while len(queue)>0:
      q = queue[0]
      del queue[0]
      if q in oldCoreObjs.keys() :
        delte = [val for val in oldCoreObjs[q] if val in notAccess]#Δ = N(q)∩Γ
        queue.extend(delte)#將Δ中的樣本加入隊列Q
        notAccess = [val for val in notAccess if val not in delte]#Γ = Γ\Δ
    k += 1
    C[k] = [val for val in OldNotAccess if val not in notAccess]
    for x in C[k]:
      if x in coreObjs.keys():
        del coreObjs[x]
  return C

# 代碼入口
dataSet = loadDataSet(r"E:\jupyter\sklearn學習\sklearn聚類\DataSet.txt")
print(dataSet)
print(dataSet.shape)
C = DBSCAN(dataSet, 0.11, 5)
draw(C, dataSet)

db = skc.DBSCAN(eps=1.5, min_samples=3).fit(dataSet) #DBSCAN聚類方法 還有參數(shù)，matric = ""距離計算方法
labels = db.labels_ #和X同一個維度，labels對應(yīng)索引序號的值 為她所在簇的序號。若簇編號為-1，表示為噪聲
print('每個樣本的簇標號:')
print(labels)
raito = len(labels[labels[:] == -1]) / len(labels) #計算噪聲點個數(shù)占總數(shù)的比例
print('噪聲比:', format(raito, '.2%'))
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0) # 獲取分簇的數(shù)目
print('分簇的數(shù)目: %d' % n_clusters_)
print("輪廓系數(shù): %0.3f" % metrics.silhouette_score(X, labels)) #輪廓系數(shù)評價聚類的好壞
for i in range(n_clusters_):
  print('簇 ', i, '的所有樣本:')
  one_cluster = X[labels == i]
  print(one_cluster)
  plt.plot(one_cluster[:,0],one_cluster[:,1],'o')
plt.show()