大蟒蛇python教程共享Python取读csv文件做dbscan分析

from sklearn import datasets  import numpy as np  import random  import matplotlib.pyplot as plt  import time  import copy  import pandas as pd  # from sklearn.datasets import load_iris     def find_neighbor(j, x, eps):      n = list()      for i in range(x.shape[0]):          temp = np.sqrt(np.sum(np.square(x[j] - x[i])))  # 计算欧式距离          if temp <= eps:              n.append(i)      return set(n)        def dbscan(x, eps, min_pts):      k = -1      neighbor_list = []  # 用来保存每个数据的邻域      omega_list = []  # 核心对象集合      gama = set([x for x in range(len(x))])  # 初始时将所有点标记为未访问      cluster = [-1 for _ in range(len(x))]  # 聚类      for i in range(len(x)):          neighbor_list.append(find_neighbor(i, x, eps))          if len(neighbor_list[-1]) >= min_pts:              omega_list.append(i)  # 将样本加入核心对象集合      omega_list = set(omega_list)  # 转化为集合便于操作      while len(omega_list) > 0:          gama_old = copy.deepcopy(gama)          j = random.choice(list(omega_list))  # 随机选取一个核心对象          k = k + 1          q = list()          q.append(j)          gama.remove(j)          while len(q) > 0:              q = q[0]              q.remove(q)              if len(neighbor_list[q]) >= min_pts:                  delta = neighbor_list[q] & gama                  deltalist = list(delta)                  for i in range(len(delta)):                      q.append(deltalist[i])                      gama = gama - delta          ck = gama_old - gama          cklist = list(ck)          for i in range(len(ck)):              cluster[cklist[i]] = k          omega_list = omega_list - ck      return cluster     # x = load_iris().data  data = pd.read_csv("testdata.csv")  x,y=data['time (sec)'],data['height (m hae)']  print(type(x))  n=len(x)  x=np.array(x)  x=x.reshape(n,1)  y=np.array(y)  y=y.reshape(n,1)  x = np.hstack((x, y))  cluster_std=[[.1]], random_state=9)     eps = 0.08  min_pts = 5  begin = time.time()  c = dbscan(x, eps, min_pts)  end = time.time()  plt.figure()  plt.scatter(x[:, 0], x[:, 1], c=c)  plt.show()

eps = 0.8  min_pts = 5