Python读取csv文件做dbscan分析

Posted 2022-04-12 空中旋转篮球

1.读取csv数据做dbscan分析

读取csv文件中相应的列，然后进行转化，处理为本算法需要的格式，然后进行dbscan运算，目前公开的代码也比较多，本文根据公开代码修改，具体代码如下：

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()

2.输出结果显示

修改参数显示：
eps = 0.8
min_Pts = 5

 3.计算效率

采用少量数据计算的时候效率问题不明显，随着数据量增大，计算效率问题就变得尤为明显，难以满足大量数据的计算需求了，后期将想办法优化计算方法或者收集C++代码进行优化了。