基于POI数据的聚类，并且将聚类结果可视化在地图上

Question

使用python读取本地csv文件，筛选大类为“旅游景点”的POI数据，进行DBSCAN聚类算法进行聚类，最后将聚类结果绘制到pyecharts的地图map上，但是最终只生成了map.html，聚类结果并没有显示到地图上。

代码如下：

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import DBSCAN
from sklearn import metrics
import pandas as pd
from pyecharts import options as opts
from pyecharts.charts import Map

UNCLASSIFIED = 0
NOISE = -1


# 计算数据点两两之间的距离
def getDistanceMatrix(datas):
    N, D = np.shape(datas)
    dists = np.zeros([N, N])

    for i in range(N):
        for j in range(N):
            vi = datas[i, :]
            vj = datas[j, :]
            dists[i, j] = np.sqrt(np.dot((vi - vj), (vi - vj)))
    return dists


# 寻找以点cluster_id为中心，eps为半径的圆内的所有点的id
def find_points_in_eps(point_id, eps, dists):
    index = (dists[point_id] <= eps)
    return np.where(index == True)[0].tolist()


# 聚类扩展
# dists：所有数据两两之间的距离 N x N
# labs: 所有数据的标签 labs N，
# cluster_id：一个簇的标号
# eps：密度评估半径
# seeds：用来进行簇扩展的点
# min_points：半径内最少的点数
def expand_cluster(dists, labs, cluster_id, seeds, eps, min_points):
    i = 0
    while i < len(seeds):
        # 获取一个临近点
        Pn = seeds[i]
        # 如果该点被标记为NOISE 则重新标记
        if labs[Pn] == NOISE:
            labs[Pn] = cluster_id
        # 如果该点没有被标记过
        elif labs[Pn] == UNCLASSIFIED:
            # 进行标记，并计算它的临近点 new_seeds
            labs[Pn] = cluster_id
            new_seeds = find_points_in_eps(Pn, eps, dists)

            # 如果new_seeds足够长则把它加入到seed队列中
            if len(new_seeds) >= min_points:
                seeds = seeds + new_seeds

        i = i + 1


def dbscan(datas, eps, min_points):
    # 计算所有点之间的距离
    dists = getDistanceMatrix(datas)

    # 将所有点的标签初始化为UNCLASSIFIED
    n_points = datas.shape[0]
    labs = [UNCLASSIFIED] * n_points

    cluster_id = 0
    # 遍历所有点
    for point_id in range(0, n_points):
        # 如果当前点已经处理过了
        if not (labs[point_id] == UNCLASSIFIED):
            continue

        # 没有处理过则计算临近点
        seeds = find_points_in_eps(point_id, eps, dists)

        # 如果临近点数量过少则标记为NOISE
        if len(seeds) < min_points:
            labs[point_id] = NOISE
        else:
            # 否则就开启一轮簇的扩张
            cluster_id = cluster_id + 1
            # 标记当前点
            labs[point_id] = cluster_id
            expand_cluster(dists, labs, cluster_id, seeds, eps, min_points)
    return labs, cluster_id


# 绘制散点图
def draw_cluster(datas, labs, n_cluster):
    plt.cla()

    colors = [plt.cm.Spectral(each)
              for each in np.linspace(0, 1, n_cluster)]

    for i, lab in enumerate(labs):
        if lab == NOISE:
            plt.scatter(datas[i, 0], datas[i, 1], s=16., color=(0, 0, 0))
        else:
            plt.scatter(datas[i, 0], datas[i, 1], s=16., color=colors[lab - 1])
    plt.show()


if __name__ == "__main__":
    # 从CSV文件中读取数据
    data = pd.read_csv("C:/Users/86136/Desktop/大数据/昆明市POI数据.csv")  # 替换成你的CSV文件路径
    filtered_data = data[data['大类'] == '旅游景点']
    selected_columns = filtered_data[['经度', '纬度']].values

    # 数据正则化
    scaler = StandardScaler()
    selected_columns = scaler.fit_transform(selected_columns)

    # 设置DBSCAN参数
    eps = 0.1
    min_points = 8

    # 执行DBSCAN聚类
    #labels, n_clusters = dbscan(selected_columns, eps, min_points)

    # 绘制散点图
    #draw_cluster(selected_columns, labels, n_clusters)

    # 构造地图数据
    map_data = [(str(selected_columns[i][0]), str(selected_columns[i][1])) for i in range(len(selected_columns))]

    # 绘制地图
    map_chart = (
        Map()
        .add("聚类结果", selected_columns, "昆明")
        .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
        .set_global_opts(
            title_opts=opts.TitleOpts(title="DBSCAN聚类结果地图"),
            visualmap_opts=opts.VisualMapOpts(),
        )
    )

    # 保存地图为HTML文件
    map_chart.render("dbscan_map.html")

csv文件如下：
[](链接: https://pan.baidu.com/s/1bHt2ajRLpJv3bxEPKR_4CA 提取码: yfzu 复制这段内容后打开百度网盘手机App，操作更方便哦)