爬虎扑体育数据，聚类分析

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

# 读取网页中的数据表

table = []

for i in range(1,7):

    table.append(pd.read_html('https://nba.hupu.com/stats/players/pts/%d' %i)[0])

# 所有数据纵向合并为数据框

players = pd.concat(table)

players.head()