kmeans 聚类前的数据分析

原始数据
#!/usr/bin/python

import matplotlib.pyplot as plt

def readfile(filename):
    datamat = []
    with open(filename, 'r') as f:
        for line in f.readlines():
            linestrlist = line.strip().split('\t')
            linelist = list(map(float, linestrlist))
            datamat.append(linelist)

    return datamat

if __name__ == "__main__":
    datamat = []
    datamat = readfile("C:\\kmeans.txt")
    vectors_set = []
    for val in enumerate(datamat):
        vectors_set.append(val[1])
    x_data = [v[0] for v in vectors_set]
    y_data = [v[1] for v in vectors_set]
    plt.plot(x_data, y_data, 'r*')
    plt.legend()
    plt.show()
K-means聚类时候，需要给定K的值，这个时候可以先画出图，大致判断一下。