python 多维高斯分布数据生成

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/itnerd/article/details/83418082

import numpy as np
import matplotlib.pyplot as plt


def gen_clusters():
    mean1 = [0,0]
    cov1 = [[1,0],[0,10]]
    data = np.random.multivariate_normal(mean1,cov1,100)
    
    mean2 = [10,10]
    cov2 = [[10,0],[0,1]]
    data = np.append(data,
                     np.random.multivariate_normal(mean2,cov2,100),
                     0)
    
    mean3 = [10,0]
    cov3 = [[3,0],[0,4]]
    data = np.append(data,
                     np.random.multivariate_normal(mean3,cov3,100),
                     0)
    
    return np.round(data,4)

def save_data(data,filename):
    with open(filename,'w') as file:
        for i in range(data.shape[0]):
            file.write(str(data[i,0])+','+str(data[i,1])+'\n')
            
def load_data(filename):
    data = []
    with open(filename,'r') as file:
        for line in file.readlines():
            data.append([ float(i) for i in line.split(',')])
    return np.array(data)

def show_scatter(data):
    x,y = data.T
    plt.scatter(x,y)
    plt.axis()
    plt.title("scatter")
    plt.xlabel("x")
    plt.ylabel("y")
    
data = gen_clusters()
save_data(data,'3clusters.txt')
d = load_data('3clusters.txt')
show_scatter(d)