machinelearning_notebook/第三次作业

import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt

def get_data(file):
    df = pd.read_csv(file,header = None)
    return df.values

def get_Polar(data):
    dist = np.sqrt(data[0]**2 + data[1]**2)
    angle = np.arctan(data[1]/data[0]) 
    return [dist,angle]

def get_distance(data,origin):
    if(data == origin).all():
        return 0
    dist = np.sqrt((data[0]-origin[0])**2 + (data[1]-origin[1])**2)
    return dist

def kmeans():
    data = get_data("dataset_circles.csv")

    polar_data = list(map(get_Polar,data.tolist()))
    polar_data = np.array(polar_data)
    # print(polar_data)
    # plt.scatter(polar_data[:,0], polar_data[:,1], s=None, c="b")
    # # plt.scatter(cluster2[:,0], cluster2[:,1], s=None, c="r")
    # plt.show()


    data_x = polar_data[:,0]
    data_y = polar_data[:,1]

    cluster_center1 = polar_data[np.random.randint(data_x.shape[0])]
    cluster_center2 = polar_data[np.random.randint(data_y.shape[0])]

    cluster1_index = np.array([],dtype="int64")
    cluster2_index = np.array([],dtype="int64")

    last_center1 = np.array([],dtype="float64")
    last_center2 = np.array([],dtype="float64")
    while True:
        for i in range(data.shape[0]):
            # print(origin)
            dist1 = get_distance(polar_data[i],cluster_center1)#获取距离
            dist2 = get_distance(polar_data[i],cluster_center2)
            if dist1 > dist2:#比距离，放到距离中心小的坐标系中
                cluster2_index = np.append(cluster2_index,i)
            else:
                cluster1_index = np.append(cluster1_index,i)
        
        last_center1 = cluster_center1
        last_center2 = cluster_center2
        
        cluster1 = polar_data[cluster1_index.tolist()]#获取两类数据
        cluster2 = polar_data[cluster2_index.tolist()]
        cluster_center1 = np.mean(cluster1[:,:2],axis=0)#求均值重新判断中心
        cluster_center2 = np.mean(cluster2[:,:2],axis=0)


        if(cluster_center1 == last_center1).all() and (cluster_center2 == last_center2).all():##如果两次聚类没有发生变化就弹出
            break
        # print("1: ",cluster_center1," ",last_center1)
        # print("2: ",cluster_center2," ",last_center2)
        # print(cluster1_index.shape[0])
        # print(cluster2_index.shape[0])

        # print()
        cluster1_index = np.array([],dtype="int64")
        cluster2_index = np.array([],dtype="int64")
    
    # print(cluster1_index)
    # print(cluster2_index)
    plt.scatter(data[cluster1_index.tolist()][:,0], data[cluster1_index.tolist()][:,1], s=None, c="b")
    plt.scatter(data[cluster2_index.tolist()][:,0], data[cluster2_index.tolist()][:,1], s=None, c="r")
    plt.show()


def main():
    kmeans()

if __name__ == "__main__":
    main()