机器学习 sklearn 无监督学习 聚类算法 K-means

Posted 2022-12-07 404detective

import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
from sklearn.cluster import KMeans

# 生成测试数据
# X为样本特征，Y为样本簇类别，共1000个样本，每个样本2个特征，对应x和y轴，共4个簇，
# 簇中心在[-1,-1], [0,0],[1,1], [2,2]， 簇方差分别为[0.4, 0.2, 0.2]
X, y = make_blobs(n_samples=1000, n_features=2 , centers=[[-1, -1], [0, 0], [1, 1], [2, 2]],
                  cluster_std=[0.4, 0.2, 0.2, 0.2], random_state=10)
#默认max_iter=300
y_pred = KMeans(n_clusters=4).fit_predict(X)

plt.figure(figsize=(12, 6))  
plt.subplot(121)
plt.xlim((-3,3))
plt.ylim((-3,3))
plt.xlabel('X1')
plt.ylabel('X2')
plt.scatter(X[:, 0], X[:, 1], c=y_pred)

plt.subplot(122)
plt.xlim((-3,3))
plt.ylim((-3,3))
plt.xlabel('X1')
plt.ylabel('X2')
plt.scatter(X[:, 0], X[:, 1], c=y)

plt.show()

cluster_std=[0.7, 0.7, 0.7, 0.7]

cluster_std=[0.7, 0.7, 0.7, 0.7]

应用

from sklearn.cluster import KMeans
import sklearn

def loadData(filePath):
    fr = open(filePath,'r+')
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        items = line.strip().split(",")
        retCityName.append(items[0])
        retData.append([float(items[i])
    for i in range(1 ,len(items))])
    return retData,retCityName

data,city=loadData("E:\\Desktop\\python_code\\sklearn\\课程数据\\聚类\\city.txt")

y_pred = KMeans(n_clusters=4).fit_predict(data)

CityCluster = [[],[],[],[]]
for i in range(len(city)):
    CityCluster[y_pred[i]].append(city[i])
for i in range(len(CityCluster)):
    print(CityCluster[i])

运行多次 北上广总在一类