导入库

from sklearn.datasets import load_iris from sklearn.cluster import KMeans from sklearn.model_selection import train_test_split import numpy as np

加载鸢尾花数据集

iris = load_iris() x = iris['data'] y = iris['target']

将数据集分为训练集和测试集

np.random.seed(0) x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1)

任务1：创建 KMeans 对象，令 n_clusters=4

########## Begin ########## kmeans = KMeans(n_clusters=4) ########## End ##########

任务2：调用 fit 函数执行训练过程

########## Begin ########## kmeans.fit(x_train) ########## End ##########

任务3：调用 predict 函数进行预测

########## Begin ########## y_pred = kmeans.predict(x_test) ########## End ##########

打印结果

print("真实结果：\n", y_test) print("预测结果：\n", y_pred)

计算 a,b,c,d

a = b = c = d = 0 m = 15 for j in range(m): for i in range(j): if y_test[i]==y_test[j] and y_pred[i]==y_pred[j]: a = a + 1 elif y_test[i]==y_test[j] and y_pred[i]!=y_pred[j]: b = b + 1 elif y_test[i]!=y_test[j] and y_pred[i]==y_pred[j]: c = c + 1 else: d = d + 1

根据公式计算 Jaccard 系数

JC = a / (a + b + c)

根据公式计算 FM 指数

FM = np.sqrt(a ** 2 / ((a + b) * (a + c)))

根据公式计算 Rand 指数

RI = 2 * (a + b) / (m * (m - 1))

打印结果

print("Jaccard 系数为{}，FM 指数为{}，Rand 指数为{}。".format(JC, FM, RI)