K-means1、找到所属簇def find_close_centroids(X, centroids):res = np.zeros((1,))for x in X:res = np.append(res, np.argmin(np.sqrt(np.sum((centroids-x)**2, axis=1))))return res[1:]2、计算新的簇中心def compute_centroi

0、引入要用到的库import numpy as npimport matplotlib.pyplot as plt1、读取数据，绘制图像with open(r'E:\zl\机器学习\1\ex1_linear_regression_ex1data1.txt') as f:populations = []profit = []for line in f.readlines():populations

异常检测1、可视化数据def visualize_dataset(X):plt.scatter(X[..., 0], X[..., 1], marker="x", label="point")2、估计参数def estimate_parameters_for_gaussian_distribution(X):mu = np.mean(X, axis=0)sigma2 = np.var(X, axi

异常检测1、可视化数据def visualize_dataset(X):plt.scatter(X[..., 0], X[..., 1], marker="x", label="point")2、估计参数def estimate_parameters_for_gaussian_distribution(X):mu = np.mean(X, axis=0)sigma2 = np.var(X, axi