python的K-means代码

以下是Python实现K-means算法的基本代码：

import numpy as np
import random

# 计算两个向量之间的欧几里得距离
def euclidean_distance(x1, x2):
    return np.sqrt(np.sum((x1 - x2)**2))

class KMeans:
    def __init__(self, K=2, max_iters=100, plot_steps=False):
        self.K = K
        self.max_iters = max_iters
        self.plot_steps = plot_steps

        # 初始化聚类中心
        self.centroids = []

        # 每个数据点所属的簇
        self.clusters = [[] for _ in range(self.K)]

    def predict(self, X):
        self.X = X
        self.n_samples, self.n_features = X.shape

        # 随机选择K个样本作为初始聚类中心
        random_sample_idxs = random.sample(range(self.n_samples), self.K)
        self.centroids = [self.X[idx] for idx in random_sample_idxs]

        # 开始迭代
        for _ in range(self.max_iters):
            self.clusters = self._create_clusters(self.centroids)
            
            if self.plot_steps:
                self._plot()

            old_centroids = self.centroids
            self.centroids = self._get_centroids(self.clusters)
            
            # 如果聚类中心不再变化，停止迭代
            if self._is_converged(old_centroids, self.centroids):
                break

            if self.plot_steps:
                self._plot()

        # 返回每个数据点所属的簇
        return self._get_cluster_labels(self.clusters)

    def _create_clusters(self, centroids):
        clusters = [[] for _ in range(self.K)]
        for idx, sample in enumerate(self.X):
            centroid_idx = self._closest_centroid(sample, centroids)
            clusters[centroid_idx].append(idx)
        return clusters

    def _closest_centroid(self, sample, centroids):
        distances = [euclidean_distance(sample, point) for point in centroids]
        closest_idx = np.argmin(distances)
        return closest_idx

    def _get_centroids(self, clusters):
        centroids = np.zeros((self.K, self.n_features))
        for idx, cluster in enumerate(clusters):
            cluster_mean = np.mean(self.X[cluster], axis=0)
            centroids[idx] = cluster_mean
        return centroids

    def _is_converged(self, old_centroids, centroids):
        distances = [euclidean_distance(old_centroids[i], centroids[i]) for i in range(self.K)]
        return sum(distances) == 0

    def _get_cluster_labels(self, clusters):
        labels = np.empty(self.n_samples)
        for cluster_idx, cluster in enumerate(clusters):
            for sample_idx in cluster:
                labels[sample_idx] = cluster_idx
        return labels

    def _plot(self):
        fig, ax = plt.subplots(figsize=(12, 8))

        for i, index in enumerate(self.clusters):
            point = self.X[index].T
            ax.scatter(*point)

        for point in self.centroids:
            ax.scatter(*point, marker="x", color="black", linewidth=2)

        plt.show()

使用示例：

from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt

X, y = make_blobs(centers=3, n_samples=500, random_state=42)

kmeans = KMeans(K=3, max_iters=150, plot_steps=True)
y_pred = kmeans.predict(X)

fig, ax = plt.subplots(figsize=(12, 8))
for i in range(len(X)):
    ax.scatter(X[i][0], X[i][1], color='C{}'.format(y_pred[i]))
plt.show()