经典k均值聚类和模糊k均值聚类python代码

经典k均值聚类的Python代码：

import numpy as np

class KMeans:
    def __init__(self, k=2, max_iter=100):
        self.k = k
        self.max_iter = max_iter

    def fit(self, X):
        self.centroids = []

        # Initialize centroids randomly
        for i in range(self.k):
            self.centroids.append(X[np.random.randint(0, len(X), size=1)[0]])

        for i in range(self.max_iter):
            # Assign points to nearest centroid
            clusters = [[] for _ in range(self.k)]
            for x in X:
                distances = [np.linalg.norm(x - c) for c in self.centroids]
                cluster = np.argmin(distances)
                clusters[cluster].append(x)

            # Update centroids
            for j in range(self.k):
                self.centroids[j] = np.mean(clusters[j], axis=0)

    def predict(self, X):
        predictions = []
        for x in X:
            distances = [np.linalg.norm(x - c) for c in self.centroids]
            cluster = np.argmin(distances)
            predictions.append(cluster)
        return predictions

模糊k均值聚类的Python代码：

import numpy as np

class FuzzyKMeans:
    def __init__(self, k=2, m=2, max_iter=100):
        self.k = k
        self.m = m
        self.max_iter = max_iter

    def fit(self, X):
        # Initialize membership matrix randomly
        self.U = np.random.rand(len(X), self.k)
        self.U = self.U / np.sum(self.U, axis=1)[:, None]

        for i in range(self.max_iter):
            # Update centroids
            centroids = []
            for j in range(self.k):
                centroid = np.sum((self.U[:,j]**self.m)[:,None] * X, axis=0) / np.sum(self.U[:,j]**self.m)
                centroids.append(centroid)

            # Update membership matrix
            distances = np.zeros((len(X), self.k))
            for j in range(self.k):
                distances[:,j] = np.linalg.norm(X - centroids[j], axis=1)

            self.U = distances ** (-2/(self.m-1))
            self.U = self.U / np.sum(self.U, axis=1)[:, None]

        self.centroids = centroids

    def predict(self, X):
        distances = np.zeros((len(X), self.k))
        for j in range(self.k):
            distances[:,j] = np.linalg.norm(X - self.centroids[j], axis=1)
        predictions = np.argmin(distances, axis=1)
        return predictions

注意，这里的经典k均值聚类代码中采用了随机初始化质心的方式，因此每次运行的结果可能不同。