生成kmeans聚类算法代码

KMeans聚类算法的原理是将数据点划分到指定的簇中，以便将相似的数据点分配到同一簇中，使其成为更大的簇。下面是使用Python实现KMeans聚类算法的代码：from sklearn.cluster import KMeans
import numpy as np

# 设置KMeans参数
kmeans = KMeans(n_clusters=3, random_state=0)# 将数据输入模型
data = np.array([[1, 2], [1, 4], [1, 0],
[4, 2], [4, 4], [4, 0]])
kmeans.fit(data)# 生成聚类标签
labels = kmeans.predict(data)
print(labels)

相关问题

Kmeans聚类算法代码

以下是KMeans聚类算法的Python代码示例：

import numpy as np
import matplotlib.pyplot as plt

# 生成随机数据
def create_data(num):
    np.random.seed(10)
    data = np.random.randn(num, 2)
    data[0:50, :] += 5
    data[50:100, :] -= 5
    return data

# 计算欧式距离
def euclidean_distance(x1, x2):
    return np.sqrt(np.sum((x1 - x2)**2))

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

    def initialize_centroids(self, data):
        centroids = data.copy()
        np.random.shuffle(centroids)
        return centroids[:self.k]

    def create_clusters(self, centroids, data):
        clusters = [[] for _ in range(self.k)]
        for point in data:
            distances = [euclidean_distance(point, centroid) for centroid in centroids]
            closest_idx = np.argmin(distances)
            clusters[closest_idx].append(point)
        return clusters

    def calculate_centroids(self, clusters):
        centroids = np.zeros((self.k, 2))
        for idx, cluster in enumerate(clusters):
            cluster_mean = np.mean(cluster, axis=0)
            centroids[idx] = cluster_mean
        return centroids

    def predict_cluster(self, clusters, data):
        y_pred = np.zeros(len(data))
        for cluster_idx, cluster in enumerate(clusters):
            for sample_idx in cluster:
                y_pred[sample_idx] = cluster_idx
        return y_pred

    def fit(self, data):
        centroids = self.initialize_centroids(data)

        for i in range(self.max_iters):
            clusters = self.create_clusters(centroids, data)
            prev_centroids = centroids
            centroids = self.calculate_centroids(clusters)

            if (centroids == prev_centroids).all():
                break

        return self.predict_cluster(clusters, data)

# 测试
data = create_data(100)
model = KMeans(k=2)
y_pred = model.fit(data)

# 可视化
plt.scatter(data[:, 0], data[:, 1], c=y_pred, cmap='viridis')
plt.show()

注：上述代码实现了一个简单的KMeans聚类算法，用于对二维数据进行聚类，其中KMeans类的fit方法返回的是每个样本所属的簇的标签。

kmeans聚类算法代码python

以下是kmeans聚类算法的Python代码：

import numpy as np
import matplotlib.pyplot as plt

def kmeans(X, K, max_iters=100):
    centroids = X[np.random.choice(len(X), K, replace=False)]
    for i in range(max_iters):
        C = np.argmin(np.sqrt(((X - centroids[:, np.newaxis])**2).sum(axis=2)), axis=)
        new_centroids = np.array([X[C == k].mean(axis=) for k in range(K)])
        if np.allclose(centroids, new_centroids):
            break
        centroids = new_centroids
    return C, centroids

# 生成数据
np.random.seed()
X = np.vstack([np.random.randn(100, 2) + [2, 2], np.random.randn(100, 2) + [-2, -2], np.random.randn(100, 2) + [2, -2]])
# 聚类
C, centroids = kmeans(X, 3)
# 可视化
plt.scatter(X[:, ], X[:, 1], c=C)
plt.scatter(centroids[:, ], centroids[:, 1], marker='x', s=200, linewidths=3, color='r')
plt.show()

该代码实现了kmeans聚类算法，其中X为输入数据，K为聚类数目，max_iters为最大迭代次数。函数返回聚类结果C和聚类中心centroids。代码中还包括了一个简单的数据生成和可视化过程。