一、

随机创建不同二维数据集作为训练集 ，并结合k-means算法将其聚类 ，你可以尝试分别聚类不同数量的簇 ，并观察聚类 效果：

聚类参数n_cluster传值不同 ，得到的聚类结果不同

代码展示：

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

plt.rcParams["font.sans-serif"] = ["SimHei"]
plt.rcParams["axes.unicode_minus"] = False

x,_ = make_blobs(
    n_samples=1000,
    centers=[[-1,-1],[0,0],[1,1],[2,2]],
    cluster_std=[0.4,0.2,0.2,0.2],
    random_state=42
)

plt.subplot(221)
plt.scatter(x[:,0],
            x[:,1],
            s=5,
            marker="o")

kmeans_2 = KMeans(n_clusters=2)
kmeans_3 = KMeans(n_clusters=3)
kmeans_4 = KMeans(n_clusters=4)

kmeans_2.fit(x)
y_pred = kmeans_2.predict(x)
plt.subplot(222)
plt.scatter(x[:,0],
            x[:,1],
            c=y_pred,
            s=5,
            marker="o")

kmeans_3.fit(x)
y_pred = kmeans_3.predict(x)
plt.subplot(224)
plt.scatter(x[:,0],
            x[:,1],
            c=y_pred,
            s=5,
            marker="o")

kmeans_4.fit(x)
y_pred = kmeans_4.predict(x)
plt.subplot(223)
plt.scatter(x[:,0],
            x[:,1],
            c=y_pred,
            s=5,
            marker="o")

plt.show()

 结果展示：

二、

 

K-means 练习题

‌数据集‌：

(2,10), (2,5), (8,4), (5,8), (7,5), (6,4), (1,2), (4,9)

1. 使用K-means算法将上述点分为2个簇，初始中心点选择(2,10)和(5,8)
2. 进行两次迭代并展示每次的簇分配和中心点更新

代码展示：

from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import numpy as np
import os
os.environ["LOKY_MAX_CPU_COUNT"] = "8"  # 设置为你想要使用的核心数

plt.rcParams["font.sans-serif"] = ["SimHei"]
plt.rcParams["axes.unicode_minus"] = False

poits = np.array([[2,10],[2,5],[8,4],[5,8],[7,5],[6,4],[1,2],[4,9]])

centers = np.array([[2,10],[5,8]])

kmeans_1 = KMeans(n_clusters=2,init=centers,n_init=1,max_iter=1)
kmeans_1.fit(poits)
centers_iter1 = kmeans_1.cluster_centers_

plt.scatter(
    poits[:,0],
    poits[:,1],
    c=kmeans_1.labels_,
    cmap="viridis"
)

# plt.scatter(
#     centers[:,0],
#     centers[:,1],
#     c="red"
# )

plt.scatter(
    centers_iter1[:,0],
    centers_iter1[:,1],
    c="orange"
)
plt.title("第一次迭代后")
plt.show()

kmeans_2 = KMeans(n_clusters=2,init=centers_iter1,n_init=1,max_iter=1)
kmeans_2.fit(poits)
centers_iter2 = kmeans_2.cluster_centers_

plt.scatter(
    poits[:,0],
    poits[:,1],
    c=kmeans_2.labels_,
    cmap="viridis"
)

plt.scatter(
    centers_iter1[:,0],
    centers_iter1[:,1],
    c="orange"
)

plt.scatter(
    centers_iter2[:,0],
    centers_iter2[:,1],
    c="green"
)

print("第二次迭代后")
plt.show()

结果展示：

 

 

三、

 

项目背景

假设你是一家电子商务公司的数据分析师，公司希望根据客户的购买行为数据进行客户细分，以便制定更有针对性的营销策略。你需要使用K-means聚类算法对客户进行分组，并使用轮廓系数确定最佳K值。

数据集

我们将使用Kaggle上的"Customer Segmentation"数据集：

• 数据集链接: Mall Customer Segmentation Data | Kaggle
• 数据集包含客户ID、性别、年龄、年收入(千美元)和消费分数(1-100)

代码展示：

import matplotlib.pyplot as plt
import pandas as pd
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
from sklearn.metrics import silhouette_score
import os

from sklearn.preprocessing import StandardScaler

os.environ["LOKY_MAX_CPU_COUNT"] = "8"  # 设置为你想要使用的核心数

plt.rcParams["font.sans-serif"] = ["SimHei"]
plt.rcParams["axes.unicode_minus"] = False

data = pd.read_csv("./data/Mall_Customers.csv",encoding="utf-8")
print(data.head())

data['Gender'] = data['Gender'].map({'Male':0,'Female':1})

X = data[["Annual Income (k$)","Spending Score (1-100)"]]

# transform = StandardScaler()
# X = transform.fit_transform(X)

range_k = range(2,11)

sc_list = []

for i in range_k:
    kmeans = KMeans(
        n_clusters=i,
        random_state=42
    )

    pred = kmeans.fit_predict(X)

    sc = silhouette_score(X,pred)

    sc_list.append(sc)

plt.plot(range_k,sc_list,"bo-")
plt.xlabel("k")
plt.ylabel("sc")
plt.title("k-sc")
plt.grid()
plt.show()


kmeans = KMeans(n_clusters=5,random_state=42)
kmeans.fit(X)
y_means = kmeans.predict(X)


plt.figure(figsize=(8,6))

scatter = plt.scatter(
    X.iloc[:,0],
    X.iloc[:,1],
    c=y_means,
    s=30,
    cmap="viridis"
)

centers = kmeans.cluster_centers_

center_scatter = plt.scatter(
    centers[:,0],
    centers[:,1],
    c="black",
    s=100,
    marker="x",
    linewidths=5,
    label="Centroids"
)

# 创建自定义图例元素
legend_elements = [
    # 添加各簇颜色说明
    plt.Line2D([0], [0],
              marker='o',
              color='w',
              label=f'Cluster {i+1}',
              markerfacecolor=plt.cm.viridis(i/4),  # 保持viridis颜色映射
              markersize=10)
    for i in range(5)
] + [
    # 添加中心点说明
    plt.Line2D([0], [0],
              marker='x',
              color='black',
              markersize=10,
              label='Centroids',
              linestyle='None')
]

# 添加右侧图例
plt.legend(
    handles=legend_elements,
    title="图例说明",
    loc='center left',
    bbox_to_anchor=(0.85, 0.5),  # 定位到画布右侧
    frameon=True,
    title_fontsize=12,
    fontsize=10,
    edgecolor='#DDDDDD'
)

plt.xlabel("年收入（k$）")
plt.ylabel("消费分数（1-100）")
plt.title("客户细分结果")
plt.grid()
plt.tight_layout()
plt.show()

结果展示：