使用支持向量机对人员聚类

0. 理论

在数学上，支持向量机能够找出更高维的支持向量，由支持向量定义更高维的平面来将数据划分为不同的簇。通过不同的核函数可以得到不同的结果。

1.使用scikit-learn通过SVM进行人员聚集

import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import scale

def createClusteredData(N, k):
    """生成随机的收入、年龄数据

    Args:
        N (int): N个人
        k (int): k个聚类

    Returns:
        tuple: X为人员的收入、年龄， y为分类结果
    """   
    # 生成随机种子 
    np.random.seed(10)
    # 每个聚类的数据量
    pointsPerCluster = float(N)/k
    X = []
    y = []
    # 生成k个聚类  
    for i in range (k):
        incomeCentroid = np.random.uniform(20000.0, 200000.0)
        ageCentroid = np.random.uniform(20.0, 70.0)
        # 每个聚类生成数据
        for j in range(int(pointsPerCluster)):
            X.append([np.random.normal(incomeCentroid, 10000.0), np.random.normal(ageCentroid, 2.0)])    
            y.append(i)
    return np.array(X), np.array(y)

N = 100
k = 5
X, y = createClusteredData(N, k)

# 画图
plt.scatter(X[:,0], X[:,1], c=y)
plt.show()

from sklearn import svm

def plotPredictions(clf):
    xx, yy = np.meshgrid(np.arange(0, 250000, 10),
                     np.arange(10, 70, 0.5))
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])

    plt.figure(figsize=(8, 6))
    Z = Z.reshape(xx.shape)
    plt.contourf(xx, yy, Z, cmap=plt.cm.Paired, alpha=0.8)
    plt.scatter(X[:,0], X[:,1], c=y.astype(np.float))
    plt.show()
    
def try_kernel(kernel_list):    
    """使用不同的核函数查看分类结果

    Args:
        kernel_list (list): 核函数列表
    """    
    for kernel in kernel_list:
        # 训练
        svc = svm.SVC(kernel= kernel).fit(X, y)
        # 预测
        # 1)年龄为40岁，年收入为20W美金的人的分类
        # 2)年龄为65岁，年收入为5W美军的人的分类
        print('核函数:{}'.format(kernel))
        print('预测结果: {}'.format(svc.predict([[200000, 40], [50000, 65]])))
        print('可视化结果:')
        # 画图
        plotPredictions(svc)
        print()
        
kernel_list = ['linear','poly','rbf','sigmoid']  
try_kernel(kernel_list)      

核函数:linear
预测结果: [0 3]
可视化结果:


C:\Users\Administrator\AppData\Local\Temp\ipykernel_14148\3712667999.py:11: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  plt.scatter(X[:,0], X[:,1], c=y.astype(np.float))

核函数:poly
预测结果: [0 3]
可视化结果:


C:\Users\Administrator\AppData\Local\Temp\ipykernel_14148\3712667999.py:11: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  plt.scatter(X[:,0], X[:,1], c=y.astype(np.float))

核函数:rbf
预测结果: [0 3]
可视化结果:


C:\Users\Administrator\AppData\Local\Temp\ipykernel_14148\3712667999.py:11: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  plt.scatter(X[:,0], X[:,1], c=y.astype(np.float))

核函数:sigmoid
预测结果: [3 0]
可视化结果:


C:\Users\Administrator\AppData\Local\Temp\ipykernel_14148\3712667999.py:11: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  plt.scatter(X[:,0], X[:,1], c=y.astype(np.float))

2.参考资料

Python数据科学与机器学习：从入门到实践
作者：
[美]弗兰克•凯恩（Frank Kane）

源代码下载：
https://www.ituring.com.cn/book/2426