机器学习算法05——SVM实战

1.SVM概念

SVM是一种二分类模型，用于特征空间上得到间隔最大的线性分类器，基本思想是使得两类离分类平面间隔最大化，并且最终转化为一个凸二次规划问题求解。

2.实例

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

from sklearn.svm import SVC

from sklearn.metrics import confusion_matrix

dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:,[2,3]].values
y = dataset.iloc[:,4].values

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=0)

sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.fit_transform(X_test)

classi = SVC(kernel='linear',random_state=0)
classi.fit(X_train,y_train)

y_pred = classi.predict(X_test)

#创建混淆矩阵
cm = confusion_matrix(y_test,y_pred)

X_set,y_set = X_train,y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classi.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
         c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('SVM (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classi.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
       c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('SVM (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()