本文共 2435 字，大约阅读时间需要 8 分钟。

算法部分不再细讲，之前发过很多：

实验：

导入需要用到的python库

import numpy as npimport matplotlib.pyplot as pltimport pandas as pd

导入数据集

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

将数据集拆分为训练集和测试集

from sklearn.model_selection import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

特征缩放

from sklearn.preprocessing import StandardScalersc = StandardScaler()X_train = sc.fit_transform(X_train)X_test = sc.transform(X_test)

对测试集进行决策树分类拟合

from sklearn.tree import DecisionTreeClassifierclassifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)classifier.fit(X_train, y_train)

预测测试集的结果

y_pred = classifier.predict(X_test)

制作混淆矩阵

from sklearn.metrics import confusion_matrixcm = confusion_matrix(y_test, y_pred)

将训练集结果进行可视化

from matplotlib.colors import ListedColormapX_set, y_set = X_train, y_trainX1, 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, classifier.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('Decision Tree Classification (Training set)')plt.xlabel('Age')plt.ylabel('Estimated Salary')plt.legend()plt.show()

将测试集结果进行可视化

from matplotlib.colors import ListedColormapX_set, y_set = X_test, y_testX1, 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, classifier.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('Decision Tree Classification (Test set)')plt.xlabel('Age')plt.ylabel('Estimated Salary')plt.legend()plt.show()