昨天我们学习了支持向量机基本概念，重申数学推导原理的重要性并向大家介绍了一篇非常不错的文章。今天，我们使用Scikit-Learn中的SVC分类器实现SVM。我们将在day16使用kernel-trick实现SVM。
导入库
import numpy as np import matplotlib.pyplot as plt import pandas as pd
导入数据
数据集依然是Social_Network_Ads，下载链接：
dataset = pd.read_csv('Social_Network_Ads.csv') X = dataset.iloc[:, [2, 3]].values y = dataset.iloc[:, 4].values
拆分数据集为训练集合和测试集合
from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
特征量化
from sklearn.preprocessing import StandardScaler sc = StandardScaler() X_train = sc.fit_transform(X_train) X_test = sc.fit_transform(X_test)
适配SVM到训练集合
from sklearn.svm import SVC classifier = SVC(kernel = 'linear', random_state = 0) classifier.fit(X_train, y_train)
预测测试集合结果
y_pred = classifier.predict(X_test)
创建混淆矩阵
from sklearn.metrics import confusion_matrix cm = confusion_matrix(y_test, y_pred)
训练集合结果可视化
from matplotlib.colors import ListedColormap 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, 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('SVM (Training set)') plt.xlabel('Age') plt.ylabel('Estimated Salary') plt.legend() plt.show()
测试集合结果可视化
from matplotlib.colors import ListedColormap 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, 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('SVM (Test set)') plt.xlabel('Age') plt.ylabel('Estimated Salary') plt.legend() plt.show()
