svm c语言代码,15 SVM - 代码案例二 - 鸢尾花数据不同分类器效果比较

SVM的章节已经讲完，具体内容请参考：《01 SVM - 大纲》

回顾案例一中的头文件：import numpy as npimport pandas as pdimport matplotlib as mplimport matplotlib.pyplot as pltimport warningsfrom sklearn import svm#svm导入from sklearn.svm import SVCfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.exceptions import ChangedBehaviorWarning

案例二 - 鸢尾花数据不同分类器效果比较

常规操作：

1、头文件引入SVM相关的包

2、防止中文乱码

3、去警告

4、读取数据

5、数据分割训练集和测试集 6:4import numpy as npimport pandas as pdimport matplotlib as mplimport matplotlib.pyplot as pltimport warningsfrom sklearn.svm import SVCfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.linear_model import LogisticRegression,RidgeClassifierfrom sklearn.neighbors import KNeighborsClassifier## 设置属性防止中文乱码mpl.rcParams['font.sans-serif'] = [u'SimHei']mpl.rcParams['axes.unicode_minus'] = Falsewarnings.filterwarnings('ignore', category=ChangedBehaviorWarning)## 读取数据# 'sepal length', 'sepal width', 'petal length', 'petal width'iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度'path = './datas/iris.data' # 数据文件路径data = pd.read_csv(path, header=None)x, y = data[list(range(4))], data[4]y = pd.Categorical(y).codes #把文本数据进行编码，比如a b c编码为 0 1 2x = x[[0, 1]]## 数据分割x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=28, train_size=0.6)

数据SVM分类器构建:svm = SVC(C=1, kernel='linear')## 模型训练svm.fit(x_train, y_train)

svm.intercept_

Linear分类器构建:

RidgeClassifier(): ridge是为了解决特征大于样本，而导致分类效果较差的情况，而提出的。

svm有一个重要的瓶颈——当特征数大于样本数的时候，效果变差。lr = LogisticRegression()rc = RidgeClassifier()knn = KNeighborsClassifier()## 模型训练lr.fit(x_train, y_train)rc.fit(x_train, y_train)knn.fit(x_train, y_train)

效果评估：svm_score1 = accuracy_score(y_train, svm.predict(x_train))svm_score2 = accuracy_score(y_test, svm.predict(x_test))lr_score1 = accuracy_score(y_train, lr.predict(x_train))lr_score2 = accuracy_score(y_test, lr.predict(x_test))rc_score1 = accuracy_score(y_train, rc.predict(x_train))rc_score2 = accuracy_score(y_test, rc.predict(x_test))knn_score1 = accuracy_score(y_train, knn.predict(x_train))knn_score2 = accuracy_score(y_test, knn.predict(x_test))

画图 - 鸢尾花数据不同分类器准确率比较:x_tmp = [0,1,2,3]y_score1 = [svm_score1, lr_score1, rc_score1, knn_score1]y_score2 = [svm_score2, lr_score2, rc_score2, knn_score2]plt.figure(facecolor='w')plt.plot(x_tmp, y_score1, 'r-', lw=2, label=u'训练集准确率')plt.plot(x_tmp, y_score2, 'g-', lw=2, label=u'测试集准确率')plt.xlim(0, 3)plt.ylim(np.min((np.min(y_score1), np.min(y_score2)))*0.9, np.max((np.max(y_score1), np.max(y_score2)))*1.1)plt.legend(loc = 'lower right')plt.title(u'鸢尾花数据不同分类器准确率比较', fontsize=16)plt.xticks(x_tmp, [u'SVM', u'Logistic', u'Ridge', u'KNN'], rotation=0)plt.grid(b=True)plt.show()

画图比较分类结果：N = 500x1_min, x2_min = x.min()x1_max, x2_max = x.max()t1 = np.linspace(x1_min, x1_max, N)t2 = np.linspace(x2_min, x2_max, N)x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点grid_show = np.dstack((x1.flat, x2.flat))[0] # 测试点

获取各个不同算法的测试值:svm_grid_hat = svm.predict(grid_show)svm_grid_hat = svm_grid_hat.reshape(x1.shape) # 使之与输入的形状相同lr_grid_hat = lr.predict(grid_show)lr_grid_hat = lr_grid_hat.reshape(x1.shape) # 使之与输入的形状相同rc_grid_hat = rc.predict(grid_show)rc_grid_hat = rc_grid_hat.reshape(x1.shape) # 使之与输入的形状相同knn_grid_hat = knn.predict(grid_show)knn_grid_hat = knn_grid_hat.reshape(x1.shape) # 使之与输入的形状相同

画图：cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])plt.figure(facecolor='w', figsize=(14,7))

1、鸢尾花SVM特征分类：plt.subplot(221)## 区域图plt.pcolormesh(x1, x2, svm_grid_hat, cmap=cm_light)## 所以样本点plt.scatter(x[0], x[1], c=y, edgecolors='k', s=50, cmap=cm_dark) # 样本## 测试数据集plt.scatter(x_test[0], x_test[1], s=120, facecolors='none', zorder=10) # 圈中测试集样本## lable列表plt.xlabel(iris_feature[0], fontsize=13)plt.ylabel(iris_feature[1], fontsize=13)plt.xlim(x1_min, x1_max)plt.ylim(x2_min, x2_max)plt.title(u'鸢尾花SVM特征分类', fontsize=16)plt.grid(b=True, ls=':')plt.tight_layout(pad=1.5)

2、鸢尾花Logistic特征分类：plt.subplot(222)## 区域图plt.pcolormesh(x1, x2, lr_grid_hat, cmap=cm_light)## 所以样本点plt.scatter(x[0], x[1], c=y, edgecolors='k', s=50, cmap=cm_dark) # 样本## 测试数据集plt.scatter(x_test[0], x_test[1], s=120, facecolors='none', zorder=10) # 圈中测试集样本## lable列表plt.xlabel(iris_feature[0], fontsize=13)plt.ylabel(iris_feature[1], fontsize=13)plt.xlim(x1_min, x1_max)plt.ylim(x2_min, x2_max)plt.title(u'鸢尾花Logistic特征分类', fontsize=16)plt.grid(b=True, ls=':')plt.tight_layout(pad=1.5)

3、鸢尾花Ridge特征分类：plt.subplot(223)## 区域图plt.pcolormesh(x1, x2, rc_grid_hat, cmap=cm_light)## 所以样本点plt.scatter(x[0], x[1], c=y, edgecolors='k', s=50, cmap=cm_dark) # 样本## 测试数据集plt.scatter(x_test[0], x_test[1], s=120, facecolors='none', zorder=10) # 圈中测试集样本## lable列表plt.xlabel(iris_feature[0], fontsize=13)plt.ylabel(iris_feature[1], fontsize=13)plt.xlim(x1_min, x1_max)plt.ylim(x2_min, x2_max)plt.title(u'鸢尾花Ridge特征分类', fontsize=16)plt.grid(b=True, ls=':')plt.tight_layout(pad=1.5)

4、鸢尾花KNN特征分类:plt.subplot(224)## 区域图plt.pcolormesh(x1, x2, knn_grid_hat, cmap=cm_light)## 所以样本点plt.scatter(x[0], x[1], c=y, edgecolors='k', s=50, cmap=cm_dark) # 样本## 测试数据集plt.scatter(x_test[0], x_test[1], s=120, facecolors='none', zorder=10) # 圈中测试集样本## lable列表plt.xlabel(iris_feature[0], fontsize=13)plt.ylabel(iris_feature[1], fontsize=13)plt.xlim(x1_min, x1_max)plt.ylim(x2_min, x2_max)plt.title(u'鸢尾花KNN特征分类', fontsize=16)plt.grid(b=True, ls=':')plt.tight_layout(pad=1.5)plt.show()