机器学习——SVM实践

SVM基本应用：

import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


# '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'


if __name__ == "__main__":
    path = '..\\8.Regression\\iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x, y = data[range(4)], data[4]
    y = pd.Categorical(y).codes
    x = x[[0, 1]]
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.6)

    # 分类器
    clf = svm.SVC(C=0.1, kernel='linear', decision_function_shape='ovr')
    # clf = svm.SVC(C=0.8, kernel='rbf', gamma=20, decision_function_shape='ovr')
    clf.fit(x_train, y_train.ravel())

    # 准确率
    print clf.score(x_train, y_train)  # 精度
    print '训练集准确率：', accuracy_score(y_train, clf.predict(x_train))
    print clf.score(x_test, y_test)
    print '测试集准确率：', accuracy_score(y_test, clf.predict(x_test))

    # decision_function
    print 'decision_function:\n', clf.decision_function(x_train)
    print '\npredict:\n', clf.predict(x_train)

    # 画图
    x1_min, x2_min = x.min()
    x1_max, x2_max = x.max()
    x1, x2 = np.mgrid[x1_min:x1_max:500j, x2_min:x2_max:500j]  # 生成网格采样点
    grid_test = np.stack((x1.flat, x2.flat), axis=1)  # 测试点
    # print 'grid_test = \n', grid_test
    # Z = clf.decision_function(grid_test)    # 样本到决策面的距离
    # print Z
    grid_hat = clf.predict(grid_test)       # 预测分类值
    grid_hat = grid_hat.reshape(x1.shape)  # 使之与输入的形状相同
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False

    cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
    cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
    plt.figure(facecolor='w')
    plt.pcolormesh(x1, x2, grid_hat, cmap=cm_light)
    plt.scatter(x[0], x[1], c=y, edgecolors='k', s=50, cmap=cm_dark)      # 样本
    plt.scatter(x_test[0], x_test[1], s=120, facecolors='none', zorder=10)     # 圈中测试集样本
    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二特征分类', fontsize=16)
    plt.grid(b=True, ls=':')
    plt.tight_layout(pad=1.5)
    plt.show()

SVM_draw:

import numpy as np
from sklearn import svm
import matplotlib as mpl
import matplotlib.colors
import matplotlib.pyplot as plt


def show_accuracy(a, b):
    acc = a.ravel() == b.ravel()
    # print '正确率：%.2f%%' % (100*float(acc.sum()) / a.size)


if __name__ == "__main__":
    data = np.loadtxt('bipartition.txt', dtype=np.float, delimiter='\t')
    x, y = np.split(data, (2, ), axis=1)
    y = y.ravel()

    # 分类器
    clf_param = (('linear', 0.1), ('linear', 0.5), ('linear', 1), ('linear', 2),
                ('rbf', 1, 0.1), ('rbf', 1, 1), ('rbf', 1, 10), ('rbf', 1, 100),
                ('rbf', 5, 0.1), ('rbf', 5, 1), ('rbf', 5, 10), ('rbf', 5, 100))
    x1_min, x1_max = x[:, 0].min(), x[:, 0].max()  # 第0列的范围
    x2_min, x2_max = x[:, 1].min(), x[:, 1].max()  # 第1列的范围
    x1, x2 = np.mgrid[x1_min:x1_max:200j, x2_min:x2_max:200j]  # 生成网格采样点
    grid_test = np.stack((x1.flat, x2.flat), axis=1)  # 测试点

    cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FFA0A0'])
    cm_dark = mpl.colors.ListedColormap(['g', 'r'])
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(14, 10), facecolor='w')
    for i, param in enumerate(clf_param):
        clf = svm.SVC(C=param[1], kernel=param[0])
        if param[0] == 'rbf':
            clf.gamma = param[2]
            title = u'高斯核，C=%.1f，$\gamma$ =%.1f' % (param[1], param[2])
        else:
            title = u'线性核，C=%.1f' % param[1]

        clf.fit(x, y)
        y_hat = clf.predict(x)
        show_accuracy(y_hat, y)  # 准确率

        # 画图
        print title
        print '支撑向量的数目：', clf.n_support_
        print '支撑向量的系数：', clf.dual_coef_
        print '支撑向量：', clf.support_
        plt.subplot(3, 4, i+1)
        grid_hat = clf.predict(grid_test)       # 预测分类值
        grid_hat = grid_hat.reshape(x1.shape)  # 使之与输入的形状相同
        plt.pcolormesh(x1, x2, grid_hat, cmap=cm_light, alpha=0.8)
        plt.scatter(x[:, 0], x[:, 1], c=y, edgecolors='k', s=40, cmap=cm_dark)      # 样本的显示
        plt.scatter(x[clf.support_, 0], x[clf.support_, 1], edgecolors='k', facecolors='none', s=100, marker='o')   # 支撑向量
        z = clf.decision_function(grid_test)
        # print 'z = \n', z
        print 'clf.decision_function(x) = ', clf.decision_function(x)
        print 'clf.predict(x) = ', clf.predict(x)
        z = z.reshape(x1.shape)
        plt.contour(x1, x2, z, colors=list('kbrbk'), linestyles=['--', '--', '-', '--', '--'],
                    linewidths=[1, 0.5, 1.5, 0.5, 1], levels=[-1, -0.5, 0, 0.5, 1])
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.title(title, fontsize=14)
    plt.suptitle(u'SVM不同参数的分类', fontsize=20)
    plt.tight_layout(1.4)
    plt.subplots_adjust(top=0.92)
    plt.savefig('1.png')
    plt.show()