5.3 SVM分类

1.鸢尾花SVM分类

鸢尾花数据集——提取码：1234

#!/usr/bin/python
# -*- coding:utf-8 -*-


# 鸢尾花SVM-二特征分类
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
# sklearn中svm
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 = 'iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    # 特征值与目标值
    x, y = data.iloc[:, range(4)], data.iloc[:, 4]
    # 将字符串数据y转换成categorical类别数据，并映射成0,1,2
    y = pd.Categorical(y).codes
    # u'花萼长度', u'花萼宽度'
    x = x.iloc[:, :2]
    # 数据集的分割
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.6)

    # 分类器
    # decision_function_shape='ovr'表示用若干个二分类转换成三分类
    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
    # 到分类器的距离，三个值哪一个大就属于哪一个类别，decision_function与predict一一对应
    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 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()

2.SVM多分类

import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
from sklearn import svm
from sklearn.metrics import accuracy_score


def extend(a, b, r):
    x = a - b
    m = (a + b) / 2
    return m - r * x / 2, m + r * x / 2


if __name__ == "__main__":

    np.random.seed(0)
    N = 20
    x = np.empty((4 * N, 2))
    # 均值的位置
    means = [(-1, 1), (1, 1), (1, -1), (-1, -1)]
    # 方差
    # numpy.eye返回一个二维数组，对角线上为1，其他地方为0
    # np.diag提取对角线或构造一个对角线数组。
    sigmas = [np.eye(2), 2 * np.eye(2), np.diag((1, 2)), np.array(((2, 1), (1, 2)))]
    for i in range(4):
        # 模型
        mn = stats.multivariate_normal(means[i], sigmas[i] * 0.3)
        # 模型中随机采样20个
        x[i * N:(i + 1) * N, :] = mn.rvs(N)
    # reshape((-1, 1)将行变成列
    a = np.array((0, 1, 2, 3)).reshape((-1, 1))
    # 将a复制N份，并且迭代返回结果
    y = np.tile(a, N).flatten()
    print('x=\n', x)
    print('y=\n', y)

    # 分类器
    # decision_function_shape='ovo'表示一对一做一个分类器
    clf = svm.SVC(C=1, kernel='rbf', gamma=1, decision_function_shape='ovo')
    # clf = svm.SVC(C=1, kernel='linear', decision_function_shape='ovr')
    clf.fit(x, y)
    y_hat = clf.predict(x)
    acc = accuracy_score(y, y_hat)
    np.set_printoptions(suppress=True)
    print(u'预测正确的样本个数：%d，正确率：%.2f%%' % (round(acc * 4 * N), 100 * acc))
    # decision_function
    # decision_function_shape='ovo'表示一对一做一个分类器，任取两个有6个分类器
    print('decision_function = \n', clf.decision_function(x))
    print('预测值为', y_hat)

    # 画决策边界
    x1_min, x2_min = np.min(x, axis=0)
    x1_max, x2_max = np.max(x, axis=0)
    x1_min, x1_max = extend(x1_min, x1_max, 1.05)
    x2_min, x2_max = extend(x2_min, x2_max, 1.05)
    x1, x2 = np.mgrid[x1_min:x1_max:500j, x2_min:x2_max:500j]
    x_test = np.stack((x1.flat, x2.flat), axis=1)
    y_test = clf.predict(x_test)
    y_test = y_test.reshape(x1.shape)
    cm_light = mpl.colors.ListedColormap(['#FF8080', '#A0FFA0', '#6060FF', '#F080F0'])
    cm_dark = mpl.colors.ListedColormap(['r', 'g', 'b', 'm'])
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(facecolor