SVM代码实践

这里写自定义目录标题

• 练习1：鸢尾花分类
• 练习2：SVM实现一个多分类器
• 练习3：SVM选用不同核参数
• 练习4：手写数字识别

练习1：鸢尾花分类

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

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()

练习2：SVM实现一个多分类器

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

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


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))
    means = [(-1, 1), (1, 1), (1, -1), (-1, -1)]
    sigmas = [np.eye(2), 2*np.eye(2), np.diag((1,2)), np.array(((2,1),(1,2)))]
    for i in range(4):
        mn = stats.multivariate_normal(means[i], sigmas[i]*0.3)
        x[i*N:(i+1)*N, :] = mn.rvs(N)
    a = np.array((0,1,2,3)).reshape((-1, 1))
    y = np.tile(a, N).flatten()
    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
    print(clf.decision_function(x))
    print(y_hat)

    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='w')
    plt.pcolormesh(x1, x2, y_test, cmap=cm_light)
    plt.scatter(x[:, 0], x[:, 1], s=40, c=y, cmap=cm_dark, alpha=0.7)
    plt.xlim((x1_min, x1_max))
    plt.ylim((x2_min, x2_max))
    plt.grid(b=True)
    plt.tight_layout(pad=2.5)
    plt.title(u'SVM多分类方法：One/One or One/Other', fontsize=18)
    plt.show()

练习3：SVM选用不同核参数

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

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()

练习4：手写数字识别

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

import numpy as np
import pandas as pd
from sklearn import svm
import matplotlib.colors
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.metrics import accuracy_score
import os
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from time import time


def show_accuracy(a, b, tip):
    acc = a.ravel() == b.ravel()
    print (tip + '正确率：%.2f%%' % (100*np.mean(acc)))


def save_image(im, i):
    im *= 15.9375
    im = 255 - im
    a = im.astype(np.uint8)
    output_path = '.\\HandWritten'
    if not os.path.exists(output_path):
        os.mkdir(output_path)
    Image.fromarray(a).save(output_path + ('\\%d.png' % i))


if __name__ == "__main__":
    print ('Load Training File Start...')
    data = np.loadtxt('optdigits.tra', dtype=np.float, delimiter=',')
    x, y = np.split(data, (-1, ), axis=1)
    images = x.reshape(-1, 8, 8)
    y = y.ravel().astype(np.int)

    print ('Load Test Data Start...')
    data = np.loadtxt('optdigits.tes', dtype=np.float, delimiter=',')
    x_test, y_test = np.split(data, (-1, ), axis=1)
    print (y_test.shape)
    images_test = x_test.reshape(-1, 8, 8)
    y_test = y_test.ravel().astype(np.int)
    print ('Load Data OK...')

    # x, x_test, y, y_test = train_test_split(x, y, test_size=0.4, random_state=1)
    # images = x.reshape(-1, 8, 8)
    # images_test = x_test.reshape(-1, 8, 8)

    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(15, 9), facecolor='w')
    for index, image in enumerate(images[:16]):
        plt.subplot(4, 8, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title(u'训练图片: %i' % y[index])
    for index, image in enumerate(images_test[:16]):
        plt.subplot(4, 8, index + 17)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        save_image(image.copy(), index)
        plt.title(u'测试图片: %i' % y_test[index])
    plt.tight_layout()
    plt.show()

    # params = {'C':np.logspace(0, 3, 7), 'gamma':np.logspace(-5, 0, 11)}
    # model = GridSearchCV(svm.SVC(kernel='rbf'), param_grid=params, cv=3)
    model = svm.SVC(C=10, kernel='rbf', gamma=0.001)
    print ('Start Learning...')
    t0 = time()
    model.fit(x, y)
    t1 = time()
    t = t1 - t0
    print ('训练+CV耗时：%d分钟%.3f秒' % (int(t/60), t - 60*int(t/60)))
    # print '最优参数：\t', model.best_params_
    #clf.fit(x, y)
    print( 'Learning is OK...')
    print ('训练集准确率：', accuracy_score(y, model.predict(x)))
    y_hat = model.predict(x_test)
    print ('测试集准确率：', accuracy_score(y_test, model.predict(x_test)))
    print (y_hat)
    print (y_test)

    err_images = images_test[y_test != y_hat]
    err_y_hat = y_hat[y_test != y_hat]
    err_y = y_test[y_test != y_hat]
    print (err_y_hat)
    print (err_y)
    plt.figure(figsize=(10, 8), facecolor='w')
    for index, image in enumerate(err_images):
        if index >= 12:
            break
        plt.subplot(3, 4, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title(u'错分为：%i，真实值：%i' % (err_y_hat[index], err_y[index]))
    plt.tight_layout()
    plt.show()