支持向量机SVM

1.概念

2.代码

鸢尾花
SVM.Intro.py

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

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

def iris_type(s):
    it = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
    return it[s]


# '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'


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


if __name__ == "__main__":
    path = '..\\8.Regression\\8.iris.data'  # 数据文件路径
    data = np.loadtxt(path, dtype=float, delimiter=',', converters={4: iris_type})
    x, y = np.split(data, (4,), axis=1)
    x = x[:, :2]
    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') #设置参数
    clf.fit(x_train, y_train.ravel()) # 训练

    # 准确率
    print clf.score(x_train, y_train)  # 打印精度
    y_hat = clf.predict(x_train) #预测
    show_accuracy(y_hat, y_train, '训练集') #打印正确率
    print clf.score(x_test, y_test)
    y_hat = clf.predict(x_test)
    show_accuracy(y_hat, y_test, '测试集')

    # 画图
    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: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

    Z = clf.decision_function(grid_test)    # 样本点到决策面的距离
    print Z
    grid_hat = clf.predict(grid_test)       # 预测分类值
    print grid_hat
    grid_hat = grid_hat.reshape(x1.shape)  # 使之与输入的形状相同
    #中文
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False

	# 设置颜色
    cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
    cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
    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: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
    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=15)
    plt.grid()
    plt.show()

SVM_draw.py

#!/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('14.bipartition.txt', dtype=np.float, delimiter='\t') #读入数据
    x, y = np.split(data, (2, ), axis=1) #第二列
    y[y == 0] = -1
    y = y.ravel() #向量形式

    # 分类器
    clfs = [svm.SVC(C=0.3, kernel='linear'), #不同核不同参数
           svm.SVC(C=10, kernel='linear'),
           svm.SVC(C=5, kernel='rbf', gamma=1),
           svm.SVC(C=5, kernel='rbf', gamma=4)]
    titles = 'Linear,C=0.3', 'Linear, C=10', 'RBF, gamma=1', 'RBF, gamma=4'

    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: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

    cm_light = matplotlib.colors.ListedColormap(['#77E0A0', '#FF8080'])
    cm_dark = matplotlib.colors.ListedColormap(['g', 'r'])
    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(10,8), facecolor='w') #窗口大小和颜色
    for i, clf in enumerate(clfs):
        clf.fit(x, y) #训练模型

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

        # 画图
        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_
        print
        plt.subplot(2, 2, 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)
        z = z.reshape(x1.shape)
        plt.contour(x1, x2, z, colors=list('krk'), linestyles=['--', '-', '--'], linewidths=[1, 2, 1], levels=[-1, 0, 1])
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.title(titles[i])
        plt.grid()
    plt.suptitle(u'SVM不同参数的分类', fontsize=18)
    plt.tight_layout(2)
    plt.subplots_adjust(top=0.92)
    plt.show()

ClassifierIndex.py

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

import numpy as np
from sklearn.metrics import accuracy_score #度量标准
from sklearn.metrics import precision_score, recall_score, f1_score, fbeta_score
from sklearn.metrics import precision_recall_fscore_support


if __name__ == "__main__":
    y_true = np.array([1, 1, 1, 1, 0, 0]) #实际值
    y_hat = np.array([1, 0, 1, 1, 1, 1]) #估计值
    print 'Accuracy：\t', accuracy_score(y_true, y_hat)
	#精确率
    # The precision is the ratio 'tp / (tp + fp)' where 'tp' is the number of
    # true positives and 'fp' the number of false positives. The precision is
    # intuitively the ability of the classifier not to label as positive a sample
    # that is negative.
    # The best value is 1 and the worst value is 0.
    precision = precision_score(y_true, y_hat)
    print 'Precision:\t', precision
	#查全率
    # The recall is the ratio 'tp / (tp + fn)' where 'tp' is the number of
    # true positives and 'fn' the number of false negatives. The recall is
    # intuitively the ability of the classifier to find all the positive samples.
    # The best value is 1 and the worst value is 0.
    recall = recall_score(y_true, y_hat)
    print 'Recall:  \t', recall
	# F1值
    # F1 score, also known as balanced F-score or F-measure
    # The F1 score can be interpreted as a weighted average of the precision and
    # recall, where an F1 score reaches its best value at 1 and worst score at 0.
    # The relative contribution of precision and recall to the F1 score are
    # equal. The formula for the F1 score is:
    #     F1 = 2 * (precision * recall) / (precision + recall)
    print 'f1 score: \t', f1_score(y_true, y_hat)
    #print 2 * (precision * recall) / (precision + recall)
	# F-beta值
    # The F-beta score is the weighted harmonic mean of precision and recall,
    # reaching its optimal value at 1 and its worst value at 0.
    # The 'beta' parameter determines the weight of precision in the combined
    # score. 'beta < 1' lends more weight to precision, while 'beta > 1'
    # favors recall ('beta -> 0' considers only precision, 'beta -> inf' only recall).
    print 'F-beta：'
    for beta in np.logspace(-3, 3, num=7, base=10): #构造等比数列，不同的beta值
        fbeta = fbeta_score(y_true, y_hat, beta=beta)
        print '\tbeta=%9.3f\tF-beta=%.5f' % (beta, fbeta)
        #print (1+beta**2)*precision*recall / (beta**2 * precision + recall)

    print precision_recall_fscore_support(y_true, y_hat, beta=1) #另一种调用方法

当出现不同类别之间的数量相差十分巨大的情况
unBalance.py

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

import numpy as np
from sklearn import svm
import matplotlib.colors
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, fbeta_score
import warnings


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


def show_recall(y, y_hat):
    # print y_hat[y == 1]
    print '召回率：%.2f%%' % (100 * float(np.sum(y_hat[y == 1] == 1)) / np.extract(y == 1, y).size)


if __name__ == "__main__":
    warnings.filterwarnings("ignore")   # UndefinedMetricWarning
    np.random.seed(0)   # 保持每次生成的数据相同

    c1 = 990
    c2 = 10
    N = c1 + c2
    x_c1 = 3*np.random.randn(c1, 2) #做了c1行，2列的高斯数据
    x_c2 = 0.5*np.random.randn(c2, 2) + (4, 4) #选定4,4点处c2行2列的数据，改变其值
    x = np.vstack((x_c1, x_c2)) #数据整合
    y = np.ones(N) #全1
    y[:c1] = -1 #后十个为-1

    # 显示大小
    s = np.ones(N) * 30
    s[:c1] = 10

    # 分类器：线性核/高斯核
    clfs = [svm.SVC(C=1, kernel='linear'),
           svm.SVC(C=1, kernel='linear', class_weight={-1: 1, 1: 50}), #设置大小类的个数
           svm.SVC(C=0.8, kernel='rbf', gamma=0.5, class_weight={-1: 1, 1: 2}),
           svm.SVC(C=0.8, kernel='rbf', gamma=0.5, class_weight={-1: 1, 1: 10})]
    titles = 'Linear', 'Linear, Weight=50', 'RBF, Weight=2', 'RBF, Weight=10'

    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: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

    cm_light = matplotlib.colors.ListedColormap(['#77E0A0', '#FF8080'])
    cm_dark = matplotlib.colors.ListedColormap(['g', 'r'])
    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(10, 8), facecolor='w')
    for i, clf in enumerate(clfs):
        clf.fit(x, y)

        y_hat = clf.predict(x)
        # show_accuracy(y_hat, y) # 正确率
        # show_recall(y, y_hat)   # 召回率
        print i+1, '次：'
        print '正确率：\t', accuracy_score(y, y_hat)
        print ' 精度 ：\t', precision_score(y, y_hat, pos_label=1)
        print '召回率：\t', recall_score(y, y_hat, pos_label=1)
        print 'F1Score：\t', f1_score(y, y_hat, pos_label=1)
        print


        # 画图
        plt.subplot(2, 2, 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=s, cmap=cm_dark)      # 样本的显示
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.title(titles[i])
        plt.grid()
    plt.suptitle(u'不平衡数据的处理', fontsize=18)
    plt.tight_layout(1.5)
    plt.subplots_adjust(top=0.92)
    plt.show()

0-9数字图像分类
数据中每行前8*8代表图像，最后一位代表数值
HandWrittenDigits.py

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

import numpy as np
from sklearn import svm
import matplotlib.colors
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.metrics import accuracy_score
import os


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('14.optdigits.tra', dtype=np.float, delimiter=',')
    x, y = np.split(data, (-1, ), axis=1)
    images = x.reshape(-1, 8, 8) #使数据变成若干个8*8的数据块
    y = y.ravel().astype(np.int)

    print 'Load Test Data Start...'
    data = np.loadtxt('14.optdigits.tes', dtype=np.float, delimiter=',')
    x_test, y_test = np.split(data, (-1, ), axis=1) #前面的给x，最后一列给y
    images_test = x_test.reshape(-1, 8, 8)
    y_test = y_test.ravel().astype(np.int) #载入数据
    print 'Load Data OK...'

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

	#显示数据，确保读取正确
    matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(15, 9), facecolor='w') #大小颜色
    for index, image in enumerate(images[:16]): #取前16个显示
        plt.subplot(4, 8, index + 1) #显示4*8
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest') #用灰度表示大小显示图片，用近邻方式
        plt.title(u'训练图片: %i' % y[index]) #显示图片的值
    for index, image in enumerate(images_test[:16]): #测试的前16个
        plt.subplot(4, 8, index + 17)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        save_image(image.copy(), index) #保存数据，带索引
        plt.title(u'测试图片: %i' % y_test[index])
    plt.tight_layout()
    plt.show()

    clf = svm.SVC(C=1, kernel='rbf', gamma=0.001)   # 确定参数，当gamma很小时，类似k近邻~ kNN
    print 'Start Learning...'
    clf.fit(x, y) #训练
    print 'Learning is OK...'
    y_hat = clf.predict(x) #训练数据的估计
    show_accuracy(y, y_hat, '训练集')
    y_hat = clf.predict(x_test) # 测试数据的估计
    print y_hat
    print y_test
    show_accuracy(y_test, y_hat, '测试集')

    err_images = images_test[y_test != y_hat] #提取出预测错误的图片
    err_y_hat = y_hat[y_test != y_hat] #提取预测错误的值
    err_y = y_test[y_test != y_hat]
    print err_y_hat
    print err_y
    plt.figure(figsize=(10, 8), facecolor='w') #打印错误图片
    for index, image in enumerate(err_images):
        if index >= 12: #只显示前12个，3*4
            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])) # 错误值和真实值
    plt.tight_layout()
    plt.show()

用支持向量的方式做回归
SVR.py

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

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


if __name__ == "__main__":
    N = 50
    np.random.seed(0)
    x = np.sort(np.random.uniform(0, 6, N), axis=0) #0-6的均匀分布，然后再排序
    y = 2*np.sin(x) + 0.1*np.random.randn(N) #加小的噪声
    x = x.reshape(-1, 1) #变成一列
    print 'x =\n', x
    print 'y =\n', y

    print 'SVR - RBF'
    svr_rbf = svm.SVR(kernel='rbf', gamma=0.2, C=100) #RBF核
    svr_rbf.fit(x, y) #训练
    print 'SVR - Linear'
    svr_linear = svm.SVR(kernel='linear', C=100) #线性核
    svr_linear.fit(x, y) #训练
    print 'SVR - Polynomial'
    svr_poly = svm.SVR(kernel='poly', degree=3, C=100) #多项式核
    svr_poly.fit(x, y) #训练
    print 'Fit OK.'

    # 思考：系数1.1改成1.5
    x_test = np.linspace(x.min(), 1.1*x.max(), 100).reshape(-1, 1) #生成数据
    y_rbf = svr_rbf.predict(x_test) #预测
    y_linear = svr_linear.predict(x_test)
    y_poly = svr_poly.predict(x_test)

    plt.figure(figsize=(9, 8), facecolor='w')
    plt.plot(x_test, y_rbf, 'r-', linewidth=2, label='RBF Kernel')
    plt.plot(x_test, y_linear, 'g-', linewidth=2, label='Linear Kernel')
    plt.plot(x_test, y_poly, 'b-', linewidth=2, label='Polynomial Kernel')
    plt.plot(x, y, 'mo', markersize=6)
    plt.scatter(x[svr_rbf.support_], y[svr_rbf.support_], s=130, c='r', marker='*', label='RBF Support Vectors') #用特殊符号标记支撑向量
    plt.legend(loc='lower left')
    plt.title('SVR', fontsize=16)
    plt.xlabel('X')
    plt.ylabel('Y')
    plt.grid(True)
    plt.show()

CV.py

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

import numpy as np
from sklearn import svm
from sklearn.model_selection import GridSearchCV    # 0.17 grid_search网格搜索
import matplotlib.pyplot as plt


if __name__ == "__main__":
    N = 50
    np.random.seed(0)
    x = np.sort(np.random.uniform(0, 6, N), axis=0)
    y = 2*np.sin(x) + 0.1*np.random.randn(N)
    x = x.reshape(-1, 1)
    print 'x =\n', x
    print 'y =\n', y

    model = svm.SVR(kernel='rbf') #模型建立
    c_can = np.logspace(-2, 2, 10)
    gamma_can = np.logspace(-2, 2, 10)
    svr = GridSearchCV(model, param_grid={'C': c_can, 'gamma': gamma_can}, cv=5) #网格搜索，遍历c_can和gammma_can的所有值，5次交叉验证
    svr.fit(x, y) #用得到的分类器训练
    print '验证参数：\n', svr.best_params_ # 打印出使用的最好的参数

    x_test = np.linspace(x.min(), x.max(), 100).reshape(-1, 1)
    y_hat = svr.predict(x_test)

    sp = svr.best_estimator_.support_
    plt.figure(facecolor='w')
    plt.scatter(x[sp], y[sp], s=120, c='r', marker='*', label='Support Vectors', zorder=3)
    plt.plot(x_test, y_hat, 'r-', linewidth=2, label='RBF Kernel')
    plt.plot(x, y, 'go', markersize=5)
    plt.legend(loc='upper right')
    plt.title('SVR', fontsize=16)
    plt.xlabel('X')
    plt.ylabel('Y')
    plt.grid(True)
    plt.show()