逻辑回归和支持向量机的分类比较 python

 

 

逻辑回归和支持向量机都是机器学习中的二分类算法，却都可以拓展为多分类，程序中SVM采用了多项式核。

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

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

#设置画图过程中，图像的最小值 与最大值取值
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))
    print('x',x.shape,type(x))
    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()#np.tile将原矩阵横向、纵向地复制;.flatten()返回一个折叠成一维的数组

#========SVM分类==========
    clf = svm.SVC(C=0.1, kernel='poly', gamma=1, decision_function_shape='ovo')
#decision_function_shape='ovo'时，为one v one，即将类别两两之间进行划分，用二分类的方法模拟多分类的结果。
    #clf = svm.SVC(C=1, kernel='linear', decision_function_shape='ovr')
#decision_function_shape='ovr'时，为one v rest，即一个类别与其他类别进行划分
    print('svm模型:\n',clf)
    clf.fit(x, y)
    y_hat = clf.predict(x)
    acc = accuracy_score(y, y_hat)
    np.set_printoptions(suppress=True)
    print ('SVM准确率：',acc = accuracy_score(y, y_hat))
    #print ('function',clf.decision_function(x))#决策函数decision_function(),计算样本点到分割超平面的函数距离
   

    #=======逻辑回归=======
    Y=y.reshape((-1,1))
    b = np.ones(Y.shape)
    X = np.column_stack((b,x))
    print(type(X),X.shape,type(b),b.shape)
    model = LogisticRegression()
    model.fit(mat(X), mat(Y))
    predictedLR = model.predict(mat(X))
    print('逻辑回归模型:\n',model)
    print('逻辑回归准确率：', accuracy_score(y, predictedLR))

    #=========画图=========
    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.scatter(mat(X)[:,1].flatten().A[0], mat(X[:,2].flatten().A[0],c=predictedLR.tolist(),marker='x')
    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()

svm模型:
 SVC(C=0.1, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape='ovo', degree=3, gamma=1, kernel='poly',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

SVM准确率： 0.8


逻辑回归模型:
 LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

逻辑回归模型准确率： 0.8