Python实现感知器算法与数据训练

 数据生成与PLA、POCKET算法训练。

a)产生两个都具有200个二维向量的数据集X_1和X_2。
    数据集X_1的样本来自均值向量〖m_1=[-5,0]〗^T 、协方差矩阵s_1=I的正态分布，属于“+1”类，
    数据集X_2的样本来自均值向量〖m_2=[0,5]〗^T、协方差矩阵s_2=I的正态分布，属于“-1”类，
    其中I是一个2*2的单位矩阵。产生的数据中80%用于训练，20%用于测试
b)分别运用PLA算法和Pocket算法，利用产生的训练样本集得到分类面，算法中用到的各类超参数自定。
c)分别在训练集和测试集上统计分类正确率。
d)分别统计两个算法的运行时间
e)画出数据集和分类面。

#encoding:utf-8
'''
@ author: Darcy

'''

import numpy as np
from numpy import *
import random
import math
import matplotlib.pyplot as plt
from matplotlib import style
import operator
import sklearn.linear_model

def Data_Creat():
    mean = (1, 0)
    cov = [[1, 0], [0, 1]]
    x_1 = np.random.multivariate_normal(mean, cov, 200)
    mean = (0, 1)
    x_2 = np.random.multivariate_normal(mean, cov, 200)

    # 增广
    b = []
    for i in range(0, 200):
        b.append(1)
    x1 = np.column_stack((b, x_1))
    x2 = np.column_stack((b, x_2))

    input_data = np.vstack((x1[:160], x2[:160]))
    test_data = np.vstack((x1[160:200], x2[160:200]))
    y = []
    y_test = []
    w = np.zeros(3)
    for i in range (0, 160):
        y.append(1)
    for i in range(160, 320):
        y.append(-1)

    for i in range (0, 40):
        y_test.append(1)
    for i in range(0, 40):
        y_test.append(-1)

    return input_data, y, w, test_data, y_test


def pic_data():
    mean = (1, 0)
    cov = [[1, 0], [0, 1]]
    x_1 = np.random.multivariate_normal(mean, cov, 200)
    mean = (0, 1)
    x_2 = np.random.multivariate_normal(mean, cov, 200)

    W_best = my_pocket()
    x = arange(-5.0, 5.0, 0.1)
    y = W_best[0]+ W_best[1] * x
    plt.plot(x, y, color="red", linewidth=1.0, linestyle="-") # 将100个散点连在一起

    plt.scatter(x_1[1:160, 0], x_1[1:160, 1], s = 160)
    plt.scatter(x_2[1:160, 0], x_2[1:160, 1], s = 160)
    plt.show()
    style.use('ggplot')



def my_pla():
    X, y, W, _, _ = Data_Creat()
    count = 0
    while 1:
        count += 1
        flag = True
        for i in range(0, len(X)):
            Y = np.dot(W, X[i])
            if sign(Y) == sign(y[i]):
                continue
            else:
                flag = False
                W = W + (np.dot(y[i], X[i]))
        if flag == True:
            break

    print("final W is:", W)
    print("number of cycles is: ", count)

    x = arange(-5.0, 5.0, 0.1)
    y = W[0] + W[1] * x + W[2] * x
    plt.plot(x, y, color="red", linewidth=1.0, linestyle="-")  # 将100个散点连在一起
    plt.show()

    return W


def my_pocket():
    time = 100
    W_best = np.zeros(3)
    X, Y, W, _, _ = Data_Creat()
    count = 0
    flag = False
    while flag == False:
        mistakes = pock_classify(W, X, Y)
        if ( len(mistakes) == 0):
            print("最终训练得到的W为：", W_best)
            break
        num_upt = mistakes[random.randint(0, len(mistakes) - 1)]
        W = W + (np.dot(Y[num_upt], X[num_upt]))
        if (len(pock_classify(W, X, Y)) < len(pock_classify(W_best, X, Y))):
            W_best = W
        count = count + 1
        print("第", count, "次更新, 选取X为：", X[num_upt], "此时W为：", W_best, "错误分类点个数为：", len(pock_classify(W_best, X, Y)))
        if count == time:
            print("最终得到的W为：", W_best, "错误分类个数为：", len(pock_classify(W_best, X, Y)))
            flag = True

    return W_best

def pock_classify(W, X, Y):
    mistakes = []
    for i in range(0, len(X)):
        y = np.dot(W, X[i])
        if sign(y) == sign(Y[i]):
            continue
        else:
            mistakes.append(i)
    return mistakes


def data_test():
    true_count = 0
    _, _, _, X, Y = Data_Creat()
    w = my_pocket()     # my_pla()
    # print(X)
    # print(Y)
    for i in range(0, 80):
        y = np.dot(w, X[i])
        if sign(y) == Y[i]:
            true_count += 1
    rate = true_count/80
    return rate


def main():

     pic_data()
     rate = data_test()
     print(rate)

if __name__ == '__main__':
    main()

运行结果：