logistic

╰+攻爆jí腚メ 2024-02-19 12:56 29阅读 0赞

## 数据的可视化和梯度上升法 ##

import matplotlib.pyplot as plt

#### 定义数据集下载函数 ####

def loadDataSet():
        dataMat = []
        labelMat = []
        f = open('testSet.txt')
        for line in f.readlines():
            line_list = line.strip().split()
            dataMat.append([1,float(line_list[0]),float(line_list[1])])
            labelMat.append(int(line_list[2]))
        return dataMat,labelMat

#### 定义激活函数 ####

def sigmoid(inX):
        return 1.0 / (1+np.exp(-inX))

import numpy as np
    dataMat,labelMat = loadDataSet()
    dataMatArr = np.array(dataMat)
    n = np.shape(dataArr)[0]
    x_cord_1 = []; y_cord_1 = []
    x_cord_2 = []; y_cord_2 = []
    for i in range(n):
        if int(labelMat[i]) == 1:
            x_cord_1.append(dataMatArr[i,1])
            y_cord_1.append(dataMatArr[i,2])
        else:
            x_cord_2.append(dataMatArr[i,1])
            y_cord_2.append(dataMatArr[i,2])

#### 绘制图像 ####

fig = plt.figure()
    ax = fig.add_subplot(111) # 将画布分成一行一列，按从左到右，从上到下去一个格子
    ax.scatter(x_cord_1,y_cord_1,s=30,c='red')
    ax.scatter(x_cord_2,y_cord_2,s=30,c='green')

<matplotlib.collections.PathCollection at 0x8db64a8>

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMyMzU3NTA5_size_16_color_FFFFFF_t_70]

![png][]

#### 实现梯度上升算法函数 ####

def gradAscent(dataMatIn, classLabels):
        # 获取数据，并转化成
        dataMatrix = np.mat(dataMatIn)
        labelMatrix = np.mat(classLabels).transpose()
        m,n = np.shape(dataMatrix)
        alpha = 0.001
        maxCycles = 500
        weights = np.ones((n,1))
        for k in range(maxCycles):
            h = sigmoid(dataMatrix * weights)
            error = (labelMatrix - h)
            weights = weights + alpha *  dataMatrix.transpose() * error
        return weights

weights = gradAscent(dataArr,labelMat)
    weights

matrix([[ 4.12414349],
            [ 0.48007329],
            [-0.6168482 ]])

#### 分析数据，画出决策边界 ####

def plotBestFit(weights):
        dataMat,labelMat = loadDataSet()
        dataArr = np.array(dataMat)
        n = np.shape(dataArr)[0]
        x_cord_1 = []; y_cord_1 = []
        x_cord_2 = []; y_cord_2 = []
        for i in range(n):
            if int(labelMat[i]) == 1:
                x_cord_1.append(dataArr[i,1])
                y_cord_1.append(dataArr[i,2])
            else:
                x_cord_2.append(dataArr[i,1])
                y_cord_2.append(dataArr[i,2])
        fig = plt.figure()
        ax = fig.add_subplot(111)
        ax.scatter(x_cord_1,y_cord_1,s=30,c='red')
        ax.scatter(x_cord_2,y_cord_2,s=30,c='green')
        x = np.arange(-3,3,0.1)
        y = (-weights[0]-weights[1]*x) / weights[2] # w0 * x0 + w1 * x1 + w2 * x2 = 0
        ax.plot(x,y)
        plt.xlabel('X1')
        plt.ylabel('X2')
        plt.show()

plotBestFit(weights.getA())  # getA()函数与mat()函数的功能相反，是将一个numpy矩阵转换为数组

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMyMzU3NTA5_size_16_color_FFFFFF_t_70 1]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMyMzU3NTA5_size_16_color_FFFFFF_t_70]: https://image.dandelioncloud.cn/pgy_files/images/2024/01/29/46cbfd435fc5441b9f5ba81c5c50a26e.png
[png]: 
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMyMzU3NTA5_size_16_color_FFFFFF_t_70 1]: https://image.dandelioncloud.cn/pgy_files/images/2024/01/29/1ad1415609634bddbd8ac24053c99e12.png