逻辑回归-二分类

读取数据

# coding: utf-8
import  numpy as np

#获取训练数据
def get_data():
    d = np.load("dataset.npz")
    #x_train,y_train分别表示8000个训练集的数据和标签
    # x_test,y_test分别表示2000个测试集的数据和标签
    x_train = d['x_train'] #8000*10，每个数据10个特征值
    y_train = d['y_train'] #8000*1
    x_test = d['x_test']   #2000*10
    y_test = d['y_test']   #2000*1
    # w = d['w']
    # b = d['b']
    return x_train,y_train,x_test,y_test

if __name__ == '__main__':
    x_train, y_train, x_test, y_test, w, b = get_data()
    print(x_train,y_train,x_test,y_test,w,b)
    print(x_train.shape, y_train.shape, x_test.shape, y_test.shape ,w.shape,b)

训练数据保存模型

#coding:utf-8
'''
1、取数据
2、随机初始化参数w和b，确定学习率alpha，确定循环次数epochs
3、根据逻辑回归计算预测值Y_
4、计算成本函数J
5、计算机J对w和b的偏导(梯度值)分别为：dw和db，中间变量是dz
6、更新w和b的值：w = w-alpha * dw   b = b-alpha * db
7、循环第3-6步的操作，共epochs次
'''
import numpy as np
from data import get_data

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

def loss(y,y_):
    return -(y*np.log(y_)+(1-y)*np.log(1-y_))

if __name__ == '__main__':

    x_train, y_train, x_test, y_test, w_data, b_data = get_data()

    #参数W和b先随机初始化
    W = np.random.rand(10)
    b = np.random.rand()
    alpha = 0.5
    epochs = 10000
    for i in range(epochs):
        z = np.sum(W*x_train, axis = -1)+b
        y_ = sigmoid(z)
        J = np.mean(loss(y_train,y_))
        dz = y_-y_train
        dw = np.mean((x_train.transpose()*dz).transpose(),axis=0)
        db = np.mean(dz)
        W = W-alpha*dw
        b = b-alpha*db
        print('第%d个epoch: 成本函数值J=%f,dw的平均值为%f,db的值为%f'%(i,J,np.mean(dw),db ))
    np.savez('model.npz',W=W,b=b)

用测试集测试

#coding:utf-8
'''
1、按照保存的w和b计算测试数据x_test的预测值y_，中间变量是线性回归值z
2、处理预测值，判断是否大于0.5，再取整后保存为Y_
3、比较预测值y_和真实值y的相同结果的个数

'''
import numpy as np
from data import get_data
from logistic import sigmoid

if __name__ == '__main__':
    x_train, y_train, x_test, y_test  = get_data()
    d = np.load('model.npz')
    w = d['W']
    b = d['b']
    z = np.sum(w * x_test, axis=-1) + b
    y_ = sigmoid(z)
    y_pred_float = (y_>0.5).astype(np.float64)
    accuracy =  np.sum((y_pred_float==y_test).astype(np.int))/y_test.shape[0]
    print('accuracy:',accuracy)

结果