逻辑回归学习

随机梯度下降

import numpy as np


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

def weight(x_train,y_train):
    m,n = x_train.shape
    # 初始化参数
    theta = np.random.rand(n) # 随机样本位于[0, 1)中
    # 学习率
    alpha = 0.001
    # 迭代次数
    cnt = 0
    max_iter = 50000
    # 误差
    error0 = error1 = 0
    # 阈值
    threshold = 0.01
    while cnt<max_iter:
        cnt += 1
        diff = np.full(n,0)
        for i in range(m):
            diff = (y_train[i]-sigmoid(theta.T@x_train[i]))*x_train[i]
            theta = theta + alpha * diff
        if (abs(diff)<threshold).all():
            break
    return theta

def predict(x_test,weights):
    if sigmoid(weights.T@x_test)>0.5:
        return 1
    else:
        return 0

if __name__ =="__main__":
    x_train = np.array([[1, 2.697, 6.254],
                    [1, 1.872, 2.014],
                    [1, 2.312, 0.812],
                    [1, 1.983, 4.990],
                    [1, 0.932, 3.920],
                    [1, 1.321, 5.583],
                    [1, 2.215, 1.560],
                    [1, 1.659, 2.932],
                    [1, 0.865, 7.362],
                    [1, 1.685, 4.763],
                    [1, 1.786, 2.532]])
    y_train = np.array([1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1])

weights = weight(x_train, y_train)
print(predict([1, 1.321, 5.583], weights))

sklearn逻辑回归

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
import numpy as np

dataset = np.loadtxt('data.txt')
x_train,x_test,y_train,y_test = train_test_split(dataset[:,0:-1],dataset[:,-1],test_size=0.3)
model = LogisticRegression()
model.fit(x_train,y_train)
print(y_test == model.predict(x_test))