基于梯度下降的逻辑回归（Logistics Regression）实现对马疝病数据集（horseColic）的分类预测

迷南。 2023-03-04 13:30 1阅读 0赞

[数据集][Link 1]  
提取码：krry

源码：

import pandas as pd
    import numpy as np
    from sklearn.linear_model import LogisticRegression
    
    #加载数据
    def load_data(path):
        data = pd.read_csv(path, sep='\t', names=[i for i in range(22)])
        data = np.array(data).tolist()
        x = []; y = []
        for i in range(len(data)):
            y.append(data[i][-1])
            del data[i][-1]
            x.append(data[i])
    
        x = np.array(x)
        y = np.array(y)
    
        return x, y
    
    def sigmoid(z):
        return 1 / (1 + np.exp(-z))
    
    def gradient(X, Y, w):
        res = []
        for k in range(22):
            sum = 0.0
            for i in range(len(Y)):
                sum += (-(Y[i] - np.dot(w.T, X[i])) * X[i, k])
            res.append(sum)
    
        res = np.array(res)
        return res
    
    
    #基于梯度下降法
    def logistics():
        train_x, train_y = load_data('horse_colic/horseColicTraining.txt')
        test_x, test_y = load_data('horse_colic/horseColicTest.txt')
    
        X = np.column_stack((np.ones((299, 1), float), train_x))
        Y = train_y
        Y = Y.reshape(299, 1)
    
        learning_rate = 0.00001
        step = 200   #迭代次数
        w = np.random.random((22, 1))
        while step > 0:
            res = gradient(X, Y, w)
            for i in range(len(w)):
                w[i] -= (learning_rate * res[i])
            step -= 1
    
        test_x = np.column_stack((np.ones((67, 1), float), test_x))  #最前面加上一列1
        sum1 = 0
        for i in range(len(test_y)):
            res = np.dot(w.T, test_x[i])
            res = sigmoid(res)
            if res > 0.5 and test_y[i] == 1:
                sum1 += 1
            elif res <= 0.5 and test_y[i] == 0:
                sum1 += 1
            else:
                continue
    
        print('手写正确率：', sum1 / len(test_y))
    
    
    #基于sklearn包
    def sklearn_logistics():
        train_x, train_y = load_data('horse_colic/horseColicTraining.txt')
        test_x, test_y = load_data('horse_colic/horseColicTest.txt')
    
        clf = 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)
        clf.fit(train_x, train_y)
        print('调包正确率：', clf.score(test_x, test_y))
    
    
    if __name__ == '__main__':
        print('请稍等...')
        logistics()
        sklearn_logistics()

结果不是很理想！！  
![在这里插入图片描述][20200803214856449.png]

[Link 1]: https://pan.baidu.com/s/14PM4zLUBr6BamLA-nEFujQ
[20200803214856449.png]: /images/20230208/c473c9fd8a9a431f92c204bc0ef1e387.png