LR回归复现

参考https://www.cnblogs.com/csu-lmw/p/10661475.html
代码目前还有bug未修复

from math import exp
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

def iris_data():
    iris = load_iris()
    df = pd.DataFrame(iris.data, columns=iris.feature_names)
    df['label'] = iris.target
    df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
    data = np.array(df.iloc[:100, [0, 1, -1]])
    return data[:, :2], data[:, -1]

class LogisticRegressionClassifier:
    def __init__(self,max_iter=300,learning_rate=0.01,random_state=4):
        self.max_iter=max_iter
        self.learning_rate=learning_rate
       # self.random_state=random_state
        self.weights=None

    def sigmoid(self,x):
        return 1/(1+exp(-x))

    def data_matrix(self,X):
        data_mat=[]
        for d in X:
            data_mat.append([1.0, d])
            return data_mat

    def fit(self,X,y):
        data_mat=self.data_matrix(X)
        self.weights=np.zeros((len(data_mat[0]),1),dtype=np.float32)
        for iter_ in range(self.max_iter):
            for i in range(len(X)):
                result = self.sigmoid(np.dot(data_mat[i], self.weights))
                error = y[i]-result
                self.weights += self.learning_rate*error*np.transpose([data_mat[i]])
        print('LR model(learning_rate={},max_iter={})'.format(self.learning_rate,self.max_iter))


    def score(self,X_test,y_test):
        right=0
        X_test=self.data_matrix(X_test)
        for x,y in zip(X_test,y_test):
            result=np.dot(x,self.weights)
            if(result>0 and y==1)or(result<0 and y==0):
                right+=1
        return right/len(X_test)

if __name__=='__main__':
    X,y=iris_data()
    X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
    clf=LogisticRegressionClassifier()
    clf.fit(X_train,y_train)
    print('the score={}'.format(clf.score(X_test,y_test)))
    x_ponits=np.arange(4,8)
    y_=-(clf.weights[1]*x_ponits+clf.weights[0])/clf.weights[2]
    plt.plot(x_ponits,y_)

    plt.scatter(X[:50,0],X[:50,1],label='0')
    plt.scatter(X[50:, 0], X[50:, 1], label='1')
    plt.legend()
    plt.show()
    ```