2.7 线性回归算法学习——多元线性回归的实现

import numpy as np

class LinearRegression:
    def __init__(self):
        """初始化模型"""
        self.coef_=None
        self.inter_=None
        self.__theta=None

    def fit(self,X_train,y_train):
        """根据训练数据集X_train, y_train训练Linear Regression模型"""
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must be equal to the size of y_train"
        X_b=np.hstack([np.ones((len(X_train),1)),X_train])
        self.__theta=np.linalg.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(y_train)
        self.inter_=self.__theta[0]
        self.coef_=self.__theta[1:]
        return self

    def predict(self,X_predict):
        """给定待预测数据集X_predict，返回表示X_predict的结果向量"""
        assert self.inter_ is not None and self.coef_ is not None, \
            "must fit before predict!"
        assert X_predict.shape[1] == len(self.coef_), \
            "the feature number of X_predict must be equal to X_train"
        X_b=np.hstack([np.ones((len(X_predict),1)),X_predict])
        return X_b.dot(self.__theta)

    def score(self,X_test,y_test):
        y_predict=self.predict(X_test)
        return self.r2_score(y_test,y_predict)

    def mean_squared_error(self,y_true, y_predict):
        """计算y_true和y_predict之间的MSE"""
        assert len(y_true) == len(y_predict), \
            "the size of y_true must be equal to the size of y_predict"
        return np.sum((y_true - y_predict) ** 2) / len(y_true)


    def r2_score(self,y_true, y_predict):
        """计算y_true和y_predict之间的R Square"""
        return 1 - self.mean_squared_error(y_true, y_predict) / np.var(y_true)
    def __repr__(self):
        return "LinearRegression()"

运行结果