简单线性回归实现

import numpy as np


class SimpleLinearRegression:

  def __init__(self):
    '''初始话Simple Linear Regression模型'''
    self.a_ = None
    self.b_ = None

  def fit(self, x_train, y_train):
    '''根据训练集x_train,y_train 训练模型'''

    assert x_train.ndim == 1, \
      "simple linear regression can only solve single feature traininng data"
    assert len(x_train) == len(y_train), \
      "the size of x_train must be equal to the size of y_train"

    # 求x_train，y_train的均值
    x_mean = np.mean(x_train)
    y_mean = np.mean(y_train)

    # 分子
    num = 0.0
    # 分母
    d = 0.0

    # 采用向量化点乘的计算
    num = (x_train - x_mean).dot(y_train - y_mean)
    d = (x_train - x_mean).dot(x_train - x_mean)

    # 使用for循环计算效率比较低
    # for x_i, y_i in zip(x_train, y_train):
    #   num += (x_train - x_mean) * (y_train - y_mean)
    #   d += (x_train - x_mean) ** 2

    self.a_ = num / d
    self.b_ = y_mean - self.a_ * x_mean
    return self

  def predict(self, x_predict):
    '''给定带预测数据集x_predict，返回表示x_predict的结果向量'''
    assert x_predict.ndim == 1, \
      "simple linear regression can only solve single feature traininng data"
    assert self.a_ is not None and self.b_ is not None, \
      "must fit before predict"

    return np.array([self._predict(x) for x in x_predict])

  def _predict(self, x_single):
    '''给定单个待预测数据x_single，返回预测结果'''
    return self.a_ * x_single + self.b_

  def score(self,x_test,y_test):
    '''根据测试集确定模型准确度 ，返回R平方'''
    y_predict = self._predict(x_test)

    return 1 - (np.sum((y_predict - y_test)**2) / len(y_test)) / np.var(y_test)


  def __repr__(self):
    return 'simple linear regression'