线性回归

• 优点：具有很强的解释性

一元线性回归

• 一个自变量和一个因变量，两个变量之前的关系用一条直线来模拟

• $$h_{\theta }(x)={\theta }_0+{\theta }_{1}x,其中{\theta }_1=\frac{{\sum }_{i=1}^m(x^{(i)}-\overline{x})(y^{(i)}-\overline{y})}{{\sum }_{i=1}^m(x^{(i)}-\overline{x}{)}^2},{\theta }_0=\overline{y}-{\theta }_1\overline{x}$$

代码实现

• 一般操作

# coding=utf-8

import numpy as np


class SimpleLinearRegression1:

    def __init__(self):
        self.a_ = None
        self.b_ = None

    def fit(self, x_train, y_train):
        assert x_train.ndim == 1, '必须是一维的'

        x_mean = np.mean(x_train)
        y_mean = np.mean(y_train)

        num = 0.
        d = 0.
        for x_i, y_i in zip(x_train, y_train):
            num += (x_i - x_mean) * (y_i - y_mean)
            d += (x_i - x_mean) ** 2
        self.a_ = num / d
        self.b_ = y_mean - self.a_ * x_mean
        return self

    def predict(self, x_predict):
        assert x_predict.ndim == 1, '必须一维数组'
        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):
        return self.a_ * x + self.b_

    def __repr__(self):
        return "SimpleLinearRegression()"

• 向量化计算

# coding=utf-8

import numpy as np

# 向量化计算
class SimpleLinearRegression2:

    def __init__(self):
        self.a_ = None
        self.b_ = None

    def fit(self, x_train, y_train):
        assert x_train.ndim == 1, '必须是一维的'

        x_mean = np.mean(x_train)
        y_mean = np.mean(y_train)

        num = (x_train - x_mean).dot(y_train - y_mean)
        d = (x_train - x_mean).dot(x_train - x_mean)
        self.a_ = num / d
        self.b_ = y_mean - self.a_ * x_mean
        return self

    def predict(self, x_predict):
        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):
        return self.a_ * x + self.b_

    def __repr__(self):
        return "SimpleLinearRegression()"