简单线性回归的实现

实现Simple Linear Regression

原始数据：

import numpy as np
import matplotlib.pyplot as plt

x = np.array([1., 2., 3., 4., 5.])
y = np.array([1., 3., 2., 3., 5.])

plt.scatter(x, y)
plt.axis([0, 6, 0, 6])
plt.show()

计算a和b，拟合直线：

x_mean = np.mean(x)
y_mean = np.mean(y)

num = 0.0
d = 0.0
for x_i, y_i in zip(x, y):
    num += (x_i - x_mean) * (y_i - y_mean)
    d += (x_i - x_mean) ** 2

a = num / d
b = y_mean - a * x_mean

y_hat = a * x + b

plt.scatter(x, y)
plt.plot(x, y_hat, color='r')
plt.axis([0, 6, 0, 6])
plt.show()

封装

import numpy as np

class SimpleLinearRegression:

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

    def fit(self, x_train, y_train):
        """根据训练集x_train,y_train训练SimpleLinearRegression模型"""
        assert x_train.ndim == 1, \
            "Simple Linear Regression can not only solve single feature training data."
        assert len(x_train) == len(y_train), \
            "the size of x_train must be equal to the size of y_train"

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

        num = 0.0
        d = 0.0
        for x, y in zip(x_train, y_train):
            num += (x - x_mean) * (y - y_mean)
            d += (x - x_mean) ** 2

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

        return self

    def predict(self, x_predict):
        """给定预测数据集x_predict,返回表示x_predict的结果向量"""
        assert x_predict.ndim == 1, \
            "Simple Linear Regression can not only solve single feature training 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_singel):
        """给定单个预测数据x_single,返回x_single的预测结果值"""
        return self.a_ * x_singel + self.b_

若想提升计算性能，可以利用向量化计算：
线性回归之向量化