向量化实现SimpleLinearRegression

In [23]:

import datetime print("Run by CYJ,",datetime.datetime.now())from playML.SimpleLinearRegression import SimpleLinearRegression2 reg2 = SimpleLinearRegression2() reg2.fit(x, y) Run by CYJ, 2022-01-17 21:09:49.796743

Out[23]:

SimpleLinearRegression2()

In [21]:

reg2.a_,reg2.b_

Out[21]:

(0.8, 0.39999999999999947)

In [20]:

y_hat2 = reg2.predict(x) plt.scatter(x, y) plt.plot(x, y_hat2, color='r') plt.axis([0, 6, 0, 6]) plt.show()

向量化实现的性能测试（向量运算效率/for循环代数运算效率=76倍）

In [24]:

import datetime print("Run by CYJ,",datetime.datetime.now())m = 1000000 big_x = np.random.random(size=m) big_y = big_x * 2 + 3 + np.random.normal(size=m)%timeit reg1.fit(big_x, big_y) %timeit reg2.fit(big_x, big_y) Run by CYJ, 2022-01-17 21:11:39.840437 1.33 s ± 11.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each) 17.3 ms ± 358 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

In [25]:

reg1.a_

Out[25]:

2.002845878151015

In [26]:

reg1.b_

Out[26]:

2.9993915955553723

In [27]:

reg2.a_

Out[27]:

2.0028458781509695

In [28]:

reg2.b_

Out[28]:

2.9993915955553945

封装的SimpleLinearRegression1和2类

import numpy as npclass SimpleLinearRegression1:def __init__(self):"""初始化Simple Linear Regression 模型"""self.a_ = Noneself.b_ = Nonedef fit(self, x_train, y_train):"""根据训练数据集x_train,y_train训练Simple Linear Regression模型"""assert x_train.ndim == 1, \"Simple Linear Regressor can 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 = 0.0d = 0.0for x, y in zip(x_train, y_train):num += (x - x_mean) * (y - y_mean)d += (x - x_mean) ** 2self.a_ = num / dself.b_ = y_mean - self.a_ * x_meanreturn selfdef 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 x_predict.ndim == 1, \"Simple Linear Regressor can 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_single):"""给定单个待预测数据x，返回x的预测结果值"""return self.a_ * x_single + self.b_def __repr__(self):return "SimpleLinearRegression1()"class SimpleLinearRegression2:def __init__(self):"""初始化Simple Linear Regression模型"""self.a_ = Noneself.b_ = Nonedef fit(self, x_train, y_train):"""根据训练数据集x_train,y_train训练Simple Linear Regression模型"""assert x_train.ndim == 1, \"Simple Linear Regressor can 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)self.a_ = (x_train - x_mean).dot(y_train - y_mean) / (x_train - x_mean).dot(x_train - x_mean)self.b_ = y_mean - self.a_ * x_meanreturn selfdef 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 x_predict.ndim == 1, \"Simple Linear Regressor can 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_single):"""给定单个待预测数据x_single，返回x_single的预测结果值"""return self.a_ * x_single + self.b_def __repr__(self):return "SimpleLinearRegression2()"

总结

以上是生活随笔为你收集整理的[云炬python3玩转机器学习]5-4向量化高效运算的全部内容，希望文章能够帮你解决所遇到的问题。

如果觉得生活随笔网站内容还不错，欢迎将生活随笔推荐给好友。