Python机器学习：线型回归法04向量化运算

核心两行代码,
向量化
比较两者运算速度
运行速度提升100倍

#性能测试
#性能测试
m = 10000000
big_x = np.random.random(size=m)
print(big_x)
big_y = big_x * 2.0 + 3.0 + np.random.normal(size=m)

向量化的

%timeit reg2.fit(big_x,big_y)

没向量化的

%timeit reg1.fit(big_x,big_y)

11.8 s ± 249 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

134 ms ± 3.2 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

num = (x_train - x_mean).dot(y_train - y_mean)
d = (x_train - x_mean).dot(x_train - x_mean)

class Simple_linear_Regression2:

    def __init__(self):
        """初始化Simple Line Regression模型"""
        self.a_ = None
        self.b_ = None

    def fit(self,x_train,y_train):
        """根据训练数据集x_train和y_train训练Simple_linear_Regression模型"""
        assert x_train.ndim == 1,\
            "Simple Linear Regression 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"
        # self.x_train = x_train
        # self.y_train = y_train

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

        num = 0.0
        d = 0.0
        #使用向量化运算
        num = (x_train - x_mean).dot(y_train - y_mean)
        d = (x_train - x_mean).dot(x_train - x_mean)
        # 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 #a_一般这样写是给函数里面计算得出的属性的
        self.b_ = y_mean - self.a_ * x_mean

        return self
    #这块自己写的没sklearn内味儿
    # def predict(self,x_predict):
    #     """给定待测数据集x_predict,返回表示x_predict的结果向量"""
    #     y_predict = [ x * self.a_ + self.b_ for x in x_predict]
    #     return y_predict
    #重新写的
    def predict(self, x_predict):
         """给定待测数据集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 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):
        """给定单个待遇测数据x_single,返回x_single的预测结果值"""
        return self.a_ * x_single + self.b_

    def __repr__(self):
        return 'Simple_linear_Regression2'