1.封装我们自己的随机梯度下降法：
def fit_sgd(self, X_train, y_train, n_iters=5, t0=5, t1=50): """根据训练数据集X_train，y_train，使用随机梯度下降法训练Linear Regression模型""" assert X_train.shape[0] == y_train.shape[0], \ "the size of X_train must be equal to the size of y_train" assert n_iters >= 1 def dJ_sgd(theta, X_b_i, y_i): return X_b_i.T.dot(X_b_i.dot(theta) - y_i) * 2. def sgd(X_b, y, initial_theta, n_iters=5, t0=5, t1=50): def learning_rate(t): return t0 / (t + t1) theta = initial_theta m = len(X_b) for i_iter in range(n_iters): indexes = np.random.permutation(m) X_b_new = X_b[indexes,:] y_new = y[indexes] for i in range(m): gradient = dJ_sgd(theta, X_b_new[i], y_new[i]) theta = theta - learning_rate(i_iter * m + i) * gradient return theta X_b = np.hstack([np.ones((len(X_train), 1)), X_train]) initial_theta = np.random.randn(X_b.shape[1]) self._theta = sgd(X_b, y_train, initial_theta, n_iters, t0, t1) self.coef_ = self._theta[1:] self.interception_ = self._theta[0] return self2.真实使用我们自己的SGD： 数据的准备与归一化处理： 随机梯度下降的过程，设置不同的n_iters，来看准确性： 3.scikit-learn中的SGD：
