翻译这段代码class GPR: def __init__(self, optimize=True): self.is_fit = False self.train_X, self.train_y = None, None self.params = {"l": 2, "sigma_f": 1} self.optimize = optimize def fit(self, X, y): # store train data self.train_X = np.asarray(X) self.train_y = np.asarray(y) # hyper parameters optimization def negative_log_likelihood_loss(params): self.params["l"], self.params["sigma_f"] = params[0], params[1] Kyy = self.kernel(self.train_X, self.train_X) + 1e-8 * np.eye(len(self.train_X)) loss = 0.5 * self.train_y.T.dot(np.linalg.inv(Kyy)).dot(self.train_y) + 0.5 * np.linalg.slogdet(Kyy)[ 1] + 0.5 * len(self.train_X) * np.log(2 * np.pi) return loss.ravel() if self.optimize: res = minimize(negative_log_likelihood_loss, [self.params["l"], self.params["sigma_f"]],bounds=((1e-4, 1e4), (1e-4, 1e4)),method='L-BFGS-B') self.params["l"], self.params["sigma_f"] = res.x[0], res.x[1] self.is_fit = True def predict(self, X): if not self.is_fit: print("GPR Model not fit yet.") return X = np.asarray(X) Kff = self.kernel(self.train_X, self.train_X) # (N, N) Kyy = self.kernel(X, X) # (k, k) Kfy = self.kernel(self.train_X, X) # (N, k) Kff_inv = np.linalg.inv(Kff + 0.5e-3 * np.eye(len(self.train_X))) # (N, N) mu = Kfy.T.dot(Kff_inv).dot(self.train_y) cov = Kyy - Kfy.T.dot(Kff_inv).dot(Kfy) return mu, cov def kernel(self, x1, x2): dist_matrix = np.sum(x1 ** 2, 1).reshape(-1, 1) + np.sum(x2 ** 2, 1) - 2 * np.dot(x1, x2.T) return self.params["sigma_f"] ** 2 * np.exp(-0.5 / self.params["l"] ** 2 * dist_matrix)

以上代码是一个名为GPR的类的定义，其中包含一个初始化函数__init__，和一个适应函数fit。
在初始化函数中，self.is_fit被赋值为False，self.train_X和self.train_y被赋值为None，self.params被赋值为{"l": 2, "sigma_f": 1}，self.optimize被赋值为传入的参数optimize。
在适应函数中，传入参数为X和y，用于对模型进行适应操作。