libcity.evaluator.utils

libcity.evaluator.utils.evaluate_model(y_pred, y_true, metrics, mode='single', path='metrics.csv')

交通状态预测评估函数 :param y_pred: (num_samples/batch_size, timeslots, …, feature_dim) :param y_true: (num_samples/batch_size, timeslots, …, feature_dim) :param metrics: 评估指标 :param mode: 单步or多步平均 :param path: 保存结果 :return:

libcity.evaluator.utils.output(method, value, field)

Parameters

• method – 评估方法

• value – 对应评估方法的评估结果值

• field – 评估的范围, 对一条轨迹或是整个模型

libcity.evaluator.utils.sort_confidence_ids(confidence_list, threshold)

Here we convert the prediction results of the DeepMove model DeepMove model output: confidence of all locations Evaluate model input: location ids based on confidence :param threshold: maxK :param confidence_list: :return: ids_list

libcity.evaluator.utils.transfer_data(data, model, maxk)

Here we transform specific data types to standard input type