# CUHKML2025-Regression — Data

来源：https://www.kaggle.com/competitions/cuhkml-2025-regression/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Dataframe_train and dataframe_test are the main dataset. The difference is that for the test data set, the “action type” (for the classification task) and “expected use time” (for the regression task) variables are masked, and you are asked to predict them.

The data was already pre-processed. Below is some brief overview of the variables, the rest can be explored on your own.

## Variables
*   ’courier_id’, ’wave_index’, ’tracking_id’, ’date’, ’group’, ’id’ - These are the demographic information of the order and its courier. The column names are somewhat self-explanatory.

*  ’courier_wave_start_lng’, ’courier_wave_start_lat’ - These are the starting longitude and latitude of that wave of a certain courier.

*  ’level’, ’speed’, ’max_load’ - These are the courier information: The level of the courier, the speed of the courier and the max load of the courier.

* ’weather_grade’ - This is the weather condition of the order.

* ’aoi_id’ - The id of the Area of Interest (i.e. the delivery destination).

* ’shop_id’ - The id of the shop.

* ’source_type’, ’source_tracking_id’, ’source_lng’, ’source_lat’ - The information of the courier’s previous action.

* ’target_lng’, ’target_lat’ - The geographical information of the target.

* ’grid_distance’ - The shortest traversable distance to the target provided by the GPS.

* ’hour’ - The hour in the day.

* ’urgency’ - Identifies how urgent the order is

* ’action_type’ - The outcome variable in the classification task. This is masked in the test set.

* ’expected_use_time’ - The outcome variable in the regression task. This is also masked in the test set

Finally, we want to remind you that NOT ALL VARIABLES ARE NECESSARILY NEEDED. So, you should use your own judgment to decide what to use for your model.

## Files

*   **dataframe_train.csv** - the training set
*   **dataframe_test.csv** - the test set
*   **regression_example.csv** - a sample submission file in the correct format
*   **questions_project.pdf** - Q&A