# Volunteer Retention Prediction — Data

来源：https://www.kaggle.com/competitions/MLSP2023-volunteers-01/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Here are datasets for the volunteer retention prediction tasks:

#Retention Task
## Files

*   **retention_train_feat.csv** - the training dataset, containing records of train volunteers participating in tasks during the **feature time span** (2020.2-2021.5). Details of each record can be found in the following session.
*   **retention_test_feat.csv** - the testing dataset.
*   **sample_submission_retention.csv** - a sample submission file in the correct format
*   **retention_gt_train.csv** - the groudtruth labels for each volunteer in the training dataset. `user_id` denotes the unique id of a volunteer, and the `count` is the label for that volunteer, representing the count of participated tasks in the **predicted time span** (2021.5 - 2022.2).  

## Columns

*   `user_id` - The unique id of a volunteer
*   `is_organizer` -  Whether the volunteer is the organizer of the task (binary)
*   `task_id` -The unique id of a task
*   `task_location` - The street name of the task location (text)
*   `task_district` - The district name of the task location (text)
*   `user_location` - The home street name of the user (text)
*   `longitude` - The longitude of the task location
*   `latitude` - The latitude of the task location
*   `task_start_time` - The start time of the task
*   `task_end_time` - The end time of the task