# Tabular Data: are gbdt still outperforming DL? — Data

来源：https://www.kaggle.com/competitions/bench-tab-v1/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The competition is constituted of 45 datasets used in the original paper. They fall under four categories: features may or may not contain categorical features and the target is either continuous or binary.

The main differences with datasets used in the paper are:
- we only use one split (shuffle split with 60% for training and 20% for both public and private LB)
- the binary target are encoded as 0 or 1

For each datasets we provide:
- train data and target
- test data
- json files listing the features and an indicator describing if they are categorical or not.

We also provide more global dictionnaries describing each tasks. 

You goal is to provide prediction for the test data of each task.