# DL Sprint 3.0 | Bengali AI Math Olympiad — Data

来源：https://www.kaggle.com/competitions/dlsprint3/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Public Train and Test Set 

The training set consists of 209 problems from Math Olympiad and their answers. All problems have non-negative integer answers. All problems are text-only with mathematical notation in LaTeX. Although some problems may involve geometry, diagrams are not used in any problem.

Because of the limited number of problems available, we are taking special precautions to secure the test set against probing, hardcoding, overfitting. Among other things, during the Phase 1 of the competition, the test set will comprise only the 100  problems. 

In Phase II, we will rerun submissions on a holdout set which is **completely different** from the training and test dataset. You should attempt to make sure your submission will complete successfully on the holdout private set problems. This may mean ensuring your submission is runnable in Kaggle environment and runs within permissible space and time limit. 

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns
### Train Set

*   `Id` - Unique id for the problem
*   `Problem` - Problem statement
*   `Answer` - Integer answer of the problem

### Test Set

*   `Id` - Unique id for the problem
*   `Problem` - Problem statement

### Submission Format
*   `Id` - Unique id for the problem
*   `Answer` - Predicted answer (**must be an Integer**)


# Holdout Set 
The holdout set will be used Phase II. The set consists of 100 new problems created in collaboration with BDMO. All the problems have non-negative integer answers as well. They will be text-only with mathematical notation in LaTeX and they will not contain diagrams. The difficulty of the problems are moderately higher than the problems in the public train and test set.

## Files
*   **test.csv** - the test set

## Columns
*   `Id` - Unique id for the problem
*   `Problem` - Problem statement

### Submission Format
*   `Id` - Unique id for the problem
*   `Answer` - Predicted answer (**must be an Integer**)