# Belle II Summer Workshop 2024: Lepton ID Challenge — Data

来源：https://www.kaggle.com/competitions/2024-b2sw-ml/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The data used in this exercise consists of charged final-state particles (\\(e, \mu, \pi, K, p\\)) reconstructed in \\( B^{0} \rightarrow D^{\ast\pm} \ell^{\mp} \nu \\) signal MC. There are about 600,000 particles in the dataset, with the majority being hadrons (~470,000), and almost equal amounts of \\(e\\) and \\(\mu\\) (~66,000 each) for the rest.

Our task is to identify \\(e\\), \\(\mu\\), and hadrons using detector information from Belle II. The target variable is derived from a truth-matching variable where different hadron species are grouped, resulting in three classes in the dataset.

The dataset is split into `train.csv` and `test.csv` files with a 70%-30% split. Training features are provided in both files, but only `train.csv` contains the target variable. Your job is to train and optimize a model using `train.csv` and make predictions on the `test.csv`.

After making predictions, you can upload them to the leaderboard. The leaderboard will use 30% of the data in the `test.csv` to evaluate the performance of your model and display the results publicly. When the competition is over, the leaderboard will re-evaluate models using the remaining 70% of the data in `test.csv` to announce the winner.

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **example_submission.csv** - an example submission file in the correct format

## Columns

*   `index` - particle index
*   `features`/`training_variables` - kinematics, ECL cluster variables, subdetector PID likelihood
*    `target` - the class label
*   etc.