---
tags:
- pytorch_model_hub_mixin
- model_hub_mixin
pipeline_tag: tabular-classification
datasets:
- pjura/mahjong_board_states
metrics:
- accuracy
model-index:
- name: mahjong_ai
  results:
  - task:
      name: Tabular Classification
      type: Tabular Classification
    dataset:
      name: pjura/mahjong_board_states
      type: tablular_data
      config: default
      split: test
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.661
---

# Mahjong AI Project

This repository contains the code and resources for developing a Mahjong AI model, focusing on tabular classification of board states. The primary goal is to predict outcomes or optimal moves based on the current game state.

## Project Structure

*   **Notebooks (`.ipynb`)**:
    *   `preprocess_*.ipynb`: Scripts for processing raw Mahjong game data into features suitable for model training.
    *   `transform_hf_dataset.ipynb`: Script for transforming data into a Hugging Face dataset format.
    *   `push_parquet_to_hub_by_year.ipynb`: Script to upload processed data (likely in Parquet format) to the Hugging Face Hub.
    *   `tenhou_prediction_deepLearning_basic.ipynb`: This notebook shows the basic process of how the classification model was trained, using features derived from player hand information (columns 68-135) and discard pool information (columns 238-373). The model predicts the discarded tile (column 510).
    *   `tenhou_prediction_multitask_hf.ipynb`: This notebook explores a new, currently non-functional approach attempting multitask learning with dynamic inputs.
*   **Python Scripts (`.py`)**:
    *   `tools.py`: Utility functions used across different notebooks.
*   **Model & Config**:
    *   `config.json`, `model.safetensors`: Configuration and saved model files associated with the trained Mahjong AI.
*   **Data**: The project utilizes the [pjura/mahjong_board_states](https://huggingface.co/datasets/pjura/mahjong_board_states) dataset from Hugging Face. The primary training notebook (`tenhou_prediction_deepLearning_basic.ipynb`) uses features derived from player hand information (columns 68-135) and discard pool information (columns 238-373), predicting the target value (discarded tile) found in column 510.

## Getting Started

This model can be used in conjunction with the [pjura/mahjong_vision](https://huggingface.co/pjura/mahjong_vision) model to create a fully automated Mahjong playing AI.

The model was trained using the [pjura/mahjong_board_states](https://huggingface.co/datasets/pjura/mahjong_board_states) dataset.