https://github.com/1adore1/-old-deadlock-winner-prediction

Predict the winning team in Valve's MOBA game Deadlock based on team picks.
https://github.com/1adore1/-old-deadlock-winner-prediction

beautifulsoup4 catboost numpy pandas python scikit-learn

Last synced: 7 days ago
JSON representation

Predict the winning team in Valve's MOBA game Deadlock based on team picks.

• Host: GitHub
• URL: https://github.com/1adore1/-old-deadlock-winner-prediction
• Owner: 1adore1
• Created: 2024-09-04T18:34:24.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-09-12T15:18:29.000Z (5 months ago)
• Last Synced: 2025-02-13T19:55:26.191Z (7 days ago)
• Topics: beautifulsoup4, catboost, numpy, pandas, python, scikit-learn
• Language: Jupyter Notebook
• Homepage:
• Size: 11.5 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# **Deadlock Winner Prediction**

### Overview

The goal of this project is to predict the winning team in the new MOBA game Deadlock by Valve, based solely on the teams picks.

### Installation

1. Clone the repository:

```

git clone https://github.com/1adore1/deadlock-winner-prediction.git

cd deadlock-winner-prediction

```

2. Install required libraries:

```

pip install -r requirements.txt

```

### Usage

  1. Preprocess the dataset by running (takes about 1 minute for 10k matches):

  ```

  python preprocess.py

  ```

  2. Train the model with:

  ```

  python train_model.py

  ```

  3. Make predictions on your input picks:

  ```

  python predict.py

  ```

### Models Used

* **Random Forest**

* **Gradient Boosting**

* **Logistic Regression**

### Data

The dataset includes match history from Deadlock, that was parsed from [tracklock.gg](https://tracklock.gg).

Dataset contains:

* **Team picks**: Heroes chosen by each team.

* **Game results**: Outcome of the match (win/loss).

---