Predicting software bugs before they occur can save time, money, and effort in the software development life cycle. This project uses machine learning techniques to predict the likelihood of bugs based on historical code and commit metrics.
Software bugs are costly and time-consuming. Early prediction of bugs can help in proactive debugging and testing. This project aims to use machine learning models to predict whether a piece of code or commit is likely to contain a bug based on historical features.
- Language: Python
- ML Libraries: scikit-learn, pandas, numpy, matplotlib, seaborn
- Modeling: Logistic Regression, Random Forest, XGBoost
- Evaluation: Accuracy, Precision, Recall, F1-Score, ROC AUC
-
Clone the repo:
git clone https://github.com/veydantkatyal/software-bug-prediction.git cd software-bug-prediction -
Install dependencies:
pip install -r requirements.txt
-
Run the hupyter notebook:
jupyter notebook bug_prediction_.ipynb.ipynb
This project is open-source licensed under MIT License.