This project focuses on performing binary classification on a dataset with 1000 points, 12 features, and labels of 1 or -1 for each point. The goal is to compare the performance of simple models to complex models using ROC diagrams and AUC scores and identify the best model.
- Python 3.11.4
- Libraries listed in
requirements.txt
- Clone the repository:
git clone https://github.com/alirezadamash/binary-classifier.git
- Navigate to the project directory:
cd binary-classifier
- Install the required libraries:
pip install -r requirements.txt
-
Place your dataset in a CSV file named
data.csv
in the project directory. -
Run the main script:
python models.py
- The ROC curve will be displayed, comparing the performance of several models. The model with the highest AUC score is considered the best.
The dataset used in this project contains 1000 points with 12 features. The labels are binary, with values of 1 or -1 for each point.
The following models are evaluated in this project:
- Logistic Regression
- Support Vecror Machine
- Decision Tree
- Random Forest
- Gradient Boosting
The performance of each model is compared using ROC diagrams and AUC scores. The model with the highest AUC score is considered the best.