Skip to content

README.MD

Latest commit

 

History

History
53 lines (39 loc) · 1.79 KB

README.MD

File metadata and controls

53 lines (39 loc) · 1.79 KB

Iris Tribuo Example

This project demonstrates how to use the Iris dataset with Tribuo.

Download iris

You can manually download and extract the data:

  1. Download the data from: https://archive.ics.uci.edu/static/public/53/iris.zip
  2. Extract the contents of the zip file into a folder named data in the project root.

Alternatively, use the following bash command:

  rm -rf data && mkdir -p data \
    && curl -L https://archive.ics.uci.edu/static/public/53/iris.zip -o data/iris.zip \
    && unzip data/iris.zip -d data \
    && rm data/iris.zip

Download fraud-detection

You can manually download and extract the data:

  1. Download the data from: https://www.kaggle.com/api/v1/datasets/download/pranavrawat1301/fraud-detection
  2. Extract the contents of the zip file into a folder named data in the project root.

Alternatively, use the following bash command:

  rm -rf data && mkdir -p data \
    && curl -L https://www.kaggle.com/api/v1/datasets/download/pranavrawat1301/fraud-detection -o data/fraud-detection.zip \
    && unzip data/fraud-detection.zip -d data \
    && mv data/fraud-detection.csv data/Fraud.csv \
    && rm data/fraud-detection.zip

Training the Model

Before training the model, ensure that the project is built:

mvn clean install

To train the model, run the TrainModel class. This will load the fraud detection dataset, split it into training and testing sets, train an XGBoost model, evaluate its performance, and save the model to models/model.tribuo.

mvn exec:java -Dexec.mainClass=ua.lviv.javaclub.tribuo.training.TrainModel

Making Predictions

Once the model is trained and saved, you can use the Predict class to make predictions on new data.

mvn exec:java -Dexec.mainClass=ua.lviv.javaclub.tribuo.predict.Predict