Upload your dataset, select models, and tune hyperparameters to optimize model performance.
- About
- Sample Datasets
- Getting Started
- Model Selection
- Tune Hyperparameters
- Model Comparison and Evaluation
- User Feedback
StreamTune is an interactive web application built with Streamlit for tuning hyperparameters of machine learning models. With StreamTune, you can easily upload your own dataset or use sample datasets like Iris and Breast Cancer. The app provides a range of models to choose from, allowing you to tune their hyperparameters and compare their performances side by side.
- Iris
- Breast Cancer
- Clone the repository:
git clone https://github.com/yourusername/streamtune-app.git
- Install the required packages:
pip install -r requirements.txt
- Run the Streamlit app:
streamlit run streamtune.py
- The app will open in your browser. Upload your dataset or use a sample dataset to get started.
- Random Forest
- k-Nearest Neighbors
- Logistic Regression
- Gradient Boosting
- Support Vector Machine
- Random Forest: Number of Trees, Max Depth
- k-Nearest Neighbors: Number of Neighbors
- Gradient Boosting: Number of Estimators, Max Depth
Choose models for comparison, tune their hyperparameters, and evaluate their performance with accuracy, confusion matrix, and classification report.
We value your feedback! Use the Feedback Form in the app to share your thoughts and suggestions with us.
© 2023 StreamTune. MIT License.