This project is an interactive Machine Learning web application built using Streamlit.
It predicts the species of a penguin based on physical features such as bill length, bill depth, flipper length, body mass, island, and sex.
The application uses a Random Forest Classifier trained on the Palmer Penguins dataset and displays both the predicted class and prediction probabilities in real time.
Click below to access the live deployed Streamlit application:
Run this project instantly in the cloud using GitHub Codespaces:
- Built an end-to-end ML web app using Streamlit
- Used Random Forest Classifier for multi-class prediction
- Implemented feature encoding and preprocessing
- Added interactive UI components (sliders, dropdowns)
- Displayed prediction probabilities for transparency
- Deployed using Streamlit Cloud
- Python
- Streamlit
- Pandas
- NumPy
- Scikit-learn
- Random Forest Algorithm
- Palmer Penguins Dataset
- Source: https://github.com/dataprofessor/data
To understand the tools and concepts used in this project, refer to:
-
Streamlit Documentation
https://docs.streamlit.io -
Scikit-learn Random Forest
https://scikit-learn.org/stable/modules/ensemble.html -
Palmer Penguins Dataset
https://allisonhorst.github.io/palmerpenguins/
- Add model accuracy and confusion matrix
- Compare multiple ML models
- Improve UI styling
- Add dataset upload functionality
Abhijith
Computer Science Student | Machine Learning Enthusiast