This repository contains a machine learning project for classifying penguin species using their features. The project focuses on utilizing data, building a classification model, and deploying a Streamlit web application for easy interaction.
The project is organized into the following structure:
.
βββ artifacts/
β βββ penguin_clean.csv
β βββ penguin_clf.pkl
βββ notebooks/
β βββ penguin_model_building.ipynb
βββ app.py
βββ requirements.txt
βββ README.md
- The artifacts/ folder contains subdirectories for data and trained model.
the dataset used for training and evaluation (penguin_cleaned.csv). models - the trained machine learning model (penguin_clf.pkl).
-
The notebooks/ folder holds the Jupyter Notebook (penguin_model_building.ipynb) used for data preprocessing, model training, and evaluation.
-
app.py is the main Streamlit application file that implements the penguin classification app.
-
requirements.txt lists the required dependencies to run the project. Use the following command to install them:
pip install -r requirements.txt
- Clone this repository to your local machine using:
git clone https://github.com/ayushmehraa/penguin-classification.git
- Navigate to the project directory:
cd penguin-classification
- Install the required dependencies:
pip install -r requirements.txt
- Run the Streamlit app:
streamlit run app.py
- Interact with the Streamlit app through your browser to classify penguin species using their features.
Feel free to contribute to this project by creating pull requests, reporting issues, or suggesting improvements. Your contributions are greatly appreciated!
This project is licensed under the MIT License.