This project involves building a machine learning model to classify iris flowers into three species: Iris Setosa, Iris Versicolor, and Iris Virginica. The model is trained and tested using the famous Iris dataset and is locally hosted using Streamlit for easy user interaction.
- Dataset: The Iris dataset from Kaggle (Dataset Link).
- Python Notebook: The complete workflow for data preprocessing, visualization, and model building.
- Trained Model: Saved using Pickle for future predictions.
- Streamlit App: A user-friendly interface to interact with the model.
- ReadMe: Documentation of the project.
- Data Analysis: Insights gained through data visualization and statistics.
- Modeling: Various machine learning algorithms tested, including Logistic Regression and Decision Trees.
- Performance Metrics: Accuracy and confusion matrix to evaluate the model.
- Deployment:
- Local Hosting: Interactive app created with Streamlit.
- Programming Language: Python
- Libraries: NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn, Streamlit
-
Clone the repository:
git clone https://github.com/DeMoN-7/Iris-Flower-Classification.git cd Iris-Flower-Classification -
Install the required dependencies:
pip install -r requirements.txt
-
Run the Streamlit app locally:
streamlit run app.py
-
Open your browser and go to
http://localhost:8501.
The Iris dataset consists of 150 samples with 4 features:
- Sepal length
- Sepal width
- Petal length
- Petal width
Target labels:
- Iris Setosa
- Iris Versicolor
- Iris Virginica
- Best Model: Logistic Regression
- Accuracy Achieved: [Include your model's accuracy here]
- Confusion matrix shows good differentiation among the species.
- Streamlit App: Users can input feature values and get predictions in real-time.
- Deploy the Streamlit app online for broader accessibility.
- Experiment with advanced algorithms like Random Forest or SVM.
- Add hyperparameter tuning for better results.
Ayush Singh
- Email: [singhayush6264@gmail.com]
- GitHub: Ayush Singh
Feel free to raise an issue or suggest improvements!