(https://colab.research.google.com/drive/1csbbEmddd5TA3cVyiMxKim64QSsnN_xr#)
A data science project that uses IBM Watson Studio's AutoAI to automatically build, evaluate, and export machine learning models for predicting salaries based on features like experience, education, and job role.
This project demonstrates how to build, train, and deploy a Salary Prediction Model using IBM Watson AutoAI.
It also integrates a custom Python GUI (Tkinter) for making predictions locally.
The project follows an end-to-end machine learning pipeline including:
- Data preprocessing
- Automated model selection & optimization (AutoAI)
- Model evaluation
- Deployment & GUI integration
AutoAI-Model-using-IBM-Watson/ │── AutoAI.ipynb # Colab notebook with AutoAI workflow │── AutoAIGUI.py # GUI application for predictions │── salary_train.csv # Training dataset │── salary_test.csv # Testing dataset │── salary_pred_online_test_result.json # Prediction results │── README.md # Project documentation │ │── Images & Results: │ ├── Feature summary.png │ ├── GUI.png │ ├── RunningGui.png │ ├── Model Evaluation.png │ ├── Model Information.png │ ├── Prediction Result.png │ ├── Relation Map.png │ ├── Progress Map.png │ ├── Maric Chart.png
✔ Automated ML model generation using IBM Watson AutoAI
✔ Graphical results – feature summary, evaluation, relation & progress maps
✔ Salary prediction GUI using Tkinter
✔ Easy-to-run Colab Notebook
✔ Training & Testing datasets provided
The dataset used is related to salary prediction with features like:
- Age
- Experience
- Education level
- Job role
📁 Files:
salary_train.csv→ Training datasetsalary_test.csv→ Testing dataset
Run the GUI with:
python AutoAIGUI.py
📌 Features:
Input fields for model features
Predict button to generate results
Displays predicted salary instantly
🚀 How to Run
1. Clone Repository
bash
Copy code
git clone https://github.com/BhoomiJaiswal0/AutoAI-Model-using-IBM-Watson.git
cd AutoAI-Model-using-IBM-Watson
2. Open Notebook in Google Colab
Upload AutoAI.ipynb
Run all cells to train & evaluate
3. Run GUI (Local)
bash
Copy code
python AutoAIGUI.py📈 Results & Visuals Feature Summary Model Evaluation Prediction Result
🌟 Benefits & Impact Automation: Saves time by auto-selecting the best ML model. Accessibility: Easy GUI for non-technical users. Scalability: Can be extended for other prediction tasks. Learning: Great for beginners exploring AutoAI & deployment.
📚 Future Scope Deploy model on IBM Watson Cloud API for real-time predictions Build a web-based dashboard using Flask/Streamlit Extend dataset with more features for improved accuracy
👩💻 Author Bhoomi Jaiswal 📌 B.Tech CSE(AIMl) | United College of Engineering & Research 🔗 GitHub Profile 🔗 GitHub Profile