Machine Learning Project Deployment 🚀

A comprehensive repository of end-to-end Machine Learning projects covering multiple real-world use cases, including healthcare, real estate, NLP, and finance.

This repository demonstrates strong expertise in:

• Data preprocessing
• Feature engineering
• Model training & evaluation
• Deployment using Streamlit
• Building reusable ML pipelines

---

📂 Repository Structure

ML_Project_Deployment/
│
├── 000_Learning_Center/              # Learning resources & practice
├── 001_Kidney_Data/                 # Kidney Disease Prediction
├── 002_House_Price_Prediction/      # House Price Prediction
├── 003_Patient_Survival_Prediction/ # Patient Survival Prediction
├── 004_Sentiment_Analysis/          # NLP Sentiment Analysis
├── 005_Company_Bankruptcy_Prediction/ # Financial Risk Prediction
│
├── main.py                          # Entry script (if applicable)
├── requirements.txt                 # Global dependencies
├── LICENSE
└── README.md

---

📌 Projects Overview

🩺 Kidney Disease Prediction

• Classification using Random Forest
• Preprocessing: Imputation, Encoding, Scaling
• Streamlit deployment

---

🏡 House Price Prediction

• Regression model for real estate pricing
• Outlier handling + scaling
• Real-time predictions via UI

---

🏥 Patient Survival Prediction

• Logistic Regression-based classification
• Full preprocessing pipeline
• Healthcare dataset application

---

💬 Sentiment Analysis

• NLP-based sentiment classification
• Excel-based batch prediction
• Streamlit interface

---

💼 Company Bankruptcy Prediction

• Financial risk prediction model
• Classification approach
• Business-focused use case

---

⚙️ Tech Stack

• Python
• Pandas, NumPy
• Scikit-learn
• Streamlit
• Jupyter Notebook

---

🚀 Key Highlights

• ✅ Multiple ML problem types (Regression, Classification, NLP)
• ✅ End-to-end pipelines
• ✅ Real-world datasets
• ✅ Deployment-ready apps
• ✅ Modular and reusable code

---

🧠 Business Impact

These projects demonstrate:

• Translating data into actionable insights
• Building scalable ML pipelines
• Handling real-world noisy datasets
• Deploying models for real users

---

🚀 How to Run Projects

git clone https://github.com/VikramVadhirajan/ML_Project_Deployment.git
cd ML_Project_Deployment/<project_folder>
pip install -r requirements.txt
streamlit run app.py

---

👨‍💻 Author

Vikram Vadhirajan
Data Analyst | Machine Learning | Python | Power BI

GitHub: https://github.com/VikramVadhirajan

---

⭐ Support

If you found this useful, consider giving this repository a ⭐