💡 Algorithm-to-Python Source Code Translator using LLMs

Tech Stack: Python, Hugging Face Transformers, Mistral 7B, LoRA, Gemini API

This project explores how large language models can be fine-tuned to automate the conversion of algorithmic descriptions into executable Python code.

• Fine-tuned the Mistral 7B model using Low-Rank Adaptation (LoRA)
• Created a custom dataset using Gemini API
• Optimized prompts and configurations for higher accuracy
• Presented at ITECHCET 2024 & published in AIP Conference Proceedings

📎 Research Paper DOI 🗁 Source Code 📈 Dataset

💼 Feature Selection & Salary Prediction using Rough Set Theory

Tech Stack: Python, Scikit-learn, Pandas

A predictive model to estimate software developer salaries using Rough Set Theory for feature selection.

• Used Rough Set Theory for key feature extraction
• Trained regression models on cleaned data
• Enhanced model interpretability and accuracy

🗁 Source Code

🌐 Personal Portfolio Website

Tech Stack: HTML, CSS, JavaScript, Bootstrap

A responsive portfolio site showcasing projects, publications, and contact information.

• Custom dark/light modes & animated transitions
• Clean layout with accessible design

🔗 Visit Portfolio 🗁 Source Code

🌫 Air Quality Prediction Model (PM2.5)

Tech Stack: Python, Scikit-learn, Time Series Analysis

Forecasting air quality using historical sensor data and regression models.

• Cleaned and preprocessed sensor data
• Engineered time-based features
• Trained and evaluated forecasting models

🗁 Source Code

📘 Data Structures & Algorithms (DSA) Repository

Tech Stack: Python, GitHub, Markdown

An organized learning repository named "Felicity" for foundational DSA concepts with clean code and visuals.

• Wrote explanations with pseudocode & complexity analysis
• Implemented core algorithms in Python
• Made beginner-friendly with good structure

🔗 Felicity