I'm a thrid-year IT student who loves turning raw data into meaningful stories. Currently diving deep into data analysis, visualisation & ML .
- 🎓 BE in Information Technology (Expected 2028)
- 📊 Focus: Data Analysis • Data Engineering • AI/ML
- 🌱 Learning: PySpark, NLP, Data Pipelines
- 🔍 Strong interest in real-world datasets & scalable systems
- 🚚 Built ETL pipelines processing 100K+ records using PySpark
- 📊 Analyzed 20K+ global data points to uncover environmental trends
- 🤖 Developed chatbot with 100% query accuracy (10/10 test cases)
- ⚙️ Strong foundation in data structures, OOP, and system design
- Data Cleaning & Preprocessing
- Feature Engineering & Transformation
- Exploratory Data Analysis (EDA)
- Scalable Data Pipelines
- Visualization & Insight Generation
Languages
Data & ML
Tools
End-to-end PySpark-based ETL pipeline built on the Olist dataset.
- Processed 100K+ orders across multiple tables
- Designed modular pipeline for scalability
- Implemented feature engineering for delivery performance
- Stored optimized output in Parquet format
Tech: PySpark • ETL • Parquet • Big Data
A retrieval-based chatbot using NLP techniques.
- Implemented TF-IDF + Cosine Similarity
- Built hybrid system for FAQs + small talk
- Applied confidence threshold filtering
- Visualized performance metrics
Tech: Python • NLP • scikit-learn • Matplotlib
EDA project analyzing pollution trends across global cities.
- Worked on 20K+ records across 50+ cities
- Identified seasonal PM2.5 trends
- Created insightful visualizations
Tech: Pandas • Matplotlib
Java-based system using OOP principles.
- Applied inheritance & polymorphism
- Implemented file-based persistence
- Automated stock tracking & reporting
Tech: Java • OOP • Serialization
- ⚙️ Advanced data pipelines using PySpark
- 🧠 NLP-based intelligent systems
- 🏗️ Data engineering concepts (warehousing, ETL optimization)
- 📈 Improving data visualization & storytelling
⭐ If you like my work, consider giving a star to my repositories!