Skip to content
View D-Durga1728's full-sized avatar
💭
## Open to work
💭
## Open to work

Highlights

  • Pro

Block or report D-Durga1728

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
D-Durga1728/README.md

Hi 👋, Durga Prasad Narsing

Data Analyst (Graduate) — MSc Data Analytics, Dublin City University 📍 Dublin, Ireland  |  🇮🇪 Eligible to Work in Ireland  |  🟢 Available Immediately Turning data into actionable insights through Python, SQL, and Machine Learning.

📧 durgaprasadnarsing1728@gmail.com  |  🔗 linkedin.com/in/durga-prasad-narsing  |  💻 github.com/D-Durga1728

Profile Views


About Me

I'm an MSc Data Analytics student at DCU (First Class with Distinction, CGPA 8.30, B.Tech Computer Science & Data Science) who solves real data problems end-to-end — from a memory bottleneck on an 82-million-row dataset to a deployed clinical risk model with fairness auditing. I work in Python, R, SQL, Power BI, and Tableau, and I'm self-directed: every project below was scoped, built, and shipped by me (team projects say so explicitly).

Currently on Stamp 2 (DCU student visa) — eligible to work part-time now, full-time unrestricted from September 2026 via Stamp 1G on MSc completion.


🛠 Tech Stack

Python R PostgreSQL Scikit-learn XGBoost Pandas Power BI Tableau Streamlit Git

Programming & Analytics: Python (Pandas, NumPy, scikit-learn, XGBoost, Plotly), R, SQL, PostgreSQL BI & Visualisation: Tableau, Power BI, Plotly (animated/interactive), Excel (Advanced) ML & Stats: Classification, regression, Random Forest, XGBoost, cross-validation, hypothesis/A-B testing, feature engineering, model calibration, fairness auditing Deployment: Django, Flask, Streamlit, Git/GitHub Actively learning: React, MCP (Model Context Protocol) & agentic AI workflows, cloud data engineering


🌟 Featured Projects

Solo — MSc Practicum, DCU · Supervisors: Dr Martin Crane, Dr Tai Tan Mai A 220,218-case clinical dataset had no Long COVID follow-up labels, so instead of overclaiming, I reframed the target honestly as a mortality proxy. Benchmarked a calibrated Logistic Regression (test AUC 0.888) against Random Forest, Gradient Boosting, XGBoost, and Stacking — DeLong testing showed none beat it, so I deployed the interpretable model. Added fairness auditing across age/sex/comorbidity (cut TPR disparity from 0.60 to 0.045) and shipped a live Streamlit risk calculator.

Team Project, 4 members (modelling & reporting role) — DCU CA683 Data Mining Merged 3 open Irish datasets (24 weather stations, EirGrid grid data, SEM wholesale prices) into one unified hourly series. Our Random Forest model reached R² 0.975 on demand and R² 0.972 on price (MAE 6.13 EUR/MWhe), confirmed with 5-fold cross-validation.

Solo — DCU CSC1143 Data Visualisation An 82-million-row, 31 GB dataset crashed every local load attempt. I rebuilt the ingestion using chunk-based Pandas processing into a working 3,569,724-row set, engineered a daysBeforeFlight feature, and shipped an animated Plotly dashboard — cutting insight delivery from hours of manual work to under 5 minutes.

Team Project, 4 members (statistical analysis & reporting role) — DCU CSC1181 Contributed statistical analysis, the ethical/legal write-up, and final report compilation on a 70,000-patient dataset. The team's XGBoost model reached 72.93% accuracy with 5-fold stratified cross-validation; I translated those results into stakeholder-ready findings.

Solo — Anurag University Built a full solo pipeline in R — cleaning, EDA, feature selection, Random Forest training, cross-validation — and deployed it as a live tcltk GUI where a user enters wine attributes and gets an instant quality prediction. Not just a notebook; a working product.


🎓 Education

MSc Data Analytics — Dublin City University, Ireland (Sep 2025 – Sep 2026) B.Tech Computer Science & Engineering (Data Science) — Anurag University, India — First Class with Distinction, CGPA 8.30


📜 Certifications

  • BCG X Data Science Job Simulation — Forage
  • Deloitte Data Analytics Job Simulation — Forage
  • Database and SQL — Infosys
  • Data Visualisation with Tableau — Infosys
  • Big Data and Hadoop — Infosys
  • Deep Learning — Scaler
  • Microsoft Excel — LinkedIn Learning

📫 Let's Talk

I'm actively looking for Data Analyst / Junior Data Scientist roles in Ireland (hybrid or on-site, Dublin). If you're hiring or just want to talk data, reach out:

📧 durgaprasadnarsing1728@gmail.com  |  🔗 LinkedIn

Data speaks — I make it understandable and useful.


Popular repositories Loading

  1. D-Durga1728 D-Durga1728 Public

  2. wine-quality-prediction-r wine-quality-prediction-r Public

    R

  3. flight-price-visualisation flight-price-visualisation Public

    The data analysis presented in our data visualisation project is the investigation into the temporal changes in the price of the flight tickets as the departure date approaches with the help of a l…

    Jupyter Notebook

  4. CardioRisk_ML-Durga- CardioRisk_ML-Durga- Public

    Forked from khu590/CardioRisk_ML

    Predictive pipeline for cardiovascular disease using machine learning. Includes data cleaning, feature engineering, model training (Logistic Regression, Random Forest, Gradient Boosting, XGBoost wi…

    Jupyter Notebook

  5. longcovid-risk-prediction longcovid-risk-prediction Public

    Predictive Modelling for Personalised Long COVID Risk Assessment | MSc Data Analytics, DCU | Calibrated LR · SHAP · Fairness Audit · Streamlit

    Python

  6. ireland-electricity-weather ireland-electricity-weather Public

    Weather-driven modelling of electricity demand and wholesale prices in Ireland using Random Forest and XGBoost — DCU CA683 Data Mining

    Jupyter Notebook