Skip to content
View VishPetkar13's full-sized avatar

Block or report VishPetkar13

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
vishpetkar13/README.md

Hello There My name is Vishal Petkar

Data Engineer Β |Β  Data Analyst Β |Β  Python Automation Engineer


πŸ‘€ About Me

I'm a Data Analytics professional with a First-Class Honours MSc in Data Analytics (Machine Learning) from the National College of Ireland, and over 4.5 years of hands-on experience in global enterprise IT environments at Capgemini Technology Services.

My background spans Major Incident Management, Problem Management, and Automation Engineering within IT Service Management, working closely with distributed technical teams across multiple regions and time zones to improve system reliability, service performance, and operational efficiency.

I have a strong foundation in Python programming and enjoy using it to automate data extraction, processing, and reporting workflows. I've built automation solutions that significantly reduced manual effort, improved reporting accuracy, and accelerated stakeholder decision-making β€” cutting weekly report generation time by 75% and eliminating manual effort for 14–16 team members across critical reporting functions.

I bring solid experience in Root Cause Analysis, SQL/PostgreSQL, and ETL workflows, and I'm actively growing my knowledge in Data Engineering, Machine Learning, and Generative AI.

I'm ITIL V3 certified and comfortable operating in high-pressure environments. I value clear communication, structured problem-solving, and turning messy operational data into actionable insights.

  • 🌍 Based in Dublin, Ireland
  • 🎯 Open to Data Engineer and Data Analyst roles
  • πŸ‘₯ Looking to collaborate on data, analytics, and automation projects
  • πŸ“š Currently self-studying cloud data platforms and AI/ML pipelines
  • πŸ’¬ Fun fact: I enjoy reading Sci-fi and Fantasy fiction

πŸ› οΈ Tech Stack & Skills

Languages & Querying

Python Β  MySQL Β  PostgreSQL

Python SQL PostgreSQL SQLite

Data & ML Libraries

Pandas NumPy Scikit-learn XGBoost OpenCV Matplotlib Seaborn

Tools & Platforms

VS Code Β  Google Cloud Β  Vim

Jupyter Tableau Git Linux ServiceNow

Domains & Methodologies

ETL EDA ITIL Root Cause Analysis Incident Management


πŸ’Ό Projects

A desktop barcode scanning and digital receipt management application built with Python.

Built an end-to-end desktop application that allows users to scan retail barcodes via webcam, store and label them in a local database, and retrieve or delete records when needed. Demonstrates practical software engineering across computer vision, database management, GUI development, and multi-threaded processing.

Key Skills Demonstrated: Python Β· OpenCV Β· ZXing Β· SQLite Β· Flet Β· Multi-threading Β· Data Persistence Β· UX Design

Python OpenCV SQLite Flet


Automated data extraction from PDFs to Excel, including pivot table generation.

Developed a Python tool that extracts targeted text and tables from PDF files, exports the structured data to Excel, and auto-generates pivot tables for analysis. Directly applicable to ETL and reporting automation workflows in data engineering environments.

Key Skills Demonstrated: Python Β· PDF Parsing Β· Excel Automation Β· Data Extraction Β· ETL Β· Reporting

Python Excel


A structured collection of SQL exercises and queries from the Udemy "Master SQL for Data Science" course.

Repository of SQL scripts covering core to advanced querying concepts including joins, subqueries, window functions, aggregations, and data manipulation β€” aligned with real-world data analytics use cases.

Key Skills Demonstrated: SQL Β· Data Querying Β· Analytical Thinking Β· Database Design

SQL PostgreSQL


MSc thesis project β€” detecting exoplanets from stellar light curves using an ensemble of CNN, K-NN, and Random Forest models.

Trained and evaluated four ML models (CNN, Random Forest, K-NN, SVM) on light curve images from NASA's Kepler, K2, and TESS missions. The best-performing ensemble (CNN + K-NN + RF) achieved an F1 score of 0.68 and recall of 0.70 on unseen test data. Awarded First-Class Honours.

Key Skills Demonstrated: Python Β· TensorFlow Β· Scikit-learn Β· CNN Β· Ensemble Learning Β· Computer Vision Β· EDA Β· NASA Exoplanet Archive

Python TensorFlow Scikit-learn Jupyter


βš™οΈ More Projects (Coming Soon)

Additional projects currently in the pipeline β€” watch this space!

Status


πŸ“„ Research & Publications

πŸŽ“ Bachelor's Thesis

Real Time Air Pollution Monitoring System New Horizon College of Engineering, Bangalore Β· May 2017

An IoT-based system for real-time detection and monitoring of atmospheric pollutants (CO2, CO, LPG, Smoke, Methane) using Arduino UNO R3 with MQ135, MQ2, and DHT11 sensors. Data was transmitted to a web portal and Android devices, with analysis of the correlation between CO2 concentration and ambient temperature.

Tech Stack: Arduino Β· IoT Β· Sensors Β· HTML Β· CSS Β· Bootstrap Β· Android


πŸ“° Published Research Papers

"Real Time Monitoring of Change in Temperature with CO2 using IoT" International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE) Vol. 5, Issue 5, May 2017 Β· DOI: 10.15680/IJIRCCE.2017.0505205 Β· Certificate No: V5I5C425

DOI IJIRCCE Impact Factor

Investigated the real-time relationship between CO2 concentration and temperature using IoT sensors deployed in Bangalore. Demonstrated a measurable positive correlation between rising CO2 levels (591–655 ppm) and ambient temperature across 20 field measurements.


"A Technical Review on Health Monitoring System at Household Using IoT" International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE) Vol. 5, Issue 5, May 2017 Β· DOI: 10.15680/IJIRCCE.2017.0505176 Β· Certificate No: V5I5C377

DOI IJIRCCE Impact Factor

A technical review of IoT-based ubiquitous health monitoring using smart household devices (Smart Mouse, Mirror, Chair) to measure vital signs including heart rate, temperature, blood pressure, and respiratory rate, with output delivered via web portal and Windows mobile application.


πŸ“œ Certifications

Certificate Issuer Date Credential
Master SQL For Data Science Udemy Jul 2025 UC-5ae0b748
Python Game Development with Pygame Udemy Jul 2022 UC-b9580b67
Crash Course on Python Coursera Jan 2022 ECYCNGZTBFVZ
Ask Questions to Make Data-Driven Decisions Coursera Jul 2021 BGXBEJMHR6N5
Foundations: Data, Data, Everywhere! Coursera Jul 2021 EJQFYZAUDKYP
Python Data Structures Coursera Sep 2020 JV337TXJ5G4C
Programming for Everybody (Getting Started with Python) Coursera Aug 2020 E855FUV2GGT6
ITIL V3 Foundation AXELOS β€” Certified

πŸ† Honors & Awards

πŸ₯‡ Spot Award β€” February 2021

Issued by: Capgemini Β· AXA Service Control Lead Β |Β  Feb 2021

Presented to Vishal Petkar for his valuable contributions and commitment to excellence.


πŸ₯‡ Spot Award β€” May 2020

Issued by: Capgemini Β· AXA Service Control Lead Β |Β  May 2020

Recognised for an extraordinary improvement in role performance, appreciation from Global Stakeholders, and taking the key initiative of self-learning Python scripting to successfully automate 6 operational reports β€” saving significant manual effort and time across teams.


πŸ“Š GitHub Stats

Vishal's GitHub Stats Β  Top Languages

GitHub Streak


🌐 Languages

English Hindi Marathi


Open to Data Engineer and Data Analyst opportunities in Ireland, India and remotely. Feel free to connect!

Pinned Loading

  1. Exoplanet-Detection-Ensemble-ML Exoplanet-Detection-Ensemble-ML Public

    MSc thesis project β€” Ensemble ML (CNN + K-NN + Random Forest) to detect exoplanets from Kepler, K2 & TESS stellar light curves. Python Β· TensorFlow Β· Scikit-learn.

    Jupyter Notebook

  2. BarCode_Reader BarCode_Reader Public

    This project to to create a barcode reader that reads barcode and stores it in persistantly in a local database

    Python

  3. SQL_For_Data_Analytics SQL_For_Data_Analytics Public

    The Repositiry contains the SQL files from the UDEMY course "Master SQL for Data Science"

  4. cosmere-analytics cosmere-analytics Public

    An end-to-end data analytics project exploring Brandon Sanderson's Cosmere universe as a publishing business case. Covers data collection, SQL analysis, Python EDA, machine learning, and an interac…

    Jupyter Notebook

  5. gamepass-intelligence gamepass-intelligence Public

    End-to-end data analytics project analysing gaming catalogues for business insights

    Jupyter Notebook

  6. PDF_ReportGeneration PDF_ReportGeneration Public

    Python