I focus on building meaningful data projects! Learn more about me
“Passion provides purpose, but data drives decisions”
– Andy Dunn
IMDB Movies – BI Project
(Skills/Tools: SQL, Alteryx, Talend, Python, ER/Studio, Tableau, GCP, PowerBi)
Movie fanatic?
Here’s Data profiling, Dimensional modelling, loading extracted content to perform data transformations on Talend to enable a great data model.
There is dealing with Slowly Changing Dimensions (SCD2) and visualising some of the most interesting questions on PowerBi and Tableau!
AirBnb Price Prediction Model
(Skills/Tools: Python, Jupyter Notebook, Numpy, Pandas, Tensorflow, Pytorch, Seaborn, Scikit-learn)
Ever wanted to know where to invest next? The aim of this Data Science project is to understand how some factors are influential to make a future sell/buy of AirBnb’s in the city of NYC utilising models like XGBoost, Random Forest to analyse along with H20 – AutoML, Shap analyses to validate the model performance!
CFA Institute – ETL Pipeline
(Skills/Tools, AWS S3, Airflow, Snowflake, Git, Python, Pydantic, Grobid, Pypdf, DBT, FastAPI)
Developing an End to End ETL Pipeline by Primarily extracting information from CFA’s website and dealing with unstructured data; This Project focusses to utilise data extractions and validations with ML libraries, data transformations, and finally data loading on Cloud platforms to design a well accomplished data architecture.
Heart Disease Prediction
(Skills/Tools: Python, Jupyter Notebook, Numpy, Pandas, Tensorflow, Pytorch, Seaborn, Scikit-learn)
Did you know there’s a death every 33 seconds due to a heart disease? Here’s how likely it is for a person to fall under this category statistical methods like p-value, t-statistics and visualization techniques like histogram, Q-Q plot, scatter plot and box-plots using various Python libraries like matplotlib, seaborn.
Sentiment Analysis Database Model
(Skills/Tools: Python, Data Analysis, NLP, MySQL)
How happy are you? Did it ever strike you?
This project cumulates all the Countries Data in various categories to cross validate the happiness indexes by Database queries, indices, views and triggers.
Using HuggingFace Transformers to understand Sentiment of sentences, it was insightful to understand how happiness differs with each category.
Patient Shelter Application
(Skills/Tools: SQL, NetBeans, Java, JavaSwing)
Corona virus has made itself home in our environment. Building Patient Shelter application creates a common ground for various institutions involved in the drug distribution and utilisation systems.
Creating technological support to eliminate the prevalent virus, this Java application is to help the world for the benefit of people by ensuring their health by bridging various roles and organisations to help goverment to track vaccinations.
Food Facility Inspection – ETL
(Skills/Tools: SQL, Alteryx, Talend, Python, Tableau, ER/studio, PowerBi)
Foodies choose to go to restaurants with Grade A inspection certification.
Here is an ETL pipeline with Data Integrated from multiple sources into dimensional and fact tables to make necessary data extraction and transformations.
Visualisations on Tableau and PowerBi to showcase various categories compared and analysed on quarterly basis
University Database model
(Skills/Tools: MySQL, ER/Studio, Beautifulsoup, PowerBi)
Executed advanced SQL techniques for data querying, preprocessing, integration, achieving data uniformity and integrity across the centralized university database
Developed dynamic PowerBI dashboards to provide actionable insights into student enrolment trends, course performance metrics, and academic outcomes, facilitating data-driven decisions and strategic improvements