PROJECT

Using Python, unstructured server log files are converted into a structured format to analyze error hits, monitor IP activity, and support cybersecurity insights. This helps in detecting issues, tracking user behavior, and identifying potential security threats more efficiently.

Using Power BI, unstructured vehicle data is transformed into an interactive and structured dashboard to analyze price trends, damage conditions, and fuel types. This helps in better visualization, insights generation, and data-driven decision-making.

This project focuses on analyzing system log data to detect errors, monitor performance, and identify unusual activity. The dashboard converts raw logs into structured insights, helping to understand error patterns, system behavior, and potential security issues.

Conducted an in-depth analysis of English Premier League (EPL) player statistics using Python, Pandas, Matplotlib, and Seaborn. Focused on key performance indicators such as goals, assists, and passes. Created insightful visualizations to uncover trends and support data-driven decision-making in football analytics.

Performed analysis on YouTube songs dataset covering views, likes, comments, and publishing patterns. Explored video IDs, channel names, song titles, tags, descriptions, and engagement metrics to uncover content trends and audience behavior.

Created a content-based movie recommender in Python. Suggested films using similarities in genre, keywords, cast, and crew. Used popular data science libraries for analysis.

This project includes a Jupyter Notebook demonstrating web scraping methods for movie-related data. It guides through extracting information from movie websites (e.g., IMDb, Rotten Tomatoes) using Python libraries like requests, BeautifulSoup, and pandas.

This project presents a data storytelling analysis of COVID-19 using Python. It blends analytical methods with visual storytelling to highlight trends, patterns, and global insights. The notebook walks through the full process — from data exploration to interactive visualizations and final takeaways.

This project uses machine learning to predict crop yield based on environmental and regional variables. Developed as a Final Year Project (FYP), it demonstrates the potential of data science to address real-world challenges in agriculture.

This project showcases an interactive Power BI dashboard created using the SuperStore sales dataset. It highlights key metrics like revenue, order value, and sales trends to support data-driven business decisions.

This dashboard provides a comprehensive view of real estate data, enabling users to analyze property sales, pricing trends, and agent performance for strategic business decisions.

This Power BI dashboard provides a detailed overview of HR data, helping organizations track workforce metrics such as employee count, gender distribution, department headcount, hiring trends, attrition rates, salary distribution, and more.

This project focuses on analyzing the Titanic dataset and building a machine learning model to predict passenger survival. The goal is to understand the key factors influencing survival and create a predictive model based on those insights.

This project explores and visualizes road traffic data in Brazil, focusing on how different incidents—like rain, accidents, and road works—affect traffic flow. The goal is to identify patterns and understand which conditions contribute most to traffic slowness.

This project focuses on cleaning and preparing a dataset containing various laptop specifications. The dataset initially contained inconsistencies, missing values, and formatting issues that needed to be resolved to enable further analysis or modeling tasks.