Analyzed Amazon reviews using Python and NLP to extract insights on customer sentiment, rating trends, and review themes. Built interactive dashboards with Plotly and maintained version control via GitLab. Focused on three products, showcasing data cleaning, EDA, and VADER sentiment analysis. .
View on GitHubBuilt ML models (Logistic Regression, Random Forest) to Analysing & Predicting products sales trends.
View on GitHubInteractive web app predicting student dropout risk with visualizations.
View on GitHubMediCareDB is a document-oriented healthcare database system built using MongoDB and Python (PyMongo). The system features automated data generation, denormalization for performance, indexed queries, and aggregation pipelines. Optimized using indexing strategies and real-time performance tracking (executionTimeMillis), MediCareDB demonstrates how NoSQL databases outperform traditional SQL systems in scalability and flexibility for dynamic, high-volume medical data.
View on GitHubEDA in Python and R to visualize dataset distributions and trends.
View on GitHubForecasted real-estate prices using Ridge Regression on a large dataset.
View on GitHubGlobal COVID-19 trend visualizations using Pandas and Matplotlib.
View on GitHubRandom Forest Regressor to predict car prices with full evaluation.
View on GitHub