This repository contains a collection of data science projects showcasing various analytical techniques, machine learning models, and data visualization approaches.
An analysis of biodiversity data from different national parks, examining species distribution, conservation status, and observation patterns. This project uses statistical analysis and data visualization to identify endangered species and conservation priorities across park systems.
Key techniques: Data cleaning, exploratory data analysis, statistical testing, conservation metrics, and interactive visualizations.
Note: The biodiversity_presentation.html file in this folder needs to be hosted together with the dataset to get an interactive presentation of the Jupyter Notebook.
An investigation into the relationship between GDP and life expectancy across different countries and time periods. This project explores global health trends and economic development patterns to understand how prosperity relates to longevity.
Key techniques: Time series analysis, correlation analysis, regression modeling, and geospatial visualization.
A predictive analysis of medical insurance costs based on various demographic and lifestyle factors. This project examines how age, BMI, smoking status, and other variables influence insurance premiums.
Key techniques: Regression analysis, feature importance, cost prediction, and demographic segmentation.
An in-depth analysis of dating profiles from OkCupid, exploring how different traits and self-presentation strategies correlate with profile completeness and potential match success.
Key techniques: Natural language processing, supervised learning (regression and classification), unsupervised learning (clustering and topic modeling), and feature importance analysis. Different visualization techniques
- Data Cleaning & Preprocessing: Handling missing values, feature engineering, and data transformation
- Exploratory Data Analysis: Statistical analysis and visualization to understand data patterns
- Machine Learning: Both supervised (regression, classification) and unsupervised (clustering, topic modeling) techniques
- Data Visualization: Creating informative and visually appealing charts and graphs
- Domain-Specific Analysis: Applying data science to diverse fields including ecology, economics, healthcare, and social dynamics
Each project includes detailed documentation and code to demonstrate the analytical process from data exploration to insights and conclusions.