This repository contains a collection of hands-on data analysis projects created using Python.
Each notebook reflects a real-world inspired task — from data cleaning and transformation to analysis and visualization — and is structured for clarity, insight, and practical use.
Objective: Analyze Facebook advertising campaign data for the year 2021 to understand spending behavior and Return on Marketing Investment (ROMI).
Key Highlights:
- Daily and rolling average ad spend and ROMI visualizations
- ROMI distribution per campaign via boxplots
- Histogram of ROMI across all campaigns
- Correlation heatmap of numeric features
- Regression analysis of total spend vs. total value
📂 Facebook_Ads_Spend_Strategy_and_ROMI.ipynb
Objective: Explore global developer trends with a focus on Python developers using the 2024 Stack Overflow survey data.
Key Highlights:
- Analysis of experience, education, income, and remote work adoption
- Python usage by age and background
- Salary comparisons across regions
- Measures of central tendency and grouped visualizations
- Final summary of trends and insights
📂 StackOverflow_Developer_Survey_Analysis.ipynb
Objective: Score and filter loan applications based on business-defined criteria and enrich them with industry ratings.
Key Highlights:
- Data cleaning, deduplication, and enrichment
- Rule-based rating system (6 factors)
- Filtering of accepted applicants
- Weekly aggregation and rating trends
- Custom color-coded visualizations
📂 Loan_Application_Rating_Analysis.ipynb
- Python
- Pandas, NumPy
- Matplotlib, Seaborn
- Jupyter Notebook
Each notebook is self-contained and includes explanations, plots, and relevant comments. These projects were created as part of my hands-on learning journey in data analytics, reflecting both technical development and an emphasis on clean structure and presentation.
Thank you for reviewing my portfolio!
Feel free to explore the notebooks and reach out for collaboration or feedback.