"Understanding migration routes is essential for conservation planning and climate change research." > This project analyzes 10,000 migratory journeys using a hybrid approach of Python-based statistics and interactive Business Intelligence.
- Comprehensive EDA: Processed 42 variables across 10,000 records.
- Geospatial Insights: Visualized flight paths using start/end coordinates.
- Predictive Indicators: Analyzed the impact of weather (Stormy, Windy) on migration success.
- Interactive Storytelling: Built a dynamic Power BI dashboard for stakeholders.
Using Pandas, Seaborn, and Matplotlib, we uncovered:
- Migration Success Rates: Correlated habitat types and weather conditions.
- Data Quality: Handled missing values (e.g., "Interrupted" column) and outliers.
- Flight Metrics: Average speed, altitude, and distance distribution across species.
An interactive report designed with a custom "Birds Dashboard Theme" featuring:
- Researcher Performance: Comparative analysis of tracking by Researcher A, B, and C.
- Weather Impact: Real-time filtering of migration outcomes based on environmental stressors.
- Species Explorer: Dynamic drill-downs into specific bird behaviors.
├── DV_bird_migration_eda.ipynb # Full Python Analysis & Data Cleaning
├── bird migration.pbix # Interactive Power BI Dashboard
├── bird_migration_data.csv # Dataset (10k records, 42 features)
└── Avian_Journeys_Presentation # Project Documentation & Summary
- For the Dashboard: Open
bird migration.pbixin Power BI Desktop. - For the EDA: Launch the
.ipynbfile in Google Colab or Jupyter to see the step-by-step data science process.
Developed as part of the Data Visualization course at San Jose State University under the guidance of Dr. Venkata Duvvuri.
- Dhruvkumar Kamleshbhai Patel
- Drashti Shah
- Sanjay Kanabhai Bharvad
- Keerthika Loganathan
- Dataset: S. Mahara (2025) via Kaggle.
- Course: DATA 230 - Data Visualization.
- Tools: Python (Seaborn), Power BI, NotebookLM.
"Migration is a vital sign for our planet."