# Ethiopian Data Science & AI Community – Open Dataset Repository
> **Empowering innovation through open, community-driven data for Ethiopia.**
Welcome to the official open dataset repository of the **Ethiopian Data Science & AI Community** — a collaborative space where researchers, students, developers, and changemakers come together to share, analyze, and build impactful data solutions for Ethiopia.
Our mission:
🔍 **Collect** Ethiopia-relevant datasets
🧠 **Analyze** real-world challenges
🚀 **Enable** AI and data science innovation across sectors
🌍 **Build** a culture of open, ethical, and inclusive data science
---
## 📁 Repository Structure
```
datasets/
│
├── README.md ← You are here!
├── data/ ← All datasets organized by domain
│ ├── finance/ ← e.g., finanicial datasets, public data
│ ├── agriculture/ ← e.g., crop yields, farming practices
│ ├── health/ ← e.g., disease prevalence, clinic access
│ ├── education/ ← e.g., enrollment, school locations
│ ├── climate/ ← e.g., rainfall, temperature
│ ├── transportation/ ← e.g., Addis Ababa mobility
│ └── language/ ← e.g., Amharic text, speech samples
│
├── templates/ ← Starter project templates
│ ├── crop_yield_predictor_starter.ipynb
│ ├── amharic_sentiment_analysis_starter.ipynb
│ └── addis_mobility_analysis_starter.ipynb
```
---
## 🌱 Starter Projects (Beginner-Friendly)
We’ve created three starter project templates to help you dive in — whether you're new to data science or ready to build advanced models.
| Project | Goal | Skills Used |
|-------|------|-------------|
| Crop Yield Predictor | Predict agricultural output using climate & soil data | Pandas, Visualization, Regression |
| Amharic Sentiment Analyzer | Classify sentiment in Amharic text | NLP, BERT, Text Cleaning |
| Addis Mobility Analyzer | Analyze urban transport patterns | OSMnx, Geospatial Analysis, Time Series |
👉 **Jump in:** Open any `.ipynb` file in Google Colab or Jupyter to get started!
---
## 📥 How to Contribute Data
We invite you …