A scalable data warehouse for collecting, cleaning, and analyzing Ethiopian medical business data scraped from Telegram channels, with integrated object detection using YOLO.
# Ethiopian Medical Data Warehouse
This project scrapes Ethiopian medical business data from **Telegram channels**, cleans and processes the data, stores it in a **data warehouse**, and applies **object detection using YOLO** for image analysis.
## 📌 Features
- ✅ **Telegram Bot Scraper** - Extracts messages and images from public channels
- ✅ **Data Cleaning & Transformation** - Processes scraped data for consistency
- ✅ **Object Detection with YOLO** - Detects relevant objects in images
- ✅ **Data Warehouse Integration** - Stores structured data for analysis
- ✅ **Logging & Monitoring** - Tracks scraping activity
---
## 📂 Project Structure
```
📂 ethiopian_medical_business_scraper
│── 📂 data_scraper
│ │── bot_scraper.py # Scrapes Telegram messages
│ │── image_scraper.py # Downloads images
│ │── config.py # Stores API keys
│ │── logging_config.py # Logging setup
│
│── 📂 data_processing
│ │── clean_data.py # Cleans and transforms data
│ │── process_images.py # Prepares images for YOLO
│
│── 📂 object_detection
│ │── yolo_detection.py # YOLO object detection
│ │── model_config.py # YOLO settings
│
│── 📂 data_warehouse
│ │── database_setup.py # Sets up database
│ │── insert_data.py # Inserts cleaned data into DB
│
│── 📂 utils
│ │── helpers.py # Utility functions
│ │── constants.py # Stores channel names
│
│── 📂 logs
│ │── scraper.log # Logs scraping activity
│
│── 📂 data
│ │── raw/
│ │ │── messages.json # Raw scraped messages
│ │ │── images/ # Downloaded images
│ │── cleaned/
│ │ │── cleaned_data.csv # Processed data
│
│── requirements.txt # Dependencies
│── README.md # Project documentation
│── .gitignore # Ignore unnecessary files
```
---
## 🔧 Installation
### 1️⃣ **Clone the repository**
```bash
git clone
github.com
cd ethiopian_medical_ …