ibnu-asma/Amharic-E-commerce-Data-Extractor

# EthioMart Amharic E-commerce Data Extractor This project builds a Named Entity Recognition (NER) system to extract key entities (e.g., products, prices, locations) from Amharic Telegram e-commerce channels for EthioMart, a centralized e-commerce platform in Ethiopia. ## Project Structure ``` ethiomart_ner/ ├── src/ # Source code │ ├── __init__.py │ ├── data_ingestion/ # Telegram scraping scripts │ ├── preprocessing/ # Text preprocessing │ ├── labeling/ # NER labeling │ ├── model_training/ # Model fine-tuning │ ├── evaluation/ # Model comparison and interpretability ├── tests/ # Unit tests ├── notebooks/ # Jupyter notebooks (EDA, training, analysis) ├── data/ # Data storage │ ├── raw/ # Raw Telegram data │ ├── processed/ # Preprocessed and labeled data │ ├── images/ # Product images │ ├── documents/ # Documents ├── models/ # Trained models ├── docs/ # Documentation and reports ├── requirements.txt # Python dependencies ├── config.yaml # Configuration file ├── README.md # Project overview └── .gitignore # Git ignore file ``` ## Setup Instructions 1. **Clone the repository**: ```bash git clone github.com cd ethiomart_ner ``` 2. **Set up a virtual environment**: ```bash python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate ``` 3. **Install dependencies**: ```bash pip install -r requirements.txt ``` 4. **Configure Telegram API**: - Create a `config.yaml` file with your Telegram API credentials: ```yaml telegram: api_id: 'YOUR_API_ID' api_hash: 'YOUR_API_HASH' phone: 'YOUR_PHONE_NUMBER' ``` 5. **Run tests** (optional): ```bash pytest tests/ ``` --- ## Full Workflow: From Data to Vendor Analytics ### 1. **Data Collection** - **Ingest Telegram posts** using …