Yafetm/Building-an-Amharic-E-commerce-Data-Extractor

# Building an Amharic E-commerce Data Extractor This repository contains the code for the 10 Academy KAIM Week 4 challenge, focused on building an Amharic Named Entity Recognition (NER) system to extract entities from Ethiopian Telegram e-commerce channels. ## Project Structure - `data/`: Contains raw and processed data (not uploaded to GitHub). - `scripts/`: Python scripts for data ingestion and preprocessing. - `README.md`: Project overview. - `.gitignore`: Specifies files/folders to ignore. - `LICENSE`: Project license. - `requirements.txt`: Dependencies. ## Setup 1. Clone the repository: `git clone github.com` 2. Install dependencies: `pip install -r requirements.txt` 3. Set up `.env` with Telegram API credentials. ## Progress - **Task 1**: Implemented data ingestion (`data_ingestion.py`) and preprocessing (`preprocessing.py`) . - **Task 2**: Planned (NER labeling). ## Next Steps - Label data in CoNLL format for NER. - Fine-tune NER models using Hugging Face.