Tensaey-sol/ethio-ecom-ner-analytics

Comprehensive analysis and processing of Ethiopian e-commerce data using NER and analytics to extract key entities (products, prices, locations) from Telegram channels, powering a centralized hub and vendor insights. # Ethio Ecom NER Analytics This repository contains the setup and development for **Ethio Ecom NER Analytics**, a real-world e-commerce analytics project focused on extracting key entities from Telegram channels in Ethiopia using Named Entity Recognition (NER) and analytics to power a centralized hub and vendor insights. The project simulates the role of a **Data Science Engineer**, leveraging data ingestion, preprocessing, NER model fine-tuning, and vendor scoring with machine learning to deliver insights for micro-lending and e-commerce optimization. --- ## 🚀 Getting Started ### 1. Clone the Repository ```bash git clone github.com cd ethio-ecom-ner-analytics ``` ### 2. Set Up a Virtual Environment ```bash python -m venv .venv ``` Activate it: - **Windows:** ```bash .venv\Scripts\activate ``` - **macOS/Linux:** ```bash source .venv/bin/activate ``` ### 3. Install Dependencies ```bash pip install --upgrade pip pip install -r requirements.txt ``` --- ## 📂 Project Structure ``` ethio-ecom-ner-analytics/ ├── .github/ │ └── workflows/ │ └── ci.yml # GitHub Actions workflow ├── .gitignore # Ignore rules for Git ├── requirements.txt # Project dependencies ├── README.md # Project documentation ├── notebooks/ # Jupyter Notebooks │ └── README.md ├── tests/ # Unit tests for scripts and functions │ └── __init__.py ├── scripts/ # Scripts for data ingestion, preprocessing, modeling │ ├── __init__.py │ └── README.md ├── data/ # Raw and processed datasets │ ├── raw/ # Raw Telegram data │ ├── processed/ # Preprocessed data │ └── conll/ # CoNLL-formatted labeled data └── .venv/ # Local virtual environment (ignored via .gitignore) ``` --- ## ⚙️ GitHub Actions CI This repository uses **GitHub Actions** fo …