---

📖 Overview

Textify is a nlp analyzer scaffold: it trains a scikit-learn/XGBoost model on a generated sample dataset (src/data_generator.py → src/train.py) and serves live predictions through a small Streamlit UI (src/app.py).

Dependencies (requirements.txt):

  pandas>=1.3.0
  numpy>=1.21.0
  scikit-learn>=1.0
  streamlit>=1.20.0
  pyyaml>=6.0
  joblib>=1.2.0

🏗️ Project Layout

Textify/
├── configs/config.yaml   # Data paths & model hyperparameters
├── data/external/         # Generated sample dataset
├── models/                 # Trained model artifact (.pkl)
├── notebooks/               # Exploratory notebooks
├── src/
│   ├── app.py                 # Streamlit UI — loads the trained model and predicts
│   ├── train.py               # Trains the model from configs/config.yaml
│   ├── data_generator.py      # Generates the sample dataset
│   ├── features/               # Feature engineering
│   ├── models/                  # Model definitions
│   └── visualization/            # Plotting helpers
└── tests/

⚡ Setup & Run

🪟 Windows (PowerShell / CMD)

git clone https://github.com/AfnanSharif/Textify.git
cd Textify

python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt

python src/train.py
streamlit run src/app.py

🍎 macOS / 🐧 Linux

git clone https://github.com/AfnanSharif/Textify.git
cd Textify

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

python src/train.py
streamlit run src/app.py

Open http://localhost:8501.

---

Created by AfnanSharif · ⭐ star this repo if it helped you