Update README.md

README.md

@@ -5,17 +5,23 @@ colorFrom: green
 colorTo: red
 sdk: static
 pinned: false
+license: mit
+short_description: JobSelect CLI and JobAnalyze 6k model
 ---
 
-# Job Description Skill Classifier [JobSelect v0.11.6 & JobAnalyze 6k v1.0] (Multi-Label)
+# Job Description Skill Classifier [JobSelect v0.12.0 & JobAnalyze 6k v1.0] (Multi-Label)
 
 [![Python](https://img.shields.io/badge/Python-3.8+-3776AB?style=flat&logo=python)](https://www.python.org/)
 [![PyTorch](https://img.shields.io/badge/PyTorch-2.12.1-%23EE4C2C?style=flat&logo=pytorch)](https://pytorch.org/)
 [![scikit-learn](https://img.shields.io/badge/scikit--learn-1.9.0-F7931E?style=flat&logo=scikit-learn)](https://scikit-learn.org/)
 [![NumPy](https://img.shields.io/badge/NumPy-2.4.6-013243?style=flat&logo=numpy)](https://numpy.org/)
 [![Pandas](https://img.shields.io/badge/Pandas-3.0.3-150458?style=flat&logo=pandas)](https://pandas.pydata.org/)
+[![Website](https://img.shields.io/badge/jobselect-website-8A2BE2?style=flat&logo=globe)](https://jobselect.vercel.app/)
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97-Hugging%20Face%20Model-FFD21E?style=flat)](https://huggingface.co/JobSelect/JobAnalyze_6k)
+[![PyPI](https://img.shields.io/badge/PyPI-JobSelect-006DAD?style=flat&logo=pypi)](https://pypi.org/project/JobSelect/)
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-Akshay%20Babu-0A66C2?style=flat&logo=linkedin)](https://www.linkedin.com/in/akshay-babu-827b85370/)
 
-This project builds a lightweight text classification pipeline that predicts **multiple technical skills** from a job posting. Given a job description (optionally augmented with role and job type), the model outputs a ranked list of likely skills.
+This project builds
 
 ![JobSelect CLI](./frontend/repo/title_page_jobselect.png)
 
@@ -76,6 +82,64 @@ It uses:
 
 ---
 
+## Project structure
+
+```text
+.
+├─ data/
+│  ├─ raw/
+│  │  └─ Job_descriptions.csv                 # Raw input dataset
+│  ├─ sample_data/
+│  │  └─ test.txt                             # Example JD, Role and Type for testing
+│  └─ clean/
+│     ├─ cleaned_job_descriptions.csv         # Cleaned master CSV
+│     ├─ cleaned_job_descriptions_internships.csv
+│     ├─ cleaned_job_descriptions_junior.csv
+│     └─ cleaned_job_descriptions_senior.csv
+│
+├─ model/
+│  ├─ prep/
+│  │  ├─ data_prep.py                         # TF-IDF + multi-hot label creation + train/test split
+│  │  ├─ sym_map.py                           # Synonym/phrase normalization map used during prep
+│  │  ├─ vectorizer.pkl                       # Saved TF-IDF vectorizer (generated by data_prep)
+│  │  ├─ prepared_data.npz                    # Saved arrays (generated by data_prep)
+│  │  └─ label_vocab.json                     # Skill label vocabulary (generated by data_prep)
+│  │
+│  ├─ model.py                                # PyTorch multi-label classifier training
+│  ├─ eval.py                                 # Thresholded evaluation + F1 metrics + baseline comparison
+│  └─ pred.py                                 # Predict top-k skills for new text
+│
+├─ model_out/
+│  ├─ skill_classifier.pt                     # Trained model weights (generated by model.py)
+│  └─ training_history.json                   # Training loss history (generated by model.py)
+│
+├─ cli/
+│  ├─ jobselect.py                              # Rich terminal CLI (prompts + prints top skills)
+│  ├─ model_select.py                           # Inference routing: API-first, LOCAL fallback (key resolved lazily)
+│  └─ api_val.py                                # API key prompt / mode selection for CLI
+
+│
+├─ test/
+│  └─ test_model.py                           # Pytest checks expected artifacts exist in model_out/ and model/prep/
+│
+├─ notebooks/
+│  ├─ 01_EDA.ipynb                            # Exploratory Data Analysis
+│  └─ 02_Data_Engineering.ipynb               # Data engineering / cleaning notes
+│
+├─ api/
+│  ├─ JobAnalyze_API.py                       # FastAPI service + Pydantic validation + API-key verification
+│  ├─ pred.py                                 # API/server-side prediction wrapper (imports model.pred)
+│  └─ supabase_client.py                     # Optional API key persistence (Supabase)
+│
+├─ pipeline.py                                # Executes notebooks + training/eval steps in order
+├─ pyproject.toml                             # Installs as a cli tool (jobselect)
+├─ requirements.txt
+└─ README.md
+
+```
+
+---
+
 ## Requirements
 
 See `requirements.txt` for the exact dependencies.
@@ -216,7 +280,20 @@ Run `api/JobAnalyze_API.py`. Requests must include:
 
 ---
 
+---
+
+## Author
+
+Developed with ❤️ by **Akshay Babu**
+
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-0A66C2?style=flat&logo=linkedin)](https://www.linkedin.com/in/akshay-babu-827b85370/)
+[![GitHub](https://img.shields.io/badge/GitHub-Follow-181717?style=flat&logo=github)](https://github.com/Ak47xdd)
+
+For questions, feedback, or collaboration opportunities, feel free to reach out!
+
+---
+
 ## References / Inspiration
 
 This repository follows a common pattern for multi-label NLP baselines:
-TF-IDF features + a simple neural network + sigmoid-based multi-label outputs.
+TF-IDF features + a simple neural network + sigmoid-based multi-label outputs.