This project is a Python-based application with Streamlit interface for parsing resumes, extracting relevant details (skills, experience, etc.), and ranking candidates against job descriptions using NLP.

This is a small public piece of code (standalone fork) taken from of one of my freelance projects.

Features

• Resume parsing: Extracts structured information like name, email, phone, skills, and experience from uploaded PDF resumes
• Candidate ranking: Compares extracted skills with a job description and ranks candidates based on relevance
• Interactive interface: Allows users to upload resumes, enter job descriptions, and view rankings directly in a web browser

Technologies

• Streamlit for the user interface
• spaCy for NLP and named entity recognition
• scikit-learn for similarity calculations
• pdfplumber for extracting text from PDF files

Installation

1. Clone the repository:

   git clone git@github.com:avrtt/nlp-resume-parser.git
   cd nlp-resume-parser

2. Create a virtual environment and activate it:

   python -m venv env
   source env/bin/activate # Windows: env\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Download the en_core_web_sm model for spaCy:

   python -m spacy download en_core_web_sm

Usage

1. Run the app:

   streamlit run app.py

2. Open your browser and navigate to http://localhost:8501

3. Upload resumes in PDF format and enter a job description; the app will parse the resumes, rank candidates, and display the results

Example output

• Parsed resume data:

  Name: Someone Someonovich
  Email: someonovich@example.com
  Phone: 1234567890
  Skills: Python, Machine Learning, NLP
  Experience: 5 years at Biba Boba Corp
  

• Ranked candidates:

  1. Someone Someonovich (Score: 0.85)
  2. Matye Bal (Score: 0.78)
  

To-do

• Add support for DOCX resume formats
• Improve ranking using advanced models
• Add database integration for storing parsed data and rankings
• Analytics dashboard (visualize candidate metrics)

License

MIT