app.py

import streamlit as st
import pdfplumber
import io
import spacy
from transformers import pipeline
import subprocess
import sys

st.set_page_config(
    page_title="Resume Screener & Skill Extractor",
    page_icon="📄",
    layout="wide"
)

# Download spaCy model if not already downloaded
@st.cache_resource
def download_spacy_model():
    try:
        nlp = spacy.load("en_core_web_sm")
    except OSError:
        subprocess.check_call([sys.executable, "-m", "spacy", "download", "en_core_web_sm"])
        nlp = spacy.load("en_core_web_sm")
    return nlp

# Load the NLP models
@st.cache_resource
def load_models():
    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
    nlp = download_spacy_model()
    return summarizer, nlp

# Initialize models
summarizer, nlp = load_models()

# Job descriptions and required skills
job_descriptions = {
    "Software Engineer": {
        "skills": ["python", "java", "javascript", "sql", "algorithms", "data structures", 
                  "git", "cloud", "web development", "software development", "coding"],
        "description": "Looking for software engineers with strong programming skills and experience in software development."
    },
    "Interaction Designer": {
        "skills": ["ui", "ux", "user research", "wireframing", "prototyping", "figma", 
                  "sketch", "adobe", "design thinking", "interaction design"],
        "description": "Seeking interaction designers with expertise in user experience and interface design."
    },
    "Data Scientist": {
        "skills": ["python", "r", "statistics", "machine learning", "data analysis", 
                  "sql", "tensorflow", "pytorch", "pandas", "numpy"],
        "description": "Looking for data scientists with strong analytical and machine learning skills."
    }
}

def extract_text_from_pdf(pdf_file):
    text = ""
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            text += page.extract_text() or ""
    return text

def analyze_resume(text, job_title):
    # Extract relevant skills
    doc = nlp(text.lower())
    found_skills = []
    required_skills = job_descriptions[job_title]["skills"]
    
    for skill in required_skills:
        if skill in text.lower():
            found_skills.append(skill)
    
    # Generate summary
    chunks = [text[i:i + 1000] for i in range(0, len(text), 1000)]
    summaries = []
    for chunk in chunks[:3]:  # Process first 3000 characters to avoid token limits
        summary = summarizer(chunk, max_length=150, min_length=50, do_sample=False)[0]["summary_text"]
        summaries.append(summary)
    
    return found_skills, " ".join(summaries)

# Streamlit UI
st.title("📄 Resume Screener & Skill Extractor")

# Add description
st.markdown("""
This app helps recruiters analyze resumes by:
- Extracting relevant skills for specific job positions
- Generating a concise summary of the candidate's background
- Identifying skill gaps for the selected role
""")

# Create two columns
col1, col2 = st.columns([2, 1])

with col1:
    # File upload
    uploaded_file = st.file_uploader("Upload Resume (PDF)", type=["pdf"])

with col2:
    # Job selection
    job_title = st.selectbox("Select Job Position", list(job_descriptions.keys()))
    
    # Show job description
    if job_title:
        st.info(f"**Required Skills:**\n" + 
                "\n".join([f"- {skill.title()}" for skill in job_descriptions[job_title]["skills"]]))

if uploaded_file and job_title:
    try:
        # Show spinner while processing
        with st.spinner("Analyzing resume..."):
            # Extract text from PDF
            text = extract_text_from_pdf(uploaded_file)
            
            # Analyze resume
            found_skills, summary = analyze_resume(text, job_title)
        
        # Display results in tabs
        tab1, tab2, tab3 = st.tabs(["📊 Skills Match", "📝 Resume Summary", "🎯 Skills Gap"])
        
        with tab1:
            # Display matched skills
            st.subheader("🎯 Matched Skills")
            if found_skills:
                for skill in found_skills:
                    st.success(f"✅ {skill.title()}")
                
                # Calculate match percentage
                match_percentage = len(found_skills) / len(job_descriptions[job_title]["skills"]) * 100
                st.metric("Skills Match", f"{match_percentage:.1f}%")
            else:
                st.warning("No direct skill matches found.")
        
        with tab2:
            # Display resume summary
            st.subheader("📝 Resume Summary")
            st.write(summary)
        
        with tab3:
            # Display missing skills
            st.subheader("📌 Skills to Develop")
            missing_skills = [skill for skill in job_descriptions[job_title]["skills"] 
                            if skill not in found_skills]
            if missing_skills:
                for skill in missing_skills:
                    st.warning(f"➖ {skill.title()}")
            else:
                st.success("Great! The candidate has all the required skills!")
        
    except Exception as e:
        st.error(f"An error occurred while processing the resume: {str(e)}")

# Add footer
st.markdown("---")
st.markdown("Made with ❤️ using Streamlit and Hugging Face")