File size: 5,262 Bytes
11996bd 4dfdb8b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
import streamlit as st
st.set_page_config(
page_title="Resume Screener & Skill Extractor",
page_icon="📄",
layout="wide"
)
# Load the NLP model
@st.cache_resource
def load_models():
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
nlp = spacy.load("en_core_web_sm")
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):
pdf_reader = PyPDF2.PdfReader(pdf_file)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
return text
def extract_text_from_docx(docx_file):
doc = Document(docx_file)
text = ""
for paragraph in doc.paragraphs:
text += paragraph.text + "\n"
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 or DOCX)", type=["pdf", "docx"])
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 based on file type
if uploaded_file.type == "application/pdf":
text = extract_text_from_pdf(uploaded_file)
else:
text = extract_text_from_docx(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")
|