|
|
import streamlit as st |
|
|
from PyPDF2 import PdfReader |
|
|
import pandas as pd |
|
|
from sklearn.feature_extraction.text import TfidfVectorizer |
|
|
from sklearn.metrics.pairwise import cosine_similarity |
|
|
from gliner import GLiNER |
|
|
import plotly.express as px |
|
|
import time |
|
|
from sentence_transformers import SentenceTransformer |
|
|
|
|
|
model = SentenceTransformer("all-mpnet-base-v2") |
|
|
|
|
|
|
|
|
st.title("AI Resume Analysis based on Keywords App") |
|
|
st.divider() |
|
|
|
|
|
job = pd.Series(st.text_area("Paste the job description and then press Ctrl + Enter", key="job_desc"), name="Text") |
|
|
|
|
|
if 'applicant_data' not in st.session_state: |
|
|
st.session_state['applicant_data'] = {} |
|
|
|
|
|
max_attempts = 1 |
|
|
|
|
|
for i in range(1, 51): |
|
|
st.subheader(f"Applicant {i} Resume", divider="green") |
|
|
applicant_key = f"applicant_{i}" |
|
|
upload_key = f"candidate_{i}" |
|
|
|
|
|
if applicant_key not in st.session_state['applicant_data']: |
|
|
st.session_state['applicant_data'][applicant_key] = {'upload_count': 0, 'uploaded_file': None, 'analysis_done': False} |
|
|
|
|
|
if st.session_state['applicant_data'][applicant_key]['upload_count'] < max_attempts: |
|
|
uploaded_file = st.file_uploader(f"Upload Applicant's {i} resume", type="pdf", key=upload_key) |
|
|
|
|
|
if uploaded_file: |
|
|
st.session_state['applicant_data'][applicant_key]['uploaded_file'] = uploaded_file |
|
|
st.session_state['applicant_data'][applicant_key]['upload_count'] += 1 |
|
|
st.session_state['applicant_data'][applicant_key]['analysis_done'] = False |
|
|
|
|
|
if st.session_state['applicant_data'][applicant_key]['uploaded_file'] and not st.session_state['applicant_data'][applicant_key]['analysis_done']: |
|
|
pdf_reader = PdfReader(st.session_state['applicant_data'][applicant_key]['uploaded_file']) |
|
|
text_data = "" |
|
|
for page in pdf_reader.pages: |
|
|
text_data += page.extract_text() |
|
|
|
|
|
with st.expander(f"See Applicant's {i} resume"): |
|
|
st.write(text_data) |
|
|
|
|
|
data = pd.Series(text_data, name='Text') |
|
|
result = pd.concat([job, data]) |
|
|
|
|
|
|
|
|
embeddings = model.encode([result]) |
|
|
similarities = model.similarity(embeddings, embeddings) |
|
|
|
|
|
|
|
|
|
|
|
for j, similarity_score in enumerate(similarities[0][1:]): |
|
|
with st.popover(f"See Result for Applicant {i}"): |
|
|
st.write(f"Similarity between Applicant's resume and job description based on keywords: {similarity_score:.2f}") |
|
|
st.info( |
|
|
f"A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's {i} resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's {i} resume and job description.") |
|
|
st.session_state['applicant_data'][applicant_key]['analysis_done'] = True |
|
|
|
|
|
else: |
|
|
st.warning(f"Maximum upload attempts has been reached ({max_attempts}).") |
|
|
if st.session_state['applicant_data'][applicant_key]['upload_count'] > 0: |
|
|
st.info(f"Files uploaded for Applicant {i}: {st.session_state['applicant_data'][applicant_key]['upload_count']} time(s).") |
|
|
|
|
|
|
|
|
|
