Spaces:
Running
Running
| import os | |
| import streamlit as st | |
| import pdfplumber | |
| from fuzzywuzzy import fuzz | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| import spacy | |
| # Load the SpaCy model | |
| nlp = spacy.load("en_core_web_sm") | |
| # Function to extract entities from text | |
| def extract_entities(text): | |
| doc = nlp(text) | |
| entities = {ent.label_: ent.text for ent in doc.ents} | |
| return entities | |
| # Function to compute matching score | |
| def compute_advanced_matching_score(cv_text, cv_entities, required_education, required_skills, required_experience): | |
| score = 0 | |
| # Named Entity Recognition Matching for Education | |
| education = cv_entities.get('EDU', '') | |
| score += fuzz.token_set_ratio(education, required_education) / 100 | |
| # Fuzzy Matching for Skills | |
| for skill in required_skills: | |
| max_skill_match_score = max([fuzz.token_set_ratio(skill, skill_in_cv) for skill_in_cv in cv_text.split()] + [0]) | |
| score += max_skill_match_score / 100 | |
| # Vector Similarity Matching for Experience | |
| experience_text = cv_entities.get('DATE', '') | |
| doc1 = nlp(experience_text) | |
| doc2 = nlp(f"{required_experience} years") | |
| score += cosine_similarity(doc1.vector.reshape(1, -1), doc2.vector.reshape(1, -1))[0][0] | |
| return score | |
| # Function to process CVs and compute scores | |
| def process_cvs(uploaded_files, required_education, required_skills, required_experience, top_cvs_count): | |
| cv_scores = {} | |
| for uploaded_file in uploaded_files: | |
| file_extension = uploaded_file.name.split('.')[-1] | |
| if file_extension in ["pdf"]: | |
| with pdfplumber.open(uploaded_file) as pdf: | |
| text = '' | |
| for page in pdf.pages: | |
| text += page.extract_text() | |
| entities = extract_entities(text) | |
| cv_scores[uploaded_file.name] = compute_advanced_matching_score(text, entities, required_education, required_skills, required_experience) | |
| top_cvs = sorted(cv_scores.items(), key=lambda x: x[1], reverse=True)[:top_cvs_count] | |
| return top_cvs | |
| def main(): | |
| st.markdown('<style>h1{text-align:center;}</style>', unsafe_allow_html=True) # Center-align the title | |
| st.title("Resume Filtering App") | |
| uploaded_files = st.file_uploader("Upload Resume Files", type=["pdf"], accept_multiple_files=True) | |
| required_education = st.text_input("Required Education") | |
| required_skills = st.text_input("Required Skills (comma-separated)") | |
| required_experience = st.text_input("Required Experience") | |
| top_cvs_count = st.number_input("Number of Top Resume to Display", min_value=1, step=1, value=3) | |
| if st.button("Match Resume"): | |
| if uploaded_files and required_education and required_skills and required_experience: | |
| required_skills = [skill.strip() for skill in required_skills.split(',')] | |
| top_cvs = process_cvs(uploaded_files, required_education, required_skills, required_experience, top_cvs_count) | |
| st.subheader("Top Matching Resume:") | |
| for filename, score in top_cvs: | |
| st.write(f"{filename}: {score:.2f}") | |
| if __name__ == "__main__": | |
| main() | |