Update app.py

app.py

@@ -1,11 +1,9 @@
 import gradio as gr
-import os
-import docx
-import pandas as pd
 from sentence_transformers import SentenceTransformer, util
+import docx
+import os
 from PyPDF2 import PdfReader
 import re
-from datetime import datetime
 
 # Load pre-trained model for sentence embedding
 model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
@@ -13,9 +11,6 @@ model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 # Define maximum number of resumes
 MAX_RESUMES = 10
 
-# Keywords related to managerial and leadership roles
-MANAGERIAL_KEYWORDS = ["manager", "team leader", "lead", "supervisor", "director", "head of", "leadership"]
-
 # Function to load job description from file path
 def load_job_description(job_desc_file):
     if not os.path.exists(job_desc_file):
@@ -34,25 +29,23 @@ def check_similarity(job_description, resume_files):
     for resume_file in resume_files:
         resume_text = extract_text_from_resume(resume_file)
         if not resume_text:
-            results.append((resume_file.name, 0, "Not Eligible", None, None))
+            results.append((resume_file.name, 0, "Not Eligible", None, "No leadership experience"))
             continue
-        
         resume_emb = model.encode(resume_text, convert_to_tensor=True)
         similarity_score = util.pytorch_cos_sim(job_emb, resume_emb)[0][0].item()
 
-        # Extract leadership experience from resume
+        # Convert similarity score to percentage
+        similarity_percentage = similarity_score * 100
+
+        # Identify leadership experience from resume
         leadership_experience = extract_leadership_experience(resume_text)
 
-        # Increase the weight of the similarity score for candidates with managerial experience
-        if leadership_experience > 0:
-            similarity_score += 0.1  # Adjust the weight based on leadership experience
-        
         # Set a higher similarity threshold for eligibility
         if similarity_score >= 0.50:
             candidate_name = extract_candidate_name(resume_text)
-            results.append((resume_file.name, similarity_score, "Eligible", candidate_name, leadership_experience))
+            results.append((resume_file.name, similarity_percentage, "Eligible", candidate_name, leadership_experience))
         else:
-            results.append((resume_file.name, similarity_score, "Not Eligible", None, None))
+            results.append((resume_file.name, similarity_percentage, "Not Eligible", None, leadership_experience))
 
     return results
 
@@ -97,64 +90,28 @@ def extract_candidate_name(resume_text):
         return matches[0]  # Returns the first match
     return "Unknown Candidate"
 
-# Extract leadership experience (years of managerial experience)
+# Extract leadership experience (looking for keywords like manager, team lead, leadership)
 def extract_leadership_experience(resume_text):
-    experience = 0
-    for keyword in MANAGERIAL_KEYWORDS:
-        pattern = r"\b" + keyword + r"\b.*?(\d{4}|\d{2})[\s\-/]*\d{2,4}"
-        matches = re.findall(pattern, resume_text, re.IGNORECASE)
-        for match in matches:
-            if isinstance(match, str) and match.isdigit():
-                experience = max(experience, int(match))  # Use the highest value
-    return experience
-
-# Main processing function
-def process_files(job_desc, resumes):
-    try:
-        # Check if the number of resumes is within the allowed limit
-        if len(resumes) > MAX_RESUMES:
-            return "Please upload no more than 10 resumes."
-
-        # Check if all necessary files are provided
-        if not job_desc or not resumes:
-            return "Please provide all necessary files."
-
-        # Load the job description
-        job_desc_text = load_job_description(job_desc)
-
-        # Check similarity
-        results = check_similarity(job_desc_text, resumes)
-
-        # Prepare the results in tabular form
-        df = pd.DataFrame(results, columns=["Resume File", "Similarity Score", "Eligibility", "Candidate Name", "Leadership Experience"])
-        
-        # Output file for downloading
-        output_filename = f"/tmp/similarity_results_{datetime.now().strftime('%Y%m%d%H%M%S')}.csv"
-        df.to_csv(output_filename, index=False)
-        
-        # Return the results as a table
-        return df, output_filename
-
-    except Exception as e:
-        # Return any errors encountered during processing
-        return f"Error processing files: {str(e)}", None
-
+    leadership_keywords = ['manager', 'management', 'team lead', 'supervised', 'leadership', 'head', 'coordinator']
+    for keyword in leadership_keywords:
+        if keyword.lower() in resume_text.lower():
+            return "Has leadership experience"
+    return "No leadership experience"
 
 # Gradio Interface Components
 job_desc_input = gr.File(label="Upload Job Description (TXT)", type="filepath")
 resumes_input = gr.Files(label="Upload Resumes (TXT, DOCX, PDF)", type="filepath")
 
 # Gradio Outputs
-results_output = gr.Dataframe(label="Analysis Results")
-download_output = gr.File(label="Download Final Results")
+results_output = gr.Dataframe(headers=["Resume File", "Similarity Score (%)", "Eligibility", "Candidate Name", "Leadership Experience"], label="Analysis Results")
 
 # Gradio Interface
 interface = gr.Interface(
-    fn=process_files,
+    fn=check_similarity,
     inputs=[job_desc_input, resumes_input],
-    outputs=[results_output, download_output],
-    title="HR Assistant - Resume Screening",
-    description="Upload job description and resumes to screen candidates and download the results in a tabular format."
+    outputs=[results_output],
+    title="HR Assistant - Resume Screening & Leadership Experience",
+    description="Upload job description and resumes to screen candidates for managerial and team leadership roles."
 )
 
 interface.launch()