Update app.py

app.py

@@ -5,14 +5,39 @@ from sentence_transformers import SentenceTransformer, util
 from gtts import gTTS
 import tempfile
 
-# Load model
+# Load the model
 model = SentenceTransformer("all-MiniLM-L6-v2")
 
+# Define a multi-domain skill set
 top_skills = [
-    "Python", "Java", "C++", "SQL", "JavaScript", "React", "Node.js",
-    "Machine Learning", "Data Analysis", "Excel", "Communication",
-    "Project Management", "AWS", "Docker", "Leadership", "Time Management",
-    "Problem Solving", "Teamwork", "Critical Thinking"
+    # Tech
+    "Python", "JavaScript", "SQL", "Machine Learning", "AWS", "Docker", "React",
+    # Marketing
+    "SEO", "Content Creation", "Brand Management", "Google Analytics", "Social Media Marketing",
+    # Finance
+    "Financial Analysis", "Accounting", "Risk Management",
+    # Healthcare
+    "Patient Care", "Diagnosis", "Treatment Planning",
+    # Education
+    "Lesson Planning", "Curriculum Design", "Classroom Management",
+    # Soft Skills
+    "Communication", "Leadership", "Teamwork", "Problem Solving", "Critical Thinking"
+]
+
+# Job mapping
+job_roles = [
+    ("Data Analyst", {"Python", "SQL", "Data Analysis"}),
+    ("Frontend Developer", {"JavaScript", "React"}),
+    ("Backend Developer", {"Python", "Docker", "AWS"}),
+    ("Machine Learning Engineer", {"Machine Learning", "Python"}),
+    ("Marketing Manager", {"SEO", "Content Creation", "Brand Management"}),
+    ("Digital Marketer", {"Google Analytics", "Social Media Marketing", "Content Creation"}),
+    ("Financial Analyst", {"Financial Analysis", "Accounting"}),
+    ("Risk Manager", {"Risk Management", "Accounting"}),
+    ("Nurse", {"Patient Care", "Diagnosis"}),
+    ("Healthcare Administrator", {"Treatment Planning", "Leadership"}),
+    ("Teacher", {"Lesson Planning", "Classroom Management"}),
+    ("Project Manager", {"Leadership", "Project Management"})
 ]
 
 def extract_text_from_pdf(pdf_file):
@@ -26,14 +51,10 @@ def extract_text_from_docx(docx_file):
     doc = docx.Document(docx_file)
     return "\n".join([p.text for p in doc.paragraphs])
 
-def summarize_resume(text):
-    summary = "This resume highlights skills in " + ", ".join(list(set(analyze_resume(text)[0].split(", ")))) + "."
-    return summary
-
-def analyze_resume(text):
+def detect_skills(text):
     sentences = [s.strip() for s in text.split(".") if len(s.strip()) > 5]
     if not sentences:
-        return "Could not extract sentences.", "", "", ""
+        return [], []
 
     sentence_embeddings = model.encode(sentences, convert_to_tensor=True)
     skill_embeddings = model.encode(top_skills, convert_to_tensor=True)
@@ -46,24 +67,26 @@ def analyze_resume(text):
         if score > 0.4:
             found_skills.append(skill)
 
-    job_titles = []
-    if "Python" in found_skills and "Data Analysis" in found_skills:
-        job_titles.append("Data Analyst")
-    if "JavaScript" in found_skills and "React" in found_skills:
-        job_titles.append("Frontend Developer")
-    if "Project Management" in found_skills:
-        job_titles.append("Project Manager")
-    if "Machine Learning" in found_skills:
-        job_titles.append("ML Engineer")
-    if not job_titles:
-        job_titles.append("General Tech Roles")
-
     missing_skills = [s for s in top_skills if s not in found_skills]
-
-    return ", ".join(found_skills), ", ".join(job_titles), ", ".join(missing_skills[:5])
+    return found_skills, missing_skills
+
+def suggest_jobs(found_skills):
+    matched_jobs = []
+    skill_set = set(found_skills)
+    for title, required_skills in job_roles:
+        if required_skills.issubset(skill_set):
+            matched_jobs.append(title)
+    if not matched_jobs:
+        matched_jobs.append("General Roles")
+    return matched_jobs
+
+def summarize_resume(found_skills):
+    if not found_skills:
+        return "No clear skills detected in resume."
+    return "This resume highlights skills in " + ", ".join(found_skills) + "."
 
 def score_resume(found_skills):
-    score = int(len(found_skills.split(", ")) / len(top_skills) * 100)
+    score = int(len(found_skills) / len(top_skills) * 100)
     return min(score, 100)
 
 def save_report(text, skills, jobs, missing, summary, score):
@@ -111,14 +134,17 @@ def process_resume(file_obj):
     else:
         return "Unsupported file format", "", "", "", "", "", None, None
 
-    summary = summarize_resume(resume_text)
-    skills, jobs, missing = analyze_resume(resume_text)
-    score = score_resume(skills)
-    report_path = save_report(resume_text, skills, jobs, missing, summary, score)
-    audio_path = text_to_speech(jobs)
-
-    return resume_text, summary, skills, jobs, missing, f"{score}/100", report_path, audio_path
-
+    found_skills, missing_skills = detect_skills(resume_text)
+    job_titles = suggest_jobs(found_skills)
+    summary = summarize_resume(found_skills)
+    skills_str = ", ".join(found_skills)
+    jobs_str = ", ".join(job_titles)
+    missing_str = ", ".join(missing_skills[:5])
+    score = score_resume(found_skills)
+    report_path = save_report(resume_text, skills_str, jobs_str, missing_str, summary, score)
+    audio_path = text_to_speech(jobs_str)
+
+    return resume_text, summary, skills_str, jobs_str, missing_str, f"{score}/100", report_path, audio_path
 
 # Build the UI
 with gr.Blocks(theme="soft") as demo: