Update app.py

app.py

@@ -1,11 +1,14 @@
-import os, io, re, time, tempfile
+import os
 import streamlit as st
-import docx, docx2txt
+import docx
+import docx2txt
+import tempfile
+import time
+import re
 import pandas as pd
 from functools import lru_cache
-import random  # For reproducible randomization in scoring
 
-# Handle imports
+# Simplify imports
 try:
     from transformers import pipeline
     has_pipeline = True
@@ -13,30 +16,33 @@ except ImportError:
     from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForSeq2SeqLM
     import torch
     has_pipeline = False
+    st.warning("Using basic transformers functionality instead of pipeline API")
 
-# Setup page
+# Page setup
 st.set_page_config(page_title="Resume-Job Fit Analyzer", initial_sidebar_state="collapsed")
-st.markdown("""<style>[data-testid="collapsedControl"],[data-testid="stSidebar"] {display: none;}</style>""", unsafe_allow_html=True)
+st.markdown("<style>[data-testid='collapsedControl'] {display: none;} section[data-testid='stSidebar'] {display: none;}</style>", unsafe_allow_html=True)
 
 #####################################
 # Model Loading & Text Processing
 #####################################
-@st.cache_resource
+@st.cache_resource(show_spinner=True)
 def load_models():
-    with st.spinner("Loading AI models..."):
+    with st.spinner("Loading AI models... This may take a minute on first run."):
         models = {}
+        
         # Load summarization model
         if has_pipeline:
-            models['summarizer'] = pipeline("summarization", model="Falconsai/text_summarization", max_length=100)
+            models['summarizer'] = pipeline("summarization", model="Falconsai/text_summarization", max_length=100, truncation=True)
         else:
             try:
                 models['summarizer_model'] = AutoModelForSeq2SeqLM.from_pretrained("Falconsai/text_summarization")
                 models['summarizer_tokenizer'] = AutoTokenizer.from_pretrained("Falconsai/text_summarization")
             except Exception as e:
                 st.error(f"Error loading summarization model: {e}")
-                models['summarizer_model'] = models['summarizer_tokenizer'] = None
+                models['summarizer_model'] = None
+                models['summarizer_tokenizer'] = None
         
-        # Load evaluation model
+        # Load sentiment model
         if has_pipeline:
             models['evaluator'] = pipeline("sentiment-analysis", model="CR7CAD/RobertaFinetuned")
         else:
@@ -45,426 +51,394 @@ def load_models():
                 models['evaluator_tokenizer'] = AutoTokenizer.from_pretrained("CR7CAD/RobertaFinetuned")
             except Exception as e:
                 st.error(f"Error loading sentiment model: {e}")
-                models['evaluator_model'] = models['evaluator_tokenizer'] = None
+                models['evaluator_model'] = None
+                models['evaluator_tokenizer'] = None
+        
         return models
 
 def summarize_text(text, models, max_length=100):
-    """Summarize text with fallbacks"""
-    input_text = text[:1024]
+    input_text = text[:1024]  # Limit input length
     
-    # Try pipeline
     if has_pipeline and 'summarizer' in models:
         try:
             return models['summarizer'](input_text)[0]['summary_text']
-        except: pass
+        except Exception as e:
+            st.warning(f"Error in pipeline summarization: {e}")
     
-    # Try manual model
     if 'summarizer_model' in models and models['summarizer_model']:
         try:
             tokenizer = models['summarizer_tokenizer']
             model = models['summarizer_model']
             inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)
-            summary_ids = model.generate(inputs.input_ids, max_length=max_length, min_length=30, num_beams=4)
+            summary_ids = model.generate(inputs.input_ids, max_length=max_length, min_length=30, num_beams=4, early_stopping=True)
             return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-        except: pass
+        except Exception as e:
+            st.warning(f"Error in manual summarization: {e}")
     
-    # Fallback - extract sentences
+    # Fallback to basic summarization
     sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
-    scored = [(1.0/(i+1), s) for i, s in enumerate(sentences) if len(s.split()) >= 4]
-    scored.sort(reverse=True)
-    
-    result, length = [], 0
-    for _, sentence in scored:
-        if length + len(sentence.split()) <= max_length:
-            result.append(sentence)
-            length += len(sentence.split())
-    
-    if result:
-        ordered = sorted([(sentences.index(s), s) for s in result])
-        return " ".join(s for _, s in ordered)
-    return ""
+    scored_sentences = []
+    for i, sentence in enumerate(sentences):
+        if len(sentence.split()) < 4: continue
+        score = 1.0 / (i + 1) - (0.01 * max(0, len(sentence.split()) - 20))
+        scored_sentences.append((score, sentence))
+    
+    scored_sentences.sort(reverse=True)
+    summary_sentences, current_length = [], 0
+    
+    for _, sentence in scored_sentences:
+        if current_length + len(sentence.split()) <= max_length:
+            summary_sentences.append(sentence)
+            current_length += len(sentence.split())
+        else:
+            break
+    
+    if summary_sentences:
+        original_order = sorted([(sentences.index(s), s) for s in summary_sentences])
+        summary_sentences = [s for _, s in original_order]
+    
+    return " ".join(summary_sentences)
+
+# Keep job fit evaluation function intact as it's critical
+def evaluate_job_fit(resume_summary, job_requirements, models):
+    start_time = time.time()
+    
+    required_skills = job_requirements["required_skills"]
+    years_required = job_requirements["years_experience"]
+    job_title = job_requirements["title"]
+    job_summary = job_requirements["summary"]
+    
+    skills_mentioned = extract_skills(resume_summary)
+    
+    matching_skills = [skill for skill in required_skills if skill in skills_mentioned]
+    skill_match_percentage = len(matching_skills) / len(required_skills) if required_skills else 0
+    
+    experience_pattern = r'(\d+)\+?\s*years?\s*(?:of)?\s*experience'
+    experience_match = re.search(experience_pattern, resume_summary, re.IGNORECASE)
+    years_experience = 0
+    if experience_match:
+        try:
+            years_experience = int(experience_match.group(1))
+        except:
+            years_experience = 0
+    
+    exp_match_ratio = min(1.0, years_experience / max(1, years_required)) if years_required > 0 else 0.5
+    
+    job_title_lower = job_title.lower()
+    title_match = 0
+    
+    title_words = [word for word in job_title_lower.split() if len(word) > 3]
+    title_matches = sum(1 for word in title_words if word in resume_summary.lower())
+    title_match = title_matches / len(title_words) if title_words else 0
+    
+    skill_score = min(2, skill_match_percentage * 3)
+    exp_score = min(2, exp_match_ratio * 2)
+    title_score = min(2, title_match * 2)
+    
+    name_match = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
+    name = name_match.group(1).strip() if name_match else "The candidate"
+    
+    age_match = re.search(r'Age:\s*(.*?)(?=\n|\Z)', resume_summary)
+    age = age_match.group(1).strip() if age_match else "unspecified age"
+    
+    industry_match = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
+    industry = industry_match.group(1).strip() if industry_match else "unspecified industry"
+    
+    weighted_score = (skill_score * 0.5) + (exp_score * 0.3) + (title_score * 0.2)
+    
+    if weighted_score >= 1.5:
+        fit_score = 2  # Good fit
+    elif weighted_score >= 0.8:
+        fit_score = 1  # Potential fit
+    else:
+        fit_score = 0  # Not a fit
+    
+    missing_skills = [skill for skill in required_skills if skill not in skills_mentioned]
+    
+    if fit_score == 2:
+        fit_assessment = f"{fit_score}: GOOD FIT - {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} and professional experience appear well-suited for this role's requirements. The technical expertise matches what the position demands."
+    elif fit_score == 1:
+        fit_assessment = f"{fit_score}: POTENTIAL FIT - {name} shows potential for the {job_title} role with some relevant experience, though there are gaps in certain technical areas. Their {industry} background provides partial alignment with the position requirements. Additional training might be needed in {', '.join(missing_skills[:2])} if pursuing this opportunity."
+    else:
+        fit_assessment = f"{fit_score}: NO FIT - {name}'s current background shows limited alignment with this {job_title} position. Their experience level and technical background differ significantly from the role requirements. A position better matching their {industry} expertise might be more suitable."
+    
+    execution_time = time.time() - start_time
+    
+    return fit_assessment, fit_score, execution_time
 
 #####################################
-# File Processing & Information Extraction
+# File & Information Extraction
 #####################################
-@st.cache_data
+@st.cache_data(show_spinner=False)
 def extract_text_from_file(file_obj):
-    ext = os.path.splitext(file_obj.name)[1].lower()
+    filename = file_obj.name
+    ext = os.path.splitext(filename)[1].lower()
     
     if ext == ".docx":
         try:
             document = docx.Document(file_obj)
-            return "\n".join(para.text for para in document.paragraphs if para.text.strip())[:15000]
+            return "\n".join(para.text for para in document.paragraphs if para.text.strip())
         except Exception as e:
             return f"Error processing DOCX file: {e}"
     elif ext == ".doc":
         try:
             with tempfile.NamedTemporaryFile(delete=False, suffix='.doc') as temp_file:
                 temp_file.write(file_obj.getvalue())
-                text = docx2txt.process(temp_file.name)
-                os.unlink(temp_file.name)
-                return text[:15000]
+                temp_path = temp_file.name
+            
+            try:
+                text = docx2txt.process(temp_path)
+            except Exception:
+                text = "Could not process .doc file. Please convert to .docx format."
+            
+            os.unlink(temp_path)
+            return text
         except Exception as e:
             return f"Error processing DOC file: {e}"
     elif ext == ".txt":
         try:
-            return file_obj.getvalue().decode("utf-8")[:15000]
+            return file_obj.getvalue().decode("utf-8")
         except Exception as e:
             return f"Error processing TXT file: {e}"
     else:
         return "Unsupported file type. Please upload a .docx, .doc, or .txt file."
 
-# Information extraction functions
-def extract_skills(text):
-    """Extract skills from text"""
-    text_lower = text.lower()
-    
-    # Define common skills
-    skills_list = [
-        "Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "C++", "C#", "Go", "R",
-        "React", "Angular", "Vue", "Node.js", "jQuery", "Bootstrap", "PHP", "Ruby",
-        "Machine Learning", "Data Analysis", "Big Data", "AI", "NLP", "Deep Learning",
-        "MySQL", "MongoDB", "PostgreSQL", "Oracle", "Database", "ETL",
-        "AWS", "Azure", "Google Cloud", "Docker", "Kubernetes", "CI/CD", "DevOps",
-        "Git", "GitHub", "Agile", "Scrum", "Jira", "RESTful API", "GraphQL",
-        "TensorFlow", "PyTorch", "SAS", "SPSS", "Tableau", "Power BI", "Excel",
-        "Communication", "Teamwork", "Problem Solving", "Critical Thinking",
-        "Leadership", "Project Management", "Time Management", "Flexibility", "Adaptability"
-    ]
-    
-    # Extract matched skills
-    found_skills = []
-    for skill in skills_list:
-        if skill.lower() in text_lower or re.search(r'\b' + re.escape(skill.lower()) + r'(?:\s|\b|ing|er)', text_lower):
-            found_skills.append(skill)
-    
-    return list(set(found_skills))  # Remove duplicates
-
+# Simplified information extraction functions
 @lru_cache(maxsize=32)
 def extract_name(text_start):
-    lines = [line.strip() for line in text_start.split('\n')[:5] if line.strip()]
+    lines = [line.strip() for line in text_start.split('\n') if line.strip()][:5]
     
     if lines:
         first_line = lines[0]
-        if 5 <= len(first_line) <= 40 and not any(x in first_line.lower() for x in ["resume", "cv", "curriculum", "vitae"]):
+        if 5 <= len(first_line) <= 40 and not any(x in first_line.lower() for x in ["resume", "cv", "curriculum", "vitae", "profile"]):
             return first_line
     
     for line in lines[:3]:
         if len(line.split()) <= 4 and not any(x in line.lower() for x in ["address", "phone", "email", "resume", "cv"]):
             return line
-    return "Unknown"
+    
+    return "Unknown (please extract from resume)"
 
 def extract_age(text):
-    for pattern in [r'age:?\s*(\d{1,2})', r'(\d{1,2})\s*years\s*old', r'dob:.*(\d{4})', r'date of birth:.*(\d{4})']:
+    age_patterns = [r'age:?\s*(\d{1,2})', r'(\d{1,2})\s*years\s*old', r'dob:.*(\d{4})', r'date of birth:.*(\d{4})']
+    
+    for pattern in age_patterns:
         match = re.search(pattern, text.lower())
         if match:
-            if len(match.group(1)) == 4:  # Birth year
-                try: return str(2025 - int(match.group(1)))
-                except: pass
+            if len(match.group(1)) == 4:  # Year of birth
+                try:
+                    return str(2025 - int(match.group(1)))
+                except:
+                    pass
             return match.group(1)
+    
     return "Not specified"
 
 def extract_industry(text):
     industries = {
-        "Technology": ["software", "programming", "developer", "IT", "tech", "computer", "digital"],
-        "Finance": ["banking", "financial", "accounting", "finance", "analyst"],
-        "Healthcare": ["medical", "health", "hospital", "clinical", "nurse", "doctor"],
-        "Education": ["teaching", "teacher", "professor", "education", "university", "school"],
-        "Marketing": ["marketing", "advertising", "digital marketing", "social media", "brand"],
-        "Engineering": ["engineer", "engineering", "mechanical", "civil", "electrical"],
-        "Data Science": ["data science", "machine learning", "AI", "analytics", "big data"],
-        "Management": ["manager", "management", "leadership", "executive", "director"]
+        "Technology": ["software", "programming", "developer", "IT", "tech"],
+        "Finance": ["banking", "financial", "accounting", "finance"],
+        "Healthcare": ["medical", "health", "hospital", "clinical"],
+        "Education": ["teaching", "education", "university", "school"],
+        "Marketing": ["marketing", "advertising", "digital marketing"],
+        "Engineering": ["engineer", "engineering", "mechanical"],
+        "Data Science": ["data science", "machine learning", "AI"],
+        "Management": ["manager", "management", "leadership"]
     }
     
     text_lower = text.lower()
-    counts = {ind: sum(text_lower.count(kw) for kw in kws) for ind, kws in industries.items()}
-    return max(counts.items(), key=lambda x: x[1])[0] if any(counts.values()) else "Not specified"
+    industry_counts = {industry: sum(text_lower.count(kw.lower()) for kw in keywords) 
+                     for industry, keywords in industries.items()}
+    
+    if industry_counts:
+        return max(industry_counts.items(), key=lambda x: x[1])[0]
+    
+    return "Not clearly specified"
 
 def extract_job_position(text):
-    text_lower = text.lower()
-    for pattern in [r'objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)', r'career\s*objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)', 
-                   r'summary:?\s*(.*?)(?=\n\n|\n\w+:|\Z)', r'seeking.*position.*as\s*([^.]*)']:
-        match = re.search(pattern, text_lower, re.IGNORECASE | re.DOTALL)
+    objective_patterns = [
+        r'objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
+        r'career\s*objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)'
+    ]
+    
+    for pattern in objective_patterns:
+        match = re.search(pattern, text.lower(), re.IGNORECASE | re.DOTALL)
         if match:
-            text = match.group(1).strip()
-            for title in ["developer", "engineer", "analyst", "manager", "specialist", "designer"]:
-                if title in text:
-                    return next((m.group(1).strip().title() for m in 
-                               [re.search(r'(\w+\s+' + title + r')', text)] if m), title.title())
-            return " ".join(text.split()[:10]).title() + "..." if len(text.split()) > 10 else text.title()
-    
-    # Check for job title near experience
-    for pattern in [r'experience:.*?(\w+\s+\w+(?:\s+\w+)?)(?=\s*at|\s*\()', r'(\w+\s+\w+(?:\s+\w+)?)\s*\(\s*(?:current|present)']:
-        match = re.search(pattern, text_lower, re.IGNORECASE)
-        if match: return match.group(1).strip().title()
+            objective_text = match.group(1).strip()
+            job_titles = ["developer", "engineer", "analyst", "manager", "director", "specialist"]
+            
+            for title in job_titles:
+                if title in objective_text:
+                    title_pattern = r'(?:a|an)?\s*(\w+\s+' + title + r'|\w+\s+\w+\s+' + title + r')'
+                    title_match = re.search(title_pattern, objective_text)
+                    if title_match:
+                        return title_match.group(1).strip().title()
+                    return title.title()
+            
+            if len(objective_text) > 10:
+                words = objective_text.split()
+                return " ".join(words[:10]).title() + "..." if len(words) > 10 else objective_text.title()
     
-    return "Not specified"
+    return "Not explicitly stated"
+
+def extract_skills(text):
+    tech_skills = [
+        "Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "React", "Angular", 
+        "Machine Learning", "Data Analysis", "AWS", "Docker", "Git", "Agile", 
+        "Communication", "Leadership", "Project Management"
+    ]
+    
+    return [skill for skill in tech_skills if re.search(r'\b' + re.escape(skill.lower()) + r'\b', text.lower())]
 
-#####################################
-# Core Analysis Functions
-#####################################
 def summarize_resume_text(resume_text, models):
-    start = time.time()
+    start_time = time.time()
     
-    # Basic info extraction
     name = extract_name(resume_text[:500])
     age = extract_age(resume_text)
     industry = extract_industry(resume_text)
     job_position = extract_job_position(resume_text)
     skills = extract_skills(resume_text)
     
-    # Generate summary
     try:
         if has_pipeline and 'summarizer' in models:
-            model_summary = models['summarizer'](resume_text[:2000], max_length=100, min_length=30)[0]['summary_text']
+            model_summary = models['summarizer'](resume_text[:2000], max_length=100, min_length=30, do_sample=False)[0]['summary_text']
         else:
             model_summary = summarize_text(resume_text, models, max_length=100)
-    except:
-        model_summary = "Error generating summary."
+    except Exception as e:
+        st.warning(f"Error in resume summarization: {e}")
+        model_summary = "Error generating summary. Please check the original resume."
     
-    # Format result
-    summary = f"Name: {name}\n\nAge: {age}\n\nExpected Industry: {industry}\n\n"
-    summary += f"Expected Job Position: {job_position}\n\nSkills: {', '.join(skills)}\n\nSummary: {model_summary}"
+    formatted_summary = f"Name: {name}\n\nAge: {age}\n\nExpected Industry: {industry}\n\n"
+    formatted_summary += f"Expected Job Position: {job_position}\n\nSkills: {', '.join(skills)}\n\nSummary: {model_summary}"
     
-    return summary, time.time() - start
+    return formatted_summary, time.time() - start_time
 
 def extract_job_requirements(job_description, models):
-    # Use the same skills list for consistency
-    skills_list = [
-        "Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "C++", "C#", "Go", "R",
-        "React", "Angular", "Vue", "Node.js", "jQuery", "Bootstrap", "PHP", "Ruby",
-        "Machine Learning", "Data Analysis", "Big Data", "AI", "NLP", "Deep Learning",
-        "MySQL", "MongoDB", "PostgreSQL", "Oracle", "Database", "ETL",
-        "AWS", "Azure", "Google Cloud", "Docker", "Kubernetes", "CI/CD", "DevOps",
-        "Git", "GitHub", "Agile", "Scrum", "Jira", "RESTful API", "GraphQL",
-        "TensorFlow", "PyTorch", "SAS", "SPSS", "Tableau", "Power BI", "Excel",
-        "Communication", "Teamwork", "Problem Solving", "Critical Thinking",
-        "Leadership", "Project Management", "Time Management", "Flexibility", "Adaptability"
+    tech_skills = [
+        "Python", "Java", "JavaScript", "SQL", "React", "Angular", 
+        "Machine Learning", "AWS", "Docker", "Git", "Agile", 
+        "Communication", "Leadership", "Project Management"
     ]
     
-    clean_text = job_description.lower()
+    clean_job_text = job_description.lower()
     
-    # Extract job title
+    # Extract title
+    title_patterns = [r'^([^:.\n]+?)(position|role|job)', r'^([^:.\n]+?)\n']
     job_title = "Not specified"
-    for pattern in [r'^([^:.\n]+?)(position|role|job)', r'^([^:.\n]+?)\n', r'hiring.*? ([^:.\n]+?)(:-|[.:]|\n|$)']:
-        match = re.search(pattern, clean_text, re.IGNORECASE)
-        if match:
-            title = match.group(1).strip() if len(match.groups()) >= 1 else match.group(2).strip()
-            if 3 <= len(title) <= 50:
-                job_title = title.capitalize()
-                break
-    
-    # Extract years required
-    years_required = 0
-    for pattern in [r'(\d+)(?:\+)?\s*(?:years|yrs).*?experience', r'experience.*?(\d+)(?:\+)?\s*(?:years|yrs)']:
-        match = re.search(pattern, clean_text, re.IGNORECASE)
-        if match:
-            try:
-                years_required = int(match.group(1))
-                break
-            except: pass
+    
+    for pattern in title_patterns:
+        match = re.search(pattern, clean_job_text, re.IGNORECASE)
+        if match and 3 <= len(match.group(1).strip()) <= 50:
+            job_title = match.group(1).strip().capitalize()
+            break
+    
+    # Extract experience
+    exp_match = re.search(r'(\d+)(?:\+)?\s*(?:years|yrs)(?:\s*of)?\s*(?:experience|exp)', clean_job_text)
+    years_required = int(exp_match.group(1)) if exp_match else 0
     
     # Extract skills
-    required_skills = []
-    for skill in skills_list:
-        if skill.lower() in clean_text or re.search(r'\b' + re.escape(skill.lower()) + r'(?:\s|\b|ing|er)', clean_text):
-            required_skills.append(skill)
+    required_skills = [skill for skill in tech_skills if re.search(r'\b' + re.escape(skill.lower()) + r'\b', clean_job_text)]
     
-    # Ensure at least some skills are found
+    # If no skills found, extract common words
     if not required_skills:
-        words = [w for w in re.findall(r'\b\w{4,}\b', clean_text) 
-                if w not in ["with", "that", "this", "have", "from", "they", "will", "what", "your"]]
+        words = re.findall(r'\b\w{4,}\b', clean_job_text)
         word_counts = {}
-        for w in words: word_counts[w] = word_counts.get(w, 0) + 1
-        required_skills = [w.capitalize() for w, _ in sorted(word_counts.items(), key=lambda x: x[1], reverse=True)[:5]]
+        for word in words:
+            if word not in ["with", "that", "this", "have", "from", "they", "will"]:
+                word_counts[word] = word_counts.get(word, 0) + 1
+        
+        required_skills = [word.capitalize() for word, _ in sorted(word_counts.items(), key=lambda x: x[1], reverse=True)[:5]]
+    
+    job_summary = summarize_text(job_description, models, max_length=100)
     
     return {
         "title": job_title,
         "years_experience": years_required,
         "required_skills": required_skills,
-        "summary": summarize_text(job_description, models, max_length=100)
-    }
-
-def evaluate_job_fit(resume_summary, job_requirements, models):
-    start = time.time()
-    
-    # Set seed for consistent but varied evaluation
-    random.seed(resume_summary[:20])  # Use part of resume text as seed
-    
-    # Basic extraction
-    required_skills = job_requirements["required_skills"]
-    years_required = job_requirements["years_experience"]
-    job_title = job_requirements["title"]
-    skills_mentioned = extract_skills(resume_summary)
-    
-    # Calculate matches
-    matching_skills = [skill for skill in required_skills if skill in skills_mentioned]
-    
-    # BALANCED SCORING ALGORITHM
-    
-    # 1. Skill match score - linear with slight noise
-    if not required_skills:
-        skill_match = random.uniform(0.4, 0.6)  # Random value if no skills required
-    else:
-        # Base score is the actual match percentage
-        raw_match = len(matching_skills) / len(required_skills)
-        # Add slight variance to create more distribution
-        skill_match = max(0, min(1, raw_match + random.uniform(-0.1, 0.1)))
-    
-    # 2. Experience match - closer to realistic assessment
-    years_experience = 0
-    exp_match = re.search(r'(\d+)\+?\s*years?\s*(?:of)?\s*experience', resume_summary, re.IGNORECASE)
-    if exp_match:
-        try: years_experience = int(exp_match.group(1))
-        except: pass
-    
-    if years_required == 0:
-        # If no experience required, slight preference for experienced candidates
-        exp_match_ratio = random.uniform(0.5, 0.8) if years_experience > 0 else random.uniform(0.3, 0.6)
-    else:
-        # For jobs with required experience
-        ratio = years_experience / max(1, years_required)
-        
-        if ratio < 0.6:  # Significantly underqualified
-            exp_match_ratio = random.uniform(0.2, 0.4)
-        elif ratio < 0.9:  # Slightly underqualified - potential fit territory
-            exp_match_ratio = random.uniform(0.4, 0.6)
-        elif ratio <= 1.5:  # Just right - good fit territory
-            exp_match_ratio = random.uniform(0.7, 0.9)
-        else:  # Overqualified - could be good or potential
-            exp_match_ratio = random.uniform(0.6, 0.8)
-    
-    # 3. Title matching - realistic assessment
-    title_words = [w for w in job_title.lower().split() if len(w) > 3]
-    
-    if not title_words:
-        title_match = random.uniform(0.4, 0.6)  # Random if no meaningful title words
-    else:
-        matches = 0
-        for word in title_words:
-            if word in resume_summary.lower():
-                matches += 1
-            # Look for similar words
-            elif any(w.startswith(word[:4]) for w in resume_summary.lower().split() if len(w) > 3):
-                matches += 0.5
-        
-        # Calculate raw match and add slight variance
-        raw_title_match = matches / len(title_words)
-        title_match = max(0, min(1, raw_title_match + random.uniform(-0.1, 0.1)))
-    
-    # Convert to 0-2 scale with slight adjustments for better distribution
-    skill_score = skill_match * 2.0
-    exp_score = exp_match_ratio * 2.0
-    title_score = title_match * 2.0
-    
-    # Extract candidate info
-    name = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
-    name = name.group(1).strip() if name else "The candidate"
-    
-    industry = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
-    industry = industry.group(1).strip() if industry else "unspecified industry"
-    
-    # Calculate weighted score - balanced weights
-    weighted_score = (skill_score * 0.45) + (exp_score * 0.35) + (title_score * 0.20)
-    
-    # Small random adjustment to increase distribution variety
-    # This creates more natural variation in scores
-    weighted_score = max(0, min(2, weighted_score + random.uniform(-0.15, 0.15)))
-    
-    # Set thresholds for better distribution across categories
-    # These thresholds aim for roughly equal distribution on average
-    if weighted_score >= 1.2:
-        fit_score = 2  # Good fit (roughly 33% of cases)
-    elif weighted_score >= 0.7:
-        fit_score = 1  # Potential fit (roughly 33% of cases)
-    else:
-        fit_score = 0  # Not a fit (roughly 33% of cases)
-    
-    # Store debug info
-    st.session_state['debug_scores'] = {
-        'skill_match': skill_match,
-        'skill_score': skill_score,
-        'exp_match_ratio': exp_match_ratio,
-        'exp_score': exp_score,
-        'title_match': title_match,
-        'title_score': title_score,
-        'weighted_score': weighted_score,
-        'fit_score': fit_score,
-        'matching_skills': matching_skills,
-        'required_skills': required_skills,
-        'skill_percentage': f"{len(matching_skills)}/{len(required_skills)}"
+        "summary": job_summary
     }
-    
-    # Generate assessment
-    missing = [skill for skill in required_skills if skill not in skills_mentioned]
-    
-    if fit_score == 2:
-        assessment = f"{fit_score}: GOOD FIT - {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} appears well-suited for this role's requirements."
-    elif fit_score == 1:
-        assessment = f"{fit_score}: POTENTIAL FIT - {name} shows potential for the {job_title} role but has gaps in certain areas. Additional training might be needed in {', '.join(missing[:2])}."
-    else:
-        assessment = f"{fit_score}: NO FIT - {name}'s background shows limited alignment with this {job_title} position. Their experience and skills differ significantly from the requirements."
-    
-    return assessment, fit_score, time.time() - start
 
 def analyze_job_fit(resume_summary, job_description, models):
-    start = time.time()
+    start_time = time.time()
     job_requirements = extract_job_requirements(job_description, models)
-    assessment, fit_score, _ = evaluate_job_fit(resume_summary, job_requirements, models)
-    return assessment, fit_score, time.time() - start
+    assessment, fit_score, execution_time = evaluate_job_fit(resume_summary, job_requirements, models)
+    return assessment, fit_score, time.time() - start_time
+
+# Load models at startup
+models = load_models()
 
 #####################################
-# Main Function
+# Main Function - Kept intact
 #####################################
 def main():
-    # Initialize session state for debug info
-    if 'debug_scores' not in st.session_state:
-        st.session_state['debug_scores'] = {}
-        
+    """Main function for the Streamlit application"""
     st.title("Resume-Job Fit Analyzer")
-    st.markdown("Upload your resume file in **.docx**, **.doc**, or **.txt** format and enter a job description to see how well you match.")
+    st.markdown(
+        """
+    Upload your resume file in **.docx**, **.doc**, or **.txt** format and enter a job description to see how well you match with the job requirements.
+    """
+    )
+
+    # Resume upload
+    uploaded_file = st.file_uploader("Upload your resume (.docx, .doc, or .txt)", type=["docx", "doc", "txt"])
 
-    # Load models and get inputs
-    models = load_models()
-    uploaded_file = st.file_uploader("Upload your resume", type=["docx", "doc", "txt"])
+    # Job description input
     job_description = st.text_area("Enter Job Description", height=200, placeholder="Paste the job description here...")
 
-    # Process when button clicked
-    if uploaded_file and job_description and st.button("Analyze Job Fit"):
-        progress = st.progress(0)
-        status = st.empty()
+    # Process button with optimized flow
+    if uploaded_file is not None and job_description and st.button("Analyze Job Fit"):
+        # Create a placeholder for the progress bar
+        progress_bar = st.progress(0)
+        status_text = st.empty()
         
         # Step 1: Extract text
-        status.text("Step 1/3: Extracting text from resume...")
+        status_text.text("Step 1/3: Extracting text from resume...")
         resume_text = extract_text_from_file(uploaded_file)
-        progress.progress(25)
+        progress_bar.progress(25)
         
         if resume_text.startswith("Error") or resume_text == "Unsupported file type. Please upload a .docx, .doc, or .txt file.":
             st.error(resume_text)
         else:
             # Step 2: Generate summary
-            status.text("Step 2/3: Analyzing resume...")
-            summary, summary_time = summarize_resume_text(resume_text, models)
-            progress.progress(50)
+            status_text.text("Step 2/3: Analyzing resume and generating summary...")
+            summary, summarization_time = summarize_resume_text(resume_text, models)
+            progress_bar.progress(50)
+            
+            # Display summary
             st.subheader("Your Resume Summary")
             st.markdown(summary)
             
-            # Step 3: Evaluate fit
-            status.text("Step 3/3: Evaluating job fit...")
-            assessment, fit_score, eval_time = analyze_job_fit(summary, job_description, models)
-            progress.progress(100)
-            status.empty()
+            # Step 3: Generate job fit assessment
+            status_text.text("Step 3/3: Evaluating job fit (this will take a moment)...")
+            assessment, fit_score, assessment_time = analyze_job_fit(summary, job_description, models)
+            progress_bar.progress(100)
 
-            # Display results
+            # Clear status messages
+            status_text.empty()
+
+            # Display job fit results
             st.subheader("Job Fit Assessment")
-            fit_labels = {0: "NOT FIT", 1: "POTENTIAL FIT", 2: "GOOD FIT"}
-            colors = {0: "red", 1: "orange", 2: "green"}
-            st.markdown(f"<h2 style='color: {colors[fit_score]};'>{fit_labels[fit_score]}</h2>", unsafe_allow_html=True)
+
+            # Display fit score with label
+            fit_labels = {
+                0: "NO FIT",
+                1: "POTENTIAL FIT",
+                2: "GOOD FIT"
+            }
+            
+            # Show the score prominently with appropriate coloring
+            score_label = fit_labels[fit_score]
+            score_colors = {0: "red", 1: "orange", 2: "green"}
+            st.markdown(f"<h2 style='color: {score_colors[fit_score]};'>{score_label}</h2>", unsafe_allow_html=True)
+
+            # Display assessment
             st.markdown(assessment)
-            st.info(f"Analysis completed in {(summary_time + eval_time):.2f} seconds")
+
+            st.info(f"Analysis completed in {(summarization_time + assessment_time):.2f} seconds")
             
-            # Recommendations
+            # Add potential next steps based on the fit score
             st.subheader("Recommended Next Steps")
+            
             if fit_score == 2:
                 st.markdown("""
                 - Apply for this position as you appear to be a good match
@@ -484,5 +458,6 @@ def main():
                 - Consider similar roles with fewer experience requirements
                 """)
 
+# Run the main function
 if __name__ == "__main__":
     main()