debug_keyword.py

#!/usr/bin/env python3
"""Debug: Why does Chef resume get 60% keyword_match for ML role?"""

from app import ATSCompatibilityAnalyzer
import re
from collections import Counter
import math

analyzer = ATSCompatibilityAnalyzer()

chef_resume = """
Chef John Smith
Executive Chef | Le Restaurant | 2015-2023
• Created award-winning French cuisine menus
• Managed kitchen staff of 20
• Sourced local organic ingredients
Skills: French cuisine, pastry, wine pairing
Education: Culinary Institute of America
"""

ml_jd = "Machine Learning Engineer with PhD, PyTorch, TensorFlow experience"

print("=" * 60)
print("DEBUG: Keyword Match Score Calculation")
print("=" * 60)

# Replicate the calculation
resume_lower = chef_resume.lower()
jd_lower = ml_jd.lower()

# Get JD words
jd_words = re.findall(r'\b[a-zA-Z]{2,}\b', jd_lower)
jd_words = [analyzer._stem_word(w) for w in jd_words if w not in analyzer.stop_words]
print(f"\nJD Keywords (stemmed): {jd_words}")

# Get resume words
resume_words = re.findall(r'\b[a-zA-Z]{2,}\b', resume_lower)
resume_words = [analyzer._stem_word(w) for w in resume_words if w not in analyzer.stop_words]
print(f"\nResume Keywords (stemmed): {resume_words}")

# Calculate what matches
jd_tf = Counter(jd_words)
max_count = max(jd_tf.values()) if jd_tf else 1
jd_weights = {word: 1 + math.log(max_count / count) for word, count in jd_tf.items()}

print(f"\nJD Weights: {jd_weights}")

resume_stems = set(resume_words)
resume_raw = set(resume_lower.split())

print(f"\nResume stems: {resume_stems}")
print(f"\nChecking matches...")

for word, weight in jd_weights.items():
    matched = False
    match_type = "NO MATCH"
    match_value = 0
    
    # Check direct match
    if word in resume_stems:
        matched = True
        match_type = "DIRECT"
        match_value = weight
    # Check raw word in resume text
    elif word in resume_lower:
        matched = True
        match_type = "IN TEXT"
        match_value = weight
    # Check containment
    elif any(word in rw or rw in word for rw in resume_stems if len(word) > 3 and len(rw) > 3):
        matched = True
        match_type = "CONTAINMENT"
        match_value = weight * 0.95
        # Show which word matched
        for rw in resume_stems:
            if len(word) > 3 and len(rw) > 3 and (word in rw or rw in word):
                print(f"    → Containment match: '{word}' with '{rw}'")
    # Check 4-char prefix
    elif any(word[:4] in rw for rw in resume_raw if len(word) >= 4 and len(rw) >= 4):
        matched = True
        match_type = "4-CHAR PREFIX"
        match_value = weight * 0.75
        for rw in resume_raw:
            if len(word) >= 4 and len(rw) >= 4 and word[:4] in rw:
                print(f"    → Prefix match: '{word}' -> '{word[:4]}' in '{rw}'")
    # Check 3-char prefix
    elif any(word[:3] == rw[:3] for rw in resume_stems if len(word) >= 3 and len(rw) >= 3):
        matched = True
        match_type = "3-CHAR PREFIX"
        match_value = weight * 0.5
        for rw in resume_stems:
            if len(word) >= 3 and len(rw) >= 3 and word[:3] == rw[:3]:
                print(f"    → 3-char prefix match: '{word}' -> '{word[:3]}' == '{rw[:3]}' ('{rw}')")
    
    status = "✅" if matched else "❌"
    print(f"{status} '{word}' (weight={weight:.2f}) -> {match_type} ({match_value:.2f})")

# Get actual score
score = analyzer._calculate_tfidf_score(chef_resume, ml_jd)
print(f"\n📊 FINAL SCORE: {score}%")