proof_of_concept_03_analysis.py

import json
from collections import defaultdict, Counter

# Load the traceability map
with open('proof_of_concept/traceability_map.json') as f:
    traceability_map = json.load(f)

# Data structures to group information
feature_tags = defaultdict(list)
tag_feature_count = defaultdict(Counter)

# Fill structures
for feature, source_type, tag in traceability_map:
    feature_tags[feature].append(tag)
    tag_feature_count[tag][feature] += 1

def print_section(title):
    print("\n" + "="*len(title))
    print(title)
    print("="*len(title))

def print_feature_list(title, tag):
    print_section(title)
    for feature, count in tag_feature_count[tag].most_common():
        print(f"- {feature}: {count} occurrences")

def print_composite_section(title, tags):
    print_section(title)
    score = Counter()
    for tag in tags:
        for feature, count in tag_feature_count[tag].items():
            score[feature] += count
    for feature, count in score.most_common():
        matching_tags = ', '.join(set(feature_tags[feature]) & set(tags))
        print(f"- {feature}: {count} occurrences ({matching_tags})")

# ===============================
# ANSWERS TO KEY QUESTIONS
# ===============================

# 🧪 Testing questions
print_section("🧪 TESTING QUESTIONS")

print_composite_section("Which features need more testing?", ['testing', 'fix', 'error'])
print_composite_section("Which features use too many mocks?", ['mock'])
print_composite_section("Which features might be poorly designed for testing (refactor)?", ['mock', 'refactor'])

# ✨ Feature evolution
print_section("✨ FEATURE QUESTIONS")

print_feature_list("Which features are being extended?", 'extension')
print_feature_list("Which features are being refactored?", 'refactor')
print_feature_list("Which features could be deprecated or removed?", 'obsolete')
print_composite_section("Which features show high activity (testing + model + config)?", ['testing', 'model', 'config'])

# ⚙️ CI/CD questions
print_section("⚙️ CI/CD QUESTIONS")

print_feature_list("Which features trigger configuration issues?", 'config')
print_feature_list("Which features introduce new models?", 'model')
print_feature_list("Which features often fail (fix)?", 'fix')

# Summary
print_section("✅ TOTAL")
print(f"Total features analyzed: {len(feature_tags)}")
print(f"Total entries in the traceability map: {len(traceability_map)}")