webapp/app/analyze_logs.py

import json
from collections import defaultdict

LOG_FILE = "logs/app.log"

total_requests = 0
total_latency = 0
query_count = defaultdict(int)
slow_requests = []

with open(LOG_FILE, "r") as f:
    for line in f:
        try:
            log = json.loads(line)

            total_requests += 1
            latency = log.get("latency_ms", 0)
            query = log.get("query", "")

            total_latency += latency
            query_count[query] += 1

            if latency > 1000:  # slow threshold
                slow_requests.append((query, latency))

        except:
            continue

# Results
print("\n📊 BASIC METRICS")
print("=" * 30)

if total_requests > 0:
    print(f"Total Requests: {total_requests}")
    print(f"Avg Latency: {total_latency // total_requests} ms")

print("\n🔥 Top Queries:")
for q, count in sorted(query_count.items(), key=lambda x: x[1], reverse=True)[:5]:
    print(f"{q} → {count} times")

print("\n⚠️ Slow Requests (>1000ms):")
for q, lat in slow_requests[:5]:
    print(f"{q} → {lat} ms")

cache_hits = 0

if log.get("latency_ms", 0) < 500:
    cache_hits += 1

print(f"\n⚡ Fast Requests (<500ms): {cache_hits}")

hit_count = 0

if log.get("cache_status") in ["strong_hit", "refined_hit"]:
    hit_count += 1

hit_rate = (hit_count / total_requests) * 100

fallback_count = 0

if log.get("cache_status") == "miss":
    fallback_count += 1

fallback_rate = (fallback_count / total_requests) * 100