perf-workshop/scenario2-memoization/config_validator.py
illustris 4fb1bd90db
init
2026-01-08 18:11:30 +05:30

153 lines
4.3 KiB
Python

#!/usr/bin/env python3
"""
Scenario 2b: The Precomputation Insight
=======================================
This simulates a config validator that checks rules against events.
The "expensive" validation function is called repeatedly with the same inputs.
This example shows three stages of optimization:
1. Naive: call the function every time
2. Memoized: cache results with @lru_cache
3. Precomputed: since inputs are known ahead of time, build a lookup table
EXERCISES:
1. Run each version and compare times
2. Profile each version - observe ncalls and cumtime
3. Think about: when is precomputation better than memoization?
"""
import sys
import time
from functools import lru_cache
# Simulated "expensive" validation function
def validate_rule_slow(rule_id, event_type):
"""
Simulate an expensive validation check.
In real life, this might query a database, parse XML, etc.
"""
# Artificial delay to simulate expensive computation
total = 0
for i in range(10000):
total += (rule_id * event_type * i) % 997
return total % 2 == 0 # Returns True or False
# The set of all valid (rule_id, event_type) pairs we'll encounter
RULES = [1, 2, 3, 4, 5]
EVENT_TYPES = [10, 20, 30, 40, 50]
def process_events_naive(events):
"""Process events using naive repeated validation."""
valid_count = 0
for rule_id, event_type, data in events:
if validate_rule_slow(rule_id, event_type):
valid_count += 1
return valid_count
# Memoized version
@lru_cache(maxsize=None)
def validate_rule_cached(rule_id, event_type):
"""Same validation but with caching."""
total = 0
for i in range(10000):
total += (rule_id * event_type * i) % 997
return total % 2 == 0
def process_events_memoized(events):
"""Process events using memoized validation."""
valid_count = 0
for rule_id, event_type, data in events:
if validate_rule_cached(rule_id, event_type):
valid_count += 1
return valid_count
# Precomputed version
def build_validation_table():
"""
Build a lookup table for all possible (rule_id, event_type) combinations.
This is O(n*m) upfront but O(1) per lookup thereafter.
"""
table = {}
for rule_id in RULES:
for event_type in EVENT_TYPES:
table[(rule_id, event_type)] = validate_rule_slow(rule_id, event_type)
return table
VALIDATION_TABLE = None # Lazy initialization
def process_events_precomputed(events):
"""Process events using precomputed lookup table."""
global VALIDATION_TABLE
if VALIDATION_TABLE is None:
VALIDATION_TABLE = build_validation_table()
valid_count = 0
for rule_id, event_type, data in events:
if VALIDATION_TABLE[(rule_id, event_type)]:
valid_count += 1
return valid_count
def generate_test_events(n):
"""Generate n random test events."""
import random
random.seed(42) # Reproducible
events = []
for i in range(n):
rule_id = random.choice(RULES)
event_type = random.choice(EVENT_TYPES)
data = f"event_{i}"
events.append((rule_id, event_type, data))
return events
def benchmark(name, func, events):
"""Run a function and report timing."""
start = time.perf_counter()
result = func(events)
elapsed = time.perf_counter() - start
print(f"{name:20s}: {elapsed:.3f}s (valid: {result})")
return elapsed
def main():
n_events = 5000
if len(sys.argv) > 1:
n_events = int(sys.argv[1])
print(f"Processing {n_events} events...")
print(f"Unique (rule, event_type) combinations: {len(RULES) * len(EVENT_TYPES)}")
print()
events = generate_test_events(n_events)
# Reset cached function for fair comparison
validate_rule_cached.cache_clear()
global VALIDATION_TABLE
VALIDATION_TABLE = None
t_naive = benchmark("Naive", process_events_naive, events)
validate_rule_cached.cache_clear()
t_memo = benchmark("Memoized", process_events_memoized, events)
VALIDATION_TABLE = None
t_pre = benchmark("Precomputed", process_events_precomputed, events)
print()
print(f"Speedup (memo vs naive): {t_naive/t_memo:.1f}x")
print(f"Speedup (precomp vs naive): {t_naive/t_pre:.1f}x")
print(f"Speedup (precomp vs memo): {t_memo/t_pre:.1f}x")
if __name__ == "__main__":
main()