[1] Add benchmarking

This commit is contained in:
KuznetsovYuM 2026-05-22 17:17:04 +00:00
parent c009c610a6
commit a1f157b283

View File

@ -159,12 +159,120 @@ def bst_collect_inorder(root):
return result
#Benchmarking
import random
import time
import csv
import os
import sys
sys.setrecursionlimit(20000)
def generate_test_data(n, seed=42):
random.seed(seed)
records = []
for i in range(1, n+1):
name = f"User_{i:05d}"
phone = f"{random.randint(100,999)}-{random.randint(1000,9999)}"
records.append((name, phone))
return records
def prepare_ordered_and_shuffled(records):
shuffled = records.copy()
random.shuffle(shuffled)
sorted_records = sorted(records, key=lambda x: x[0])
return shuffled, sorted_records
def measure_operations(struct_ops, records, mode_name, repeats=5):
results = []
for rep in range(repeats):
ds = struct_ops['create']()
start = time.perf_counter()
for name, phone in records:
ds = struct_ops['insert'](ds, name, phone)
insert_time = time.perf_counter() - start
existing_names = [name for name, _ in records]
sample_existing = random.sample(existing_names, 100)
nonexistent = [f"Missing_{i}" for i in range(10)]
search_names = sample_existing + nonexistent
random.shuffle(search_names)
start = time.perf_counter()
for name in search_names:
struct_ops['find'](ds, name)
find_time = time.perf_counter() - start
to_delete = random.sample(existing_names, 50)
start = time.perf_counter()
for name in to_delete:
ds = struct_ops['delete'](ds, name)
delete_time = time.perf_counter() - start
results.append({
'structure': struct_ops['name'],
'mode': mode_name,
'repetition': rep+1,
'insert_time': insert_time,
'find_time': find_time,
'delete_time': delete_time
})
return results
def run_full_benchmark():
N = 10000
base_records = generate_test_data(N)
shuffled, sorted_records = prepare_ordered_and_shuffled(base_records)
structures = {
'LinkedList': {
'name': 'LinkedList',
'create': lambda: None,
'insert': linked_list_add,
'find': linked_list_find,
'delete': linked_list_remove,
},
'HashTable': {
'name': 'HashTable',
'create': lambda: hash_table_create(100),
'insert': hash_table_put,
'find': hash_table_get,
'delete': hash_table_remove,
},
'BST': {
'name': 'BST',
'create': lambda: None,
'insert': bst_add,
'find': bst_find,
'delete': bst_remove,
}
}
all_results = []
for name, ops in structures.items():
print(f"Benchmarking {name} on random order...")
all_results.extend(measure_operations(ops, shuffled, 'random', repeats=5))
print(f"Benchmarking {name} on sorted order...")
all_results.extend(measure_operations(ops, sorted_records, 'sorted', repeats=5))
os.makedirs('docs/data', exist_ok=True)
csv_path = 'docs/data/experiment_results.csv'
with open(csv_path, 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
writer.writerow(['Structure', 'Mode', 'Repeat', 'Insert (sec)', 'Search (sec)', 'Delete (sec)'])
for r in all_results:
writer.writerow([
r['structure'],
r['mode'],
r['repetition'],
f"{r['insert_time']:.6f}",
f"{r['find_time']:.6f}",
f"{r['delete_time']:.6f}"
])
print(f"Experiment finished. Results saved to {csv_path}")
if __name__ == '__main__':
tree = None
tree = bst_add(tree, 'Zoe', '111')
tree = bst_add(tree, 'Alice', '222')
tree = bst_add(tree, 'Bob', '333')
tree = bst_add(tree, 'Alice', '444')
print(bst_find(tree, 'Alice')) # 444
tree = bst_remove(tree, 'Bob')
print(bst_collect_inorder(tree)) # [('Alice','444'), ('Zoe','111')]
run_full_benchmark()