278 lines
7.4 KiB
Python
278 lines
7.4 KiB
Python
def linked_list_add(head, name, phone):
|
|
curr = head
|
|
while curr is not None:
|
|
if curr['name'] == name:
|
|
curr['phone'] = phone
|
|
return head
|
|
curr = curr['next']
|
|
|
|
new_node = {'name': name, 'phone': phone, 'next': None}
|
|
if head is None:
|
|
return new_node
|
|
|
|
curr = head
|
|
while curr['next'] is not None:
|
|
curr = curr['next']
|
|
curr['next'] = new_node
|
|
return head
|
|
|
|
|
|
def linked_list_find(head, name):
|
|
curr = head
|
|
while curr is not None:
|
|
if curr['name'] == name:
|
|
return curr['phone']
|
|
curr = curr['next']
|
|
return None
|
|
|
|
|
|
def linked_list_remove(head, name):
|
|
if head is None:
|
|
return None
|
|
if head['name'] == name:
|
|
return head['next']
|
|
prev = head
|
|
curr = head['next']
|
|
while curr is not None:
|
|
if curr['name'] == name:
|
|
prev['next'] = curr['next']
|
|
return head
|
|
prev = curr
|
|
curr = curr['next']
|
|
return head
|
|
|
|
|
|
def linked_list_collect_all(head):
|
|
records = []
|
|
curr = head
|
|
while curr is not None:
|
|
records.append((curr['name'], curr['phone']))
|
|
curr = curr['next']
|
|
records.sort(key=lambda pair: pair[0])
|
|
return records
|
|
|
|
|
|
|
|
#HASH
|
|
def _hash_bucket_index(key, table_size):
|
|
return hash(key) % table_size
|
|
|
|
|
|
def hash_table_create(bucket_count=10):
|
|
return [None] * bucket_count
|
|
|
|
|
|
def hash_table_put(table, name, phone):
|
|
idx = _hash_bucket_index(name, len(table))
|
|
table[idx] = linked_list_add(table[idx], name, phone)
|
|
return table
|
|
|
|
|
|
def hash_table_get(table, name):
|
|
idx = _hash_bucket_index(name, len(table))
|
|
return linked_list_find(table[idx], name)
|
|
|
|
|
|
def hash_table_remove(table, name):
|
|
idx = _hash_bucket_index(name, len(table))
|
|
table[idx] = linked_list_remove(table[idx], name)
|
|
return table
|
|
|
|
|
|
def hash_table_collect_all(table):
|
|
all_records = []
|
|
for head in table:
|
|
curr = head
|
|
while curr is not None:
|
|
all_records.append((curr['name'], curr['phone']))
|
|
curr = curr['next']
|
|
all_records.sort(key=lambda pair: pair[0])
|
|
return all_records
|
|
|
|
|
|
#BST
|
|
def _bst_new_node(name, phone):
|
|
return {'name': name, 'phone': phone, 'left': None, 'right': None}
|
|
|
|
|
|
def bst_add(root, name, phone):
|
|
"""Insert or update. Returns (possibly new) root."""
|
|
if root is None:
|
|
return _bst_new_node(name, phone)
|
|
|
|
if name == root['name']:
|
|
root['phone'] = phone
|
|
elif name < root['name']:
|
|
root['left'] = bst_add(root['left'], name, phone)
|
|
else:
|
|
root['right'] = bst_add(root['right'], name, phone)
|
|
return root
|
|
|
|
|
|
def bst_find(root, name):
|
|
if root is None:
|
|
return None
|
|
if name == root['name']:
|
|
return root['phone']
|
|
elif name < root['name']:
|
|
return bst_find(root['left'], name)
|
|
else:
|
|
return bst_find(root['right'], name)
|
|
|
|
|
|
def _bst_find_minimum(node):
|
|
while node['left'] is not None:
|
|
node = node['left']
|
|
return node
|
|
|
|
|
|
def bst_remove(root, name):
|
|
if root is None:
|
|
return None
|
|
|
|
if name < root['name']:
|
|
root['left'] = bst_remove(root['left'], name)
|
|
elif name > root['name']:
|
|
root['right'] = bst_remove(root['right'], name)
|
|
else:
|
|
if root['left'] is None:
|
|
return root['right']
|
|
if root['right'] is None:
|
|
return root['left']
|
|
|
|
successor = _bst_find_minimum(root['right'])
|
|
root['name'] = successor['name']
|
|
root['phone'] = successor['phone']
|
|
root['right'] = bst_remove(root['right'], successor['name'])
|
|
return root
|
|
|
|
|
|
def bst_collect_inorder(root):
|
|
result = []
|
|
def inorder(node):
|
|
if node is None:
|
|
return
|
|
inorder(node['left'])
|
|
result.append((node['name'], node['phone']))
|
|
inorder(node['right'])
|
|
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__':
|
|
run_full_benchmark() |