2026-rff_mp/PaulVA/lab1/experiments.py

import random
import time
import csv
import os

from phonebook import *

N = 10000
REPEATS = 5

def generate_test_data():
    records = [
        (f"User_{i:05d}", f"+7900000{i:04d}")
        for i in range(N)
    ]

    records_shuffled = records.copy()
    random.shuffle(records_shuffled)

    records_sorted = records.copy()

    return records_shuffled, records_sorted

def measure_experiment(insert_function, find_function, delete_function, records):
    insert_times = []
    find_times = []
    delete_times = []

    for _ in range(REPEATS):
        structure = None

        start = time.perf_counter()

        for name, phone in records:
            structure = insert_function(structure, name, phone)

        insert_times.append(time.perf_counter() - start)

    structure_for_find = structure

    names = [name for name, phone in records]
    search_names = random.sample(names, 100) + [
        "NotFound_001",
        "NotFound_002",
        "NotFound_003",
        "NotFound_004",
        "NotFound_005",
        "NotFound_006",
        "NotFound_007",
        "NotFound_008",
        "NotFound_009",
        "NotFound_010"
    ]

    for _ in range(REPEATS):
        start = time.perf_counter()

        for name in search_names:
            find_function(structure_for_find, name)

        find_times.append(time.perf_counter() - start)

    delete_names = random.sample(names, 50)

    for _ in range(REPEATS):
        structure = structure_for_find

        start = time.perf_counter()

        for name in delete_names:
            structure = delete_function(structure, name)

        delete_times.append(time.perf_counter() - start)

    return insert_times, find_times, delete_times

def measure_hash(records):
    insert_times = []
    find_times = []
    delete_times = []

    names = [name for name, phone in records]
    search_names = random.sample(names, 100) + [
        f"NotFound_{i:03d}" for i in range(10)
    ]
    delete_names = random.sample(names, 50)

    for _ in range(REPEATS):
        buckets = ht_create()

        start = time.perf_counter()

        for name, phone in records:
            ht_insert(buckets, name, phone)

        insert_times.append(time.perf_counter() - start)

    structure_for_find = buckets

    for _ in range(REPEATS):
        start = time.perf_counter()

        for name in search_names:
            ht_find(structure_for_find, name)

        find_times.append(time.perf_counter() - start)

    for _ in range(REPEATS):
        buckets = structure_for_find.copy()

        start = time.perf_counter()

        for name in delete_names:
            ht_delete(buckets, name)

        delete_times.append(time.perf_counter() - start)

    return insert_times, find_times, delete_times

def average(values):
    return sum(values) / len(values)

def run():
    records_shuffled, records_sorted = generate_test_data()

    results = []

    for order_name, records in [
        ("random", records_shuffled),
        ("sorted", records_sorted)
    ]:
        print("Order:", order_name)

        ll = measure_experiment(
            ll_insert,
            ll_find,
            ll_delete,
            records
        )

        results.append(["LinkedList", order_name, "insert", *ll[0]])
        results.append(["LinkedList", order_name, "find", *ll[1]])
        results.append(["LinkedList", order_name, "delete", *ll[2]])

        ht = measure_hash(records)

        results.append(["HashTable", order_name, "insert", *ht[0]])
        results.append(["HashTable", order_name, "find", *ht[1]])
        results.append(["HashTable", order_name, "delete", *ht[2]])

        bst = measure_experiment(
            bst_insert,
            bst_find,
            bst_delete,
            records
        )

        results.append(["BST", order_name, "insert", *bst[0]])
        results.append(["BST", order_name, "find", *bst[1]])
        results.append(["BST", order_name, "delete", *bst[2]])

    os.makedirs("docs/data", exist_ok=True)

    with open("docs/data/results.csv", "w", newline="", encoding="utf-8") as file:
        writer = csv.writer(file)

        writer.writerow([
            "structure",
            "order",
            "operation",
            "run1",
            "run2",
            "run3",
            "run4",
            "run5",
            "average"
        ])

        for row in results:
            writer.writerow(row + [average(row[3:])])

    print("Results saved to docs/data/results.csv")

if __name__ == "__main__":
    run()