[1] Data structures lab

KuznetsovMA/lab1/docs/data/results.csv

@@ -0,0 +1,19 @@
+structure,order,operation,run1,run2,run3,run4,run5,average
+LinkedList,random,insert,3.000600399999712,3.022712899999533,2.9421689999999217,2.9075659000000087,3.0319512999994913,2.980999899999733
+LinkedList,random,find,0.031094500000108383,0.02800200000001496,0.034349299999121286,0.029372199999670556,0.03242119999958959,0.031047839999700955
+LinkedList,random,delete,0.017322699999567703,0.0368361000000732,0.04029200000059063,0.03775789999963308,0.03554420000000391,0.033550579999973705
+HashTable,random,insert,0.011551699999472476,0.012756400000398571,0.011765299999751733,0.011679000000185624,0.011983400000644906,0.011947160000090662
+HashTable,random,find,0.00012409999999363208,0.00011009999980160501,0.0001415999995515449,0.00010400000064691994,0.00010089999977935804,0.000116139999954612
+HashTable,random,delete,6.38999999864609e-05,6.779999966965988e-05,6.0600000324484427e-05,6.070000017643906e-05,6.0600000324484427e-05,6.272000009630574e-05
+BST,random,insert,0.014788199999202334,0.014159299999846553,0.013975800000480376,0.014118900000539725,0.013331299999663315,0.01407469999994646
+BST,random,find,0.00013829999988956843,0.00011389999963284936,0.00011369999992894009,0.00011379999978089472,0.00011439999980211724,0.00011881999980687397
+BST,random,delete,8.690000049682567e-05,6.450000000768341e-05,6.2199999774748e-05,6.209999992279336e-05,6.229999962670263e-05,6.759999996575061e-05
+LinkedList,sorted,insert,2.4411346000006233,2.36463619999995,2.2797248999995645,2.2860746000005747,2.2526011999998445,2.3248343000001115
+LinkedList,sorted,find,0.024703000000044995,0.02455259999987902,0.02468479999970441,0.02444869999999355,0.02606350000041857,0.02489052000000811
+LinkedList,sorted,delete,0.012835599999561964,0.027673999999933585,0.027570299999752024,0.02708100000018021,0.02999909999925876,0.02503199999973731
+HashTable,sorted,insert,0.011780100000578386,0.010850699999537028,0.010314100000869075,0.010621500000524975,0.011015500000212342,0.010916380000344362
+HashTable,sorted,find,0.0001464000006308197,0.00017980000029638177,0.00016909999976633117,0.00012620000052265823,0.00023630000032426324,0.0001715600003080908
+HashTable,sorted,delete,0.00016370000048482325,0.00018089999957737746,0.0001443999999537482,7.579999964946182e-05,6.469999971159268e-05,0.0001258999998754007
+BST,sorted,insert,3.5400651999998445,3.5145174999997835,3.5583661999999094,3.5149656000003233,3.481246600000304,3.521832220000033
+BST,sorted,find,0.03275260000009439,0.030442500000390282,0.02994349999971746,0.030269500000031258,0.030329999999594293,0.030747619999965538
+BST,sorted,delete,0.012705400000413647,0.01333390000036161,0.013192000000344706,0.013699000000087835,0.013079800000014075,0.013202020000244374

KuznetsovMA/lab1/docs/report.md

@@ -0,0 +1,34 @@
+Лабораторная работа 1
+
+
+
+Цель работы
+
+
+
+Нужно было сделать три структуры данных и проверить как они работают на телефонном справочнике.
+
+
+
+Ход работы
+
+
+
+Сделал связный список хеш таблицу и двоичное дерево поиска. Для всех структур сделал добавление поиск удаление и вывод записей. Для проверки создал 10000 записей с именами User\_00000 и т.д. Потом проверил работу со случайным порядком и с отсортированным порядком. Каждый эксперимент повторял 5 раз.
+
+
+
+Результаты
+
+
+
+Результаты сохранились в results.csv. Также сделал графики для добавления поиска и удаления. По результатам видно что связный список медленно ищет записи потому что нужно идти по элементам. Хеш таблица работает примерно одинаково при разном порядке записей. У двоичного дерева порядок записей влияет намного сильнее. Если добавлять записи по порядку дерево становится похожим на обычный список и работает медленнее.
+
+
+
+Вывод
+
+
+
+В работе я сделал три структуры данных и проверил их работу. Самой удобной для телефонного справочника получилась хеш таблица. Связный список проще но поиск медленный. Двоичное дерево может работать быстро но сильно зависит от порядка добавления данных.
+

KuznetsovMA/lab1/experiments.py

@@ -0,0 +1,185 @@
+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()

KuznetsovMA/lab1/graphs.py

@@ -0,0 +1,56 @@
+import csv
+import os
+import matplotlib.pyplot as plt
+
+data = []
+
+with open("docs/data/results.csv", "r", encoding="utf-8") as file:
+    reader = csv.DictReader(file)
+
+    for row in reader:
+        data.append(row)
+
+def get_average(structure, order, operation):
+    for row in data:
+        if (
+            row["structure"] == structure
+            and row["order"] == order
+            and row["operation"] == operation
+        ):
+            return float(row["average"])
+
+    return 0
+
+structures = ["LinkedList", "HashTable", "BST"]
+orders = ["random", "sorted"]
+
+os.makedirs("docs/data", exist_ok=True)
+
+for operation in ["insert", "find", "delete"]:
+    random_values = [
+        get_average(s, "random", operation)
+        for s in structures
+    ]
+
+    sorted_values = [
+        get_average(s, "sorted", operation)
+        for s in structures
+    ]
+
+    x = range(len(structures))
+
+    plt.figure()
+    plt.bar([i - 0.2 for i in x], random_values, width=0.4, label="random")
+    plt.bar([i + 0.2 for i in x], sorted_values, width=0.4, label="sorted")
+
+    plt.xticks(list(x), structures)
+    plt.ylabel("Time, seconds")
+    plt.title(operation.capitalize() + " time")
+    plt.yscale("log")
+    plt.legend()
+    plt.tight_layout()
+
+    plt.savefig("docs/data/graph_" + operation + ".png")
+    plt.close()
+
+print("Graphs saved to docs/data/")

KuznetsovMA/lab1/phonebook.py

@@ -0,0 +1,211 @@
+def ll_insert(head, name, phone):
+    new_node = {
+        'name': name,
+        'phone': phone,
+        'next': None
+    }
+
+    if head is None:
+        return new_node
+
+    current = head
+
+    while current['next'] is not None:
+        if current['name'] == name:
+            current['phone'] = phone
+            return head
+        current = current['next']
+
+    if current['name'] == name:
+        current['phone'] = phone
+    else:
+        current['next'] = new_node
+
+    return head
+
+def ll_find(head, name):
+    current = head
+
+    while current is not None:
+        if current['name'] == name:
+            return current['phone']
+        current = current['next']
+
+    return None
+
+def ll_delete(head, name):
+    if head is None:
+        return None
+
+    if head['name'] == name:
+        return head['next']
+
+    current = head
+
+    while current['next'] is not None:
+        if current['next']['name'] == name:
+            current['next'] = current['next']['next']
+            return head
+
+        current = current['next']
+
+    return head
+
+def ll_list_all(head):
+    records = []
+    current = head
+
+    while current is not None:
+        records.append((current['name'], current['phone']))
+        current = current['next']
+
+    records.sort(key=lambda x: x[0])
+    return records
+
+def hash_function(name, table_size):
+    total = 0
+
+    for ch in name:
+        total = (total * 31 + ord(ch)) % table_size
+
+    return total
+
+def ht_create(size=1000):
+    return [None] * size
+
+def ht_insert(buckets, name, phone):
+    index = hash_function(name, len(buckets))
+    buckets[index] = ll_insert(buckets[index], name, phone)
+    return buckets
+
+def ht_find(buckets, name):
+    index = hash_function(name, len(buckets))
+    return ll_find(buckets[index], name)
+
+def ht_delete(buckets, name):
+    index = hash_function(name, len(buckets))
+    buckets[index] = ll_delete(buckets[index], name)
+    return buckets
+
+def ht_list_all(buckets):
+    records = []
+
+    for bucket in buckets:
+        current = bucket
+
+        while current is not None:
+            records.append((current['name'], current['phone']))
+            current = current['next']
+
+    records.sort(key=lambda x: x[0])
+    return records
+
+def bst_insert(root, name, phone):
+    new_node = {
+        'name': name,
+        'phone': phone,
+        'left': None,
+        'right': None
+    }
+
+    if root is None:
+        return new_node
+
+    current = root
+
+    while True:
+        if name < current['name']:
+            if current['left'] is None:
+                current['left'] = new_node
+                break
+            current = current['left']
+
+        elif name > current['name']:
+            if current['right'] is None:
+                current['right'] = new_node
+                break
+            current = current['right']
+
+        else:
+            current['phone'] = phone
+            break
+
+    return root
+
+def bst_find(root, name):
+    current = root
+
+    while current is not None:
+        if name == current['name']:
+            return current['phone']
+
+        if name < current['name']:
+            current = current['left']
+        else:
+            current = current['right']
+
+    return None
+
+def bst_delete(root, name):
+    parent = None
+    current = root
+
+    while current is not None and current['name'] != name:
+        parent = current
+
+        if name < current['name']:
+            current = current['left']
+        else:
+            current = current['right']
+
+    if current is None:
+        return root
+
+    if current['left'] is None:
+        child = current['right']
+
+    elif current['right'] is None:
+        child = current['left']
+
+    else:
+        successor_parent = current
+        successor = current['right']
+
+        while successor['left'] is not None:
+            successor_parent = successor
+            successor = successor['left']
+
+        current['name'] = successor['name']
+        current['phone'] = successor['phone']
+
+        if successor_parent['left'] == successor:
+            successor_parent['left'] = successor['right']
+        else:
+            successor_parent['right'] = successor['right']
+
+        return root
+
+    if parent is None:
+        return child
+
+    if parent['left'] == current:
+        parent['left'] = child
+    else:
+        parent['right'] = child
+
+    return root
+
+def bst_list_all(root):
+    records = []
+
+    def inorder(node):
+        if node is None:
+            return
+
+        inorder(node['left'])
+        records.append((node['name'], node['phone']))
+        inorder(node['right'])
+
+    inorder(root)
+
+    return records