Merge pull request '[1] Лабораторная работа №1:' (#257) from YaroslavtsevAS/2026-rff_mp:YaroslavtsevAS-lab1 into develop

Reviewed-on: UNN/2026-rff_mp#257

YaroslavtsevAS/docs/results.csv

@@ -0,0 +1,19 @@
+Structure,Mode,Operation,Run1,Run2,Run3,Run4,Run5,Average
+LinkedList,random,Insert,7.614908,8.007141,8.790796,9.036304,9.488376,8.587505
+LinkedList,random,Search,0.084409,0.086699,0.114697,0.095945,0.220154,0.120381
+LinkedList,random,Delete,0.116604,0.110528,0.109806,0.113804,0.050557,0.100260
+LinkedList,sorted,Insert,9.123691,10.006184,8.030617,9.528127,7.143701,8.766464
+LinkedList,sorted,Search,0.119573,0.094237,0.082494,0.104148,0.043972,0.088885
+LinkedList,sorted,Delete,0.023634,0.023499,0.023649,0.023649,0.023822,0.023651
+HashTable,random,Insert,0.397523,0.339688,0.343173,0.445151,0.352442,0.375595
+HashTable,random,Search,0.009526,0.008965,0.009936,0.008976,0.008971,0.009275
+HashTable,random,Delete,0.004966,0.004936,0.004983,0.005517,0.005983,0.005277
+HashTable,sorted,Insert,0.935748,0.769911,0.394893,0.332380,0.302012,0.546989
+HashTable,sorted,Search,0.005751,0.005670,0.005420,0.005354,0.005321,0.005503
+HashTable,sorted,Delete,0.003136,0.003161,0.003117,0.003158,0.003138,0.003142
+BST,random,Insert,0.046068,0.046076,0.042452,0.023921,0.023297,0.036363
+BST,random,Search,0.000274,0.000229,0.000228,0.000226,0.000226,0.000236
+BST,random,Delete,0.000362,0.000344,0.000343,0.000336,0.000347,0.000346
+BST,sorted,Insert,14.359368,13.962086,16.018128,14.777863,15.188039,14.861097
+BST,sorted,Search,0.056389,0.053998,0.057459,0.087951,0.084866,0.068133
+BST,sorted,Delete,0.070368,0.066086,0.069282,0.066915,0.071834,0.068897

YaroslavtsevAS/lab1.py

@@ -0,0 +1,616 @@
+import time
+import random
+import csv
+import os
+import sys
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+sys.setrecursionlimit(20000)
+
+
+def ll_insert(head, name, phone):
+    current = head
+    while current:
+        if current["name"] == name:
+            current["phone"] = phone
+            return head
+        current = current["next"]
+    return {
+        "name": name,
+        "phone": phone,
+        "next": head
+    }
+
+def ll_find(head, name):
+    current = head
+    while current:
+        if current["name"] == name:
+            return current["phone"]
+        current = current["next"]
+    return None
+
+def ll_delete(head, name):
+    if not head:
+        return None
+    if head["name"] == name:
+        return head["next"]
+    current = head
+    while current["next"]:
+        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:
+        records.append(
+            (current["name"], current["phone"])
+        )
+        current = current["next"]
+    records.sort(key=lambda x: x[0])
+    return records
+
+
+def hash_function(name, size):
+    return sum(ord(c) for c in name) % size
+
+def ht_create(size=2000):
+    return [None] * size
+
+def ht_insert(buckets, name, phone):
+    index = hash_function(name, len(buckets))
+    buckets[index] = ll_insert(
+        buckets[index],
+        name,
+        phone
+    )
+
+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
+    )
+
+def ht_list_all(buckets):
+    records = []
+    for bucket in buckets:
+        current = bucket
+        while current:
+            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:
+        if name == current["name"]:
+            return current["phone"]
+
+        if name < current["name"]:
+            current = current["left"]
+
+        else:
+            current = current["right"]
+
+    return None
+
+
+def bst_find_min(node):
+    current = node
+    while current["left"]:
+        current = current["left"]
+    return current
+
+
+def bst_delete(root, name):
+
+    if root is None:
+        return None
+
+    if name < root["name"]:
+        root["left"] = bst_delete(
+            root["left"],
+            name
+        )
+
+    elif name > root["name"]:
+        root["right"] = bst_delete(
+            root["right"],
+            name
+        )
+
+    else:
+        if root["left"] is None:
+            return root["right"]
+        if root["right"] is None:
+            return root["left"]
+        min_node = bst_find_min(root["right"])
+
+        root["name"] = min_node["name"]
+        root["phone"] = min_node["phone"]
+
+        root["right"] = bst_delete(
+            root["right"],
+            min_node["name"]
+        )
+
+    return root
+
+
+def bst_list_all(root):
+    records = []
+    stack = []
+    current = root
+    while stack or current:
+        while current:
+            stack.append(current)
+            current = current["left"]
+
+        current = stack.pop()
+
+        records.append(
+            (current["name"], current["phone"])
+        )
+
+        current = current["right"]
+    return records
+
+def copy_linked_list(head):
+    if not head:
+        return None
+
+    new_head = {
+        "name": head["name"],
+        "phone": head["phone"],
+        "next": None
+    }
+
+    current_new = new_head
+    current_old = head["next"]
+
+    while current_old:
+
+        current_new["next"] = {
+            "name": current_old["name"],
+            "phone": current_old["phone"],
+            "next": None
+        }
+
+        current_new = current_new["next"]
+        current_old = current_old["next"]
+
+    return new_head
+
+
+def copy_bst(node):
+
+    if not node:
+        return None
+
+    return {
+        "name": node["name"],
+        "phone": node["phone"],
+        "left": copy_bst(node["left"]),
+        "right": copy_bst(node["right"])
+    }
+
+
+def generate_test_data(N=10000):
+
+    records = []
+
+    for i in range(N):
+        name = f"User_{i:05d}"
+        phone = f"+7-999-{random.randint(1000000, 9999999)}"
+        records.append((name, phone))
+    records_shuffled = records.copy()
+    random.shuffle(records_shuffled)
+    records_sorted = sorted(records)
+    return records_shuffled, records_sorted
+
+
+def get_test_queries(records):
+
+    existing = random.sample(records, 100)
+    existing_names = [name for name, _ in existing]
+    missing_names = [
+        f"None_{i:05d}"
+        for i in range(10)
+    ]
+    queries = existing_names + missing_names
+    random.shuffle(queries)
+    return queries
+
+
+def get_delete_names(records):
+    selected = random.sample(records, 50)
+    return [name for name, _ in selected]
+
+
+def measure_insertion(structure_type, records, repeats=5):
+
+    times = []
+    for _ in range(repeats):
+        if structure_type == "LinkedList":
+            structure = None
+        elif structure_type == "HashTable":
+            structure = ht_create()
+
+        else:
+            structure = None
+        start = time.perf_counter()
+        for name, phone in records:
+            if structure_type == "LinkedList":
+                structure = ll_insert(
+                    structure,
+                    name,
+                    phone
+                )
+
+            elif structure_type == "HashTable":
+                ht_insert(
+                    structure,
+                    name,
+                    phone
+                )
+
+            else:
+                structure = bst_insert(
+                    structure,
+                    name,
+                    phone
+                )
+        end = time.perf_counter()
+        times.append(end - start)
+    return times
+
+
+
+def measure_search(
+    structure_type,
+    structure,
+    queries,
+    repeats=5
+):
+
+    times = []
+
+    for _ in range(repeats):
+        start = time.perf_counter()
+        for name in queries:
+            if structure_type == "LinkedList":
+                ll_find(structure, name)
+            elif structure_type == "HashTable":
+                ht_find(structure, name)
+
+            else:
+
+                bst_find(structure, name)
+        end = time.perf_counter()
+        times.append(end - start)
+    return times
+
+
+def measure_deletion(
+    structure_type,
+    structure,
+    delete_names,
+    repeats=5
+):
+
+    times = []
+
+    for _ in range(repeats):
+        if structure_type == "LinkedList":
+            temp = copy_linked_list(structure)
+        elif structure_type == "HashTable":
+            temp = structure.copy()
+            for i in range(len(temp)):
+                if temp[i]:
+                    temp[i] = copy_linked_list(temp[i])
+
+        else:
+            temp = copy_bst(structure)
+        start = time.perf_counter()
+        for name in delete_names:
+            if structure_type == "LinkedList":
+                temp = ll_delete(temp, name)
+            elif structure_type == "HashTable":
+                ht_delete(temp, name)
+            else:
+                temp = bst_delete(temp, name)
+        end = time.perf_counter()
+        times.append(end - start)
+    return times
+
+def build_structure(structure_type, records):
+    if structure_type == "LinkedList":
+        structure = None
+        for name, phone in records:
+            structure = ll_insert(
+                structure,
+                name,
+                phone
+            )
+
+    elif structure_type == "HashTable":
+        structure = ht_create()
+        for name, phone in records:
+            ht_insert(
+                structure,
+                name,
+                phone
+            )
+
+    else:
+        structure = None
+        for name, phone in records:
+            structure = bst_insert(
+                structure,
+                name,
+                phone
+            )
+    return structure
+
+
+def run_experiment(N=10000):
+    records_shuffled, records_sorted = generate_test_data(N)
+    queries = get_test_queries(records_shuffled)
+    delete_names = get_delete_names(records_shuffled)
+    structures = [
+        "LinkedList",
+        "HashTable",
+        "BST"
+    ]
+    modes = [
+        ("random", records_shuffled),
+        ("sorted", records_sorted)
+    ]
+    results = []
+    for structure in structures:
+        for mode_name, records in modes:
+            insert_times = measure_insertion(
+                structure,
+                records
+            )
+            final_structure = build_structure(
+                structure,
+                records
+            )
+            search_times = measure_search(
+                structure,
+                final_structure,
+                queries
+            )
+            delete_times = measure_deletion(
+                structure,
+                final_structure,
+                delete_names
+            )
+            results.append({
+                "Structure": structure,
+                "Mode": mode_name,
+                "Insert": insert_times,
+                "Search": search_times,
+                "Delete": delete_times,
+                "AvgInsert":
+                    sum(insert_times) / len(insert_times),
+                "AvgSearch":
+                    sum(search_times) / len(search_times),
+                "AvgDelete":
+                    sum(delete_times) / len(delete_times)
+            })
+
+    return results
+
+def save_to_csv(results):
+    os.makedirs("docs", exist_ok=True)
+    with open(
+        "docs/results.csv",
+        "w",
+        newline="",
+        encoding="utf-8"
+    ) as file:
+        writer = csv.writer(file)
+        writer.writerow([
+            "Structure",
+            "Mode",
+            "Operation",
+            "Run1",
+            "Run2",
+            "Run3",
+            "Run4",
+            "Run5",
+            "Average"
+        ])
+
+        for result in results:
+            writer.writerow([
+                result["Structure"],
+                result["Mode"],
+                "Insert",
+                *[f"{x:.6f}" for x in result["Insert"]],
+                f"{result['AvgInsert']:.6f}"
+            ])
+            writer.writerow([
+                result["Structure"],
+                result["Mode"],
+                "Search",
+                *[f"{x:.6f}" for x in result["Search"]],
+                f"{result['AvgSearch']:.6f}"
+            ])
+            writer.writerow([
+                result["Structure"],
+                result["Mode"],
+                "Delete",
+                *[f"{x:.6f}" for x in result["Delete"]],
+                f"{result['AvgDelete']:.6f}"
+            ])
+
+
+def plot_results(results):
+    structures = [
+        "LinkedList",
+        "HashTable",
+        "BST"
+    ]
+    operations = [
+        "AvgInsert",
+        "AvgSearch",
+        "AvgDelete"
+    ]
+    titles = [
+        "Insert",
+        "Search",
+        "Delete"
+    ]
+    fig, axes = plt.subplots(
+        1,
+        3,
+        figsize=(18, 6)
+    )
+    for ax, operation, title in zip(
+        axes,
+        operations,
+        titles
+    ):
+        x = np.arange(len(structures))
+        width = 0.35
+        random_vals = []
+        sorted_vals = []
+        for structure in structures:
+            for result in results:
+                if (
+                    result["Structure"] == structure
+                    and result["Mode"] == "random"
+                ):
+                    random_vals.append(
+                        result[operation]
+                    )
+                if (
+                    result["Structure"] == structure
+                    and result["Mode"] == "sorted"
+                ):
+                    sorted_vals.append(
+                        result[operation]
+                    )
+
+        ax.bar(
+            x - width / 2,
+            random_vals,
+            width,
+            label="Random"
+        )
+        ax.bar(
+            x + width / 2,
+            sorted_vals,
+            width,
+            label="Sorted"
+        )
+        ax.set_xticks(x)
+        ax.set_xticklabels(structures)
+        ax.set_ylabel("Time (sec)")
+        ax.set_title(title)
+        ax.legend()
+        ax.grid(True)
+    plt.tight_layout()
+    plt.savefig(
+        "docs/performance_comparison.png",
+        dpi=300
+    )
+    plt.show()
+
+
+if __name__ == "__main__":
+    print("\nTesting data structures...\n")
+    results = run_experiment(N=10000)
+    save_to_csv(results)
+    plot_results(results)
+    print("\nResults saved:")
+    print("docs/results.csv")
+    print("docs/performance_comparison.png")
+    print("\nConclusions:\n")
+    print(
+        "1. LinkedList is the slowest structure "
+        "for searching."
+    )
+
+    print(
+        "2. HashTable shows the best "
+        "search performance."
+    )
+
+    print(
+        "3. BST works well on random data."
+    )
+
+    print(
+        "4. Sorted data causes BST degradation."
+    )
+
+    print(
+        "5. HashTable is best for frequent search."
+    )
+
+    print(
+        "6. BST is useful for ordered data."
+    )