全面的 Python 数据结构备忘单

全面的 Python 数据结构备忘单

目录

1. 列表
2. 元组
3. 套装
4. 词典
5. 字符串
6. 数组
7. 堆栈
8. 队列
9. 链接列表
10. 树
11. 堆
12. 图表
13. 高级数据结构

列表

列表是有序的、可变的序列。

创建

empty_list = []
list_with_items = [1, 2, 3]
list_from_iterable = list("abc")
list_comprehension = [x for x in range(10) if x % 2 == 0]

常用操作

# Accessing elements
first_item = my_list[0]
last_item = my_list[-1]

# Slicing
subset = my_list[1:4]  # Elements 1 to 3
reversed_list = my_list[::-1]

# Adding elements
my_list.append(4)  # Add to end
my_list.insert(0, 0)  # Insert at specific index
my_list.extend([5, 6, 7])  # Add multiple elements

# Removing elements
removed_item = my_list.pop()  # Remove and return last item
my_list.remove(3)  # Remove first occurrence of 3
del my_list[0]  # Remove item at index 0

# Other operations
length = len(my_list)
index = my_list.index(4)  # Find index of first occurrence of 4
count = my_list.count(2)  # Count occurrences of 2
my_list.sort()  # Sort in place
sorted_list = sorted(my_list)  # Return new sorted list
my_list.reverse()  # Reverse in place

先进技术

# List as stack
stack = [1, 2, 3]
stack.append(4)  # Push
top_item = stack.pop()  # Pop

# List as queue (not efficient, use collections.deque instead)
queue = [1, 2, 3]
queue.append(4)  # Enqueue
first_item = queue.pop(0)  # Dequeue

# Nested lists
matrix = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
flattened = [item for sublist in matrix for item in sublist]

# List multiplication
repeated_list = [0] * 5  # [0, 0, 0, 0, 0]

# List unpacking
a, *b, c = [1, 2, 3, 4, 5]  # a=1, b=[2, 3, 4], c=5

元组

元组是有序的、不可变的序列。

创建

empty_tuple = ()
single_item_tuple = (1,)  # Note the comma
tuple_with_items = (1, 2, 3)
tuple_from_iterable = tuple("abc")

常用操作

# Accessing elements (similar to lists)
first_item = my_tuple[0]
last_item = my_tuple[-1]

# Slicing (similar to lists)
subset = my_tuple[1:4]

# Other operations
length = len(my_tuple)
index = my_tuple.index(2)
count = my_tuple.count(3)

# Tuple unpacking
a, b, c = (1, 2, 3)

先进技术

# Named tuples
from collections import namedtuple
Point = namedtuple('Point', ['x', 'y'])
p = Point(11, y=22)
print(p.x, p.y)

# Tuple as dictionary keys (immutable, so allowed)
dict_with_tuple_keys = {(1, 2): 'value'}

套

集合是独特元素的无序集合。

创建

empty_set = set()
set_with_items = {1, 2, 3}
set_from_iterable = set([1, 2, 2, 3, 3])  # {1, 2, 3}
set_comprehension = {x for x in range(10) if x % 2 == 0}

常用操作

# Adding elements
my_set.add(4)
my_set.update([5, 6, 7])

# Removing elements
my_set.remove(3)  # Raises KeyError if not found
my_set.discard(3)  # No error if not found
popped_item = my_set.pop()  # Remove and return an arbitrary element

# Other operations
length = len(my_set)
is_member = 2 in my_set

# Set operations
union = set1 | set2
intersection = set1 & set2
difference = set1 - set2
symmetric_difference = set1 ^ set2

先进技术

# Frozen sets (immutable)
frozen = frozenset([1, 2, 3])

# Set comparisons
is_subset = set1 <= set2
is_superset = set1 >= set2
is_disjoint = set1.isdisjoint(set2)

# Set of sets (requires frozenset)
set_of_sets = {frozenset([1, 2]), frozenset([3, 4])}

词典

字典是键值对的可变映射。

创建

empty_dict = {}
dict_with_items = {'a': 1, 'b': 2, 'c': 3}
dict_from_tuples = dict([('a', 1), ('b', 2), ('c', 3)])
dict_comprehension = {x: x**2 for x in range(5)}

常用操作

# Accessing elements
value = my_dict['key']
value = my_dict.get('key', default_value)

# Adding/Updating elements
my_dict['new_key'] = value
my_dict.update({'key1': value1, 'key2': value2})

# Removing elements
del my_dict['key']
popped_value = my_dict.pop('key', default_value)
last_item = my_dict.popitem()  # Remove and return an arbitrary key-value pair

# Other operations
keys = my_dict.keys()
values = my_dict.values()
items = my_dict.items()
length = len(my_dict)
is_key_present = 'key' in my_dict

先进技术

# Dictionary unpacking
merged_dict = {**dict1, **dict2}

# Default dictionaries
from collections import defaultdict
dd = defaultdict(list)
dd['key'].append(1)  # No KeyError

# Ordered dictionaries (Python 3.7+ dictionaries are ordered by default)
from collections import OrderedDict
od = OrderedDict([('a', 1), ('b', 2), ('c', 3)])

# Counter
from collections import Counter
c = Counter(['a', 'b', 'c', 'a', 'b', 'b'])
print(c.most_common(2))  # [('b', 3), ('a', 2)]

弦乐

字符串是不可变的 Unicode 字符序列。

创建

single_quotes = 'Hello'
double_quotes = "World"
triple_quotes = '''Multiline
string'''
raw_string = r'C:\Users\name'
f_string = f"The answer is {40 + 2}"

常用操作

# Accessing characters
first_char = my_string[0]
last_char = my_string[-1]

# Slicing (similar to lists)
substring = my_string[1:4]

# String methods
upper_case = my_string.upper()
lower_case = my_string.lower()
stripped = my_string.strip()
split_list = my_string.split(',')
joined = ', '.join(['a', 'b', 'c'])

# Other operations
length = len(my_string)
is_substring = 'sub' in my_string
char_count = my_string.count('a')

先进技术

# String formatting
formatted = "{} {}".format("Hello", "World")
formatted = "%s %s" % ("Hello", "World")

# Regular expressions
import re
pattern = r'\d+'
matches = re.findall(pattern, my_string)

# Unicode handling
unicode_string = u'\u0061\u0062\u0063'

数组

数组是紧凑的数值序列（来自数组模块）。

创建和使用

from array import array
int_array = array('i', [1, 2, 3, 4, 5])
float_array = array('f', (1.0, 1.5, 2.0, 2.5))

# Operations (similar to lists)
int_array.append(6)
int_array.extend([7, 8, 9])
popped_value = int_array.pop()

堆栈

堆栈可以使用lists或collections.deque来实现。

实施和使用

# Using list
stack = []
stack.append(1)  # Push
stack.append(2)
top_item = stack.pop()  # Pop

# Using deque (more efficient)
from collections import deque
stack = deque()
stack.append(1)  # Push
stack.append(2)
top_item = stack.pop()  # Pop

队列

队列可以使用collections.deque或queue.Queue来实现。

实施和使用

# Using deque
from collections import deque
queue = deque()
queue.append(1)  # Enqueue
queue.append(2)
first_item = queue.popleft()  # Dequeue

# Using Queue (thread-safe)
from queue import Queue
q = Queue()
q.put(1)  # Enqueue
q.put(2)
first_item = q.get()  # Dequeue

链表

Python没有内置链表，但可以实现。

实施简单

class Node:
    def __init__(self, data):
        self.data = data
        self.next = None

class LinkedList:
    def __init__(self):
        self.head = None

    def append(self, data):
        if not self.head:
            self.head = Node(data)
            return
        current = self.head
        while current.next:
            current = current.next
        current.next = Node(data)

树木

树可以使用自定义类来实现。

简单的二叉树实现

class TreeNode:
    def __init__(self, value):
        self.value = value
        self.left = None
        self.right = None

class BinaryTree:
    def __init__(self, root):
        self.root = TreeNode(root)

    def insert(self, value):
        self._insert_recursive(self.root, value)

    def _insert_recursive(self, node, value):
        if value < node.value:
            if node.left is None:
                node.left = TreeNode(value)
            else:
                self._insert_recursive(node.left, value)
        else:
            if node.right is None:
                node.right = TreeNode(value)
            else:
                self._insert_recursive(node.right, value)

堆

堆可以使用 heapq 模块来实现。

用法

import heapq

# Create a heap
heap = []
heapq.heappush(heap, 3)
heapq.heappush(heap, 1)
heapq.heappush(heap, 4)

# Pop smallest item
smallest = heapq.heappop(heap)

# Create a heap from a list
my_list = [3, 1, 4, 1, 5, 9]
heapq.heapify(my_list)

图表

图可以使用字典来实现。

实施简单

class Graph:
    def __init__(self):
        self.graph = {}

    def add_edge(self, u, v):
        if u not in self.graph:
            self.graph[u] = []
        self.graph[u].append(v)

    def bfs(self, start):
        visited = set()
        queue = [start]
        visited.add(start)
        while queue:
            vertex = queue.pop(0)
            print(vertex, end=' ')
            for neighbor in self.graph.get(vertex, []):
                if neighbor not in visited:
                    visited.add(neighbor)
                    queue.append(neighbor)

高级数据结构

特里树

class TrieNode:
    def __init__(self):
        self.children = {}
        self.is_end = False

class Trie:
    def __init__(self):
        self.root = TrieNode()

    def insert(self, word):
        node = self.root
        for char in word:
            if char not in node.children:
                node.children[char] = TrieNode()
            node = node.children[char]
        node.is_end = True

    def search(self, word):
        node = self.root
        for char in word:
            if char not in node.children:
                return False
            node = node.children[char]
        return node.is_end

不相交集（并查集）

class DisjointSet:
    def __init__(self, vertices):
        self.parent = {v: v for v in vertices}
        self.rank = {v: 0 for v in vertices}

    def find(self, item):
        if self.parent[item] != item:
            self.parent[item] = self.find(self.parent[item])
        return self.parent[item]

    def union(self, x, y):
        xroot = self.find(x)
        yroot = self.find(y)
        if self.rank[xroot] < self.rank[yroot]:
            self.parent[xroot] = yroot
        elif self.rank[xroot] > self.rank[yroot]:
            self.parent[yroot] = xroot
        else:
            self.parent[yroot] = xroot
            self.rank[xroot] += 1

这份全面的备忘单涵盖了广泛的 Python 数据结构，从基本的内置类型到更高级的自定义实现。每个部分都包含创建方法、常用操作以及适用的高级技术。
0

以上是全面的 Python 数据结构备忘单的详细内容。更多信息请关注PHP中文网其他相关文章！