データ圧縮をマスターする：Pythonでのハフマン符号化の詳細な探求

            
from collections import Counter

def calculate_frequencies(text):
    return Counter(text)

            

              
                Copy
              
            
          

            
import heapq

class Node:
    def __init__(self, char, freq, left=None, right=None):
        self.char = char
        self.freq = freq
        self.left = left
        self.right = right

    # Define comparison methods for heapq
    def __lt__(self, other):
        return self.freq < other.freq

    def __eq__(self, other):
        if(other == None):
            return False
        if(not isinstance(other, Node)):
            return False
        return self.freq == other.freq

def build_huffman_tree(frequencies):
    priority_queue = []
    for char, freq in frequencies.items():
        heapq.heappush(priority_queue, Node(char, freq))

    while len(priority_queue) > 1:
        left_child = heapq.heappop(priority_queue)
        right_child = heapq.heappop(priority_queue)

        merged_node = Node(None, left_child.freq + right_child.freq, left_child, right_child)
        heapq.heappush(priority_queue, merged_node)

    return priority_queue[0] if priority_queue else None

            

              
                Copy
              
            
          

            
def generate_huffman_codes(node, current_code="", codes={}):
    if node is None:
        return

    # If it's a leaf node, store the character and its code
    if node.char is not None:
        codes[node.char] = current_code
        return

    # Traverse left (assign '0')
    generate_huffman_codes(node.left, current_code + "0", codes)
    # Traverse right (assign '1')
    generate_huffman_codes(node.right, current_code + "1", codes)

    return codes

            

              
                Copy
              
            
          

            
def encode(text, codes):
    encoded_text = ""
    for char in text:
        encoded_text += codes[char]
    return encoded_text

def decode(encoded_text, root_node):
    decoded_text = ""
    current_node = root_node
    for bit in encoded_text:
        if bit == '0':
            current_node = current_node.left
        else: # bit == '1'
            current_node = current_node.right

        # If we reached a leaf node
        if current_node.char is not None:
            decoded_text += current_node.char
            current_node = root_node # Reset to root for next character
    return decoded_text

            

              
                Copy
              
            
          

            
import heapq
from collections import Counter

class HuffmanNode:
    def __init__(self, char, freq, left=None, right=None):
        self.char = char
        self.freq = freq
        self.left = left
        self.right = right

    def __lt__(self, other):
        return self.freq < other.freq

class HuffmanCoding:
    def __init__(self, text):
        self.text = text
        self.frequencies = self._calculate_frequencies(text)
        self.root = self._build_huffman_tree(self.frequencies)
        self.codes = self._generate_huffman_codes(self.root)

    def _calculate_frequencies(self, text):
        return Counter(text)

    def _build_huffman_tree(self, frequencies):
        priority_queue = []
        for char, freq in frequencies.items():
            heapq.heappush(priority_queue, HuffmanNode(char, freq))

        while len(priority_queue) > 1:
            left_child = heapq.heappop(priority_queue)
            right_child = heapq.heappop(priority_queue)

            merged_node = HuffmanNode(None, left_child.freq + right_child.freq, left_child, right_child)
            heapq.heappush(priority_queue, merged_node)

        return priority_queue[0] if priority_queue else None

    def _generate_huffman_codes(self, node, current_code="", codes={}):
        if node is None:
            return

        if node.char is not None:
            codes[node.char] = current_code
            return

        self._generate_huffman_codes(node.left, current_code + "0", codes)
        self._generate_huffman_codes(node.right, current_code + "1", codes)

        return codes

    def encode(self):
        encoded_text = ""
        for char in self.text:
            encoded_text += self.codes[char]
        return encoded_text

    def decode(self, encoded_text):
        decoded_text = ""
        current_node = self.root
        for bit in encoded_text:
            if bit == '0':
                current_node = current_node.left
            else: # bit == '1'
                current_node = current_node.right

            if current_node.char is not None:
                decoded_text += current_node.char
                current_node = self.root
        return decoded_text

# Example Usage:
text_to_compress = "this is a test of huffman coding in python. it is a global concept."
huffman = HuffmanCoding(text_to_compress)

encoded_data = huffman.encode()
print(f"Original Text: {text_to_compress}")
print(f"Encoded Data: {encoded_data}")
print(f"Original Size (approx bits): {len(text_to_compress) * 8}")
print(f"Compressed Size (bits): {len(encoded_data)}")

decoded_data = huffman.decode(encoded_data)
print(f"Decoded Text: {decoded_data}")

# Verification
assert text_to_compress == decoded_data

            

              
                Copy