Python Counter计数器详解 - 词频统计与数据分析教程

from collections import Counter

# 从可迭代对象创建
c = Counter(iterable)

# 从关键字参数创建
c = Counter(a=3, b=2, c=1)

# 从字典创建
c = Counter({"a": 3, "b": 2})

from collections import Counter

# 从字符串创建
c1 = Counter("abracadabra")
print(f"字符串计数: {c1}")
print(f"最常见的3个: {c1.most_common(3)}")

# 从列表创建
c2 = Counter(["apple", "banana", "apple", "cherry", "banana", "apple"])
print(f"\n列表计数: {c2}")

# 访问计数
print(f"apple出现次数: {c2['apple']}")
print(f"orange出现次数: {c2['orange']}")  # 不存在返回0，不引发KeyError

# elements() 获取所有元素
elements = list(c2.elements())
print(f"\n所有元素: {elements}")

字符串计数: Counter({'a': 5, 'b': 2, 'r': 2, 'c': 1, 'd': 1})
最常见的3个: [('a', 5), ('b', 2), ('r', 2)]

列表计数: Counter({'apple': 3, 'banana': 2, 'cherry': 1})
apple出现次数: 3
orange出现次数: 0

所有元素: ['apple', 'apple', 'apple', 'banana', 'banana', 'cherry']

from collections import Counter

c1 = Counter(a=3, b=2, c=1)
c2 = Counter(a=1, b=3, d=2)

print(f"c1: {c1}")
print(f"c2: {c2}")

# 加法：合并计数
print(f"\nc1 + c2: {c1 + c2}")

# 减法：相减（忽略负数和零）
print(f"c1 - c2: {c1 - c2}")

# 交集：取最小值
print(f"c1 & c2: {c1 & c2}")

# 并集：取最大值
print(f"c1 | c2: {c1 | c2}")

# update 和 subtract
c3 = Counter(a=3, b=2)
c3.update({"a": 2, "c": 1})
print(f"\nupdate后: {c3}")

c4 = Counter(a=3, b=2)
c4.subtract({"a": 1, "b": 3})
print(f"subtract后: {c4}")  # b=-1 允许负数

c1: Counter({'a': 3, 'b': 2, 'c': 1})
c2: Counter({'b': 3, 'd': 2, 'a': 1})

c1 + c2: Counter({'a': 4, 'b': 5, 'd': 2, 'c': 1})
c1 - c2: Counter({'a': 2, 'c': 1})
c1 & c2: Counter({'a': 1, 'b': 2})
c1 | c2: Counter({'a': 3, 'b': 3, 'd': 2, 'c': 1})

update后: Counter({'a': 5, 'b': 2, 'c': 1})
subtract后: Counter({'a': 2, 'b': -1})

from collections import Counter
import re

class TextAnalyzer:
    """文本分析工具"""

    def __init__(self, text):
        self.text = text
        self.words = re.findall(r'\b\w+\b', text.lower())

    def word_frequency(self, top_n=10):
        """词频统计"""
        return Counter(self.words).most_common(top_n)

    def char_frequency(self):
        """字符频率统计"""
        return Counter(self.text)

    def word_count(self):
        """总词数"""
        return len(self.words)

    def unique_words(self):
        """不重复词数"""
        return len(set(self.words))

    def compare(self, other_text):
        """比较两段文本的词汇重叠度"""
        other_words = set(re.findall(r'\b\w+\b', other_text.lower()))
        common = set(self.words) & other_words
        ratio = len(common) / len(set(self.words)) if self.words else 0
        return len(common), ratio

# 使用示例
text1 = "Python is a great programming language. Python is easy to learn. Python is powerful."
text2 = "Java is a popular programming language. Java is widely used in enterprise."

analyzer = TextAnalyzer(text1)

print("词频统计:")
for word, count in analyzer.word_frequency(5):
    print(f"  {word}: {count}")

print(f"\n总词数: {analyzer.word_count()}")
print(f"不重复词数: {analyzer.unique_words()}")

common, ratio = analyzer.compare(text2)
print(f"\n与text2共同词汇: {common}个, 重叠率: {ratio:.1%}")

词频统计:
  python: 3
  is: 3
  a: 1
  great: 1
  programming: 1

总词数: 13
不重复词数: 9

与text2共同词汇: 4个, 重叠率: 44.4%