【无标题】ngram

from collections import Counter

def generate_ngrams(text, n):
    # 将文本拆分成单词
    words = text.split()
    
    # 创建一个空列表来存储N-gram
    ngrams = []
    
    # 用于生成N-gram的循环
    for i in range(len(words) - n + 1):
        # 将连续的n个单词连接成一个N-gram
        ngram = ' '.join(words[i:i + n])
        ngrams.append(ngram)
    
    return ngrams

def count_ngrams(ngrams):
    # 使用Counter统计N-gram的频率
    return Counter(ngrams)

# 示例文本
text = "The quick brown fox jumps over the lazy dog. The quick brown fox is fast."

# 生成和统计二元组（bigram）
n = 2
bigrams = generate_ngrams(text, n)
bigram_freq = count_ngrams(bigrams)

# 输出结果
print("Bigrams and their frequencies:")
for bigram, freq in bigram_freq.items():
    print(f"{bigram}: {freq}")

# 生成和统计三元组（trigram）
n = 3
trigrams = generate_ngrams(text, n)
trigram_freq = count_ngrams(trigrams)

# 输出结果
print("\nTrigrams and their frequencies:")
for trigram, freq in trigram_freq.items():
    print(f"{trigram}: {freq}")