从文档集中提取TF-IDF值的降序排位前200的词汇

好的，以下是提取TF-IDF值降序排位前200的词汇的Python代码：

import os
import math
from collections import Counter

# 计算TF值
def compute_tf(word_freq, doc_words):
    tf_dict = {}
    doc_word_count = len(doc_words)
    for word, freq in word_freq.items():
        tf_dict[word] = freq / float(doc_word_count)
    return tf_dict

# 计算IDF值
def compute_idf(doc_list):
    idf_dict = {}
    n = len(doc_list)

    # 统计每个词在多少篇文档中出现过
    idf_dict = dict.fromkeys(doc_list[0].keys(), 0)
    for doc in doc_list:
        for word, count in doc.items():
            if count > 0:
                idf_dict[word] += 1

    # 计算每个词的IDF值
    for word, count in idf_dict.items():
        idf_dict[word] = math.log(n / float(count))

    return idf_dict

# 计算TF-IDF值
def compute_tfidf(tf_dict, idf_dict):
    tfidf_dict = {}
    for word, tf in tf_dict.items():
        tfidf_dict[word] = tf * idf_dict[word]
    return tfidf_dict

# 读取文档集
doc_list = []
for filename in os.listdir('./docs'):
    with open(os.path.join('./docs', filename), 'r') as f:
        doc_words = f.read().lower().split()
        word_freq = dict(Counter(doc_words))
        doc_list.append(word_freq)

# 计算每个文档中每个词的TF-IDF值
tfidf_list = []
for doc in doc_list:
    tf_dict = compute_tf(doc, doc_words)
    idf_dict = compute_idf(doc_list)
    tfidf_dict = compute_tfidf(tf_dict, idf_dict)
    tfidf_list.append(tfidf_dict)

# 统计每个词在整个文档集中的TF-IDF值
word_tfidf = {}
for tfidf_dict in tfidf_list:
    for word, tfidf in tfidf_dict.items():
        if word in word_tfidf:
            word_tfidf[word] += tfidf
        else:
            word_tfidf[word] = tfidf

# 将TF-IDF值降序排列并输出前200个词汇
sorted_word_tfidf = sorted(word_tfidf.items(), key=lambda x: x[1], reverse=True)
for word, tfidf in sorted_word_tfidf[:200]:
    print(word, tfidf)

需要注意的是，这段代码假设文档集都存储在`./docs`目录下，每个文档都是纯文本文件。你需要根据自己的情况修改相应的路径和文件格式。