【自然语言】使用词袋模型，TF-IDF模型和Word2Vec模型进行文本向量化

一、任务目标

python代码写将 HarryPorter 电子书作为语料库，分别使用词袋模型，TF-IDF模型和Word2Vec模型进行文本向量化。

1. 首先将数据预处理，Word2Vec 训练时要求考虑每个单词前后的五个词汇，地址为

作为其上下文，生成的向量维度为50维

2.分别搜索 courtroom 和 wizard 这两个词语义最近的5个单词

3.对wizard 和witch 这两个单词在二维平面上进行可视化

二、代码部分

nltk.download('punkt')
nltk.download('stopwords')

from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from gensim.models import Word2Vec
from gensim.models import TfidfModel
from gensim.corpora import Dictionary
import matplotlib.pyplot as plt# 导入停用词
stop_words = set(stopwords.words('english'))# 加载数据
corpus_file = '/Users/zhengyawen/Downloads/HarryPorter.txt'
with open(corpus_file, 'r', encoding='utf-8') as file:data = file.read()# 预处理数据
sentences = [word_tokenize(sentence.lower()) for sentence in data.split('.')]
preprocessed_sentences = []
for sentence in sentences:valid_words = []for word in sentence:if word.isalpha() and word not in stop_words:valid_words.append(word)preprocessed_sentences.append(valid_words)# 构建Word2Vec模型
w2v_model = Word2Vec(sentences=preprocessed_sentences, vector_size=50, window=5, min_count=1, sg=0)# 获取单词向量
vector_courtroom = w2v_model.wv['courtroom']
vector_wizard = w2v_model.wv['wizard']# 搜索与“courtroom”和“wizard”最相似的5个单词
similar_words_courtroom = w2v_model.wv.most_similar('courtroom', topn=5)
similar_words_wizard = w2v_model.wv.most_similar('wizard', topn=5)print("Word2Vec模型:")
print("单词 courtroom 的向量:", vector_courtroom)
print("单词 wizard 的向量:", vector_wizard)
print("语义最近的5个单词 (courtroom):")
for word, similarity in similar_words_courtroom:print(f"{word}: {similarity}")print("\n语义最近的5个单词 (wizard):")
for word, similarity in similar_words_wizard:print(f"{word}: {similarity}")# 构建词袋模型
dictionary = Dictionary(preprocessed_sentences)
corpus = [dictionary.doc2bow(sentence) for sentence in preprocessed_sentences]
tfidf_model = TfidfModel(corpus)
corpus_tfidf = tfidf_model[corpus]# 可视化Word2Vec模型中wizard和witch的向量
words_to_plot = ['wizard', 'witch']
word_vectors = [w2v_model.wv[word] for word in words_to_plot]# 可视化
plt.figure(figsize=(10, 6))
for i, word in enumerate(words_to_plot):plt.scatter(word_vectors[i][0], word_vectors[i][1], label=word)plt.xlabel('Dimension 1')
plt.ylabel('Dimension 2')
plt.title('Visualization of Word Vectors')
plt.legend()
plt.show()