You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 lines
1.2 KiB
33 lines
1.2 KiB
6 months ago
|
import csv
|
||
|
|
|
||
|
|
import pandas as pd
|
||
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
||
|
|
from sklearn.metrics.pairwise import cosine_similarity
|
||
|
|
|
||
|
|
def tf_idf(items, user):
|
||
|
|
# 数据载入
|
||
|
|
articles = items
|
||
|
|
|
||
|
|
df = pd.DataFrame(articles)
|
||
|
|
|
||
|
|
# 提取TF-IDF特征
|
||
|
|
tfidf_vectorizer = TfidfVectorizer()
|
||
|
|
tfidf_matrix = tfidf_vectorizer.fit_transform(df['content'])
|
||
|
|
|
||
|
|
# 计算余弦相似度
|
||
|
|
cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
|
||
|
|
|
||
|
|
# 根据相似度推荐
|
||
|
|
def recommend_articles(article_id, user, cosine_sim=cosine_sim):
|
||
|
|
sim_scores = list(enumerate(cosine_sim[article_id - 1]))
|
||
|
|
sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
|
||
|
|
sim_scores = sim_scores[1:6] # 推荐前5个相似文章
|
||
|
|
article_indices = [i[0] for i in sim_scores]
|
||
|
|
with open('collections/{}.csv'.format(user), 'a+', encoding='utf-8',newline='') as f:
|
||
|
|
write=csv.DictWriter(f,fieldnames=['文章ID','content','时间','收藏数量','喜欢数量','图片资源'])
|
||
|
|
for j in article_indices:
|
||
|
|
write.writerow(items[j])
|
||
|
|
|
||
|
|
|
||
|
|
# 推荐与文章ID为1的旅游攻略相似的文章
|
||
|
|
recommend_articles(1,user)
|