12.12企业搜索推荐

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# 示例数据
data = {
    'item_id': [1, 2, 3],
    'title': ['Python教程', 'Java编程入门', '数据分析实战'],
    'description': ['学习Python编程的基础知识...', '掌握Java编程的核心技能...', '深入理解数据分析的实战应用...']
}
df = pd.DataFrame(data)

# 文本预处理
tfidf = TfidfVectorizer(stop_words='english')
df['description'] = df['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(df['description'])

# 计算相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[df['title'] == title].tolist()[0]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:3]  # 取前两个最相似的项目
    item_indices = [i[0] for i in sim_scores]
    return df['title'].iloc[item_indices]

# 示例调用
print(get_recommendations('Python教程'))