11.11企业画像推荐

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

# 假设我们有一个企业数据集，包括企业描述和推荐产品
data = {
    'company_description': ['公司A专注于科技研发...', '公司B是一家制造企业...'],
    'recommended_products': ['产品X', '产品Y']
}

df = pd.DataFrame(data)

# 使用TF-IDF向量化企业描述
tfidf = TfidfVectorizer(stop_words='english')
df['company_description'] = df['company_description'].fillna('')
tfidf_matrix = tfidf.fit_transform(df['company_description'])

# 计算企业描述之间的相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[df['recommended_products'] == 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]  # 取前两个最相似的企业
    product_indices = [i[0] for i in sim_scores]
    return df['recommended_products'].iloc[product_indices]

# 测试推荐函数
print(get_recommendations('产品X'))