12.12企业画像推荐

import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity

# 假设我们有一个包含企业画像数据的DataFrame
enterprise_profiles = pd.DataFrame({
    'enterprise_id': [1, 2, 3],
    'industry': ['Tech', 'Finance', 'Retail'],
    'revenue': [1000, 500, 800],
    'credit_score': [750, 800, 700]
})

# 另一个包含产品信息的DataFrame
products = pd.DataFrame({
    'product_id': [101, 102, 103],
    'industry_focus': ['Tech', 'Finance', 'All'],
    'price_range': ['High', 'Medium', 'Low']
})

# 计算企业画像与产品的相似度
similarity_matrix = cosine_similarity(enterprise_profiles[['industry', 'revenue', 'credit_score']],
                                       products[['industry_focus', 'price_range']])

# 基于相似度进行推荐
recommendations = []
for i, row in similarity_matrix.iterrows():
    recommended_product_index = row.argmax()
    recommendations.append(products.iloc[recommended_product_index]['product_id'])

print(f"Recommended products for enterprise {enterprise_profiles['enterprise_id'][i]}: {recommendations}")