MongoDBを使用してデータのインテリジェントなレコメンド機能を実装する方法

{
  user_id: "用户ID",
  item_id: "物品ID",
  rate: "用户对物品的评分",
  timestamp: "评分时间"
}

{
  item_id: "物品ID",
  features: ["物品特征1", "物品特征2", "物品特征3", ...]
}

from pymongo import MongoClient

client = MongoClient()
db = client['recommendation']
collection = db['ratings']

data = [
  {"user_id": "user1", "item_id": "item1", "rate": 4, "timestamp": "2019-01-01"},
  {"user_id": "user1", "item_id": "item2", "rate": 5, "timestamp": "2019-01-01"},
  {"user_id": "user2", "item_id": "item1", "rate": 3, "timestamp": "2019-01-02"},
  {"user_id": "user2", "item_id": "item3", "rate": 2, "timestamp": "2019-01-02"},
  ...
]

collection.insert_many(data)

from pymongo import MongoClient

client = MongoClient()
db = client['recommendation']
collection = db['items']

data = [
  {"item_id": "item1", "features": ["特征1", "特征2", "特征3", ...]},
  {"item_id": "item2", "features": ["特征4", "特征5", "特征6", ...]},
  {"item_id": "item3", "features": ["特征7", "特征8", "特征9", ...]},
  ...
]

collection.insert_many(data)

from pymongo import MongoClient

client = MongoClient()
db = client['recommendation']
collection = db['ratings']

def user_based_recommendation(user_id, top_k):
    user_ratings = collection.find({"user_id": user_id}).sort('rate', -1).limit(top_k)
    recommended_items = []
    for rating in user_ratings:
        item_ratings = collection.find({"item_id": rating["item_id"]}).sort('rate', -1).limit(top_k)
        for item_rating in item_ratings:
            if item_rating["user_id"] != user_id and item_rating["item_id"] not in recommended_items:
                recommended_items.append(item_rating["item_id"])
                break
    return recommended_items

user_id = "user1"
top_k = 10
recommended_items = user_based_recommendation(user_id, top_k)
print(recommended_items)

from pymongo import MongoClient

client = MongoClient()
db = client['recommendation']
collection = db['items']

def content_based_recommendation(items, top_k):
    recommended_items = []
    for item in items:
        item_features = collection.find_one({"item_id": item["item_id"]})["features"]
        similar_items = collection.find({"features": {"$in": item_features}}).sort('item_id', 1).limit(top_k)
        for similar_item in similar_items:
            if similar_item["item_id"] != item["item_id"] and similar_item["item_id"] not in recommended_items:
                recommended_items.append(similar_item["item_id"])
    return recommended_items

items = [
  {"item_id": "item1", "features": ["特征1", "特征2", "特征3"]},
  {"item_id": "item2", "features": ["特征4", "特征5", "特征6"]},
  ...
]

top_k = 10
recommended_items = content_based_recommendation(items, top_k)
print(recommended_items)