Looker 데이터 소스에 대해 작성된 컨텍스트로 에이전트 동작 안내

이 페이지에서는 Looker의 Conversational Analytics API 데이터 에이전트에 효과적인 프롬프트를 작성하기 위한 권장 구조를 설명합니다. 이러한 프롬프트는 system_instruction 매개변수를 사용하여 문자열로 정의하는 작성된 컨텍스트입니다.

Looker의 작성된 컨텍스트에 대해 알아야 할 사항

Looker 개발자는 LookML 매개변수를 사용하여 Looker 모델에서 직접 일부 컨텍스트를 정의할 수도 있습니다. 데이터 에이전트는 시스템 안내의 주요 정의에서 이를 다시 정의하지 않아도 이러한 LookML 정의에서 적절한 컨텍스트를 수집합니다.

데이터 에이전트는 다음 LookML 매개변수에서 컨텍스트를 도출할 수 있습니다.

  • description: 이 LookML 매개변수는 필드에만 설명을 정의하며, 이는 fields 및 measures 키에서 정의할 수 있는 설명에 해당합니다.
  • synonyms: 이 LookML 매개변수는 필드의 동의어만 정의하며, 이는 fields 및 measures 키에서 정의할 수 있는 동의어에 해당합니다.
  • relationship: 이 LookML 매개변수는 조인된 뷰 간의 join 관계를 정의합니다.

시스템 요청 사항의 주요 구성요소 예시

다음 섹션에는 Looker의 시스템 안내 주요 구성요소의 예가 포함되어 있습니다. 이러한 키에는 다음이 포함됩니다.

이러한 주요 구성요소에 관한 설명은 작성된 컨텍스트로 에이전트 동작 안내 문서 페이지를 참고하세요.

tables로 데이터 설명하기

다음 YAML 코드 블록은 테이블 order_items의 tables 키의 기본 구조를 보여줍니다.

- tables:
  - table:
    - name: order_items
    - tags:
      - ecommerce
      - transaction

fields를 사용하여 일반적으로 사용되는 필드 설명

다음 샘플 YAML 코드는 orders_items 테이블의 total_sale_price, total_gross_margin, created_month_name, 30_day_repeat_purchase_rate, count과 같은 주요 필드를 설명합니다.

- tables:
  - table:
    - name: order_items
    - synonyms:
        - sales
        - line items
        - items sold
        - orders
    - fields:
      - field:
        - name: total_sale_price
        - description: "The total monetary value from items sold. Corresponds to 'Revenue'."
        - aggregations: ['sum', 'avg']
      - field:
        - name: total_gross_margin
        - description: "Revenue minus the cost of goods sold. Corresponds to 'Profit'."
        - aggregations: ['sum', 'avg']
      - field:
        - name: created_month_name
        - description: "The month name when an order was created, used for monthly reporting."
      - field:
        - name: 30_day_repeat_purchase_rate
        - description: "Measures the likelihood of a customer to purchase again soon. Corresponds to 'Buying Propensity'."
        - aggregations: ['avg']
      - field:
        - name: count
        - description: "A count of order items."
        - aggregations: ['sum']

이 예에서는 synonyms 필드가 기본 LookML에 이미 정의되어 있으므로 여기에서 다시 정의할 필요가 없습니다.

measures로 비즈니스 측정항목 정의

예를 들어 다음과 같이 수입에서 비용을 뺀 값을 계산하는 테이블 계산 profit를 정의할 수 있습니다.

- tables:
  - table:
    - name: order_items
    - measures:
      - measure:
        - name: profit
        - description: Raw profit (earnings minus cost).
        - exp: earnings - cost
        - synonyms: gains

relationships로 테이블 조인 정의

예를 들어 주문 항목 탐색의 order_items 테이블과 users 테이블 간에 다음과 같이 order_items_to_users 관계를 정의할 수 있습니다.

- relationships:
    - relationship:
        - name: order_items_to_users
        - description: >-
            Connects customer order data to user information with the user_id and id fields to allow an aggregated view of sales by customer demographics.
        - relationship_type: many-to-one
        - join_type: left
        - left_table: order_items.order_items
        - right_table: order_items.users
        - relationship_columns:
            - left_column: user_id
            - right_column: id

golden_queries로 정확도 개선

예를 들어 order_items 테이블의 데이터에 대한 일반적인 분석의 골든 쿼리를 다음과 같이 정의할 수 있습니다.

- tables:
  - table:
    - golden_queries:
      - golden_query:
        - natural_language_query: What were total sales over the last year?
        - sql_query: >-
            SELECT SUM(total_sale_price) AS total_sales FROM order_items
            WHERE created_date >= '2024-01-01' AND created_date < '2025-01-01';

또는 다음과 같이 SQL 쿼리 대신 Looker 쿼리를 사용하여 골든 쿼리를 정의할 수 있습니다.

- tables:
  - table:
    - golden_queries:
      - question: what were total sales over the last year
        looker_query:
          model: thelook
          view: order_items
          fields:
          - order_items.total_sale_price
          filters:
            order_items.created_date: last year
          sorts: []
          limit: null
          query_timezone: America/Los_Angeles

golden_action_plans로 여러 단계의 작업 개요 작성

예를 들어 연령대별 주문 분류를 표시하는 작업 계획을 정의하고 SQL 쿼리 및 시각화 관련 단계에 관한 세부정보를 다음과 같이 포함할 수 있습니다.

- tables:
  - table:
    - golden_action_plans:
      - golden_action_plan:
        - natural_language_query: What is the correlation between customer age cohort and buying propensity?
        - action_plan:
          - step: "First, run a query in Looker to get the data needed for the analysis. You need to group by `users.age` (NOT AGE TIER) and calculate the average `order_items.30_day_repeat_purchase_rate` for each age."
          - step: "Then, pass the resulting data table to the Python tool. Use a library to create a scatter plot with a regression line to visualize the correlation between raw age and the average 30-day repeat purchase rate."

glossaries를 사용하여 비즈니스 용어 설명

예를 들어 다음과 같이 특정 비즈니스 컨텍스트에 따라 일반적인 비즈니스 상태 및 '단골 고객'과 같은 용어를 정의할 수 있습니다.

- glossaries:
  - glossary:
      - term: Loyal Customer
      - description: A customer who has made more than one purchase. Maps to the dimension 'user_order_facts.repeat_customer' being 'Yes'. High value loyal customers are those with high 'user_order_facts.lifetime_revenue'.
      - synonyms:
        - repeat customer
        - returning customer

additional_descriptions에 추가 안내 포함

예를 들어 additional_descriptions 키를 사용하여 다음과 같이 에이전트에 관한 정보를 제공할 수 있습니다.

- additional_descriptions:
    - text: The user is typically a Sales Manager, Product Manager, or Marketing Analyst. They need to understand performance trends, build customer lists for campaigns, and analyze product sales.

예: YAML을 사용하는 Looker의 시스템 안내

다음 예는 가상의 영업 분석가 에이전트에 대한 샘플 시스템 안내를 보여줍니다.

- system_instruction: >-
    You are an expert sales, product, and operations analyst for our e-commerce store. Your primary function is to answer questions by querying the 'Order Items' Explore. Always be concise and data-driven. When asked about 'revenue' or 'sales', use 'order_items.total_sale_price'. For 'profit' or 'margin', use 'order_items.total_gross_margin'. For 'customers' or 'users', use 'users.count'. The default date for analysis is 'order_items.created_date' unless specified otherwise.
- tables:
  - table:
      - name: order_items
      - synonyms:
          - sales
          - line items
          - items sold
          - orders
      - fields:
        - field:
          - name: user_id
        - field:
          - name: total_sale_price
          - description: "The total monetary value from items sold. Corresponds to 'Revenue'."
          - aggregations: ['sum', 'avg']
        - field:
          - name: total_gross_margin
          - description: "Revenue minus the cost of goods sold. Corresponds to 'Profit'."
          - aggregations: ['sum', 'avg']
        - field:
          - name: created_month_name
          - description: "The month name when an order was created, used for monthly reporting."
        - field:
          - name: 30_day_repeat_purchase_rate
          - description: "Measures the likelihood of a customer to purchase again soon. Corresponds to 'Buying Propensity'."
          - aggregations: ['avg']
        - field:
          - name: count
          - description: "A count of order items."
          - aggregations: ['sum']
      - measures:
        - measure:
          - name: profit
          - description: Raw profit (earnings minus cost).
          - exp: earnings - cost
          - synonyms: gains
      - golden_queries:
        - golden_query:
          - natural_language_query: what were total sales over the last year
          - sql_query: >-
              SELECT SUM(total_sale_price) AS total_sales FROM order_items
              WHERE created_date >= '2024-01-01' AND created_date < '2025-01-01';
        - golden_query:
          - natural_language_query: Show monthly profit for the last year, pivoted on product category for Jeans and Accessories.
          - sql_query: >-
              SELECT DATE_TRUNC(oi.created_date, MONTH) AS sale_month,
              SUM(CASE WHEN p.category = 'Jeans' THEN oi.total_gross_margin ELSE 0 END) AS "Jeans",
              SUM(CASE WHEN p.category = 'Accessories' THEN oi.total_gross_margin ELSE 0 END) AS "Accessories"
              FROM order_items AS oi
              INNER JOIN products AS p ON oi.product_id = p.id
              WHERE oi.created_date >= '2024-01-01' AND oi.created_date < '2025-01-01'
              AND p.category IN ('Jeans', 'Accessories')
              GROUP BY 1
              ORDER BY 1;
        - golden_query:
          - natural_language_query: How many items are still in 'Processing' status for more than 3 days, by Distribution Center?
          - sql_query: >-
              SELECT dc.name AS distribution_center, COUNT(oi.id) AS items_in_processing FROM order_items AS oi
              INNER JOIN distribution_centers AS dc ON oi.distribution_center_id = dc.id
              WHERE oi.status = 'Processing'
              AND oi.created_date < DATE_SUB(CURRENT_DATE(), INTERVAL 3 DAY)
              GROUP BY 1
              ORDER BY 2 DESC;
        - golden_query:
          - natural_language_query: What is the total revenue from new customers acquired this year?
          - sql_query: >-
              SELECT SUM(oi.total_sale_price) AS total_revenue_from_new_customers
              FROM order_items AS oi
              JOIN users AS u ON oi.user_id = u.id
              JOIN user_order_facts AS uof ON u.id = uof.user_id
              WHERE uof.first_order_year = EXTRACT(YEAR FROM CURRENT_DATE());
      - golden_action_plans:
        - golden_action_plan:
          - natural_language_query: whats the correlation between customer age cohort and buying propensity.
          - action_plan:
            - step: "First, run a query in Looker to get the data needed for the analysis. You need to group by `users.age` (NOT AGE TIER) and calculate the average `order_items.30_day_repeat_purchase_rate` for each age."
            - step: "Then, pass the resulting data table to the Python tool. Use a library to create a scatter plot with a regression line to visualize the correlation between raw age and the average 30-day repeat purchase rate."
  - table:
      - name: users
      - synonyms:
          - customers
          - shoppers
          - clients
          - purchasers
      - fields:
        - field:
          - name: id
        - field:
          - name: email
        - field:
          - name: state
        - field:
          - name: count
          - aggregations: ['sum']
  - table:
      - name: products
      - synonyms:
          - items
          - merchandise
          - SKUs
      - fields:
        - field:
          - name: category
          - description: "The category of the product (e.g., Jeans, Accessories)."
        - field:
          - name: brand
          - description: "The brand name of the product."
  - table:
    - name: inventory_items
    - synonyms:
        - stock
        - inventory
        - on-hand
    - fields:
      - field:
        - name: total_cost
        - description: "The total cost of items in inventory."
        - aggregations: ['sum']
    - golden_queries:
      - golden_query:
        - natural_language_query: "Show me total cost of unsold inventory for the 'Outerwear' category"
        - sql_query: >-
            SELECT SUM(ii.total_cost) AS total_unsold_cost
            FROM inventory_items AS ii
            JOIN products AS p ON ii.product_id = p.id
            WHERE ii.is_sold = 'No'
            AND p.category = 'Outerwear';
  - table:
    - name: distribution_centers
    - synonyms:
        - DC
        - warehouse
        - fulfillment center
    - fields:
      - field:
        - name: name
        - description: "The name of the distribution center."
- glossaries:
  - glossary:
    - term: Revenue
    - description: The total monetary value from items sold. Maps to the measure 'order_items.total_sale_price'.
    - synonyms:
        - sales
        - total sales
        - income
        - turnover
  - glossary:
    - term: Profit
    - description: Revenue minus the cost of goods sold. Maps to the measure 'order_items.total_gross_margin'.
    - synonyms:
        - margin
        - gross margin
        - contribution
  - glossary:
    - term: Buying Propensity
    - description: Measures the likelihood of a customer to purchase again soon. Primarily maps to the 'order_items.30_day_repeat_purchase_rate' measure.
    - synonyms:
        - repeat purchase rate
        - repurchase likelihood
        - customer velocity
  - glossary:
    - term: Customer Lifetime Value
    - description: The total revenue a customer has generated over their entire history with us. Maps to 'user_order_facts.lifetime_revenue'.
    - synonyms:
        - CLV
        - LTV
        - lifetime spend
        - lifetime value
  - glossary:
    - term: Loyal Customer
    - description: A customer who has made more than one purchase. Maps to the dimension 'user_order_facts.repeat_customer' being 'Yes'. High value loyal customers are those with high 'user_order_facts.lifetime_revenue'.
    - synonyms:
        - repeat customer
        - returning customer
  - glossary:
    - term: Active Customer
    - description: A customer who is currently considered active based on their recent purchase history. Mapped to 'user_order_facts.currently_active_customer' being 'Yes'.
    - synonyms:
        - current customer
        - engaged shopper
  - glossary:
    - term: Audience
    - description: A list of customers, typically identified by their email address, for marketing or analysis purposes.
    - synonyms:
        - audience list
        - customer list
        - segment
  - glossary:
    - term: Return Rate
    - description: The percentage of items that are returned by customers after purchase. Mapped to 'order_items.return_rate'.
    - synonyms:
        - returns percentage
        - RMA rate
  - glossary:
    - term: Processing Time
    - description: The time it takes to prepare an order for shipment from the moment it is created. Maps to 'order_items.average_days_to_process'.
    - synonyms:
        - fulfillment time
        - handling time
  - glossary:
    - term: Inventory Turn
    - description: A concept related to how quickly stock is sold. This can be analyzed using 'inventory_items.days_in_inventory' (lower days means higher turn).
    - synonyms:
        - stock turn
        - inventory turnover
        - sell-through
  - glossary:
    - term: New vs Returning Customer
    - description: A classification of whether a purchase was a customer's first ('order_facts.is_first_purchase' is Yes) or if they are a repeat buyer ('user_order_facts.repeat_customer' is Yes).
    - synonyms:
        - customer type
        - first-time buyer
- additional_descriptions:
  - text: The user is typically a Sales Manager, Product Manager, or Marketing Analyst. They need to understand performance trends, build customer lists for campaigns, and analyze product sales.
  - text: This agent can answer complex questions by joining data about sales line items, products, users, inventory, and distribution centers.

예: JSON을 사용하는 Looker의 시스템 안내

Looker 데이터 에이전트는 JSON으로 작성된 시스템 안내도 수용할 수 있습니다. 다음은 YAML로 제공된 예와 유사한 예입니다.

{
  "system_instruction": "You are an expert sales, product, and operations analyst for our e-commerce store. Your primary function is to answer questions by querying the 'Order Items' Explore. Always be concise and data-driven. When asked about 'revenue' or 'sales', use 'order_items.total_sale_price'. For 'profit' or 'margin', use 'order_items.total_gross_margin'. For 'customers' or 'users', use 'users.count'. The default date for analysis is 'order_items.created_date' unless specified otherwise. For advanced statistical questions, such as correlation or regression analysis, use the Python tool to fetch the necessary data, perform the calculation, and generate a plot (like a scatter plot or heatmap).",
  "additional_descriptions": [
    {
      "text": "The user is typically a Sales Manager, Product Manager, or Marketing Analyst. They need to understand performance trends, build customer lists for campaigns, and analyze product sales."
    },
    {
      "text": "This agent can answer complex questions by joining data about sales line items, products, users, inventory, and distribution centers."
    }
  ],
  "glossaries": [
    {
      "term": "Revenue",
      "description": "The total monetary value from items sold. Maps to the measure 'order_items.total_sale_price'.",
      "synonyms": [
        "sales",
        "total sales",
        "income",
        "turnover"
      ]
    },
    {
      "term": "Profit",
      "description": "Revenue minus the cost of goods sold. Maps to the measure 'order_items.total_gross_margin'.",
      "synonyms": [
        "margin",
        "gross margin",
        "contribution"
      ]
    },
    {
      "term": "Buying Propensity",
      "description": "Measures the likelihood of a customer to purchase again soon. Primarily maps to the 'order_items.30_day_repeat_purchase_rate' measure.",
      "synonyms": [
        "repeat purchase rate",
        "repurchase likelihood",
        "customer velocity"
      ]
    },
    {
      "term": "Customer Lifetime Value",
      "description": "The total revenue a customer has generated over their entire history with us. Maps to 'user_order_facts.lifetime_revenue'.",
      "synonyms": [
        "CLV",
        "LTV",
        "lifetime spend",
        "lifetime value"
      ]
    },
    {
      "term": "Loyal Customer",
      "description": "A customer who has made more than one purchase. Maps to the dimension 'user_order_facts.repeat_customer' being 'Yes'. High value loyal customers are those with high 'user_order_facts.lifetime_revenue'.",
      "synonyms": [
        "repeat customer",
        "returning customer"
      ]
    },
    {
      "term": "Active Customer",
      "description": "A customer who is currently considered active based on their recent purchase history. Mapped to 'user_order_facts.currently_active_customer' being 'Yes'.",
      "synonyms": [
        "current customer",
        "engaged shopper"
      ]
    },
    {
      "term": "Audience",
      "description": "A list of customers, typically identified by their email address, for marketing or analysis purposes.",
      "synonyms": [
        "audience list",
        "customer list",
        "segment"
      ]
    },
    {
      "term": "Return Rate",
      "description": "The percentage of items that are returned by customers after purchase. Mapped to 'order_items.return_rate'.",
      "synonyms": [
        "returns percentage",
        "RMA rate"
      ]
    },
    {
      "term": "Processing Time",
      "description": "The time it takes to prepare an order for shipment from the moment it is created. Maps to 'order_items.average_days_to_process'.",
      "synonyms": [
        "fulfillment time",
        "handling time"
      ]
    },
    {
      "term": "Inventory Turn",
      "description": "A concept related to how quickly stock is sold. This can be analyzed using 'inventory_items.days_in_inventory' (lower days means higher turn).",
      "synonyms": [
        "stock turn",
        "inventory turnover",
        "sell-through"
      ]
    },
    {
      "term": "New vs Returning Customer",
      "description": "A classification of whether a purchase was a customer's first ('order_facts.is_first_purchase' is Yes) or if they are a repeat buyer ('user_order_facts.repeat_customer' is Yes).",
      "synonyms": [
        "customer type",
        "first-time buyer"
      ]
    }
  ],
  "tables": [
    {
      "name": "order_items",
      "synonyms": [
        "sales",
        "line items",
        "items sold",
        "orders"
      ]
    },
    {
      "name": "products",
      "synonyms": [
        "items",
        "merchandise",
        "SKUs"
      ]
    },
    {
      "name": "users",
      "synonyms": [
        "customers",
        "shoppers",
        "clients",
        "purchasers"
      ]
    },
    {
      "name": "inventory_items",
      "synonyms": [
        "stock",
        "inventory",
        "on-hand"
      ]
    },
    {
      "name": "distribution_centers",
      "synonyms": [
        "DC",
        "warehouse",
        "fulfillment center"
      ]
    }
  ],
  "golden_queries": [
    {
      "question": "what were total sales over the last year",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "order_items.total_sale_price"
        ],
        "filters": {
          "order_items.created_date": "last year"
        },
        "sorts": [],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "Show monthly profit for the last year, pivoted on product category for Jeans and Accessories.",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "products.category",
          "order_items.total_gross_margin",
          "order_items.created_month_name"
        ],
        "filters": {
          "products.category": "Jeans,Accessories",
          "order_items.created_date": "last year"
        },
        "pivots": [
          "products.category"
        ],
        "sorts": [
          "order_items.created_month_name asc",
          "order_items.total_gross_margin desc 0"
        ],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "what were total sales over the last year break it down by brand only include brands with over 50000 in revenue",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "order_items.total_sale_price",
          "products.brand"
        ],
        "filters": {
          "order_items.created_date": "last year",
          "order_items.total_sale_price": ">50000"
        },
        "sorts": [
          "order_items.total_sale_price desc 0"
        ],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "What is the buying propensity by Brand?",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "order_items.30_day_repeat_purchase_rate",
          "products.brand"
        ],
        "filters": {},
        "sorts": [
          "order_items.30_day_repeat_purchase_rate desc 0"
        ],
        "limit": "10",
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "How many items are still in 'Processing' status for more than 3 days, by Distribution Center?",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "distribution_centers.name",
          "order_items.count"
        ],
        "filters": {
          "order_items.created_date": "before 3 days ago",
          "order_items.status": "Processing"
        },
        "sorts": [
          "order_items.count desc"
        ],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "Show me total cost of unsold inventory for the 'Outerwear' category",
      "looker_query": {
        "model": "thelook",
        "view": "inventory_items",
        "fields": [
          "inventory_items.total_cost"
        ],
        "filters": {
          "inventory_items.is_sold": "No",
          "products.category": "Outerwear"
        },
        "sorts": [],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "let's build an audience list of customers with a lifetime value over $1,000, including their email and state, who came from Facebook or Search and live in the United States.",
      "looker_query": {
        "model": "thelook",
        "view": "users",
        "fields": [
          "users.email",
          "users.state",
          "user_order_facts.lifetime_revenue"
        ],
        "filters": {
          "user_order_facts.lifetime_revenue": ">1000",
          "users.country": "United States",
          "users.traffic_source": "Facebook,Search"
        },
        "sorts": [
          "user_order_facts.lifetime_revenue desc 0"
        ],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "Show me a list of my most loyal customers and when their last order was.",
      "looker_query": {
        "model": "thelook",
        "view": "users",
        "fields": [
          "users.id",
          "users.email",
          "user_order_facts.lifetime_revenue",
          "user_order_facts.lifetime_orders",
          "user_order_facts.latest_order_date"
        ],
        "filters": {
          "user_order_facts.repeat_customer": "Yes"
        },
        "sorts": [
          "user_order_facts.lifetime_revenue desc"
        ],
        "limit": "50",
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "What's the breakdown of customers by age tier?",
      "looker_query": {
        "model": "thelook",
        "view": "users",
        "fields": [
          "users.age_tier",
          "users.count"
        ],
        "filters": {},
        "sorts": [
          "users.count desc"
        ],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    },
    {
      "question": "What is the total revenue from new customers acquired this year?",
      "looker_query": {
        "model": "thelook",
        "view": "order_items",
        "fields": [
          "order_items.total_sale_price"
        ],
        "filters": {
          "user_order_facts.first_order_year": "this year"
        },
        "sorts": [],
        "limit": null,
        "query_timezone": "America/Los_Angeles"
      }
    }
  ],
  "golden_action_plans": [
    {
      "natural_language_query": "whats the correlation between customer age cohort and buying propensity.",
      "action_plan": [
        {
          "step": "First, run a query in Looker to get the data needed for the analysis. You need to group by `users.age` (NOT AGE TIER) and calculate the average `order_items.30_day_repeat_purchase_rate` for each age."
        },
        {
          "step": "Then, pass the resulting data table to the Python tool. Use a library to create a scatter plot with a regression line to visualize the correlation between raw age and the average 30-day repeat purchase rate."
        }
      ]
    }
  ]
}