Fix fanout in customers model

.gitignore

@@ -6,8 +6,11 @@ env
 target/
 dbt_packages/
 logs/
+profiles.yml
 
 .DS_Store
 
 .user.yml
-*.hurl
+
+.ruff_cache
+__pycache__

.pre-commit-config.yaml

@@ -7,23 +7,17 @@ repos:
       - id: trailing-whitespace
       - id: requirements-txt-fixer
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.3.3
+    rev: v0.3.4
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
       - id: ruff-format
   - repo: https://github.com/sqlfluff/sqlfluff
-    rev: "3.0.1"
+    rev: "3.0.3"
     hooks:
-      - id: sqlfluff-lint
-        additional_dependencies:
-          [
-            "dbt-metricflow[duckdb,snowflake,postgres]~=0.6.0",
-            "sqlfluff-templater-dbt~=3.0.1",
-          ]
       - id: sqlfluff-fix
         additional_dependencies:
           [
-            "dbt-metricflow[duckdb,snowflake,postgres]~=0.6.0",
-            "sqlfluff-templater-dbt~=3.0.1",
+            "dbt-metricflow[snowflake,bigquery,postgres]~=0.6.0",
+            "sqlfluff-templater-dbt~=3.0.3",
           ]

Taskfile.yml

@@ -12,11 +12,11 @@ tasks:
 
   build:
     cmds:
-      - source .venv/bin/activate && dbt deps
-      - source .venv/bin/activate && dbt seed
+      - dbt deps
+      - dbt seed
       - rm -rf jaffle-data
-      - source .venv/bin/activate && dbt run
-      - source .venv/bin/activate && dbt test
+      - dbt run
+      - dbt test
 
   setup:
     cmds:

dbt_project.yml

@@ -2,11 +2,15 @@ config-version: 2
 
 name: "jaffle_shop"
 version: "3.0.0"
-require-dbt-version: ">=1.7.1"
+require-dbt-version: ">=1.5.0"
 
 dbt-cloud:
   project-id: 283328 # Put your project id here
 
+# If you want to run SQLFluff pre-commit hooks you'll need
+# to set up a working profile it can use and list it below
+profile: default
+
 model-paths: ["models"]
 analysis-paths: ["analyses"]
 test-paths: ["data-tests"]

macros/cents_to_dollars.sql

@@ -1,5 +1,13 @@
 {# A basic example for a project-wide macro to cast a column uniformly #}
 
-{% macro cents_to_dollars(column_name, precision=2) -%}
-    ({{ column_name }} / 100)::numeric(16, {{ precision }})
+{% macro cents_to_dollars(column_name) -%}
+    {{ return(adapter.dispatch('cents_to_dollars')(column_name)) }}
 {%- endmacro %}
+
+{% macro default__cents_to_dollars(column_name) -%}
+    ({{ column_name }} / 100)::numeric(16, 2)
+{%- endmacro %}
+
+{% macro bigquery__cents_to_dollars(column_name) %}
+    round(cast(({{ column_name }} / 100) as numeric), 2)
+{% endmacro %}

models/marts/customers.sql

@@ -6,19 +6,13 @@ customers as (
 
 ),
 
-orders_table as (
+orders as (
 
     select * from {{ ref('orders') }}
 
 ),
 
-order_items_table as (
-
-    select * from {{ ref('order_items') }}
-
-),
-
-order_summary as (
+customer_orders_summary as (
 
     select
         orders.customer_id,
@@ -27,14 +21,11 @@ order_summary as (
         count(distinct orders.order_id) > 1 as is_repeat_buyer,
         min(orders.ordered_at) as first_ordered_at,
         max(orders.ordered_at) as last_ordered_at,
-        sum(order_items.product_price) as lifetime_spend_pretax,
+        sum(orders.subtotal) as lifetime_spend_pretax,
+        sum(orders.tax_paid) as lifetime_tax_paid,
         sum(orders.order_total) as lifetime_spend
 
-    from orders_table as orders
-
-    left join
-        order_items_table as order_items
-        on orders.order_id = order_items.order_id
+    from orders
 
     group by 1
 
@@ -44,21 +35,22 @@ joined as (
 
     select
         customers.*,
-        order_summary.count_lifetime_orders,
-        order_summary.first_ordered_at,
-        order_summary.last_ordered_at,
-        order_summary.lifetime_spend_pretax,
-        order_summary.lifetime_spend,
+        customer_orders_summary.count_lifetime_orders,
+        customer_orders_summary.first_ordered_at,
+        customer_orders_summary.last_ordered_at,
+        customer_orders_summary.lifetime_spend_pretax,
+        customer_orders_summary.lifetime_tax_paid,
+        customer_orders_summary.lifetime_spend,
 
         case
-            when order_summary.is_repeat_buyer then 'returning'
+            when customer_orders_summary.is_repeat_buyer then 'returning'
             else 'new'
         end as customer_type
 
     from customers
 
-    left join order_summary
-        on customers.customer_id = order_summary.customer_id
+    left join customer_orders_summary
+        on customers.customer_id = customer_orders_summary.customer_id
 
 )
 

models/marts/customers.yml

@@ -1,6 +1,9 @@
 models:
   - name: customers
     description: Customer overview data mart, offering key details for each unique customer. One row per customer.
+    tests:
+      - dbt_utils.expression_is_true:
+          expression: "lifetime_spend_pretax + lifetime_tax_paid = lifetime_spend"
     columns:
       - name: customer_id
         description: The unique key of the orders mart.
@@ -17,6 +20,8 @@ models:
         description: The timestamp of a customer's most recent order.
       - name: lifetime_spend_pretax
         description: The sum of all the pre-tax subtotals of every order a customer has placed.
+      - name: lifetime_tax_paid
+        description: The sum of all the tax portion of every order a customer has placed.
       - name: lifetime_spend
         description: The sum of all the order totals (including tax) that a customer has ever placed.
       - name: customer_type

models/marts/order_items.sql

@@ -29,6 +29,7 @@ order_supplies_summary as (
 
     select
         product_id,
+
         sum(supply_cost) as supply_cost
 
     from supplies

models/marts/order_items.yml

@@ -5,6 +5,11 @@ models:
         tests:
           - not_null
           - unique
+      - name: order_id
+        tests:
+          - relationships:
+              to: ref('orders')
+              field: order_id
 
 unit_tests:
   - name: test_supply_costs_sum_correctly

models/marts/orders.sql

@@ -6,7 +6,7 @@ orders as (
 
 ),
 
-order_items_table as (
+order_items as (
 
     select * from {{ ref('order_items') }}
 
@@ -16,14 +16,15 @@ order_items_summary as (
 
     select
         order_id,
+
+        sum(supply_cost) as order_cost,
+        sum(product_price) as order_items_subtotal,
+        count(order_item_id) as count_order_items,
         sum(case when is_food_item then 1 else 0 end)
             as count_food_items,
         sum(case when is_drink_item then 1 else 0 end)
-            as count_drink_items,
-
-        sum(supply_cost) as order_cost
-
-    from order_items_table
+            as count_drink_items
+    from order_items
 
     group by 1
 
@@ -33,11 +34,12 @@ order_items_summary as (
 compute_booleans as (
 
     select
-
         orders.*,
         order_items_summary.order_cost,
+        order_items_summary.order_items_subtotal,
         order_items_summary.count_food_items,
         order_items_summary.count_drink_items,
+        order_items_summary.count_order_items,
         order_items_summary.count_food_items > 0 as is_food_order,
         order_items_summary.count_drink_items > 0 as is_drink_order
 

models/marts/orders.yml

@@ -1,6 +1,11 @@
 models:
   - name: orders
     description: Order overview data mart, offering key details for each order inlcluding if it's a customer's first order and a food vs. drink item breakdown. One row per order.
+    tests:
+      - dbt_utils.expression_is_true:
+          expression: "order_items_subtotal = subtotal"
+      - dbt_utils.expression_is_true:
+          expression: "order_total = subtotal + tax_paid"
     columns:
       - name: order_id
         description: The unique key of the orders mart.

models/staging/stg_order_items.yml

@@ -7,3 +7,10 @@ models:
         tests:
           - not_null
           - unique
+      - name: order_id
+        description: The corresponding order each order item belongs to
+        tests:
+          - not_null
+          - relationships:
+              to: ref('stg_orders')
+              field: order_id

models/staging/stg_orders.sql

@@ -16,8 +16,12 @@ renamed as (
         customer as customer_id,
 
         ---------- numerics
-        (order_total / 100.0) as order_total,
-        (tax_paid / 100.0) as tax_paid,
+        subtotal as subtotal_cents,
+        tax_paid as tax_paid_cents,
+        order_total as order_total_cents,
+        {{ cents_to_dollars('subtotal') }} as subtotal,
+        {{ cents_to_dollars('tax_paid') }} as tax_paid,
+        {{ cents_to_dollars('order_total') }} as order_total,
 
         ---------- timestamps
         {{ dbt.date_trunc('day','ordered_at') }} as ordered_at

models/staging/stg_orders.yml

@@ -1,6 +1,9 @@
 models:
   - name: stg_orders
     description: Order data with basic cleaning and transformation applied, one row per order.
+    tests:
+      - dbt_utils.expression_is_true:
+          expression: "order_total - tax_paid = subtotal"
     columns:
       - name: order_id
         description: The unique key for each order.

models/staging/stg_products.sql

@@ -20,7 +20,7 @@ renamed as (
 
 
         ---------- numerics
-        (price / 100.0) as product_price,
+        {{ cents_to_dollars('price') }} as product_price,
 
         ---------- booleans
         coalesce(type = 'jaffle', false) as is_food_item,

models/staging/stg_supplies.sql

@@ -19,7 +19,7 @@ renamed as (
         name as supply_name,
 
         ---------- numerics
-        (cost / 100.0) as supply_cost,
+        {{ cents_to_dollars('cost') }} as supply_cost,
 
         ---------- booleans
         perishable as is_perishable_supply

package-lock.yml

@@ -1,8 +1,10 @@
 packages:
-- package: dbt-labs/dbt_utils
-  version: 1.1.1
-- package: calogica/dbt_date
-  version: 0.10.0
-- package: dbt-labs/audit_helper
-  version: 0.10.0
-sha1_hash: ef1c92462efce413655c7e7cbfc1b093c132ef83
+  - package: dbt-labs/dbt_utils
+    version: 1.1.1
+  - package: calogica/dbt_date
+    version: 0.10.0
+  - package: dbt-labs/audit_helper
+    version: 0.11.0
+  - package: calogica/dbt_expectations
+    version: 0.10.3
+sha1_hash: 04cccdda410558cb2751bfe1ee6c1f6f61b60776

packages.yml

@@ -4,4 +4,6 @@ packages:
   - package: calogica/dbt_date
     version: 0.10.0
   - package: dbt-labs/audit_helper
-    version: 0.10.0
+    version: 0.11.0
+  - package: calogica/dbt_expectations
+    version: 0.10.3