dbt cert submission

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+    "editor.tabSize": 2,
+    "editor.detectIndentation": false
+}

Pipfile

@@ -8,6 +8,7 @@ dbt-core = "==1.3.0"
 dbt-databricks = {extras = ["odbc"]}
 pytest-mock = "*"
 glob2 = "*"
+numpy = "==1.24.1"
 
 [dev-packages]
 pytest = "*"

jaffle_shop/models/final/finance/_exposures.yml

@@ -0,0 +1,14 @@
+version: 2
+
+################################################################################
+# EXPOSURES      https://docs.getdbt.com/reference/exposure-properties
+################################################################################
+exposures:
+  - name: fnl_finance_returned_orders
+    description: Inksacio Dashboard
+    type: dashboard
+    url: url: https://inksacio.uk.octopus.engineering/my_certification_finance_dashboard/
+    owner:
+      email: [email protected]
+    depends_on:
+      - ref('fnl_finance_returned_orders')

jaffle_shop/models/final/finance/_models.yml

@@ -0,0 +1,17 @@
+version: 2
+
+models: 
+  - name: fnl_finance_returned_orders
+    config:
+      tags: ['access:public']
+    meta:
+      owner: '[email protected]'
+    description: |
+      Report on the value of returned orders. 1 row per customer with total returned value for 
+      that customer
+    columns:
+      - name: customer_id
+        description: Primary key
+        tests:
+          - unique
+          - not_null

jaffle_shop/models/final/finance/fnl_finance_returned_orders.sql

@@ -0,0 +1,14 @@
+WITH returned_orders AS (
+    SELECT
+      customer_id
+      , amount AS value
+    FROM {{ ref('wh_orders') }}
+    WHERE status = 'returned'
+    GROUP BY customer_id
+)
+
+SELECT
+  customer_id
+  , SUM(value) AS total_value
+FROM returned_orders
+GROUP BY customer_id

jaffle_shop/models/final/sales/_exposures.yml

@@ -0,0 +1,14 @@
+version: 2
+
+################################################################################
+# EXPOSURES      https://docs.getdbt.com/reference/exposure-properties
+################################################################################
+exposures:
+  - name: fnl_sales_first_orders
+    description: Inksacio Dashboard
+    type: dashboard
+    url: url: https://inksacio.uk.octopus.engineering/my_certification_sales_dashboard/
+    owner:
+      email: [email protected]
+    depends_on:
+      - ref('fnl_sales_first_orders')

jaffle_shop/models/final/sales/_models.yml

@@ -0,0 +1,16 @@
+version: 2
+
+models: 
+  - name: fnl_sales_first_orders
+    config:
+      tags: ['access:public']
+    meta:
+      owner: '[email protected]'
+    description: |
+      Report on the numbers of customers making their first order per month.
+    columns:
+      - name: first_order_month
+        description: Primary key
+        tests:
+          - unique
+          - not_null

jaffle_shop/models/final/sales/fnl_sales_first_orders.sql

@@ -0,0 +1,14 @@
+WITH customer_first_orders AS (
+  SELECT
+    customer_id
+    -- Get just the month from the first order date
+    , DATE_FORMAT(first_order, 'MMMM') As first_order_month
+  FROM {{ ref('wh_customers') }}
+)
+
+SELECT
+  first_order_month
+  , COUNT(*) AS number_of_customers
+FROM customer_first_orders
+GROUP BY first_order_month
+

jaffle_shop/models/staging/src_seeds/_models.yml

@@ -0,0 +1,61 @@
+version: 2
+
+models:
+  - name: stg_customers_pii
+    config:
+      tags: ['access:private']
+    meta: 
+      owner: '[email protected]'
+    description: |
+      Staging table for csv containing customer information.
+    columns:
+      - name: customer_id
+        tests:
+          - unique
+          - not_null
+      - name: first_name
+        meta:
+          sensitive: true
+      - name: last_name
+        meta:
+          sensitive: true
+  - name: stg_customers
+    config:
+      tags: ['access:private']
+    meta: 
+      owner: '[email protected]'
+    description: |
+      Staging table for csv containing customer information with PII columns hashed.
+    columns:
+      - name: customer_id
+        tests:
+          - unique
+          - not_null
+      - name: first_name_hash
+        tests:
+          - dbt_expectations.expect_column_to_exist
+      - name: last_name_hash
+        tests:
+          - dbt_expectations.expect_column_to_exist
+
+  - name: stg_orders
+    columns:
+      - name: order_id
+        tests:
+          - unique
+          - not_null
+      - name: status
+        tests:
+          - accepted_values:
+              values: ['placed', 'shipped', 'completed', 'return_pending', 'returned']
+
+  - name: stg_payments
+    columns:
+      - name: payment_id
+        tests:
+          - unique
+          - not_null
+      - name: payment_method
+        tests:
+          - accepted_values:
+              values: ['credit_card', 'coupon', 'bank_transfer', 'gift_card']

jaffle_shop/models/staging/src_seeds/stg_customers.sql

@@ -0,0 +1,3 @@
+SELECT
+  {{ hash_sensitive_columns('stg_customers_pii') }}
+FROM {{ ref('stg_customers_pii') }}

jaffle_shop/seeds/_seeds.yml

@@ -0,0 +1,30 @@
+version: 2
+
+seeds:
+  - name: raw_customers
+    description: |
+      Table containing customer_id, and their first and last name.
+    config:
+      column_types:
+        id: int
+        first_name: string
+        last_name: string
+  - name: raw_orders
+    description: |
+      Table containing information about customers orders
+    config:
+      column_types:
+        id: int
+        user_id: int
+        order_date: date
+        status: string
+  - name: raw_payments
+    description: |
+      Table containing information about customers payments
+    config:
+      column_types:
+        id: int
+        order_id: int
+        payment_method: string
+        amount: int
+

jaffle_shop/seeds/dbt_project_evaluator_exceptions.csv

@@ -0,0 +1,2 @@
+fct_name,column_name,id_to_exclude,comment
+fct_staging_dependent_on_staging,parent,stg_customers_pii,Scrubbing pii permitted in staging layer.