Merge pull request #18 from Ritik574-coder/dbt_branch

feat(intermediate): add customer contact cleaning and validation model

Author: Ritik574-coder

models/intermediate/Customers/int_customers_contact.sql

@@ -1,6 +1,74 @@
+-- ============================================================================
+-- Model: int_customers_contact
+--
+-- Purpose:
+--   Standardizes customer contact information by cleaning and validating
+--   email addresses, phone numbers, and preferred communication channels.
+--   This model corrects common email domain typographical errors, formats
+--   phone numbers into a consistent structure, and normalizes customer
+--   communication preferences for reliable downstream analytical models.
+--
+-- Maintainer: Ritik
+-- ============================================================================
 SELECT
     customer_id,
-    email,
-    phone,
-    preferred_channel
+
+    CASE
+        WHEN email IS NULL OR TRIM(email) = '' THEN 'Unknown'
+        WHEN TRIM(LOWER(email)) NOT LIKE '%@%' THEN 'Unknown'
+        WHEN PATINDEX('%@%@%', TRIM(LOWER(email))) > 0 THEN
+                LEFT(TRIM(LOWER(email)),CHARINDEX('@', TRIM(LOWER(email))) - 1)
+                + '@' +
+                REPLACE(
+                    SUBSTRING(
+                        TRIM(LOWER(email)),
+                        CHARINDEX('@', TRIM(LOWER(email))) + 1,
+                        LEN(email)),'@','')
+        ELSE
+            CONCAT(
+                LEFT(TRIM(LOWER(email)),CHARINDEX('@', TRIM(LOWER(email))) - 1), '@',
+                CASE
+                    WHEN RIGHT(
+                        TRIM(LOWER(email)),
+                        LEN(TRIM(email)) - CHARINDEX('@', TRIM(email))) = 'yahoocom' THEN 'yahoo.com'
+                    WHEN RIGHT(
+                        TRIM(LOWER(email)),
+                        LEN(TRIM(email)) - CHARINDEX('@', TRIM(email))) = 'iclod.com' THEN 'icloud.com'
+                    WHEN RIGHT(
+                        TRIM(LOWER(email)),
+                        LEN(TRIM(email)) - CHARINDEX('@', TRIM(email))) = 'outook.com' THEN 'outlook.com'
+                    WHEN RIGHT(
+                        TRIM(LOWER(email)),
+                        LEN(TRIM(email)) - CHARINDEX('@', TRIM(email))) = 'ahoo.com' THEN 'yahoo.com'
+                    ELSE RIGHT(
+                        TRIM(LOWER(email)),
+                        LEN(TRIM(email)) - CHARINDEX('@', TRIM(email)))
+                END
+        )
+    END AS email,
+
+    CASE 
+        WHEN TRIM(phone) LIKE '+1__________'   THEN CONCAT('+1 (', SUBSTRING(TRIM(phone), 3, 3), ') ', SUBSTRING(TRIM(phone), 6, 3),'-',   SUBSTRING(TRIM(phone),9,4))
+        WHEN TRIM(phone) LIKE '__________'     THEN CONCAT('+1 (', SUBSTRING(TRIM(phone), 1 ,3), ') ', SUBSTRING(TRIM(phone), 4 ,3), '-',  SUBSTRING(TRIM(phone), 7, 4))
+        WHEN TRIM(phone) LIKE '___-___-____'   THEN CONCAT('+1 (', SUBSTRING(TRIM(phone), 1, 3), ') ', SUBSTRING(TRIM(phone), 5, 3),       SUBSTRING(TRIM(phone), 8 ,5))
+        WHEN TRIM(phone) LIKE '___.___.____'   THEN CONCAT('+1 (', SUBSTRING(TRIM(phone), 1, 3), ') ', SUBSTRING(TRIM(phone), 5, 3), '-',  SUBSTRING(TRIM(phone),9, 4))
+        WHEN TRIM(phone) LIKE '(___) ___-____' THEN CONCAT('+1 ',  SUBSTRING(TRIM(phone), 1, 14))
+        WHEN TRIM(phone) IS NULL OR TRIM(phone) = '' THEN 'Unknown'
+        ELSE 'Unknown'
+    END  as phone,
+
+    CASE TRIM(LOWER(preferred_channel))
+        WHEN 'app'        THEN 'Mobile App'
+        WHEN 'mobile app' THEN 'Mobile App'
+        WHEN 'mobile'     THEN 'Mobile App'
+        WHEN 'in store'   THEN 'In Store'
+        WHEN 'in-store'   THEN 'In Store'
+        WHEN 'store'      THEN 'In Store'
+        WHEN 'catalog'    THEN 'Catalog'
+        WHEN 'online'     THEN 'Website'
+        WHEN 'web'        THEN 'Website'
+        WHEN 'phone'      THEN 'Phone Call'
+        ELSE 'Unknown'
+    END as preferred_channel
+
 FROM {{ ref('stg_customers') }} ;

models/intermediate/_int__retail_models.yml

@@ -51,6 +51,46 @@ models:
         tests:
           - not_null
 
+####################################################################################
+####################### Model: int_customers_contact ###############################
+####################################################################################
+  - name: int_customers_contact
+    description: |
+      Cleans and standardizes customer contact information for downstream
+      analytical models. This model validates and normalizes email addresses,
+      formats phone numbers into a consistent structure, and standardizes
+      preferred communication channels to improve data quality and reporting.
+
+    columns:
+      - name: email
+        description: |
+          Standardized customer email address. Invalid or missing email
+          addresses are replaced with 'Unknown'. Common domain spelling
+          mistakes are automatically corrected.
+        tests:
+          - not_null
+
+      - name: phone
+        description: |
+          Standardized customer phone number formatted as
+          +1 (XXX) XXX-XXXX. Invalid or missing phone numbers are
+          replaced with 'Unknown'.
+        tests:
+          - not_null
+
+      - name: preferred_channel
+        description: |
+          Standardized customer preferred communication channel.
+          Source values are normalized into business-friendly categories.
+        tests:
+          - not_null
+          - accepted_values:
+              arguments:
+                values:
+                  ['Mobile App', 'In Store', 'Catalog', 'Website', 'Phone Call', 'Unknown']
+
+
+
 ####################################################################################
 ####################### Model: int_customer_location ###############################
 ####################################################################################