Merge pull request #76 from Ritik574-coder/dbt_branch

Build end-to-end dbt warehouse with cleaned staging, marts, tests, an…

Author: Ritik574-coder

script/silver/dbt_project/dbt_project.yml

@@ -9,27 +9,39 @@ version: '1.0.0'
 profile: 'dbt_project'
 
 # These configurations specify where dbt should look for different types of files.
-# The `model-paths` config, for example, states that models in this project can be
-# found in the "models/" directory. You probably won't need to change these!
 model-paths: ["models"]
 analysis-paths: ["analyses"]
 test-paths: ["tests"]
 seed-paths: ["seeds"]
 macro-paths: ["macros"]
 snapshot-paths: ["snapshots"]
 
-clean-targets:         # directories to be removed by `dbt clean`
+clean-targets:
   - "target"
   - "dbt_packages"
 
-
-# Configuring models
-# Full documentation: https://docs.getdbt.com/docs/configuring-models
-
-# In this example config, we tell dbt to build all models in the example/
-# directory as views. These settings can be overridden in the individual model
-# files using the `{{ config(...) }}` macro.
+# Configuring models with Medallion Architecture layers
 models:
   dbt_project:
-    silver:
-      +materialized: table
+
+    # ─── Staging Layer (Bronze → Silver Raw Cleaning) ───
+    staging:
+      +materialized: view
+      +schema: silver
+
+    # ─── Intermediate Layer (Business Transformations) ───
+    intermediate:
+      +materialized: view
+      +schema: silver
+
+    # ─── Marts Layer (Gold Layer - Business Ready) ───
+    marts:
+      dimensions:
+        +materialized: table
+        +schema: gold
+      facts:
+        +materialized: table
+        +schema: gold
+      reporting:
+        +materialized: view
+        +schema: gold

script/silver/dbt_project/models/intermediate/Customers/int_customers_standardized.sql

@@ -0,0 +1,46 @@
+-- Intermediate Model: int_customers_standardized
+-- Purpose: Further refine customer data with business-specific transformations
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_customers') }}
+)
+
+SELECT
+    customer_id,
+    title,
+    first_name,
+    last_name,
+    CONCAT(first_name, ' ', last_name) AS full_name,
+    gender,
+    date_of_birth,
+    age,
+
+    CASE
+        WHEN age BETWEEN 0 AND 17 THEN 'Under 18'
+        WHEN age BETWEEN 18 AND 24 THEN '18-24'
+        WHEN age BETWEEN 25 AND 34 THEN '25-34'
+        WHEN age BETWEEN 35 AND 44 THEN '35-44'
+        WHEN age BETWEEN 45 AND 54 THEN '45-54'
+        WHEN age BETWEEN 55 AND 64 THEN '55-64'
+        WHEN age >= 65 THEN '65+'
+        ELSE 'Unknown'
+    END AS age_group,
+
+    email,
+    phone,
+    address,
+    city,
+    state_abbr,
+    state_full,
+    zip_code,
+    country,
+    region,
+    customer_segment,
+    loyalty_points,
+    is_active,
+    account_created_date,
+    preferred_channel,
+    annual_income_usd,
+    company,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Employees/int_employees_standardized.sql

@@ -0,0 +1,28 @@
+-- Intermediate Model: int_employees_standardized
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_employees') }}
+)
+
+SELECT
+    employee_id,
+    first_name,
+    last_name,
+    CONCAT(first_name, ' ', last_name) AS full_name,
+    email,
+    phone,
+    job_title,
+    department,
+    store_id,
+    store_name,
+    store_city,
+    hire_date,
+    years_employed,
+    annual_salary_usd,
+    commission_rate_pct,
+    is_active,
+    performance_rating,
+    manager_id,
+    DATEDIFF(YEAR, hire_date, GETDATE()) AS calculated_tenure_years,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Inventory/int_inventory_summary.sql

@@ -0,0 +1,24 @@
+-- Intermediate Model: int_inventory_summary
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_inventory') }}
+)
+
+SELECT
+    snapshot_date,
+    product_id,
+    product_name,
+    sku,
+    category,
+    stock_on_hand,
+    stock_reserved,
+    stock_available,
+    reorder_level,
+    unit_cost,
+    unit_price,
+    inventory_value,
+    CASE WHEN stock_available <= reorder_level THEN 'Yes' ELSE 'No' END AS needs_reorder,
+    warehouse_location,
+    store_id,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Products/int_products_standardized.sql

@@ -0,0 +1,39 @@
+-- Intermediate Model: int_products_standardized
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_products') }}
+)
+
+SELECT
+    product_id,
+    sku,
+    product_name,
+    brand,
+    category,
+    sub_category,
+    department,
+    base_price_usd,
+    cost_price_usd,
+    gross_margin_pct,
+    CASE WHEN base_price_usd > 0 THEN (base_price_usd - cost_price_usd) / base_price_usd * 100 ELSE NULL END AS calculated_margin_pct,
+    weight_kg,
+    is_available,
+    stock_quantity,
+    reorder_level,
+    CASE WHEN stock_quantity <= reorder_level THEN 'Yes' ELSE 'No' END AS low_stock_flag,
+    supplier_name,
+    supplier_country,
+    warranty_years,
+    rating_avg,
+    review_count,
+    CASE
+        WHEN rating_avg >= 4.5 THEN 'Excellent'
+        WHEN rating_avg >= 3.5 THEN 'Good'
+        WHEN rating_avg >= 2.5 THEN 'Average'
+        WHEN rating_avg >= 1.0 THEN 'Poor'
+        ELSE 'Not Rated'
+    END AS rating_category,
+    launched_date,
+    product_url,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Returns/int_returns_summary.sql

@@ -0,0 +1,28 @@
+-- Intermediate Model: int_returns_summary
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_returns') }}
+)
+
+SELECT
+    return_id,
+    original_txn_id,
+    original_order_id,
+    customer_id,
+    customer_name,
+    product_id,
+    product_name,
+    quantity_returned,
+    return_date,
+    return_reason,
+    refund_amount,
+    refund_method,
+    return_channel,
+    restocked,
+    return_status,
+    handled_by_emp_id,
+    notes,
+    DATEPART(YEAR, return_date) AS return_year,
+    DATEPART(MONTH, return_date) AS return_month,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Reviews/int_reviews_summary.sql

@@ -0,0 +1,24 @@
+-- Intermediate Model: int_reviews_summary
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_reviews') }}
+)
+
+SELECT
+    review_id,
+    txn_id,
+    customer_id,
+    customer_name,
+    product_id,
+    product_name,
+    rating,
+    rating_text,
+    review_date,
+    verified_purchase,
+    helpful_votes,
+    review_channel,
+    review_title,
+    DATEPART(YEAR, review_date) AS review_year,
+    DATEPART(MONTH, review_date) AS review_month,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Stores/int_stores_standardized.sql

@@ -0,0 +1,32 @@
+-- Intermediate Model: int_stores_standardized
+
+WITH staging AS (
+    SELECT * FROM {{ ref('src_stores') }}
+)
+
+SELECT
+    store_id,
+    store_name,
+    store_type,
+    address,
+    city,
+    state,
+    state_full,
+    CONCAT(city, ', ', state) AS store_location,
+    zip_code,
+    country,
+    region,
+    district,
+    phone,
+    manager_name,
+    opened_date,
+    DATEDIFF(YEAR, opened_date, GETDATE()) AS years_operating,
+    sq_footage,
+    num_employees,
+    annual_rent_usd,
+    CASE WHEN sq_footage > 0 THEN TRY_CAST(num_employees AS DECIMAL(10,2)) / sq_footage * 1000 ELSE NULL END AS employees_per_1000_sqft,
+    is_active,
+    has_parking,
+    has_cafe,
+    GETDATE() AS _loaded_at
+FROM staging

script/silver/dbt_project/models/intermediate/Transactions/int_transactions_enriched.sql

@@ -0,0 +1,95 @@
+-- Intermediate Model: int_transactions_enriched
+
+WITH staging AS (
+
+    SELECT *
+    FROM {{ ref('src_transactions') }}
+
+)
+
+SELECT
+
+    transaction_id,
+    order_id,
+    order_line_number,
+
+    order_date,
+    order_year,
+    order_month,
+    order_month_name,
+    order_quarter,
+    order_day_of_week,
+
+    customer_id,
+    product_id,
+
+    -- Sales Metrics
+    TRY_CAST(quantity_ordered AS INT) AS quantity_ordered,
+
+    TRY_CAST(unit_list_price AS DECIMAL(18,2)) AS unit_list_price,
+
+    TRY_CAST(discount_pct AS DECIMAL(18,2)) AS discount_pct,
+
+    TRY_CAST(unit_selling_price AS DECIMAL(18,2)) AS unit_selling_price,
+
+    TRY_CAST(line_total_before_tax AS DECIMAL(18,2)) AS line_total_before_tax,
+
+    TRY_CAST(tax_rate_pct AS DECIMAL(18,2)) AS tax_rate_pct,
+
+    TRY_CAST(tax_amount AS DECIMAL(18,2)) AS tax_amount,
+
+    TRY_CAST(line_total_with_tax AS DECIMAL(18,2)) AS line_total_with_tax,
+
+    -- Derived Metrics
+    (
+        TRY_CAST(unit_selling_price AS DECIMAL(18,2))
+        *
+        TRY_CAST(quantity_ordered AS INT)
+    ) AS gross_sales_amount,
+
+    TRY_CAST(cost_price AS DECIMAL(18,2)) AS cost_price,
+
+    TRY_CAST(gross_profit AS DECIMAL(18,2)) AS gross_profit,
+
+    (
+        TRY_CAST(line_total_with_tax AS DECIMAL(18,2))
+        -
+        TRY_CAST(cost_price AS DECIMAL(18,2))
+    ) AS net_profit,
+
+    CASE
+        WHEN TRY_CAST(line_total_with_tax AS DECIMAL(18,2)) = 0 THEN NULL
+
+        ELSE ROUND(
+            (
+                (
+                    TRY_CAST(line_total_with_tax AS DECIMAL(18,2))
+                    -
+                    TRY_CAST(cost_price AS DECIMAL(18,2))
+                )
+                /
+                TRY_CAST(line_total_with_tax AS DECIMAL(18,2))
+            ) * 100,
+            2
+        )
+
+    END AS profit_margin_pct,
+
+    -- Dimensions
+    store_id,
+    employee_id,
+
+    promo_id,
+    promo_name,
+
+    LOWER(TRIM(sales_channel)) AS sales_channel,
+
+    payment_method,
+    shipping_method,
+    order_status,
+    is_returned,
+
+    -- Audit Column
+    GETDATE() AS _loaded_at
+
+FROM staging