week one project

README.md

@@ -1,6 +1,20 @@
 # Analytics engineering with dbt
 
-Template repository for the projects and environment of the course: Analytics engineering with dbt
+Questions to week 1 project:
+Q: How many users do we have?
+A: 130
+
+Q: On average, how many orders do we receive per hour?
+A: 7.52
+
+Q: On average, how long does an order take from being placed to being delivered?
+A: 3.89
+
+Q: How many users have only made one purchase? Two purchases? Three+ purchases?
+A: 1 order- 25, 2 orders - 28, 3+ orders - 71
+
+Q: On average, how many unique sessions do we have per hour?
+A: 16.33
 
 > Please note that this sets some environment variables so if you create some new terminals please load them again.
 

greenery/.gitignore

@@ -0,0 +1,4 @@
+
+target/
+dbt_packages/
+logs/

greenery/dbt_project.yml

@@ -0,0 +1,42 @@
+
+# Name your project! Project names should contain only lowercase characters
+# and underscores. A good package name should reflect your organization's
+# name or the intended use of these models
+name: 'greenery'
+version: '1.0.0'
+config-version: 2
+
+# This setting configures which "profile" dbt uses for this project.
+profile: 'greenery'
+
+# 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"]
+
+target-path: "target"  # directory which will store compiled SQL files
+clean-targets:         # directories to be removed by `dbt clean`
+  - "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 tables. These settings can be overridden in the individual model files
+# using the `{{ config(...) }}` macro.
+models:
+  greenery:
+    # Config indicated by + and applies to all files under models/example/
+    example:
+      +materialized: view
+
+    post-hook:
+      - "{{ grant(role='reporting') }}"
+

greenery/macros/grant_usage.sql

@@ -0,0 +1,10 @@
+{% macro grant(role) %}
+
+    {% set sql %}
+      GRANT USAGE ON SCHEMA {{ schema }} TO ROLE {{ role }};
+      GRANT SELECT ON {{ this }} TO ROLE {{ role }};
+    {% endset %}
+
+    {% set table = run_query(sql) %}
+
+{% endmacro %}

greenery/macros/row_to_columns.sql

@@ -0,0 +1,18 @@
+{% macro row_to_columns(table_name,column_name,count_column) %}
+
+    {% set new_columns = dbt_utils.get_column_values(
+        table = ref( table_name ),
+        column = column_name
+    ) %}
+    {% for new_column in new_columns %}
+        count( case when {{ column_name }} = '{{ new_column }}' 
+        then {{count_column}}
+        else NULL
+        end ) as {{new_column}}_count
+        {% if not loop.last %}
+        ,
+        {% endif %}
+    {% endfor %}
+
+{% endmacro %}
+

greenery/models/example/marts/Core/core_models.yml

@@ -0,0 +1,29 @@
+version: 2
+
+models:
+  - name: dim_products
+    description: "Products we sell"
+    columns:
+      - name: product_guid
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null
+
+  - name: dim_users
+    description: "Prospective and purchasing customers "
+    columns:
+      - name: user_guid
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null
+  - name: fact_orders
+    description: "Orders that have been placed "
+    columns:
+      - name: order_guid
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null
+

greenery/models/example/marts/Core/dim_products.sql

@@ -0,0 +1,16 @@
+{{ config(materialized='table') }}
+
+with product as (
+    select
+    *
+    from {{ref('src_products')}}
+)
+
+
+
+SELECT
+    product_guid
+    ,product_name
+    ,price as product_price
+    ,inventory as product_inventory
+FROM product

greenery/models/example/marts/Core/dim_users.sql

@@ -0,0 +1,52 @@
+{{ config(materialized='table') }}
+
+
+with users as (
+    SELECT
+    *
+    from {{ref('src_users')}}
+)
+
+,first_order AS (
+    SELECT
+        DISTINCT 
+        USER_GUID,
+        CREATED_AT_TSTAMP_EST as FIRST_ORDER_CREATED_TSTAMP_EST
+    FROM {{ref('fact_orders')}}
+    WHERE USER_ORDER_RANK = 1
+)
+
+,first_delivered_order AS (
+    SELECT
+    DISTINCT 
+        USER_GUID,
+        DELIVERED_AT_TSTAMP_EST as FIRST_ORDER_DELIVERED_TSTAMP_EST
+    FROM {{ref('fact_orders')}}
+    WHERE USER_DELIVERED_RANK = 1
+)
+
+
+,combined AS (
+    select
+        u.USER_GUID
+        ,u.FIRST_NAME
+        ,u.LAST_NAME
+        ,u.FULL_NAME
+        ,u.EMAIL
+        ,u.PHONE_NUMBER
+        ,u.CREATED_AT_TSTAMP_EST as SYSTEM_CREATED_TSTAMP_EST
+        ,u.UPDATED_AT_TSTAMP_EST AS SYSTEM_UPDATED_TSTAMP_EST
+        ,fo.FIRST_ORDER_CREATED_TSTAMP_EST
+        ,fd.FIRST_ORDER_DELIVERED_TSTAMP_EST
+    from users u
+    left join first_order fo
+        on u.user_guid = fo.user_guid
+    left join first_delivered_order fd
+        on u.user_guid = fd.user_guid
+
+)
+
+
+SELECT
+*
+from combined

greenery/models/example/marts/Core/fact_orders.sql

@@ -0,0 +1,58 @@
+{{ config(materialized='table') }}
+
+with int_order_table as (
+    SELECT
+    *
+    from {{ref('int_fact_orders')}}
+)
+
+,additions as (
+    SELECT
+
+    --ids
+        o.ORDER_GUID
+        ,o.USER_GUID
+        ,o.PROMO_GUID
+        ,o.ADDRESS_GUID
+        ,o.TRACKING_GUID
+    --timestamps
+        ,o.CREATED_AT_TSTAMP_EST
+        ,o.DELIVERED_AT_TSTAMP_EST
+        ,o.ESTIMATED_DELIVERY_TSTAMP_EST
+    --user
+        ,o.CUSTOMER_FULL_NAME   
+        ,o.SHIP_ADDRESS
+        ,o.SHIP_ZIPCODE
+        ,o.SHIP_STATE
+        ,o.SHIP_COUNTRY
+
+    --order details
+        ,o.SHIPPING_SERVICE
+        ,o.STATUS
+        ,case when estimated_delivery_tstamp_est < delivered_at_tstamp_est then 'Delivered Late'
+            when estimated_delivery_tstamp_est >= delivered_at_tstamp_est then 'Delivered On Time'
+            when delivered_at_tstamp_est is null and estimated_delivery_tstamp_est >= current_timestamp() then 'Pending delivery - On Time'
+            when delivered_at_tstamp_est is null and estimated_delivery_tstamp_est < current_timestamp() then 'Pending delivery - Late'
+            when estimated_delivery_tstamp_est is null then 'No estimated delivery given'
+            else 'NA' 
+        end as delivery_timeframe_compliance
+        ,rank() over (partition by user_guid order by created_at_tstamp_est) as user_order_rank
+        ,case when rank() over (partition by user_guid order by created_at_tstamp_est desc) = 1 then TRUE else FALSE end as user_most_recent_order_flag
+        ,case 
+            when delivered_at_tstamp_est is not null then rank() over (partition by user_guid order by delivered_at_tstamp_est) 
+        end as user_delivered_rank
+
+    --numbers
+        ,o.ORDER_COST
+        ,o.ORDER_DISCOUNT_AMT
+        ,o.PRE_DISCOUNT_TOTAL
+        ,o.CUSTOMER_SHIPPING_COST
+        ,o.CUSTOMER_ORDER_TOTAL
+
+    from int_order_table o
+
+)
+
+SELECT
+*
+from additions

greenery/models/example/marts/Marketing/marketing_models.yml

@@ -0,0 +1,12 @@
+
+version: 2
+
+models:
+  - name: user_order_fact
+    description: "High level information about our users such as most recent order, how many total orders, and customer attributes "
+    columns:
+      - name: user_guid
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null

greenery/models/example/marts/Marketing/user_order_fact.sql

@@ -0,0 +1,55 @@
+{{ config(materialized='table') }}
+
+with user_most_recent_orders as (
+    select
+        user_guid,
+        ship_address,
+        ship_state,
+        ship_zipcode,
+        ship_country,
+        created_at_tstamp_est as last_order_tstamp_est
+    from {{ref('fact_orders')}} fo
+    where user_most_recent_order_flag = TRUE
+)
+
+,user_info as (
+    select
+    *
+    from {{ref('dim_users')}}
+
+)
+
+,user_order_history as (
+    select
+        user_guid,
+        count(distinct order_guid) as order_count,
+        count(distinct case when delivered_at_tstamp_est is not null then order_guid end) as delivered_order_count
+        from {{ref('fact_orders')}}
+    group by 1 
+)
+
+,combined as (
+    select
+        ui.user_guid,
+        ui.full_name,
+        ui.email,
+        ui.phone_number,
+        ui.first_order_created_tstamp_est,
+        ui.first_order_delivered_tstamp_est,
+        uo.ship_address as last_ship_address,
+        uo.ship_state as last_ship_state,
+        uo.ship_zipcode as last_ship_zipcode,
+        uo.ship_country as last_ship_country,
+        uo.last_order_tstamp_est,
+        coalesce(oh.order_count,0) as order_count,
+        coalesce(oh.delivered_order_count,0) as delivered_order_count
+    from user_info ui
+    left join user_order_history oh
+    on ui.user_guid = oh.user_guid
+    left join user_most_recent_orders uo
+    on ui.user_guid = uo.user_guid
+)
+
+SELECT
+*
+from combined

greenery/models/example/marts/Product/fact_page_views.sql

@@ -0,0 +1,49 @@
+{{ config(materialized='table') }}
+
+with website_events as (
+    SELECT
+    *
+    from {{ref('src_events')}}
+    where lower(event_type) = 'page_view'
+)
+
+,products as (
+    SELECT
+    *
+    from {{ref('dim_products')}}
+)
+
+,users as (
+    SELECT
+    *
+    from {{ref('dim_users')}}
+)
+
+,combined as (
+    select 
+    --about event
+        e.event_guid
+        ,e.session_guid
+        ,e.created_at_tstamp_est as event_tstamp_est
+        ,e.page_url
+
+    --about user
+        ,e.user_guid
+        ,u.first_order_created_tstamp_est as user_first_order_tstamp_est
+        ,u.email as user_email
+    --about order   
+        ,order_guid
+
+    --about product
+        ,e.product_guid
+        ,p.product_name
+    from website_events e
+    left join  products p
+    on e.product_guid = p.product_guid
+    left join users u
+    on e.user_guid = u.user_guid
+)
+
+SELECT
+*
+from combined