Week 2

greenery/.gitignore

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

greenery/README.md

@@ -0,0 +1,36 @@
+Week 3 Answers:
+
+Overall Conversion Rate: 62.5%
+
+Product level conversion:
+product_id	conversion rate
+fb0e8be7-5ac4-4a76-a1fa-2cc4bf0b2d80	0.676923077
+5b50b820-1d0a-4231-9422-75e7f6b0cecf	0.533333333
+80eda933-749d-4fc6-91d5-613d29eb126f	0.5
+be49171b-9f72-4fc9-bf7a-9a52e259836b	0.530612245
+64d39754-03e4-4fa0-b1ea-5f4293315f67	0.508474576
+74aeb414-e3dd-4e8a-beef-0fa45225214d	0.609375
+55c6a062-5f4a-4a8b-a8e5-05ea5e6715a3	0.507936508
+58b575f2-2192-4a53-9d21-df9a0c14fc25	0.516129032
+d3e228db-8ca5-42ad-bb0a-2148e876cc59	0.464285714
+e18f33a6-b89a-4fbc-82ad-ccba5bb261cc	0.422535211
+c7050c3b-a898-424d-8d98-ab0aaad7bef4	0.493333333
+bb19d194-e1bd-4358-819e-cd1f1b401c0c	0.5
+37e0062f-bd15-4c3e-b272-558a86d90598	0.548387097
+05df0866-1a66-41d8-9ed7-e2bbcddd6a3d	0.55
+6f3a3072-a24d-4d11-9cef-25b0b5f8a4af	0.5
+615695d3-8ffd-4850-bcf7-944cf6d3685b	0.553846154
+579f4cd0-1f45-49d2-af55-9ab2b72c3b35	0.571428571
+e8b6528e-a830-4d03-a027-473b411c7f02	0.465753425
+843b6553-dc6a-4fc4-bceb-02cd39af0168	0.514705882
+5ceddd13-cf00-481f-9285-8340ab95d06d	0.550724638
+35550082-a52d-4301-8f06-05b30f6f3616	0.533333333
+4cda01b9-62e2-46c5-830f-b7f262a58fb1	0.375
+689fb64e-a4a2-45c5-b9f2-480c2155624d	0.608695652
+b66a7143-c18a-43bb-b5dc-06bb5d1d3160	0.538461538
+e706ab70-b396-4d30-a6b2-a1ccf3625b52	0.508474576
+e5ee99b6-519f-4218-8b41-62f48f59f700	0.52238806
+b86ae24b-6f59-47e8-8adc-b17d88cbd367	0.603773585
+c17e63f7-0d28-4a95-8248-b01ea354840e	0.581818182
+a88a23ef-679c-4743-b151-dc7722040d8c	0.52173913
+e2e78dfc-f25c-4fec-a002-8e280d61a2f2	0.53968254

greenery/dbt_project.yml

@@ -0,0 +1,46 @@
+
+# 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/
+    staging:
+      +materialized: view
+    marts:
+      +materialized: table
+
+  post-hook:
+      - "GRANT SELECT ON {{this}} TO reporting"
+
+on-run-end:
+    - "GRANT USAGE ON SCHEMA {{schema}} TO reporting"

greenery/macros/event_type_agg.sql

@@ -0,0 +1,3 @@
+{%- macro events(event_type) -%}
+    SUM(CASE WHEN event_type = '{{event_type}}' THEN 1 ELSE 0 END)
+{%- endmacro -%}

greenery/models/models/marts/core/intermediate/int_order_products.sql

@@ -0,0 +1,12 @@
+{{ config (materialized='table')}}
+
+SELECT
+    order_id,
+    order_items_surrogate_key,
+    o.product_id,
+    product_name,
+    price,
+    inventory as available_inventory,
+    quantity as quanity_purchased
+FROM {{ref('stg_greenery_order_items')}} o
+JOIN {{ref('stg_greenery_products')}} p ON p.product_id = o.product_id

greenery/models/models/marts/core/schema.yml

@@ -0,0 +1,10 @@
+version: 2
+
+models:
+  - name: int_order_products
+    description: Detailed product descriptions for order lines
+    columns:
+      - name: order_items_surrogate_key
+        tests:
+          - unique
+          - not_null

greenery/models/models/marts/marketing/intermediate/int_user_orders.sql

@@ -0,0 +1,37 @@
+{{ config (materialized='table')}}
+
+WITH user_order_count as (
+SELECT
+    user_id,
+    count(order_id) as order_count
+FROM {{ref('stg_greenery_orders')}}
+WHERE order_status = 'delivered'
+GROUP BY 1
+)
+
+SELECT
+    u.user_id,
+    u.first_name,
+    u.last_name,
+    u.email,
+    u.phone_number,
+    u.user_address_id,
+    ua.address,
+    ua.zipcode,
+    ua.state,
+    ua.country,
+    o.address_id,
+    o.order_created_at_utc,
+    o.order_cost,
+    shipping_cost,
+    order_total,
+    order_tracking_id,
+    shipping_service,
+    order_estimated_delivery_at_utc,
+    order_delivered_at_utc,
+    order_status,
+    COALESCE(order_count,0) as user_order_count
+FROM {{ref('stg_greenery_users')}} u
+JOIN {{ref('stg_greenery_orders')}} o on o.user_id = u.user_id
+JOIN {{ref('stg_greenery_addresses')}} ua on ua.address_id = u.user_address_id
+LEFT JOIN user_order_count uc on uc.user_id = u.user_id

greenery/models/models/marts/marketing/schema.yml

@@ -0,0 +1,10 @@
+version: 2
+
+models:
+  - name: int_user_orders
+    description: Order data structured around the users placing them
+    columns:
+      - name: order_id
+        tests:
+          - unique
+          - not_null

greenery/models/models/marts/product/fct_product_conversion.sql

@@ -0,0 +1,15 @@
+
+{%- set event_types = dbt_utils.get_column_values(
+    table=ref('stg_greenery_events'),
+    column='event_type'
+) -%}
+
+SELECT
+    p.product_id
+    {%- for event in event_types %}
+  , {{events(event)}} AS {{event}}_counts
+  {%- endfor %} 
+
+from {{ref('stg_greenery_products')}} p
+left join {{ref('stg_greenery_events')}} e on e.product_id = p.product_id
+group by 1

greenery/models/models/marts/product/fct_sessions.sql

@@ -0,0 +1,13 @@
+{{ config (materialized='table')}}
+
+SELECT
+    session_id,
+    u.user_id,
+    u.first_name,
+    u.last_name,
+    session_first_event,
+    session_last_event,
+    session_last_event - session_first_event as session_length,
+    case when session_conversion_events > 0 then TRUE else FALSE end as session_converted
+FROM {{ref('int_session_events')}} s
+LEFT JOIN {{ref('stg_greenery_users')}} u on u.user_id = s.user_id

greenery/models/models/marts/product/intermediate/int_session_events.sql

@@ -0,0 +1,19 @@
+{{ config (materialized='table')}}
+
+{%- set event_types = dbt_utils.get_column_values(
+    table=ref('stg_greenery_events'),
+    column='event_type'
+) -%}
+
+SELECT
+    session_id,
+    user_id,
+    min(created_at_utc) as session_first_event,
+    max(created_at_utc) as session_last_event,
+    sum(case when order_id is not null then 1 else 0 end) AS session_conversion_events
+    {%- for event in event_types %}
+  , {{events(event)}} AS {{event}}_counts
+  {%- endfor %} 
+
+FROM {{ref('stg_greenery_events')}} e 
+GROUP BY 1,2

greenery/models/models/marts/product/schema.yml

@@ -0,0 +1,17 @@
+version: 2
+
+models:
+  - name: int_session_events
+    description: Basic details about the sessions associated with events
+    columns:
+      - name: session_id
+        tests:
+          - unique
+          - not_null
+  - name: fct_sessions
+    description: Aggregated session performance data
+    columns:
+      - name: session_id
+        tests:
+          - unique
+          - not_null

greenery/models/models/schema.yml

@@ -0,0 +1,21 @@
+
+version: 2
+
+models:
+  - name: my_first_dbt_model
+    description: "A starter dbt model"
+    columns:
+      - name: id
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null
+
+  - name: my_second_dbt_model
+    description: "A starter dbt model"
+    columns:
+      - name: id
+        description: "The primary key for this table"
+        tests:
+          - unique
+          - not_null

greenery/models/models/staging/README.md

@@ -0,0 +1,68 @@
+How many users do we have?
+A: 130
+<!-- SQL: select count(distinct user_id) from dbt_charlie_m.tbl_users -->
+
+On average, how many orders do we receive per hour?
+A: 7.5
+SQL: 
+<!-- 
+with hour_orders as (
+select 
+  date_trunc('hour', created_at) as order_hour,
+  count(order_id) as order_count
+from dbt_charlie_m.tbl_orders
+group by 1
+)
+select avg(order_count)
+from hour_orders 
+-->
+
+On average, how long does an order take from being placed to being delivered?
+A: 3 days, 21 hours
+SQL:
+<!-- with x as (
+select 
+  order_id,
+  date_trunc('hour', delivered_at_utc) - date_trunc('hour', created_at) as diff,
+  created_at
+
+from dbt_charlie_m.tbl_orders
+where status = 'delivered'
+)
+select avg(diff) from x -->
+
+How many users have only made one purchase? Two purchases? Three+ purchases?
+A: 1 order: 25; 2 orders: 28; 3+ orders: 71
+SQL:
+<!-- 
+with user_order_count as (
+select
+  user_id,
+  count(order_id) as order_count
+
+from dbt_charlie_m.tbl_orders
+group by 1
+)
+
+select
+  count(case when order_count = 1 then user_id else null end) as one_order,
+  count(case when order_count = 2 then user_id else null end) as two_orders,
+  count(case when order_count >= 3 then user_id else null end) as three_plus_orders
+from user_order_count -->
+
+On average, how many unique sessions do we have per hour?
+A: 16.3
+SQL:
+<!-- 
+with hour_sessions as (
+select
+  date_trunc('hour', created_at_utc) as hour,
+  count(distinct session_id) as unique_sessions
+from dbt_charlie_m.tbl_events
+group by 1
+)
+
+select
+  avg(unique_sessions) as avg_session_count
+from hour_sessions
+ -->

greenery/models/models/staging/greenery_sources.yml

@@ -0,0 +1,37 @@
+version: 2
+sources:
+  - name: greenery_src
+    schema: public
+    database: dbt
+    quoting:
+      database: false
+      schema: false
+      identifier: false
+    freshness:
+      warn_after: {count: 24, period: hour}
+      error_after: {count: 48, period: hour}
+    tables:
+      - name: addresses
+        description: >
+          Contains delivery location information associated with greenery's users (GDPR)
+      - name: events
+        loaded_at_field: created_at
+        description: >
+          Contains information regarding greenery's users site events
+      - name: orders
+        loaded_at_field: created_at
+        description: >
+          Contains information regarding orders, deliveries and shipping
+      - name: order_items
+        description: >
+          Contains list of items per order
+      - name: products
+        description: >
+          Contains information regarding greenery's products
+      - name: promos
+        description: >
+          Contains information regarding greenery's promotions
+      - name: users
+        loaded_at_field: created_at
+        description: >
+          Contains demographic information and contact details for greenery's users (GDPR)

greenery/models/models/staging/stg_greenery_addresses.sql

@@ -0,0 +1,20 @@
+{{config(
+    materialized='table'
+) }}
+
+with sources as (
+    select * from {{ source('greenery_src', 'addresses') }} as addresses
+)
+
+, rename_recast as (
+    SELECT
+        address_id,
+        address,
+        zipcode,
+        state,
+        country
+
+    FROM sources
+)
+
+select * from rename_recast