Wk 4

greenery/.gitignore

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

greenery/README.md

@@ -0,0 +1,16 @@
+Welcome to your new dbt project!
+
+### Using the starter project
+
+Try running the following commands:
+- dbt run
+- dbt test
+
+
+### Resources:
+- Learn more about dbt [in the docs](https://docs.getdbt.com/docs/introduction)
+- Check out [Discourse](https://discourse.getdbt.com/) for commonly asked questions and answers
+- Join the [chat](https://community.getdbt.com/) on Slack for live discussions and support
+- Find [dbt events](https://events.getdbt.com) near you
+- Check out [the blog](https://blog.getdbt.com/) for the latest news on dbt's development and best practices
+

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: tables
+    marts: 
+      +post-hook: 
+        - "GRANT SELECT ON {{ this }} TO ROLE reporting;"
+
+snapshots:
+  greenery: 
+    target_schema: dbt_ple
+    target_database: dev_db

greenery/macros/get_event_types.sql

@@ -0,0 +1,21 @@
+{% macro get_event_types() %}
+
+{% set event_types_query %}
+select distinct
+event_type
+from stg_events
+order by 1
+{% endset %}
+
+{% set results = run_query(event_types_query) %}
+
+{% if execute %}
+{# Return the first column #}
+{% set results_list = results.columns[0].values() %}
+{% else %}
+{% set results_list = [] %}
+{% endif %}
+
+{{ return(results_list) }}
+
+{% endmacro %}

greenery/macros/grant_select.sql

@@ -0,0 +1,9 @@
+{% macro grant_select(role) %}
+
+    {% set sql %}
+      GRANT SELECT ON {{ this }} TO ROLE {{ role }};
+    {% endset %}
+
+    {% set table = run_query(sql) %}
+
+{% endmacro %}

greenery/macros/positive_values.sql

@@ -0,0 +1,10 @@
+
+{% test positive_values(model, column_name) %}
+
+
+   select *
+   from {{ model }}
+   where {{ column_name }} < 0
+
+
+{% endtest %}

greenery/models/example/my_first_dbt_model.sql

@@ -0,0 +1,27 @@
+
+/*
+    Welcome to your first dbt model!
+    Did you know that you can also configure models directly within SQL files?
+    This will override configurations stated in dbt_project.yml
+
+    Try changing "table" to "view" below
+*/
+
+{{ config(materialized='table') }}
+
+with source_data as (
+
+    select 1 as id
+    union all
+    select null as id
+
+)
+
+select *
+from source_data
+
+/*
+    Uncomment the line below to remove records with null `id` values
+*/
+
+-- where id is not null

greenery/models/example/my_second_dbt_model.sql

@@ -0,0 +1,6 @@
+
+-- Use the `ref` function to select from other models
+
+select *
+from {{ ref('my_first_dbt_model') }}
+where id = 1

greenery/models/example/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/intermediate/_intermediate.yml

@@ -0,0 +1,134 @@
+version: 2
+
+models:
+  - name: int_user_address
+    description: "All user information"
+    columns:
+      - name: user_id
+        description: "unqiue user id"
+        tests: 
+          - unique
+          - not_null
+
+      - name: first_name
+        description: "user first name"
+
+      - name: last_name
+        description: "user last name"
+
+      - name: email
+        description: "user email"
+
+      - name: phone_number
+        description: "user phone number"
+
+      - name: created_at
+        description: "user created at date and time"
+        tests: 
+         - not_null
+
+      - name: updated_at
+        description: "user information update date and time"
+        tests: 
+         - not_null
+
+      - name: address_id
+        description: "user address id"
+        tests: 
+         - not_null
+
+      - name: address
+        description: "user address"
+
+      - name: zipcode
+        description: "user zipcode"
+
+      - name: state
+        description: "user state"
+
+      - name: country
+        description: "user country"
+
+  - name: int_user_events
+    description: "user events data"
+    columns:
+      - name: user_id
+        description: "unique user id per event session on the site"
+        tests: 
+         - unique
+         - not_null
+
+      - name: num_sessions
+        description: "total number of sessions per user id"
+
+      - name: first_session_date
+        description: "user first session"
+        tests: 
+          - not_null
+
+      - name: last_session_date
+        description: "user last session"
+        tests: 
+          - not_null
+
+      - name: total_session_duration
+        description: "total hours user spent on the site"
+
+      - name: checkout
+        description: "user checked out during session"
+
+      - name: package_shipped
+        description: "user's package was shipped during session"
+
+      - name: page_view
+        description: "user viewed a page during session"
+
+      - name: add_to_cart
+        description: "user added to cart during session"
+
+      - name: total_orders
+        description: "total orders related to the session"
+
+      - name: total_products
+        description: "total products related to the session"
+
+  - name: int_user_orders
+    description: "total order information by user"
+    columns:
+      - name: user_id
+        description: "unique user_id"
+
+      - name: total_orders
+        description: "total orders each user purchased"
+        tests: 
+         - positive_values
+
+      - name: total_promos_used
+        description: "total promo code used for all orders"
+
+      - name: recent_order_date
+        description: "most recent order date"
+
+      - name: total_spent
+        description: "total spent on all orders by user"
+        test:
+         - positive_values
+
+  - name: int_product_conv_rate
+    description: "product conversion rate"
+    columns:
+      - name: product_id
+        description: "product id"
+
+      - name: total_orders
+        description: "total orders each user purchased by product"
+        tests: 
+         - positive_values
+
+      - name: total_sessions
+        description: "total sessions by product"
+
+      - name: conversion_rate
+        description: "total orders divide by total sessions by product"
+
+

greenery/models/intermediate/int_product_conv_rate.sql

@@ -0,0 +1,37 @@
+
+{{
+  config(
+    materialized='table'
+  )
+}}
+
+with ts as (
+select 
+    split_part(page_url, '/',5) product_id,
+    products.name product_name,
+    count( distinct events.session_id) total_sessions
+from {{ ref('stg_events')}} events
+join {{ ref('stg_products')}} products
+on events.product_id = products.product_id
+group by 1,2),
+
+cs as (
+select 
+    orders.product_id,
+    products.name product_name,
+    count(  orders.order_id) total_orders
+from {{ ref('stg_order_items')}} orders
+left join {{ ref('stg_products')}} products
+on orders.product_id = products.product_id
+group by 1,2)
+
+select 
+ts.product_id,
+ts.product_name,
+cs.total_orders,
+ts.total_sessions,
+cs.total_orders/ts.total_sessions conversion_rate
+from ts
+left join cs
+on ts.product_id = cs.product_id
+order by conversion_rate desc 

greenery/models/intermediate/int_user_address.sql

@@ -0,0 +1,23 @@
+{{
+  config(
+    materialized='table'
+  )
+}}
+
+
+select
+  u.user_id,
+  u.first_name,
+  u.last_name,
+  u.email,
+  u.phone_number,
+  u.created_at,
+  u.updated_at,
+  u.address_id,
+  a.address,
+  lpad(a.zipcode:: varchar, 5,'0') as zipcode,
+  a.state,
+  a.country
+from {{ ref('stg_users')}} u
+left join {{ ref('stg_addresses')}} a
+on u.address_id = a.address_id

greenery/models/intermediate/int_user_events.sql

@@ -0,0 +1,22 @@
+
+{{
+  config(
+    materialized='table'
+  )
+}}
+
+{%- set event_types = get_event_types() -%}
+
+select
+  e.user_id,
+  count(distinct e.session_id) num_sessions,
+  min(e.created_at) first_session_date,
+  max(e.created_at) last_session_date,
+  datediff(hour, first_session_date, last_session_date) total_session_duration,
+  count(e.order_id) total_orders,
+  count(e.product_id) total_products
+  {%- for event_type in event_types %}
+    ,sum(case when event_type = '{{event_type}}' then 1 else 0 end) {{event_type}}
+    {%- endfor %}
+from {{ ref('stg_events')}} e
+group by 1