project_week1_

greenery/.gitignore

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

greenery/README.md

@@ -0,0 +1,15 @@
+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/README_project_answers.md

@@ -0,0 +1,54 @@
+1] How many users do we have?
+    - We have 130 distinct users
+    select count(distinct user_id)
+    from DEV_DB.DBT_KLYMPERIFLEXPORTCOM.STG_USERS
+
+2] On average, how many orders do we receive per hour?
+    - On average receive 7.5 orders per hour
+    with 
+    cte_orders_per_hour as (
+    select
+    date_trunc('hour', created_at) as order_hour,
+    count(distinct order_id) as total_hourly_orders
+    from DEV_DB.DBT_KLYMPERIFLEXPORTCOM.stg_orders
+    group by 1
+    )
+    select 
+        round(avg(total_hourly_orders),1) as avg_hourly_orders
+    from cte_orders_per_hour;
+
+3] On average, how long does an order take from being placed to being delivered?
+    - On average we take 3.9 days to deliver the goods from the time of placing the order
+    select
+    round(avg(datediff(days, created_at, delivered_at)),1) as days_to_delivery
+    from DEV_DB.DBT_KLYMPERIFLEXPORTCOM.stg_orders
+
+4] How many users have only made one purchase? Two purchases? Three+ purchases?
+   - In our historical data we have 25 users that placed 1 order, 28 users with 2 orders while 71 ordered more than 3.
+   with order_count as (
+    select
+        user_id,
+        count(order_id) as total_orders
+    from DEV_DB.DBT_KLYMPERIFLEXPORTCOM.stg_orders
+    group by 1)
+
+    select
+        sum(case when total_orders = 1 then 1 else 0 end) as nr_users_1_order,
+        sum(case when total_orders = 2 then 1 else 0 end) as nr_users_2_order,
+        sum(case when total_orders >= 3 then 1 else 0 end) as nr_users_3_order
+    from order_count;
+
+5] On average, how many unique sessions do we have per hour?
+    -We average at 16.3 sessions per hour
+    with
+        cte_hourly_sessions as (
+        select
+        date_trunc('hour', created_at) as hourly_session,
+        count(distinct session_id) as total_sessions
+    from DEV_DB.DBT_KLYMPERIFLEXPORTCOM.stg_events
+    group by 1)
+
+    select 
+        round(avg(total_sessions),1) as avg_hourly_sessions
+    from cte_hourly_sessions;
+

greenery/dbt_project.yml

@@ -0,0 +1,37 @@
+
+# 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"]
+
+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 views. 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

greenery/macros/lbs_to_kgs.sql

@@ -0,0 +1,6 @@
+{% macro lbs_to_kgs(column_name, precision=2) %}
+    ROUND(
+       (CASE WHEN {{ column_name }} = -99 THEN NULL ELSE {{ column_name }} END / 2.205)::NUMERIC, 
+       {{ precision }}
+    )
+{% endmacro %}

greenery/macros/positive_values.sql

@@ -0,0 +1,8 @@
+{% 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/staging/postgres/_postgres__models.yml

@@ -0,0 +1,45 @@
+version: 2
+
+models:
+  - name: stg_addresses
+    description: Addresses in the platform with geographical dimentions
+    columns:
+     - name: address_id
+       tests:
+          - unique
+  - name: stg_events
+    description: All events occuring on the platform with url, product type, users, timestamps
+    columns:
+     - name: event_id
+       tests:
+          - unique
+  - name: stg_order_items
+    description: Information on quantity of items and product in a specific order
+    columns:
+     - name: order_id
+       tests:
+          - unique
+  - name: stg_orders
+    description: All platform orders with metdata info such as user, costs, delivery times etc
+    columns:
+     - name: order_id
+       tests:
+          - unique
+  - name: stg_products
+    description: Products on the platform with name, price and inventory availability
+    columns:
+     - name: product_id
+       tests:
+          - unique
+  - name: stg_promos
+    description: Promotion codes and discounts
+    columns:
+     - name: promo_id
+       tests:
+          - unique
+  - name: stg_users
+    description: Platfom's users personal information
+    columns:
+     - name: user_id
+       tests:
+          - unique

greenery/models/staging/postgres/_postgres__sources.yml

@@ -0,0 +1,23 @@
+version: 2
+
+sources:
+
+  - name: postgress # this data originates from postgress
+    schema: public # this is the schema our raw data lives in
+    database: raw # this is the name of the database that our source data lives in
+
+    quoting:
+      database: false
+      schema: false
+      identifier: false
+
+
+    tables:
+      # The source tables with raw data from postgress
+      - name: events
+      - name: users
+      - name: addresses
+      - name: orders
+      - name: products
+      - name: order_items
+      - name: promos

greenery/models/staging/postgres/stg_addresses.sql

@@ -0,0 +1,15 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    address_id,
+    address,
+    zipcode,
+    state,
+    country
+from {{ source ('postgress', 'addresses') }}

greenery/models/staging/postgres/stg_events.sql

@@ -0,0 +1,18 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    event_id,
+    session_id,
+    user_id,
+    page_url,
+    created_at,
+    event_type
+    order_id,
+    product_id
+from {{ source ('postgress', 'events') }}

greenery/models/staging/postgres/stg_order_items.sql

@@ -0,0 +1,13 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    order_id,
+    product_id,
+    quantity
+from {{ source ('postgress', 'order_items') }}

greenery/models/staging/postgres/stg_orders.sql

@@ -0,0 +1,23 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    order_id,
+    user_id,
+    promo_id,
+    address_id,
+    created_at,
+    order_cost,
+    shipping_cost,
+    order_total,
+    tracking_id,
+    shipping_service,
+    estimated_delivery_at,
+    delivered_at,
+    status
+from {{ source ('postgress', 'orders') }}

greenery/models/staging/postgres/stg_products.sql

@@ -0,0 +1,14 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    product_id,
+    name,
+    price,
+    inventory
+from {{ source ('postgress', 'products') }}

greenery/models/staging/postgres/stg_promos.sql

@@ -0,0 +1,13 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    promo_id,
+    discount,
+    status
+from {{ source ('postgress', 'promos') }}

greenery/models/staging/postgres/stg_users.sql

@@ -0,0 +1,18 @@
+--snowflake_warehouse env_var is to demosntrate another config we can apply. In our case we only have 1 size of 
+--transformer_dev warehouse but we could have multiple and depending on model requirements
+--we could choose to run/deploy against a bigger warehouse
+{{ config(
+     materialized='table',
+     snowflake_warehouse=env_var('SNOWFLAKE_WAREHOUSE_XS'))
+}}
+
+select
+    user_id,
+    first_name,
+    last_name,
+    email,
+    phone_number,
+    created_at,
+    updated_at,
+    address_id
+from {{ source ('postgress', 'users') }}