Project w2

greenery/.gitignore

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

greenery/Project 1/readme.md

@@ -0,0 +1,108 @@
+# Week 1 Project:
+
+**Question :**  
+How many users do we have?  
+
+**Answer :**  
+130 unique users  
+
+**Query :**  
+
+```sql  
+SELECT COUNT(DISTINCT(user_id)) AS COUNT
+FROM dev_db.dbt_burjack86gmailcom.stg_postgres__users
+```
+
+---  
+
+**Question :**  
+On average, how many orders do we receive per hour?  
+
+**Answer :**  
+On average, we receive approximately 15 orders per hour
+
+**Query :**  
+
+```sql
+SELECT DISTINCT
+    AVG(COUNT(*)) OVER () AS avg_orders_per_hour
+FROM
+    dev_db.dbt_burjack86gmailcom.stg_postgres__orders
+GROUP BY
+    EXTRACT(HOUR FROM created_at)
+```
+
+---  
+
+**Question :**    
+On average, how long does an order take from being placed to being delivered?  
+
+**Answer :**  
+On average, it takes almost 4 days (circa 3 days and 22 hours) for an order to be delivered.
+
+**Query :**  
+
+```sql
+SELECT AVG(DATEDIFF(DAY, created_at, delivered_at)) AS avg_delivery_days
+FROM dev_db.dbt_burjack86gmailcom.stg_postgres__orders
+WHERE status = 'delivered'
+```
+
+---  
+
+**Question :**  
+How many users have only made one purchase? Two purchases? Three+ purchases?  
+
+**Answer :** 
+Users by number of purchases are as follows:
+One purchase = 25  
+Two purchases = 28  
+Three+ purchases = 71  
+
+**Query :**  
+
+```sql
+WITH agg_purchases AS(
+SELECT
+    COUNT(DISTINCT(order_id)) AS order_count
+    , CASE 
+        WHEN order_count = 1 THEN '=1'
+        WHEN order_count = 2 THEN '=2'
+        WHEN order_count >= 3 THEN '>= 3'
+    END AS purchase_cohort
+FROM dev_db.dbt_burjack86gmailcom.stg_postgres__orders
+GROUP BY user_id
+)
+
+SELECT
+    purchase_cohort,
+    COUNT(order_count) AS order_count
+FROM agg_purchases
+GROUP BY purchase_cohort
+```
+
+---  
+
+**Question :**    
+On average, how many unique sessions do we have per hour?  
+
+**Answer :**    
+On average, there are almost 40 sessions per hour (39.46).
+
+**Query :**  
+
+```sql
+WITH sessions_hour AS (
+SELECT DISTINCT
+    EXTRACT(HOUR FROM created_at),
+    COUNT(DISTINCT(session_id)) AS sessions_per_hour
+FROM dev_db.dbt_burjack86gmailcom.stg_postgres__events
+GROUP BY EXTRACT(HOUR FROM created_at)
+ORDER BY EXTRACT(HOUR FROM created_at)
+)
+
+SELECT 
+AVG(sessions_per_hour) AS avg_sessions_per_hour
+FROM sessions_hour
+```
+

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/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/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/marts/Marketing/fact_users_orders.sql

@@ -0,0 +1,18 @@
+{{
+  config(
+    materialized='table'
+  )
+}}
+
+SELECT 
+    u.user_id
+    , count(o.order_id) AS  count_orders
+    , count(case when o.promo_id is not null then o.promo_id end) AS count_promo_orders
+    , date(min(o.created_at)) AS first_order_date
+    , date(max(o.created_at)) AS last_order_date
+    , round(avg(o.order_total),2) AS avg_order_total
+FROM {{ ref ('stg_postgres__users') }} u 
+LEFT JOIN {{ ref ('stg_postgres__orders') }} o 
+ON u.user_id = o.user_id
+WHERE o.status = 'delivered'
+group by all

greenery/models/staging/postgres/_postgres__sources.yml

@@ -0,0 +1,30 @@
+version: 2
+
+sources:
+
+  - name: postgres # project name
+    schema: public 
+    database: raw 
+
+    tables:
+      - name: addresses
+        description: >
+          Address IDs for each customer
+      - name: users
+        description: >
+          Table that has customers ID and information
+      - name: promos
+        description: >
+          Promo codes, status, and discounts.
+      - name: products
+        description: >
+          Products list including name, price, and inventory.
+      - name: orders
+        description: >
+          Oders event table.
+      - name: order_items
+        description: >
+          Producsts for each order event.
+      - name: events
+        description: >
+          Events by user and webpage.

greenery/models/staging/postgres/stg_postgres__addresses.sql

@@ -0,0 +1,2 @@
+select ADDRESS_ID, ADDRESS, ZIPCODE, STATE, COUNTRY
+from {{source('postgres', 'addresses')}}

greenery/models/staging/postgres/stg_postgres__addresses.yml

@@ -0,0 +1,19 @@
+version: 2
+
+models:
+  - name: stg_postgres__addresses
+    description: Table for customer adresses
+    columns:
+      - name: address_id
+        description: Unique address ID in the platform (Primary key)
+        tests:
+          - unique
+          - not_null
+      - name: address
+        description: Address description (street number, name etc)
+      - name: zipcode
+        description: The zipcode
+      - name: state
+        description: Address' State 
+      - name: country
+        description: Address' country 

greenery/models/staging/postgres/stg_postgres__events.sql

@@ -0,0 +1,2 @@
+select EVENT_ID, SESSION_ID, USER_ID, PAGE_URL, CREATED_AT, EVENT_TYPE, ORDER_ID, PRODUCT_ID
+from {{source('postgres', 'events')}}

greenery/models/staging/postgres/stg_postgres__events.yml

@@ -0,0 +1,26 @@
+version: 2
+
+models:
+
+  - name: stg_postgres__events
+    description: Events based on customers interaction with website
+    columns:
+      - name: event_id
+        description: Unique event ID in the platform (Primary key)
+        tests:
+          - unique
+          - not_null
+      - name: session_id
+        description: session browsing ID  (Primary key)
+      - name: user_id
+        description: User ID indicating to whom the event is associated with
+      - name: page_url
+        description: URL of the event
+      - name: created_at
+        description: Timestamp of the event 
+      - name: event_type
+        description: Type of event 
+      - name: order_id
+        description: Order ID related to the event if there was one
+      - name: product_id
+        description: Product ID related to the event if there was one

greenery/models/staging/postgres/stg_postgres__order_items.sql

@@ -0,0 +1,2 @@
+select ORDER_ID, PRODUCT_ID, QUANTITY
+from {{source('postgres', 'order_items')}}

greenery/models/staging/postgres/stg_postgres__order_items.yml

@@ -0,0 +1,13 @@
+version: 2
+
+models:
+
+  - name: stg_postgres__order_items
+    description: Table that links orders with products and quantities
+    columns:
+      - name: order_id
+        description: Order ID
+      - name: product_id
+        description: Product ID
+      - name: quantity
+        description: Quantity ordered

greenery/models/staging/postgres/stg_postgres__orders.sql

@@ -0,0 +1,2 @@
+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('postgres', 'orders')}}

greenery/models/staging/postgres/stg_postgres__orders.yml

@@ -0,0 +1,36 @@
+version: 2
+
+models:
+
+  - name: stg_postgres__orders
+    description: Table with customers orders and its information
+    columns:
+      - name: order_id
+        description: Unique order ID in the platform (Primary key)
+        tests:
+          - unique
+          - not_null
+      - name: user_id
+        description: User ID related to the order
+      - name: promo_id
+        description: Promo ID if there was on applied to the order
+      - name: address_id
+        description: Delivery address ID
+      - name: created_at
+        description: Timestamp indicating when the order was created
+      - name: order_cost
+        description: Cost for the respective order
+      - name: shipping_cost
+        description: Cost of shipping
+      - name: order_total
+        description: Total cost of the order
+      - name: tracking_id
+        description: Tracking number for the order
+      - name: shipping_service
+        description: Company that was used for shipping
+      - name: estimated_delivery_at
+        description: Estimated date of delivery
+      - name: delivered_at
+        description: Actual time of delivery
+      - name: status
+        description: Order Status

greenery/models/staging/postgres/stg_postgres__products.sql

@@ -0,0 +1,2 @@
+select PRODUCT_ID, NAME, PRICE, INVENTORY
+from {{source('postgres', 'products')}}