Week 2 project

greenery/.gitignore

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

greenery/README.md

@@ -0,0 +1,52 @@
+# Week 1
+
+## Metrics:
+
+- **Total Users**: The total number of unique users registered on the platform.
+- **Average Orders per Hour**: The average number of orders placed every hour.
+- **Average Hours to Deliver**: On average, the number of hours it takes from an order being placed to being delivered.
+- **Users by Purchase Count**: How many users have made one, two, or three or more purchases.
+- **Average Sessions per Hour**: The average number of unique browsing sessions on the platform every hour.
+
+## Results:
+
+| Metric                          | Value      |
+|---------------------------------|------------|
+| Total Users                     | 130        |
+| Average Orders per Hour         | 7.520      |
+| Average Hours to Deliver        | 93.403     |
+| Users with One Purchase         | 25         |
+| Users with Two Purchases        | 28         |
+| Users with Three+ Purchases     | 71         |
+| Average Sessions per Hour       | 16.327     |
+
+
+# Week 2
+
+## Business objectives:
+
+- **What is our user repeat rate?**: The ratio of users who made two or more purchases over total users.
+- **Define good indicators for potential repeat users**
+- **Define good indicators for potential non-repeat users**
+
+
+## Results:
+
+| Metric                          | Value      |
+|---------------------------------|------------|
+| Repeat rate                     | 79.84%     |
+
+- **Define good indicators for potential repeat users**
+  - **Number of itens on previous order**
+  - **Usage of promo codes**
+  - **Number of sessions until purchase**
+  - **Average delivery time for the user**
+  - **Good Reviews on the products**
+  - **Good Reviews of the platform itself**
+
+- **Define good indicators for potential non-repeat users**
+  - **Type of product ordered (one-type purchases)**
+  - **Email spam rate**
+  - **Average delivery time for the user**
+  - **Bad Reviews on the products**
+  - **Bad Reviews of the platform itself**

greenery/analyses/week_1_project.sql

@@ -0,0 +1,90 @@
+WITH 
+	--1. How many users do we have?
+	qtt_users AS (
+		SELECT
+			COUNT(DISTINCT user_id) AS distinct_users
+		FROM {{ ref("stg_postgres__users") }}
+	)--qtt_users
+
+
+
+	--2. On average, how many orders do we receive per hour?
+	, orders_per_hour AS (
+		SELECT
+			date_trunc('HOUR', created_at) AS hour
+			, COUNT(DISTINCT order_id) 	   AS order_count
+		FROM {{ ref("stg_postgres__orders") }}
+		GROUP BY date_trunc('HOUR', created_at)
+	)--orders_per_hour
+
+
+	, avg_orders_per_hour AS (
+		SELECT
+			AVG(order_count) 	   AS avg_order_per_hour
+		FROM orders_per_hour
+	)--avg_orders_per_hour
+
+
+	--3. On average, how long does an order take from being placed to being delivered?
+	, avg_delivery_time AS (
+        SELECT 
+			AVG(DATEDIFF(hour, created_at, delivered_at)) AS avg_hours_to_deliver
+        FROM {{ ref("stg_postgres__orders") }}
+        WHERE delivered_at IS NOT NULL
+	)--avg_delivery_time
+
+
+
+	-- 4. How many users have only made one purchase? Two purchases? Three+ purchases?
+    , purchases_by_user AS (
+        SELECT 
+			user_id
+			, COUNT(DISTINCT order_id) AS total_purchases
+        FROM {{ ref("stg_postgres__orders") }}
+        GROUP BY user_id
+    )--purchases_by_user  
+
+	, purchase_counter AS (
+        SELECT
+            SUM(CASE WHEN total_purchases = 1 THEN 1 ELSE 0 end)  AS users_with_one_purchase
+            , SUM(CASE WHEN total_purchases = 2 THEN 1 ELSE 0 end)  AS users_with_two_purchase
+            , SUM(CASE WHEN total_purchases >= 3 THEN 1 ELSE 0 end) AS users_with_three_purchase
+        FROM purchases_by_user
+    )--purchase_counter
+
+
+
+    -- 5. On average, how many unique sessions do we have per hour?
+    ,sessions_per_hour AS (
+        SELECT
+            DATE_TRUNC('HOUR', created_at) AS session_hour
+            , COUNT(DISTINCT session_id)     AS session_count
+        FROM {{ ref("stg_postgres__events") }}
+        GROUP BY DATE_TRUNC('HOUR', created_at) 
+    )
+
+    avg_sessions_per_hour AS (
+        SELECT 
+			AVG(session_count) AS avg_session_per_hour 
+		FROM sessions_per_hour
+    )
+
+
+
+SELECT
+	qtt_users.distinct_users
+	, avg_orders_per_hour.avg_order_per_hour 
+	, avg_delivery_time.avg_hours_to_deliver
+	, purchase_counter.users_with_one_purchase
+	, purchase_counter.users_with_two_purchase
+	, purchase_counter.users_with_three_purchase
+	, avg_sessions_per_hour.avg_session_per_hour
+FROM qtt_users
+CROSS JOIN 
+	avg_orders_per_hour
+CROSS JOIN
+	avg_delivery_time
+CROSS JOIN
+	purchase_counter
+CROSS JOIN
+	avg_sessions_per_hour

greenery/analyses/week_2_project.sql

@@ -0,0 +1,25 @@
+with
+purchases_per_user AS (
+	SELECT
+		user_id
+		,COUNT(DISTINCT order_id) AS purchase_counter
+    FROM {{ ref("stg_postgres__orders") }}
+    GROUP BY user_id
+)--purchases_per_user
+
+, purchase_counter AS (
+	SELECT
+    	COUNT(user_id) AS users_who_purchased
+        , sum(CASE WHEN purchase_counter >= 2 
+				   THEN 1 
+				   ELSE 0 
+				   END
+              ) AS users_who_purchased_twice_or_more
+    FROM purchases_per_user
+)--purchase_counter
+
+SELECT
+    users_who_purchased,
+    users_who_purchased_twice_or_more,
+    users_who_purchased_twice_or_more / users_who_purchased as repeat_rate
+FROM purchase_counter

greenery/dbt_project.yml

@@ -0,0 +1,39 @@
+
+# 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
+    marts:
+      +materialized: table

greenery/models/marts/core/_core__models.yml

@@ -0,0 +1,38 @@
+version: 2
+
+models:
+  - name: dim_products
+    columns:
+    - name: product_id
+      description: Unique UUID for each product
+      tests:
+        - unique
+        - not_null
+        - relationships:
+            to: ref('stg_postgres__products')
+            field: product_id
+
+  - name: dim_users
+    columns:
+      - name: user_id
+        description: Unique UUID for each user
+        tests:
+          - unique
+          - not_null
+          - relationships:
+              to: ref('stg_postgres__users')
+              field: user_id
+
+  - name: fact_orders
+    columns:
+      - name: order_id
+        description: Unique UUID for each order
+        tests:
+          - unique
+          - not_null
+      - name: user_id
+        description: Unique UUID for each user
+        tests:
+          - relationships:
+              to: ref('stg_postgres__users')
+              field: user_id

greenery/models/marts/core/dim_products.sql

@@ -0,0 +1,34 @@
+WITH
+products AS (
+SELECT 
+	product_id
+	,name 
+	,price
+	,inventory
+FROM {{ ref("stg_postgres__products") }}
+)--products
+
+, ordered_products AS (
+SELECT 
+	product_id
+	,num_orders
+	,quantity_shipped
+	,quantity_delivered
+	,quantity_preparing
+	,total_quantity 
+FROM {{ ref("int_products") }}
+)--ordered_products
+
+SELECT 
+	products.product_id
+	,products.name 
+	,products.price
+	,products.inventory
+	,ordered_products_summary.num_orders
+	,ordered_products_summary.quantity_shipped
+	,ordered_products_summary.quantity_delivered
+	,ordered_products_summary.quantity_preparing
+	,ordered_products_summary.total_quantity 
+
+FROM products
+left join ordered_products_summary using (product_id)

greenery/models/marts/core/dim_users.sql

@@ -0,0 +1,10 @@
+select 
+	user_id
+	,first_name 
+	,last_name
+	,email
+	,phone_number
+	,created_at
+	,updated_at
+	,address_id
+FROM {{ ref("stg_postgres__users") }}

greenery/models/marts/core/fact_orders.sql

@@ -0,0 +1,45 @@
+WITH
+orders AS (
+SELECT 
+	order_id
+	,promo_id 
+	,user_id
+	,address_id
+	,created_at
+	,order_cost
+	,shipping_cost
+	,order_total
+	,tracking_id
+	,shipping_service
+	,estimated_delivery_at
+	,delivered_at
+	,status 
+FROM {{ ref("stg_postgres__orders") }}
+)--orders
+
+, promos AS (
+SELECT 
+	promo_id
+	,discount 
+	,status
+FROM {{ ref("stg_postgres__promos") }}
+)--promos
+
+SELECT 
+	orders.order_id
+	,orders.promo_id 
+	,orders.user_id
+	,orders.address_id
+	,orders.created_at
+	,orders.order_cost
+	,orders.shipping_cost
+	,orders.order_total
+	,orders.tracking_id
+	,orders.shipping_service
+	,orders.estimated_delivery_at
+	,orders.delivered_at
+	,orders.status 
+	,promos.discount AS promo_discount
+FROM orders
+LEFT JOIN promos 
+	ON orders.promo_id = promos.promo_id