add pre-hooks and modified macro

.pre-commit-config.yaml

@@ -0,0 +1,38 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.6.0
+  hooks:
+    - id: check-yaml
+    - id: end-of-file-fixer
+    - id: trailing-whitespace
+- repo: https://github.com/sqlfluff/sqlfluff
+  rev: 3.1.1 # ensure version matches your Pipfile
+  hooks:
+    - id: sqlfluff-lint
+      additional_dependencies: [
+        'dbt-snowflake==1.8.3',
+        'sqlfluff-templater-dbt==3.1.1' # ensure version matches your Pipfile
+      ]
+    - id: sqlfluff-fix
+      stages: [manual]  # this command is available only to run manually
+      additional_dependencies: [
+        'dbt-snowflake==1.8.3',
+        'sqlfluff-templater-dbt==3.1.1' # ensure version matches your Pipfile
+      ]
+- repo: https://github.com/dbt-checkpoint/dbt-checkpoint
+  rev: v2.0.3
+  hooks:
+  - id: dbt-compile # Compiles dbt (necessary for future hooks)
+  - id: dbt-docs-generate # Generates the dbt docs (necessary for some future hooks)
+  - id: check-source-table-has-description # Ensures all source tables have descriptions
+  - id: check-column-desc-are-same # Ensures all models have the same descriptions for the same column names.
+  - id: check-model-has-tests # Ensures all models have at least 2 tests
+    args: ["--test-cnt", "2", "--"]
+    files: ^models/
+  - id: check-script-semicolon # Ensure that the model does not have a semicolon at the end of the file.
+  - id: check-script-has-no-table-name # Ensures models only use source or ref macro to specify the table name.
+  - id: check-model-has-all-columns # Ensures that mart models have all columns in the database also specified in the .yml
+    files: ^models/marts
+  - id: check-model-tags  # Ensures that models inside the core folder have specified tags
+    args: ["--tags", "hourly,daily,weekly,monthly","--"]
+    files: ^models/marts/core

Pipfile

@@ -0,0 +1,14 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+dbt-core = "==1.8.3"
+dbt-snowflake = "==1.8.3"
+sqlfluff = "==3.1.1"
+sqlfluff-templater-dbt = "==3.1.1"
+pre-commit = "==3.8.0"
+
+[requires]
+python_version = "3.12"

dbt_project.yml

@@ -44,4 +44,4 @@ seeds:
     dbt_project_evaluator_exceptions:
       +enabled: false
 
-# on-run-end: "{{ dbt_project_evaluator.print_dbt_project_evaluator_issues() }}"
+on-run-end: "{{ dbt_project_evaluator.print_dbt_project_evaluator_issues() }}"

macros/lagging_over_column.sql

@@ -0,0 +1,18 @@
+{% macro lagging_over_column(
+    column_name,
+    partition_by_first_column,
+    order_by,
+    coalesce_value,
+    new_name_column,
+    partition_by_second_column=none) %}
+
+    COALESCE(LAG( {{ column_name }} ) OVER (
+        {% if partition_by_second_column is not none %}
+            PARTITION BY {{ partition_by_first_column }}, {{ partition_by_second_column }}
+        {% else %}
+            PARTITION BY {{ partition_by_first_column }}
+        {% endif %}
+
+        ORDER BY {{ order_by }}), {{ coalesce_value }}
+    ) AS  {{ new_name_column }}
+{% endmacro %}

macros/lagging_over_column.yml

@@ -0,0 +1,24 @@
+version: 2
+
+macros:
+  - name: lagging_over_column
+    description: A macro applies lagging function to the specified column and allows to coalesce null with a defined value.
+    arguments:
+      - name: column_name
+        type: string
+        description: The name of the column that needs to be lagged.
+      - name: partition_by_first_column
+        type: string
+        description: The first grouping column.
+      - name: order_by
+        type: string
+        description: Ordering column (created_at as a default value).
+      - name: coalesce_value
+        type: string
+        description: Value that should be used instead of null.
+      - name: new_name_column
+        type: string
+        description: Name of the column returned by the macro.
+      - name: partition_by_second_column
+        type: string
+        description: The second grouping column (none by default).

macros/rolling_aggregations_over_time.sql

@@ -0,0 +1,17 @@
+{% macro rolling_aggregations_over_time(
+    column_name,
+    aggregation_type=avg,
+    time_window=7,
+    partition_by=none,
+    order_by='created_at') %}
+
+    {{ aggregation_type }}( {{ column_name }} ) OVER (
+        {% if partition_by is not none %}
+            PARTITION BY {{ partition_by }}
+        {% endif %}
+
+        ORDER BY {{ order_by }}
+
+        ROWS BETWEEN {{ time_window }} PRECEDING AND CURRENT ROW
+    ) AS {{ aggregation_type }}_{{ time_window }}_periods_{{ column_name }}
+{% endmacro %}

macros/rolling_aggregations_over_time.yml

@@ -0,0 +1,21 @@
+version: 2
+
+macros:
+  - name: rolling_aggregations_over_time
+    description: A macro calculates an aggregation over a specified time window.
+    arguments:
+      - name: column_name
+        type: string
+        description: The name of the column to which an aggregation function is applied.
+      - name: aggregation_type
+        type: string
+        description: Type of an aggregation (average is set as default).
+      - name: time_window
+        type: integer
+        description: Time window of an aggregation.
+      - name: partition_by
+        type: string
+        description: Grouping column (none value as a default).
+      - name: order_by
+        type: string
+        description: Ordering column (created_at as a default value).

models/docs/docs_bingeflix.md

@@ -1,9 +1,134 @@
 # Bingeflix Docs
 This file contains doumentation for Bingeflix data sources.
 
+## Events
+
+This section contains documentation on events.
+
+{% docs bingeflix_events %} 
+This table contains information about the behavioral events of users while they interact with the platform.
+{% enddocs %}
+
+{% docs bingeflix_column_session_id %}
+The unique identifier of the session in the Bingeflix application.
+{% enddocs %}
+
+{% docs bingeflix_column_event_created_at %}
+When the event was logged.
+{% enddocs %}
+
+{% docs bingeflix_column_event_name %}
+The name of the event.
+{% enddocs %}
+
+{% docs bingeflix_column_event_id %}
+The unique identifier of the event.
+{% enddocs %}
+
+## Subscription plans
+
+This section contains documentation on subscription plans.
+
+{% docs bingeflix_subscription_plans %} 
+This table contains information on users' subscription plans.
+{% enddocs %}
+
+{% docs bingeflix_column_subscription_plan_id %}
+The unique identifier of the subscription plan.
+{% enddocs %}
+
+{% docs bingeflix_column_plan_name %}
+The name of the subscription plan.
+{% enddocs %}
+
+{% docs bingeflix_column_payment_period %}
+The user's payment period.
+{% enddocs %}
+
+## Subscriptions
+
+This section contains documentation on subscriptions.
+
+{% docs bingeflix_subscriptions %} 
+This table contains information on users' subscriptions.
+{% enddocs %}
+
+{% docs bingeflix_column_subscription_id %}
+The unique identifier of the subscription.
+{% enddocs %}
+
+{% docs bingeflix_column_starts_at %}
+When the subscription started.
+{% enddocs %}
+
+{% docs bingeflix_column_ends_at %}
+When the subscription ends.
+{% enddocs %}
+
+{% docs bingeflix_column_pricing %}
+The monthly cost of the subscription.
+{% enddocs %}
+
+{% docs bingeflix_column_billing_period %}
+The cadence of the billing period.
+{% enddocs %}
+
+
 ## Users
 This section contains documentation from the Bingeflix Users table.
 
+{% docs bingeflix_users %} 
+This table contains information on all users. 
+{% enddocs %}
+
 {% docs bingeflix_column_user_id %}
-The unique identifier of the Bingeflix user. A user is created when...
+The unique identifier of the Bingeflix user.
+{% enddocs %}
+
+{% docs bingeflix_column_created_at %}
+When the user account was created.
+{% enddocs %}
+
+{% docs bingeflix_column_phone_number %}
+The user's phone number.
+{% enddocs %}
+
+{% docs bingeflix_column_deleted_at %}
+When the user's account was deleted.
+{% enddocs %}
+
+{% docs bingeflix_column_username %}
+The username associated with the user.
+{% enddocs %}
+
+{% docs bingeflix_column_name %}
+The full name of the user (first and last).
+{% enddocs %}
+
+{% docs bingeflix_column_sex %}
+The user's gender.
+{% enddocs %}
+
+{% docs bingeflix_column_email %}
+The user's email address.
+{% enddocs %}
+
+{% docs bingeflix_column_birthdate %}
+The user's bithdate.
+{% enddocs %}
+
+{% docs bingeflix_column_current_age %}
+The user's current age.
+{% enddocs %}
+
+{% docs bingeflix_column_age_at_acquisition %}
+The age of the user when they became a Bingeflix user.
+{% enddocs %}
+
+{% docs bingeflix_column_region %}
+The region where the user lives.
+{% enddocs %}
+
+{% docs bingeflix_column_country %}
+The country where the user lives.
 {% enddocs %}

models/marts/core/dim_users_max_14_days.sql

@@ -0,0 +1,55 @@
+WITH
+
+users AS (
+    SELECT
+        *
+    FROM
+        {{ ref('stg_bingeflix__users') }}
+),
+
+users_subscription_facts AS (
+    SELECT
+        user_id,
+        MIN(starts_at) AS first_subscription_starts_at,
+        COUNT(DISTINCT subscription_id) AS count_of_subscriptions
+    FROM
+        {{ ref('stg_bingeflix__subscriptions') }}
+    GROUP BY 1
+),
+
+final AS (
+    SELECT
+        u.user_id,
+        created_at,
+        phone_number,
+        deleted_at,
+        username,
+        name,
+        sex,
+        email,
+        birthdate,
+        TRUNCATE(DATEDIFF(MONTH, birthdate, CURRENT_DATE)/12) AS current_age,
+        TRUNCATE(DATEDIFF(MONTH, birthdate, created_at)/12) AS age_at_acquisition,
+        region,
+        country,
+        usf.first_subscription_starts_at,
+        usf.count_of_subscriptions
+    FROM
+        users AS u
+        LEFT JOIN users_subscription_facts AS usf ON u.user_id = usf.user_id
+)
+
+SELECT
+
+    region,
+    country,
+    created_at,
+
+    {{ rolling_aggregations_over_time(
+        column_name='count_of_subscriptions',
+        aggregation_type='max',
+        time_window=14,
+        partition_by='region'
+    ) }}
+
+FROM final

models/marts/core/dim_users_max_14_days.yml

@@ -0,0 +1,24 @@
+models:
+  - name: dim_users_max_14_days
+    description: This model contains information on maximum number of subscriptions for regions and countries with a rollout of 14 days.
+    columns:
+
+      - name: created_at
+        description: When the user account was created.
+        data_tests:
+          - not_null
+
+      - name: region
+        description: Where the user lives.
+        data_tests:
+          - not_null
+
+      - name: country
+        description: Where the user lives.
+        data_tests:
+          - not_null
+
+      - name: max_14_periods_count_of_subscriptions
+        description: Maximum number of subscriptions for the last 14 days.
+        data_tests:
+          - not_null

models/marts/core/fct_events.yml

@@ -0,0 +1,31 @@
+models:
+  - name: fct_events
+    description: This model contains information about Bingeflix events.
+    columns:
+      - name: session_id
+        description: '{{ doc("bingeflix_column_session_id") }}'
+        data_tests:
+          - not_null
+
+      - name: created_at
+        description: '{{ doc("bingeflix_column_event_created_at") }}'
+        data_tests:
+          - not_null
+
+      - name: user_id
+        description: '{{ doc("bingeflix_column_user_id") }}'
+        data_tests:
+          - not_null
+
+      - name: event_name
+        description: '{{ doc("bingeflix_column_event_name") }}'
+        data_tests:
+          - not_null
+
+      - name: event_id
+        description: '{{ doc("bingeflix_column_event_id") }}'
+        data_tests:
+          - unique
+          - not_null
+
+