feat(appliance): initial release of MERICA standalone appliance v1.0.0

This commit is contained in:
2026-10-21 17:16:46 +07:00
commit 851be0cda7
144 changed files with 31135 additions and 0 deletions
+28
View File
@@ -0,0 +1,28 @@
name: 'dlh_transformation'
version: '1.0.0'
config-version: 2
profile: 'dlh_postgres'
model-paths: ["models"]
analysis-paths: ["analyses"]
test-paths: ["tests"]
seed-paths: ["seeds"]
macro-paths: ["macros"]
snapshot-paths: ["snapshots"]
clean-targets:
- "target"
- "dbt_packages"
models:
dlh_transformation:
bronze:
+materialized: view
+schema: bronze
silver:
+materialized: table
+schema: silver
gold:
+materialized: table
+schema: gold
@@ -0,0 +1,7 @@
{% macro generate_schema_name(custom_schema_name, node) -%}
{%- if custom_schema_name is none -%}
{{ target.schema }}
{%- else -%}
{{ custom_schema_name | trim }}
{%- endif -%}
{%- endmacro %}
@@ -0,0 +1,20 @@
-- dbt Bronze View Model: environmental_permits
{{ config(materialized='view') }}
SELECT
permit_id,
permit_number,
applicant_name,
company_name,
business_type,
activity_type,
activity_type AS permit_type,
location,
status,
environmental_score,
issued_date,
expiry_date,
created_at,
updated_at
FROM {{ source('public', 'environmental_permits') }}
@@ -0,0 +1,4 @@
-- dbt Bronze View Model: raw_cems_telemetry_logs
{{ config(materialized='view') }}
SELECT * FROM {{ source('public', 'raw_cems_telemetry_logs') }}
@@ -0,0 +1,4 @@
-- dbt Bronze View Model: ref_emission_sources
{{ config(materialized='view') }}
SELECT * FROM {{ source('public', 'ref_emission_sources') }}
@@ -0,0 +1,15 @@
-- dbt Bronze Ref Facilities Model
{{ config(materialized='view') }}
SELECT
facility_id,
facility_name,
operator_name,
license_number,
region_zone,
facility_type,
max_daily_capacity_ton,
facility_status,
compliance_rating,
created_at
FROM {{ source('public', 'ref_waste_facilities') }}
@@ -0,0 +1,4 @@
-- dbt Bronze View Model: stasiun_spku
{{ config(materialized='view') }}
SELECT * FROM {{ source('public', 'stasiun_spku') }}
@@ -0,0 +1,16 @@
-- dbt Bronze Raw Waste Orders Model
{{ config(materialized='view') }}
SELECT
order_id,
manifest_code,
facility_id,
generator_company,
waste_category,
volume_ton,
tariff_per_ton,
transport_fee,
order_status,
order_date,
created_at
FROM {{ source('public', 'raw_waste_orders') }}
@@ -0,0 +1,12 @@
-- dbt Gold Model: fct_spku_daily_mart
{{ config(materialized='table', schema='gold') }}
SELECT
stasiun_id,
nama_stasiun_clean,
AVG(ispu_value) AS avg_daily_ispu,
MAX(ispu_value) AS max_daily_ispu,
COUNT(*) AS total_readings,
CURRENT_DATE AS mart_date
FROM {{ ref('stg_spku_realtime') }}
GROUP BY stasiun_id, nama_stasiun_clean
@@ -0,0 +1,9 @@
-- dbt Gold Regulatory Compliance Mart
SELECT
permit_type,
status,
COUNT(permit_id) AS total_permits,
COUNT(DISTINCT company_name) AS unique_companies,
CURRENT_TIMESTAMP AS mart_refreshed_at
FROM {{ ref('silver_permits_enriched') }}
GROUP BY permit_type, status
@@ -0,0 +1,21 @@
-- dbt Gold Industrial Emission Compliance & Load Mart
SELECT
region_zone,
industry_sector,
COUNT(log_id) AS total_telemetry_events,
COUNT(DISTINCT source_id) AS active_chimneys_count,
ROUND(AVG(so2_mg_nm3), 2) AS avg_so2_concentration,
ROUND(AVG(nox_mg_nm3), 2) AS avg_nox_concentration,
ROUND(AVG(pm_dust_mg_nm3), 2) AS avg_pm_concentration,
ROUND(SUM(so2_mass_rate_kg_h) / 1000.0, 3) AS total_so2_emission_ton,
ROUND(SUM(nox_mass_rate_kg_h) / 1000.0, 3) AS total_nox_emission_ton,
ROUND(SUM(pm_mass_rate_kg_h) / 1000.0, 3) AS total_pm_emission_ton,
COUNT(CASE WHEN compliance_status = 'EXCEEDING_LIMIT' THEN 1 END) AS total_violations_count,
ROUND(
(COUNT(CASE WHEN compliance_status = 'COMPLIANT' THEN 1 END)::NUMERIC / NULLIF(COUNT(log_id), 0)) * 100.0,
2
) AS compliance_rate_percent,
CURRENT_TIMESTAMP AS mart_refreshed_at
FROM {{ ref('silver_cems_emission_enriched') }}
GROUP BY region_zone, industry_sector
ORDER BY total_violations_count DESC, total_so2_emission_ton DESC
@@ -0,0 +1,16 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
stasiun_id,
nama_stasiun,
CAST(recorded_at AS DATE) AS observation_date,
AVG(pm25_value) AS avg_pm25,
MAX(pm25_value) AS max_pm25,
AVG(pm10_value) AS avg_pm10,
MAX(pm10_value) AS max_pm10,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_spku_sensor_clean') }}
GROUP BY 1, 2, 3
@@ -0,0 +1,13 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
CAST(issued_date AS DATE) AS permit_date,
permit_type,
permit_status,
COUNT(permit_id) AS total_permits,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_environmental_permits_clean') }}
GROUP BY 1, 2, 3
@@ -0,0 +1,16 @@
-- dbt Gold Regional Waste Revenue & Compliance Mart
SELECT
region_zone,
facility_type,
waste_category,
COUNT(order_id) AS total_orders,
COUNT(DISTINCT facility_id) AS active_facilities_count,
COUNT(DISTINCT generator_company) AS active_generators_count,
ROUND(SUM(volume_ton), 2) AS total_waste_volume_ton,
ROUND(SUM(total_order_amount), 2) AS total_gross_revenue,
ROUND(AVG(total_order_amount / NULLIF(volume_ton, 0)), 2) AS avg_revenue_per_ton,
COUNT(CASE WHEN environmental_compliance_status = 'COMPLIANT' THEN 1 END) AS compliant_orders_count,
CURRENT_TIMESTAMP AS mart_refreshed_at
FROM {{ ref('silver_waste_manifest_enriched') }}
GROUP BY region_zone, facility_type, waste_category
ORDER BY total_waste_volume_ton DESC
@@ -0,0 +1,14 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
kecamatan,
tanggal_laporan,
COUNT(lokasi_tps) AS total_tps,
SUM(volume_sampah_m3) AS total_volume_sampah_m3,
AVG(volume_sampah_m3) AS avg_volume_per_tps_m3,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_gws_waste_reports_clean') }}
GROUP BY 1, 2
+12
View File
@@ -0,0 +1,12 @@
version: 2
models:
- name: gold_compliance_summary_mart
description: dbt Model gold_compliance_summary_mart auto-registered with Shift-Left
quality assertions
columns:
- name: permit_type
tests:
- not_null
- name: status
tests:
- not_null
+34
View File
@@ -0,0 +1,34 @@
version: 2
models:
- name: silver_permits_enriched
description: dbt Model silver_permits_enriched auto-registered with Shift-Left quality
assertions
config:
contract:
enforced: true
columns:
- name: company_name
data_type: character varying(255)
- name: dbt_validated_at
data_type: timestamp with time zone
- name: issued_date
data_type: date
- name: permit_id
tests:
- unique
- not_null
data_type: character varying(50)
- name: permit_number
tests:
- unique
data_type: character varying(50)
- name: permit_type
data_type: character varying(50)
- name: status
tests:
- not_null
data_type: character varying(50)
- name: updated_at
tests:
- not_null
data_type: timestamp with time zone
@@ -0,0 +1,31 @@
-- dbt Silver Cleansed CEMS Telemetry Enriched with Master Sources
SELECT
t.log_id,
t.telemetry_timestamp,
t.source_id,
s.facility_name,
s.industry_sector,
s.chimney_code,
s.region_zone,
t.so2_mg_nm3,
s.max_so2_limit_mg_nm3,
t.nox_mg_nm3,
s.max_nox_limit_mg_nm3,
t.pm_dust_mg_nm3,
s.max_pm_limit_mg_nm3,
t.co_mg_nm3,
t.flue_gas_flow_m3_s,
t.flue_temp_celsius,
ROUND((t.so2_mg_nm3 * t.flue_gas_flow_m3_s * 3600.0) / 1000000.0, 3) AS so2_mass_rate_kg_h,
ROUND((t.nox_mg_nm3 * t.flue_gas_flow_m3_s * 3600.0) / 1000000.0, 3) AS nox_mass_rate_kg_h,
ROUND((t.pm_dust_mg_nm3 * t.flue_gas_flow_m3_s * 3600.0) / 1000000.0, 3) AS pm_mass_rate_kg_h,
CASE
WHEN t.so2_mg_nm3 > s.max_so2_limit_mg_nm3 OR t.nox_mg_nm3 > s.max_nox_limit_mg_nm3 OR t.pm_dust_mg_nm3 > s.max_pm_limit_mg_nm3
THEN 'EXCEEDING_LIMIT'
ELSE 'COMPLIANT'
END AS compliance_status,
t.sensor_status
FROM {{ ref('bronze_raw_cems_telemetry_logs') }} t
JOIN {{ ref('bronze_ref_emission_sources') }} s
ON t.source_id = s.source_id
WHERE t.sensor_status = 'VALID'
@@ -0,0 +1,38 @@
{{ config(
materialized='incremental',
unique_key='permit_id',
schema='silver'
) }}
WITH cdc_raw AS (
SELECT
CAST(permit_id AS VARCHAR) AS permit_id,
TRIM(applicant_name) AS applicant_name,
LOWER(permit_type) AS permit_type,
CAST(status AS VARCHAR) AS permit_status,
CAST(issued_date AS TIMESTAMP) AS issued_date,
CAST(updated_at AS TIMESTAMP) AS updated_at,
_sling_op,
CAST(_sling_ts AS TIMESTAMP) AS _sling_ts,
ROW_NUMBER() OVER (
PARTITION BY permit_id
ORDER BY _sling_ts DESC
) AS row_num
FROM {{ source('bronze_lakehouse', 'environmental_permits_cdc') }}
{% if is_incremental() %}
WHERE _sling_ts > (SELECT MAX(_sling_ts) FROM {{ this }})
{% endif %}
)
SELECT
permit_id,
applicant_name,
permit_type,
permit_status,
issued_date,
updated_at,
_sling_ts,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM cdc_raw
WHERE row_num = 1
AND _sling_op != 'D' -- Buang record yang di-DELETE
@@ -0,0 +1,22 @@
{{ config(
materialized='table',
schema='silver'
) }}
WITH raw_sheets AS (
SELECT
TRIM(CAST(lokasi_tps AS VARCHAR)) AS lokasi_tps,
TRIM(CAST(kecamatan AS VARCHAR)) AS kecamatan,
CAST(volume_sampah_m3 AS NUMERIC(10,2)) AS volume_sampah_m3,
CAST(tanggal_laporan AS DATE) AS tanggal_laporan
FROM {{ source('bronze_lakehouse', 'gws_waste_reports') }}
WHERE lokasi_tps IS NOT NULL AND lokasi_tps != ''
)
SELECT
lokasi_tps,
kecamatan,
volume_sampah_m3,
tanggal_laporan,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM raw_sheets
@@ -0,0 +1,12 @@
-- dbt Silver Cleansed Environmental Permits
SELECT
permit_id,
permit_number,
company_name,
permit_type,
status,
issued_date,
updated_at,
CURRENT_TIMESTAMP AS dbt_validated_at
FROM {{ ref('bronze_environmental_permits') }}
WHERE status != 'REVISED'
@@ -0,0 +1,17 @@
{{ config(
materialized='table',
schema='silver'
) }}
WITH raw_json AS (
SELECT json_payload FROM {{ source('bronze_lakehouse', 'spku_api_raw') }}
)
SELECT
(json_payload->>'stasiun_id')::VARCHAR AS stasiun_id,
(json_payload->>'nama_stasiun')::VARCHAR AS nama_stasiun,
(json_payload->>'pm25')::NUMERIC(8,2) AS pm25_value,
(json_payload->>'pm10')::NUMERIC(8,2) AS pm10_value,
(json_payload->>'recorded_at')::TIMESTAMP AS recorded_at,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM raw_json
@@ -0,0 +1,27 @@
-- dbt Silver Cleansed Manifest Orders Enriched with Master Facilities
SELECT
o.order_id,
o.manifest_code,
o.order_date,
o.generator_company,
o.waste_category,
o.volume_ton,
o.tariff_per_ton,
o.transport_fee,
ROUND((o.volume_ton * o.tariff_per_ton) + o.transport_fee, 2) AS total_order_amount,
o.order_status,
f.facility_id,
f.facility_name,
f.region_zone,
f.facility_type,
f.compliance_rating,
f.facility_status,
CASE
WHEN f.facility_status = 'ACTIVE' AND o.volume_ton <= f.max_daily_capacity_ton THEN 'COMPLIANT'
WHEN f.facility_status != 'ACTIVE' THEN 'UNLICENSED_FACILITY_WARNING'
ELSE 'CAPACITY_EXCEEDED_WARNING'
END AS environmental_compliance_status
FROM {{ ref('bronze_waste_orders') }} o
LEFT JOIN {{ ref('bronze_ref_facilities') }} f
ON o.facility_id = f.facility_id
WHERE o.order_status != 'CANCELLED'
@@ -0,0 +1,10 @@
-- dbt Silver Model: stg_spku_realtime
{{ config(materialized='table', schema='silver') }}
SELECT
stasiun_id,
LOWER(TRIM(nama_stasiun)) AS nama_stasiun_clean,
CAST(ispu_val AS FLOAT) AS ispu_value,
created_at
FROM {{ source('bronze', 'spku_api_raw') }}
WHERE ispu_val IS NOT NULL
+36
View File
@@ -0,0 +1,36 @@
version: 2
sources:
- name: bronze_lakehouse
schema: bronze_lakehouse
tables:
- name: environmental_permits_cdc
description: Tabel landing Bronze staging untuk Change Data Capture (CDC) Perizinan
Lingkungan
- name: gws_waste_reports
description: Tabel landing Bronze staging laporan penanganan sampah Google Workspace
- name: spku_api_raw
description: Tabel landing Bronze staging raw JSON payload sensor kualitas udara
SPKU
- name: bronze
schema: bronze_lakehouse
tables:
- name: environmental_permits_cdc
- name: gws_waste_reports
- name: spku_api_raw
- name: public
schema: public
tables:
- name: ref_waste_facilities
description: Master dataset fasilitas pengolahan limbah regional
- name: raw_waste_orders
description: Tabel transaksi manifest pengiriman dan penerimaan limbah
- name: ref_emission_sources
description: Auto-registered source table 'ref_emission_sources' from canvas pipeline
- name: raw_cems_telemetry_logs
description: Auto-registered source table 'raw_cems_telemetry_logs' from canvas
pipeline
- name: stasiun_spku
description: Auto-registered source table 'stasiun_spku' from canvas pipeline
- name: environmental_permits
description: Auto-registered source table 'environmental_permits' from canvas
pipeline
+12
View File
@@ -0,0 +1,12 @@
dlh_postgres:
target: dev
outputs:
dev:
type: postgres
host: "{{ env_var('POSTGRES_HOST', 'postgres') }}"
port: 5432
user: "{{ env_var('POSTGRES_USER', 'dlh_user') }}"
pass: "{{ env_var('POSTGRES_PASSWORD', 'dlh_password') }}"
dbname: "{{ env_var('POSTGRES_DB', 'dlh_lakehouse') }}"
schema: public
threads: 4