feat(extract): add OpenWeatherMap daily weather extractor

Adds extract/openweathermap package with daily weather extraction for 8
coffee-growing regions (Brazil, Vietnam, Colombia, Ethiopia, Honduras,
Guatemala, Indonesia). Feeds crop stress signal for commodity sentiment score.

Extractor:
- OWM One Call API 3.0 / Day Summary — one JSON.gz per (location, date)
- extract_weather: daily, fetches yesterday + today (16 calls max)
- extract_weather_backfill: fills 2020-01-01 to yesterday, capped at 500
  calls/run with resume cursor '{location_id}:{date}' for crash safety
- Full idempotency via file existence check; state tracking via extract_core

SQLMesh:
- seeds.weather_locations (8 regions with lat/lon/variety)
- foundation.fct_weather_daily: INCREMENTAL_BY_TIME_RANGE, grain
  (location_id, observation_date), dedup via hash key, crop stress flags:
  is_frost (<2°C), is_heat_stress (>35°C), is_drought (<1mm), in_growing_season

Landing path: LANDING_DIR/weather/{location_id}/{year}/{date}.json.gz

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Deeman
2026-02-25 22:40:27 +01:00
parent c3c8333407
commit 08e74665bb
31 changed files with 1377 additions and 915 deletions

View File

@@ -1,19 +1,12 @@
-- Serving mart: ICE certified Coffee C warehouse stocks, analytics-ready.
--
-- Adds 30-day rolling average, week-over-week change, and drawdown from
-- 52-week high. Physical supply indicator used alongside S/D and positioning.
--
-- "Certified stocks" = coffee graded and stamped as eligible for delivery
-- against ICE Coffee C futures — traders watch this as a squeeze indicator.
--
-- Grain: one row per report_date.
/* Serving mart: ICE certified Coffee C warehouse stocks, analytics-ready. */ /* Adds 30-day rolling average, week-over-week change, and drawdown from */ /* 52-week high. Physical supply indicator used alongside S/D and positioning. */ /* "Certified stocks" = coffee graded and stamped as eligible for delivery */ /* against ICE Coffee C futures — traders watch this as a squeeze indicator. */ /* Grain: one row per report_date. */
MODEL (
name serving.ice_warehouse_stocks,
kind INCREMENTAL_BY_TIME_RANGE (
time_column report_date
),
grain (report_date),
grain (
report_date
),
start '2000-01-01',
cron '@daily'
);
@@ -23,45 +16,25 @@ WITH base AS (
f.report_date,
f.total_certified_bags,
f.pending_grading_bags,
-- Week-over-week change (compare to 7 calendar days ago via LAG over ordered rows)
-- Using LAG(1) since data is daily: compares to previous trading/reporting day
f.total_certified_bags
- LAG(f.total_certified_bags, 1) OVER (ORDER BY f.report_date) AS wow_change_bags,
-- 30-day rolling average (smooths daily noise)
round(
AVG(f.total_certified_bags::double) OVER (
ORDER BY f.report_date ROWS BETWEEN 29 PRECEDING AND CURRENT ROW
),
f.total_certified_bags /* Week-over-week change (compare to 7 calendar days ago via LAG over ordered rows) */ /* Using LAG(1) since data is daily: compares to previous trading/reporting day */ - LAG(f.total_certified_bags, 1) OVER (ORDER BY f.report_date) AS wow_change_bags,
ROUND(
AVG(f.total_certified_bags::DOUBLE) OVER (ORDER BY f.report_date ROWS BETWEEN 29 PRECEDING AND CURRENT ROW),
0
) AS avg_30d_bags,
-- 52-week high (365 calendar days ≈ 252 trading days; use 365-row window as proxy)
MAX(f.total_certified_bags) OVER (
ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW
) AS high_52w_bags,
-- Drawdown from 52-week high (pct below peak — squeeze indicator)
round(
(f.total_certified_bags::double
- MAX(f.total_certified_bags) OVER (
ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW
)::double
)
/ NULLIF(
MAX(f.total_certified_bags) OVER (
ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW
)::double,
0
) * 100,
) AS avg_30d_bags, /* 30-day rolling average (smooths daily noise) */
MAX(f.total_certified_bags) OVER (ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW) AS high_52w_bags, /* 52-week high (365 calendar days ≈ 252 trading days; use 365-row window as proxy) */
ROUND(
(
f.total_certified_bags::DOUBLE - MAX(f.total_certified_bags) OVER (ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW)::DOUBLE
) / NULLIF(
MAX(f.total_certified_bags) OVER (ORDER BY f.report_date ROWS BETWEEN 364 PRECEDING AND CURRENT ROW)::DOUBLE,
0
) * 100,
2
) AS drawdown_from_52w_high_pct
FROM foundation.fct_ice_warehouse_stocks f
WHERE f.report_date BETWEEN @start_ds AND @end_ds
) AS drawdown_from_52w_high_pct /* Drawdown from 52-week high (pct below peak — squeeze indicator) */
FROM foundation.fct_ice_warehouse_stocks AS f
WHERE
f.report_date BETWEEN @start_ds AND @end_ds
)
SELECT
b.report_date,
d.commodity_name,
@@ -72,7 +45,9 @@ SELECT
b.avg_30d_bags,
b.high_52w_bags,
b.drawdown_from_52w_high_pct
FROM base b
CROSS JOIN foundation.dim_commodity d
WHERE d.ice_stock_report_code = 'COFFEE-C'
ORDER BY b.report_date
FROM base AS b
CROSS JOIN foundation.dim_commodity AS d
WHERE
d.ice_stock_report_code = 'COFFEE-C'
ORDER BY
b.report_date