9de3a3ba01
Replaced the OWM extractor (8 locations, API key required, 14,600-call backfill over 30+ days) with Open-Meteo (12 locations, no API key, ERA5 reanalysis, full backfill in 12 API calls ~30 seconds). - Rename extract/openweathermap → extract/openmeteo (git mv) - Rewrite api.py: fetch_archive (ERA5, date-range) + fetch_recent (forecast, past_days=10 to cover ERA5 lag); 9 daily variables incl. et0 and VPD - Rewrite execute.py: _split_and_write() unzips parallel arrays into per-day flat JSON; no cursor / rate limiting / call cap needed - Update pipelines.py: --package openmeteo, timeout 120s (was 1200s) - Update fct_weather_daily.sql: flat Open-Meteo field names (temperature_2m_* etc.), remove pressure_afternoon_hpa, add et0_mm + vpd_max_kpa + is_high_vpd - Remove OPENWEATHERMAP_API_KEY from CLAUDE.md env vars table Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
120 lines
4.1 KiB
Python
120 lines
4.1 KiB
Python
"""Pipeline execution via local subprocess."""
|
|
|
|
import subprocess
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass
|
|
class PipelineResult:
|
|
success: bool
|
|
output: str
|
|
error: str | None = None
|
|
|
|
|
|
PIPELINES = {
|
|
"extract": {
|
|
"command": ["uv", "run", "--package", "psdonline", "extract_psd"],
|
|
"timeout_seconds": 1800,
|
|
},
|
|
"extract_cot": {
|
|
"command": ["uv", "run", "--package", "cftc_cot", "extract_cot"],
|
|
"timeout_seconds": 1800,
|
|
},
|
|
"extract_prices": {
|
|
"command": ["uv", "run", "--package", "coffee_prices", "extract_prices"],
|
|
"timeout_seconds": 300,
|
|
},
|
|
"extract_ice": {
|
|
"command": ["uv", "run", "--package", "ice_stocks", "extract_ice"],
|
|
"timeout_seconds": 600,
|
|
},
|
|
"extract_ice_aging": {
|
|
"command": ["uv", "run", "--package", "ice_stocks", "extract_ice_aging"],
|
|
"timeout_seconds": 600,
|
|
},
|
|
"extract_ice_historical": {
|
|
"command": ["uv", "run", "--package", "ice_stocks", "extract_ice_historical"],
|
|
"timeout_seconds": 600,
|
|
},
|
|
"extract_ice_all": {
|
|
"command": ["uv", "run", "--package", "ice_stocks", "extract_ice_all"],
|
|
"timeout_seconds": 1800,
|
|
},
|
|
"extract_weather": {
|
|
"command": ["uv", "run", "--package", "openmeteo", "extract_weather"],
|
|
"timeout_seconds": 120,
|
|
},
|
|
"extract_weather_backfill": {
|
|
"command": ["uv", "run", "--package", "openmeteo", "extract_weather_backfill"],
|
|
"timeout_seconds": 120,
|
|
},
|
|
"extract_all": {
|
|
"command": ["meta", "extract", "extract_cot", "extract_prices", "extract_ice_all", "extract_weather"],
|
|
"timeout_seconds": 6600,
|
|
},
|
|
"transform": {
|
|
"command": ["uv", "run", "--package", "sqlmesh_materia", "sqlmesh", "-p", "transform/sqlmesh_materia", "plan", "prod", "--no-prompts", "--auto-apply"],
|
|
"timeout_seconds": 3600,
|
|
},
|
|
# Copies serving.* tables from lakehouse.duckdb → serving.duckdb (atomic swap).
|
|
# Run after every transform. Requires both DUCKDB_PATH and SERVING_DUCKDB_PATH.
|
|
"export_serving": {
|
|
"command": ["uv", "run", "python", "-c",
|
|
"import logging; logging.basicConfig(level=logging.INFO); "
|
|
"from materia.export_serving import export_serving; export_serving()"],
|
|
"timeout_seconds": 300,
|
|
},
|
|
}
|
|
|
|
|
|
META_PIPELINES: dict[str, list[str]] = {
|
|
"extract_all": ["extract", "extract_cot", "extract_prices", "extract_ice_all", "extract_weather"],
|
|
}
|
|
|
|
|
|
def run_pipeline(pipeline_name: str) -> PipelineResult:
|
|
assert pipeline_name, "pipeline_name must not be empty"
|
|
|
|
if pipeline_name not in PIPELINES:
|
|
return PipelineResult(
|
|
success=False,
|
|
output="",
|
|
error=f"Unknown pipeline: {pipeline_name}. Available: {', '.join(PIPELINES.keys())}",
|
|
)
|
|
|
|
# Meta-pipelines run a sequence of sub-pipelines, stopping on first failure
|
|
if pipeline_name in META_PIPELINES:
|
|
combined_output = []
|
|
for sub in META_PIPELINES[pipeline_name]:
|
|
result = run_pipeline(sub)
|
|
combined_output.append(result.output)
|
|
if not result.success:
|
|
return PipelineResult(
|
|
success=False,
|
|
output="\n".join(combined_output),
|
|
error=f"Sub-pipeline '{sub}' failed: {result.error}",
|
|
)
|
|
return PipelineResult(success=True, output="\n".join(combined_output))
|
|
|
|
pipeline = PIPELINES[pipeline_name]
|
|
timeout_seconds = pipeline["timeout_seconds"]
|
|
|
|
try:
|
|
result = subprocess.run(
|
|
pipeline["command"],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=timeout_seconds,
|
|
)
|
|
return PipelineResult(
|
|
success=result.returncode == 0,
|
|
output=result.stdout,
|
|
error=result.stderr if result.returncode != 0 else None,
|
|
)
|
|
except subprocess.TimeoutExpired:
|
|
return PipelineResult(
|
|
success=False,
|
|
output="",
|
|
error=f"Pipeline '{pipeline_name}' timed out after {timeout_seconds} seconds",
|
|
)
|