"""Collect Latest Weather Forecast (ECMWF IFS 0.25°)
===================================================

Fetches the latest ECMWF IFS 0.25° weather forecast from OpenMeteo API
for all 51 strategic grid points.

Use Case: Run before inference to get fresh weather forecasts extending 15 days ahead.

Model: ECMWF IFS 0.25° (Integrated Forecasting System)
- Resolution: 0.25° (~25 km, high quality for Europe)
- Forecast horizon: 15 days (360 hours)
- Free tier: Enabled since ECMWF October 2025 open data release
- Higher quality than GFS, especially for European weather systems

Output: data/raw/weather_forecast_latest.parquet
Size: ~850 KB (51 points × 7 vars × 360 hours)
Runtime: ~1-2 minutes (51 API requests at 1 req/sec)

This forecast extends the existing 375 weather features into future timestamps.
During inference, concatenate historical weather + this forecast for continuous time series.

Author: Claude
Date: 2025-11-10 (Updated: 2025-11-11 - upgraded to ECMWF IFS 0.25° 15-day forecasts)
"""

import sys
from pathlib import Path

# Add src to path
sys.path.append(str(Path(__file__).parent.parent))

from src.data_collection.collect_openmeteo_forecast import OpenMeteoForecastCollector

# Output file
OUTPUT_DIR = Path(__file__).parent.parent / 'data' / 'raw'
OUTPUT_FILE = OUTPUT_DIR / 'weather_forecast_latest.parquet'

print("="*80)
print("LATEST WEATHER FORECAST COLLECTION (ECMWF IFS 0.25\u00b0)")
print("="*80)
print()
print("Model: ECMWF IFS 0.25\u00b0 (Integrated Forecasting System)")
print("Forecast horizon: 15 days (360 hours)")
print("Temporal resolution: Hourly")
print("Grid points: 51 strategic locations across FBMC")
print("Variables: 7 weather parameters")
print("Estimated runtime: ~1-2 minutes")
print()
print("Free tier: Enabled since ECMWF October 2025 open data release")
print()

# Initialize collector with conservative rate limiting (1 req/sec = 60/min)
print("Initializing OpenMeteo forecast collector...")
collector = OpenMeteoForecastCollector(requests_per_minute=60)
print("[OK] Collector initialized")
print()

# Run collection
try:
    forecast_df = collector.collect_all_forecasts(OUTPUT_FILE)

    if not forecast_df.is_empty():
        print()
        print("="*80)
        print("COLLECTION SUCCESS")
        print("="*80)
        print()
        print(f"Output: {OUTPUT_FILE}")
        print(f"Shape: {forecast_df.shape[0]:,} rows x {forecast_df.shape[1]} columns")
        print(f"Date range: {forecast_df['timestamp'].min()} to {forecast_df['timestamp'].max()}")
        print(f"Grid points: {forecast_df['grid_point'].n_unique()}")
        print(f"Weather variables: {len([c for c in forecast_df.columns if c not in ['timestamp', 'grid_point', 'latitude', 'longitude']])}")
        print()

        # Data quality summary
        null_count_total = forecast_df.null_count().sum_horizontal()[0]
        null_pct = (null_count_total / (forecast_df.shape[0] * forecast_df.shape[1])) * 100
        print(f"Data completeness: {100 - null_pct:.2f}%")

        if null_pct > 0:
            print()
            print("Missing data by column:")
            for col in forecast_df.columns:
                null_count = forecast_df[col].null_count()
                if null_count > 0:
                    pct = (null_count / len(forecast_df)) * 100
                    print(f"  - {col}: {null_count:,} ({pct:.2f}%)")

        print()
        print("="*80)
        print("NEXT STEPS")
        print("="*80)
        print()
        print("1. During inference, extend weather time series:")
        print("   weather_hist = pl.read_parquet('data/processed/features_weather_24month.parquet')")
        print("   weather_fcst = pl.read_parquet('data/raw/weather_forecast_latest.parquet')")
        print("   # Engineer forecast features (pivot to match historical structure)")
        print("   weather_fcst_features = engineer_forecast_features(weather_fcst)")
        print("   weather_full = pl.concat([weather_hist, weather_fcst_features])")
        print()
        print("2. Feed extended time series to Chronos 2:")
        print("   - Historical period: Actual observations")
        print("   - Forecast period: ECMWF IFS 0.25\u00b0 forecast (15 days)")
        print("   - Model sees continuous weather time series")
        print()
        print("[OK] Weather forecast collection COMPLETE!")
    else:
        print()
        print("[ERROR] No weather forecast data collected")
        print()
        print("Possible causes:")
        print("  - OpenMeteo API access issues")
        print("  - Network connectivity problems")
        print("  - ECMWF model unavailable")
        print()
        sys.exit(1)

except KeyboardInterrupt:
    print()
    print()
    print("="*80)
    print("COLLECTION INTERRUPTED")
    print("="*80)
    print()
    print("Collection was stopped by user.")
    print()
    print("To restart: Run this script again")
    print()
    sys.exit(130)

except Exception as e:
    print()
    print()
    print("="*80)
    print("COLLECTION FAILED")
    print("="*80)
    print()
    print(f"Error: {e}")
    print()
    import traceback
    traceback.print_exc()
    print()
    sys.exit(1)