#!/usr/bin/env python3
"""
Read and analyze already extracted Arctic GRIB coordinate data
"""
import numpy as np
import os

def read_extracted_arctic_data():
    """Read the Arctic coordinate data that was already extracted."""
    
    base_path = "/Users/nakas/Documents/pythonGribExtraction"
    
    # File paths for the extracted data
    data_file = f"{base_path}/wave_data_Significant_height_of_combined_wind_waves_and_swell_data.npy"
    lats_file = f"{base_path}/wave_data_Significant_height_of_combined_wind_waves_and_swell_lats.npy"
    lons_file = f"{base_path}/wave_data_Significant_height_of_combined_wind_waves_and_swell_lons.npy"
    
    print("🧪 Reading extracted Arctic GRIB coordinate data")
    print("=" * 60)
    
    # Check if files exist
    for filepath in [data_file, lats_file, lons_file]:
        if not os.path.exists(filepath):
            print(f"❌ File not found: {filepath}")
            return
        print(f"✅ Found: {os.path.basename(filepath)}")
    
    try:
        # Load the numpy arrays
        print("\n📂 Loading extracted arrays...")
        wave_data = np.load(data_file)
        lats = np.load(lats_file) 
        lons = np.load(lons_file)
        
        print(f"✅ Arrays loaded successfully")
        print(f"📏 Data shape: {wave_data.shape}")
        print(f"📏 Coordinates shape: lats={lats.shape}, lons={lons.shape}")
        
        # Validate data ranges 
        print(f"\n📊 Data validation:")
        print(f"Wave height range: {np.nanmin(wave_data):.3f} to {np.nanmax(wave_data):.3f} m")
        print(f"Latitude range: {np.nanmin(lats):.2f} to {np.nanmax(lats):.2f}°")
        print(f"Longitude range: {np.nanmin(lons):.2f} to {np.nanmax(lons):.2f}°")
        
        # Check for valid data
        valid_mask = ~np.isnan(wave_data) & ~np.isnan(lats) & ~np.isnan(lons)
        valid_count = np.sum(valid_mask)
        total_count = wave_data.size
        
        print(f"\n🔍 Data quality:")
        print(f"Total grid points: {total_count:,}")
        print(f"Valid data points: {valid_count:,}")
        print(f"Valid percentage: {(valid_count/total_count)*100:.1f}%")
        
        # Arctic region filter (lat >= 50°N)
        arctic_mask = (lats >= 50.0) & (lats <= 85.0) & valid_mask
        arctic_count = np.sum(arctic_mask)
        
        print(f"\n🧊 Arctic region (50°-85°N):")
        print(f"Arctic data points: {arctic_count:,}")
        
        if arctic_count > 0:
            arctic_lats = lats[arctic_mask]
            arctic_lons = lons[arctic_mask]
            arctic_waves = wave_data[arctic_mask]
            
            print(f"Arctic lat range: {arctic_lats.min():.2f} to {arctic_lats.max():.2f}°")
            print(f"Arctic lon range: {arctic_lons.min():.2f} to {arctic_lons.max():.2f}°")
            print(f"Arctic wave range: {arctic_waves.min():.3f} to {arctic_waves.max():.3f} m")
            
            # Sample some Arctic points
            print(f"\n🎯 Sample Arctic coordinate points:")
            sample_indices = np.random.choice(len(arctic_lats), min(10, len(arctic_lats)), replace=False)
            
            for i, idx in enumerate(sample_indices):
                print(f"  {i+1:2d}. Lat: {arctic_lats[idx]:7.2f}°, Lon: {arctic_lons[idx]:8.2f}°, Wave: {arctic_waves[idx]:.3f}m")
            
            # Create a sample dataset for your app
            print(f"\n💾 Creating sample dataset...")
            sample_size = min(1000, arctic_count)  # Sample 1000 points
            sample_indices = np.random.choice(arctic_count, sample_size, replace=False)
            
            sample_data = []
            for idx in sample_indices:
                sample_data.append({
                    'latitude': float(arctic_lats[idx]),
                    'longitude': float(arctic_lons[idx]),
                    'value': float(arctic_waves[idx]),
                    'parameter': 'Significant height of combined wind waves and swell',
                    'parameter_type': 'wave_height'
                })
            
            # Save sample as simple text format
            output_file = "/tmp/arctic_sample_coordinates.txt"
            with open(output_file, 'w') as f:
                f.write("latitude,longitude,wave_height\n")
                for point in sample_data:
                    f.write(f"{point['latitude']:.6f},{point['longitude']:.6f},{point['value']:.6f}\n")
            
            print(f"Sample data saved to: {output_file}")
            print(f"\n✅ Arctic coordinate data analysis COMPLETE!")
            print(f"You have {arctic_count:,} real Arctic coordinate points ready to use")
            
            return sample_data
        
        else:
            print("❌ No Arctic data points found")
    
    except Exception as e:
        print(f"❌ Failed to read extracted data: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    read_extracted_arctic_data()