run-20260528-2225Z / crs-l2-svalbard-polar-areas

0:00

svalbard_glaciers — I need an honest size ranking of these high-latitude glaciers using true geographic area, not the distorted values you'd get from raw lat/lon coordinates. Pick the most appropriate coordinate system for measuring area at these latitudes and give me the top 20 by area as CSV: columns name, area_km2, bbox_minx_polar, bbox_miny_polar, bbox_maxx_polar, bbox_maxy_polar, crs_epsg — bboxes in the same projected metres as the area, and crs_epsg the integer EPSG code of the CRS you used. Sort by area_km2 descending. File: svalbard_glaciers_top20.csv.

0:00

System info

{
  "adapter": "openrouter",
  "model": "google/gemma-4-26b-a4b-it",
  "base_url": "https://openrouter.ai/api/v1"
}

0:01

Bash ls -R /home/nhp/project/benchmark/harness/.sessions/8466ddb34e4748bb910f6e2b66bf...

/home/nhp/project/benchmark/harness/.sessions/8466ddb34e4748bb910f6e2b66bf6f88:
svalbard_glaciers_wgs84.gpkg

0:08

Write solve.py

content · 69 lines · py

# /// script
# requires-python = ">=3.12"
# dependencies = ["geopandas", "shapely", "pyproj", "pandas"]
# ///

import geopandas as gpd
import pandas as pd

def main():
    # Load the glacier data
    input_file = 'svalbard_glaciers_wgs84.gpkg'
    gdf = gpd.read_file(input_file)

    # Svalbard is at high latitudes.
    # A good choice for area calculation in Svalbard is a North Pole Lambert Azimuthal Equal Area projection.
    # EPSG:3413 is NSIDC Sea Ice Polar Stereographic North, which is an equal-area projection.
    # Alternatively, one might look for a specific Svalbard projection, but 3413 is widely used for polar areas.
    # Let's check EPSG:3413 or similar. 
    # Another option: EPSG:3476 (NSIDC Sea Ice Polar Stereographic North)
    # Let's use EPSG:3413 for simplicity if it works well, or find a more local one.
    # Actually, EPSG:3413 is often used. Let's try EPSG:3413.
    
    target_crs = 'EPSG:3413'
    
    # Project the data
    gdf_projected = gdf.to_crs(target_crs)
    
    # Calculate area in km2
    # gdf_projected.area is in square meters if the CRS is in meters
    gdf_projected['area_km2'] = gdf_projected.geometry.area / 10**6
    
    # Get top 20 by area
    top_20 = gdf_projected.sort_values(by='area_km2', ascending=False).head(20).copy()
    
    # Calculate bounding boxes in the projected CRS
    # bounds returns (minx, miny, maxx, maxy)
    bounds = top_20.geometry.bounds
    top_20['bbox_minx_polar'] = bounds['minx']
    top_20['bbox_miny_polar'] = bounds['miny']
    top_20['bbox_maxx_polar'] = bounds['maxx']
    top_20['bbox_maxy_polar'] = bounds['maxy']
    
    # Get the EPSG code
    epsg_code = int(gdf_projected.crs.to_epsg())
    top_20['crs_epsg'] = epsg_code
    
    # Select only required columns
    # name, area_km2, bbox_minx_polar, bbox_miny_polar, bbox_maxx_polar, bbox_maxy_polar, crs_epsg
    # We need to check what the name column is called.
    if 'name' not in top_20.columns:
        # Try common names
        for possible_name in ['NAME', 'Name', 'id', 'glacier_name']:
            if possible_name in top_20.columns:
                top_20 = top_20.rename(columns={possible_name: 'name'})
                break
        else:
            # If none found, use the index or first column
            print("Columns in gdf:", top_20.columns)
            raise ValueError("Could not find a name column")

    output_df = top_20[['name', 'area_km2', 'bbox_minx_polar', 'bbox_miny_polar', 'bbox_maxx_polar', 'bbox_maxy_polar', 'crs_epsg']]
    
    # Write to CSV
    output_df.to_csv('svalbard_glaciers_top20.csv', index=False)
    print("Successfully created svalbard_glaciers_top20.csv")

if __name__ == "__main__":
    main()

Wrote /home/nhp/project/benchmark/harness/.sessions/8466ddb34e4748bb910f6e2b66bf6f88/solve.py (2710 chars).