Skip to main content

Read Data

Common examples for reading geospatial data in Fused.

Python Packages​

geopandas​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/subway_stations.geojson"):
    import geopandas as gpd
    
    return gpd.read_file(path)

shapely​

@fused.udf
def udf():
    import geopandas as gpd
    from shapely.geometry import Point, Polygon
    
    # Create geometries with shapely
    points = [Point(-122.4, 37.8), Point(-122.3, 37.7)]
    polygon = Polygon([(-122.5, 37.7), (-122.3, 37.7), (-122.3, 37.9), (-122.5, 37.9)])
    
    gdf = gpd.GeoDataFrame(
        {'type': ['point', 'point', 'polygon']},
        geometry=points + [polygon],
        crs=4326
    )
    
    return gdf

duckdb​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/housing_2024.parquet"):
    import duckdb
    
    conn = duckdb.connect()
    result = conn.execute(f"""
        SELECT * 
        FROM '{path}'
        WHERE latitude IS NOT NULL
        LIMIT 1000
    """).df()
    
    return result

rioxarray​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/elevation.tif"):
    import rioxarray as rxr
    
    # Read raster data with rioxarray
    raster = rxr.open_rasterio(path)
    
    # Convert to DataFrame for display
    df = raster.to_dataframe().reset_index()
    
    return df.head(1000)

xarray​

@fused.udf
def udf():
    import xarray as xr
    
    # Download NetCDF data to mount disk for proper reading
    path = fused.download('s3://fused-sample/demo_data/2025_01_01_ERA5_surface.nc','2025_01_01_ERA5_surface.nc')
    ds = xr.open_dataset(path)
    
    # Convert to DataFrame
    df = ds.to_dataframe().reset_index()
    
    return df.head(1000)

Table Formats (Vector)​

GeoJSON (.geojson, .json)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/US_states.geojson"):
    import geopandas as gpd
    
    return gpd.read_file(path)

Shapefile (.shp + .shx, .dbf, .prj)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/US_states_shapefile.shp"):
    import geopandas as gpd
    
    return gpd.read_file(path)

GeoPackage (.gpkg)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/US_states_geopackage.gpkg"):
    import geopandas as gpd
    
    return gpd.read_file(path)

KML/KMZ (.kml, .kmz)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/US_states.kml"):
    import geopandas as gpd
    
    return gpd.read_file(path)

Parquet (.parquet)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/buildings.parquet"):
    import geopandas as gpd
    
    return gpd.read_parquet(path)

CSV with coordinates (.csv)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/subway_stations.csv"):
    import pandas as pd
    import geopandas as gpd
    from shapely.geometry import Point
    
    # Read CSV
    df = pd.read_csv(path)
    
    # Convert to GeoDataFrame
    gdf = gpd.GeoDataFrame(
        df, 
        geometry=gpd.points_from_xy(df.longitude, df.latitude),
        crs=4326
    )
    
    return gdf

Excel (.xlsx)​

@fused.udf
def udf(path: str = "s3://fused-sample/demo_data/table/subway_stations.xlsx"):
    import pandas as pd
    import geopandas as gpd
    from shapely.geometry import Point
    
    # Read Excel file
    df = pd.read_excel(path)
    
    # Convert to GeoDataFrame if coordinates exist
    if 'longitude' in df.columns and 'latitude' in df.columns:
        gdf = gpd.GeoDataFrame(
            df,
            geometry=gpd.points_from_xy(df.longitude, df.latitude),
            crs=4326
        )
        return gdf
    
    return df

Array Formats (Raster)​

GeoTIFF (.tif, .tiff)​

@fused.udf
def udf(
    path: str = 's3://fused-sample/demo_data/satellite_imagery/wildfires.tiff'
):
    import rasterio

    with rasterio.open(path) as src:
        data = src.read()
        bounds = src.bounds

    return data, bounds

NetCDF (.nc)​

@fused.udf
def udf():
    import xarray as xr
    
    # Download to mount disk for proper NetCDF reading
    path = fused.download('s3://fused-sample/demo_data/climate_data.nc', 'climate_data.nc')
    
    # Open NetCDF dataset
    ds = xr.open_dataset(path)
    
    return ds.to_dataframe().reset_index().head(1000)

STAC Catalog​

Earth on AWS​

@fused.udf
def udf(
    bounds: fused.types.Bounds = [-77.083, 38.804, -76.969, 38.983],
):
    import odc.stac
    import pystac_client
    import planetary_computer

    odc.stac.configure_s3_access(aws_unsigned=True)
    catalog = pystac_client.Client.open("https://earth-search.aws.element84.com/v1")

    # Loading Elevation model
    items = catalog.search(
        collections=["cop-dem-glo-30"], 
        bbox=bounds
    ).item_collection()

    xarray_dataset = odc.stac.load(
        items,
        crs="EPSG:3857",
        bands=["data"],
        resolution=150,
        bbox=bounds,
    ).astype(int)

    return xarray_dataset["data"], bounds

Microsoft Planetary Computer​

@fused.udf
def udf(
    bounds: fused.types.Bounds = [-122.463,37.755,-122.376,37.803],
):
    import odc.stac
    import planetary_computer
    import pystac_client
    
    catalog = pystac_client.Client.open(
        "https://planetarycomputer.microsoft.com/api/stac/v1",
        modifier=planetary_computer.sign_inplace,
    )

    # Loading Elevation model
    items = catalog.search(collections=["cop-dem-glo-30"],bbox=bounds).item_collection()
    
    xarray_dataset = odc.stac.load(
        items,
        crs="EPSG:3857",
        bands=["data"],
        resolution=150,
        bbox=bounds,
    ).astype(int)
    
    return xarray_dataset["data"], bounds