tunned-geobr 0.1.2__py3-none-any.whl → 0.2.0__py3-none-any.whl

tunned_geobr/__init__.py

@@ -1,4 +1,4 @@
-from .read_state import read_state
+from .read_state_direct import read_state
 from .read_amazon import read_amazon
 from .read_biomes import read_biomes
 from .read_country import read_country
@@ -16,7 +16,7 @@ from .list_geobr import list_geobr
 from .read_census_tract import read_census_tract
 from .read_meso_region import read_meso_region
 from .read_micro_region import read_micro_region
-from .read_municipality import read_municipality
+from .read_municipality_direct import read_municipality
 from .read_weighting_area import read_weighting_area
 from .read_neighborhood import read_neighborhood
 from .read_health_region import read_health_region
@@ -36,3 +36,35 @@ from .read_climate_aggressiveness import read_climate_aggressiveness
 from .read_amazon_ibas import read_amazon_ibas
 from .read_atlantic_forest_ibas import read_atlantic_forest_ibas
 from .read_settlements import read_settlements
+from .read_apcb_amazon import read_apcb_amazon
+from .read_apcb_caatinga import read_apcb_caatinga
+from .read_apcb_cerrado_pantanal import read_apcb_cerrado_pantanal
+from .read_apcb_mata_atlantica import read_apcb_mata_atlantica
+from .read_apcb_pampa import read_apcb_pampa
+from .read_apcb_zcm import read_apcb_zcm
+from .read_natural_caves import read_natural_caves
+from .read_ports import read_ports
+from .read_public_aerodromes import read_public_aerodromes
+from .read_private_aerodromes import read_private_aerodromes
+from .read_state_highways import read_state_highways
+from .read_federal_highways import read_federal_highways
+from .read_railways import read_railways
+from .read_waterways import read_waterways
+from .read_heliports import read_heliports
+from .read_snci_properties import read_snci_properties
+from .read_sigef_properties import read_sigef_properties
+from .read_atlantic_forest_law_limits import read_atlantic_forest_law_limits
+from .read_fossil_occurrences import read_fossil_occurrences
+from .read_cave_potential import read_cave_potential
+from .read_rppn import read_rppn
+from .read_archaeological_sites import read_archaeological_sites
+from .read_ebas import read_ebas
+from .read_vegetation import read_vegetation
+from .read_transmission_lines_ons import read_transmission_lines_ons
+from .read_water_bodies_ana import read_water_bodies_ana
+from .read_pan_strategic_areas import read_pan_strategic_areas
+from .read_geographic_regions import read_geographic_regions
+from .read_biosphere_reserves import read_biosphere_reserves
+from .read_census_tract_2022 import read_census_tract_2022
+from .read_neighborhoods_2022 import read_neighborhoods_2022
+from .read_baze_sites import read_baze_sites

tunned_geobr/read_apcb_amazon.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_amazon(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Amazon region.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Amazon region.
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Amazon APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_amazonia
+    
+    # Read Amazon APCB data
+    >>> apcb = read_apcb_amazonia()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/amazonia.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Amazon APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_apcb_caatinga.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_caatinga(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Caatinga region.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Caatinga region.
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Caatinga APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_caatinga
+    
+    # Read Caatinga APCB data
+    >>> apcb = read_apcb_caatinga()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/caatinga.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Caatinga APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_apcb_cerrado_pantanal.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_cerrado_pantanal(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Cerrado and Pantanal regions.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Cerrado and Pantanal regions.
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Cerrado and Pantanal APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_cerrado_pantanal
+    
+    # Read Cerrado and Pantanal APCB data
+    >>> apcb = read_apcb_cerrado_pantanal()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/cerrado_pantanal.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Cerrado and Pantanal APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_apcb_mata_atlantica.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_mata_atlantica(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Atlantic Forest region.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Atlantic Forest region.
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Atlantic Forest APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_mata_atlantica
+    
+    # Read Atlantic Forest APCB data
+    >>> apcb = read_apcb_mata_atlantica()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/mataatlantica.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Atlantic Forest APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_apcb_pampa.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_pampa(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Pampa region.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Pampa region.
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Pampa APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_pampa
+    
+    # Read Pampa APCB data
+    >>> apcb = read_apcb_pampa()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/pampa.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Pampa APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_apcb_zcm.py

@@ -0,0 +1,78 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_apcb_zcm(simplified=False):
+    """Download Priority Areas for Biodiversity Conservation (APCB) data for the Coastal and Marine Zone.
+    
+    This function downloads and processes APCB data from the Ministry of Environment (MMA). 
+    The data includes priority areas for biodiversity conservation in the Coastal and Marine Zone (ZCM).
+    Original source: Ministério do Meio Ambiente (MMA)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Coastal and Marine Zone APCB data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_apcb_zcm
+    
+    # Read Coastal and Marine Zone APCB data
+    >>> apcb = read_apcb_zcm()
+    """
+    
+    url = "https://www.gov.br/mma/pt-br/assuntos/biodiversidade-e-biomas/biomas-e-ecossistemas/conservacao-1/areas-prioritarias/arquivos/zcm.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'Nome',        # Area name
+                    'Importanci',  # Importance
+                    'Prioridade',  # Priority
+                    'Area_km2',    # Area in km²
+                    'Oportunida',  # Opportunity
+                    'Ameaca'       # Threats
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Coastal and Marine Zone APCB data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_archaeological_sites.py

@@ -0,0 +1,94 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_archaeological_sites(simplified=False):
+    """Download Archaeological Sites data from IPHAN.
+    
+    This function downloads and processes data about archaeological sites in Brazil 
+    from IPHAN (Instituto do Patrimônio Histórico e Artístico Nacional). The data 
+    includes location and basic information about registered archaeological sites.
+    Original source: IPHAN - Instituto do Patrimônio Histórico e Artístico Nacional
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with archaeological sites data
+        Columns:
+        - geometry: Site location
+        - nome: Site name
+        - municipio: Municipality
+        - uf: State
+        - tipo: Site type
+        - exposicao: Exposure type
+        - relevancia: Relevance
+        - preservacao: Preservation state
+        - datacao: Dating
+        - artefatos: Artifacts found
+        - fonte: Data source
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_archaeological_sites
+    
+    # Read archaeological sites data
+    >>> sites = read_archaeological_sites()
+    """
+    
+    url = "http://portal.iphan.gov.br/geoserver/SICG/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=SICG:sitios&maxFeatures=50000&outputFormat=SHAPE-ZIP"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from IPHAN")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = [f for f in os.listdir(temp_dir) if f.endswith('.shp')]
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(os.path.join(temp_dir, shp_files[0]))
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            # Print columns for debugging
+            print("Available columns:", gdf.columns)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'nome',       # Site name
+                    'municipio',  # Municipality
+                    'uf',         # State
+                    'tipo',       # Site type
+                    'relevancia', # Relevance
+                    'preservacao' # Preservation state
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading archaeological sites data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_archaeological_sites()

tunned_geobr/read_atlantic_forest_law_limits.py

@@ -0,0 +1,74 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_atlantic_forest_law_limits(simplified=False):
+    """Download Atlantic Forest Legal Limits data from MMA/IBGE.
+    
+    This function downloads and processes data about the Atlantic Forest legal limits 
+    as defined by Law 11.428/2006. The data is provided by IBGE and MMA (Ministry of Environment).
+    Original source: MMA - Ministério do Meio Ambiente
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Atlantic Forest legal limits data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_atlantic_forest_law_limits
+    
+    # Read Atlantic Forest legal limits data
+    >>> limits = read_atlantic_forest_law_limits()
+    """
+    
+    url = "http://antigo.mma.gov.br/estruturas/202/_arquivos/shape_mata_atlantica_ibge_5milhoes_policonica_sirgas2000shp_202.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MMA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = [f for f in os.listdir(temp_dir) if f.endswith('.shp')]
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(os.path.join(temp_dir, shp_files[0]))
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'NM_TEMA',    # Theme name
+                    'NM_REGIAO',  # Region name
+                    'AREA_KM2',   # Area in km²
+                    'LEI',        # Law reference
+                    'FONTE'       # Data source
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading Atlantic Forest legal limits data: {str(e)}")
+        
+    return gdf