tunned-geobr 0.1.2__py3-none-any.whl → 0.2.1__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/list_geobr.py

@@ -1,39 +1,117 @@
-from requests import get
 import pandas as pd
-from io import StringIO
-from urllib.error import HTTPError
-import re
+from tabulate import tabulate
 
 def list_geobr():
-    """Prints available functions, according to latest README.md file
-
-    Example output
-    ------------------------------
-    Function: read_immediate_region
-    Geographies available: Immediate region
-    Years available: 2017
-    Source: IBGE
-    ------------------------------
-
+    """Lists all available datasets in the tunned_geobr package.
+    
+    This function displays a comprehensive table of all geographic datasets
+    available in the tunned_geobr package, including information about the
+    geographies, years, and sources.
+    
+    Returns
+    -------
+    pandas.DataFrame
+        A DataFrame containing information about all available datasets
+    
+    Example
+    -------
+    >>> from tunned_geobr import list_geobr
+    >>> datasets = list_geobr()
     """
+    
+    # Create a comprehensive list of all datasets
+    datasets = [
+        # Original geobr datasets
+        {"Function": "read_country", "Geography": "Country", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_region", "Geography": "Region", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_state", "Geography": "State", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_state_direct", "Geography": "State (direct)", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_meso_region", "Geography": "Meso region", "Years": "1991, 2000, 2010, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020", "Source": "IBGE"},
+        {"Function": "read_micro_region", "Geography": "Micro region", "Years": "1991, 2000, 2010, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020", "Source": "IBGE"},
+        {"Function": "read_immediate_region", "Geography": "Immediate region", "Years": "2017, 2019, 2020", "Source": "IBGE"},
+        {"Function": "read_intermediate_region", "Geography": "Intermediate region", "Years": "2017, 2019, 2020", "Source": "IBGE"},
+        {"Function": "read_municipality", "Geography": "Municipality", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_municipality_direct", "Geography": "Municipality (direct)", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_weighting_area", "Geography": "Census weighting area", "Years": "2010", "Source": "IBGE"},
+        {"Function": "read_census_tract", "Geography": "Census tract", "Years": "2000, 2010", "Source": "IBGE"},
+        {"Function": "read_census_tract_2022", "Geography": "Census tract 2022", "Years": "2022", "Source": "IBGE"},
+        {"Function": "read_statistical_grid", "Geography": "Statistical grid", "Years": "2010", "Source": "IBGE"},
+        {"Function": "read_comparable_areas", "Geography": "Comparable areas", "Years": "1872, 1900, 1911, 1920, 1933, 1940, 1950, 1960, 1970, 1980, 1991, 2000, 2010", "Source": "IBGE"},
+        {"Function": "read_health_region", "Geography": "Health region", "Years": "1991, 1994, 1997, 2001, 2005, 2013", "Source": "DataSUS"},
+        {"Function": "read_metro_area", "Geography": "Metropolitan area", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_urban_area", "Geography": "Urban area", "Years": "2005, 2015", "Source": "IBGE"},
+        {"Function": "read_urban_concentrations", "Geography": "Urban concentrations", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_amazon", "Geography": "Amazon", "Years": "All", "Source": "IBGE, MMA, and others"},
+        {"Function": "read_biomes", "Geography": "Biomes", "Years": "2004, 2019", "Source": "IBGE"},
+        {"Function": "read_conservation_units", "Geography": "Conservation units", "Years": "All", "Source": "MMA"},
+        {"Function": "read_disaster_risk_area", "Geography": "Disaster risk areas", "Years": "2010", "Source": "CEMADEN and IBGE"},
+        {"Function": "read_indigenous_land", "Geography": "Indigenous lands", "Years": "All", "Source": "FUNAI"},
+        {"Function": "read_semiarid", "Geography": "Semi-arid region", "Years": "All", "Source": "IBGE and others"},
+        {"Function": "read_health_facilities", "Geography": "Health facilities", "Years": "All", "Source": "DataSUS"},
+        {"Function": "read_neighborhood", "Geography": "Neighborhood", "Years": "2010", "Source": "IBGE"},
+        {"Function": "read_neighborhoods_2022", "Geography": "Neighborhoods 2022", "Years": "2022", "Source": "IBGE"},
+        {"Function": "read_schools", "Geography": "Schools", "Years": "All", "Source": "INEP"},
+        {"Function": "read_ports", "Geography": "Ports", "Years": "All", "Source": "Ministério da Infraestrutura"},
+        {"Function": "read_municipal_seat", "Geography": "Municipal seats", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_pop_arrangements", "Geography": "Population arrangements", "Years": "2015", "Source": "IBGE"},
+        {"Function": "read_rppn", "Geography": "Private Natural Heritage Reserves", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_settlements", "Geography": "Rural settlements", "Years": "All", "Source": "INCRA"},
+        
+        # Additional datasets in tunned_geobr
+        {"Function": "read_mining_processes", "Geography": "Mining processes", "Years": "All", "Source": "ANM"},
+        {"Function": "read_ebas", "Geography": "Endemic Bird Areas", "Years": "All", "Source": "Global Forest Watch"},
+        {"Function": "read_vegetation", "Geography": "Brazilian Vegetation", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_transmission_lines_ons", "Geography": "Transmission Lines", "Years": "All", "Source": "ONS"},
+        {"Function": "read_water_bodies_ana", "Geography": "Water Bodies", "Years": "All", "Source": "ANA"},
+        {"Function": "read_pan_strategic_areas", "Geography": "PAN Strategic Areas", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_geographic_regions", "Geography": "Geographic Regions", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_biosphere_reserves", "Geography": "Biosphere Reserves", "Years": "All", "Source": "MMA"},
+        {"Function": "read_baze_sites", "Geography": "BAZE Sites", "Years": "2018", "Source": "MMA"},
+        
+        # Environmental and conservation datasets
+        {"Function": "read_amazon_ibas", "Geography": "Amazon IBAs", "Years": "All", "Source": "SAVE Brasil"},
+        {"Function": "read_atlantic_forest_ibas", "Geography": "Atlantic Forest IBAs", "Years": "All", "Source": "SAVE Brasil"},
+        {"Function": "read_atlantic_forest_law_limits", "Geography": "Atlantic Forest Law Limits", "Years": "All", "Source": "MMA/IBGE"},
+        {"Function": "read_apcb_amazon", "Geography": "APCB Amazon", "Years": "All", "Source": "MMA"},
+        {"Function": "read_apcb_caatinga", "Geography": "APCB Caatinga", "Years": "All", "Source": "MMA"},
+        {"Function": "read_apcb_cerrado_pantanal", "Geography": "APCB Cerrado/Pantanal", "Years": "All", "Source": "MMA"},
+        {"Function": "read_apcb_mata_atlantica", "Geography": "APCB Atlantic Forest", "Years": "All", "Source": "MMA"},
+        {"Function": "read_apcb_pampa", "Geography": "APCB Pampa", "Years": "All", "Source": "MMA"},
+        {"Function": "read_apcb_zcm", "Geography": "APCB Coastal/Marine", "Years": "All", "Source": "MMA"},
+        
+        # Geological and natural features datasets
+        {"Function": "read_natural_caves", "Geography": "Natural Caves", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_cave_potential", "Geography": "Cave Potential", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_fossil_occurrences", "Geography": "Fossil Occurrences", "Years": "All", "Source": "SGB"},
+        {"Function": "read_archaeological_sites", "Geography": "Archaeological Sites", "Years": "All", "Source": "IPHAN"},
+        {"Function": "read_geology", "Geography": "Geology", "Years": "All", "Source": "CPRM"},
+        {"Function": "read_geomorphology", "Geography": "Geomorphology", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_pedology", "Geography": "Pedology", "Years": "All", "Source": "IBGE"},
+        {"Function": "read_climate_aggressiveness", "Geography": "Climate Aggressiveness", "Years": "All", "Source": "IBGE"},
+        
+        # Transportation and infrastructure datasets
+        {"Function": "read_public_aerodromes", "Geography": "Public Aerodromes", "Years": "All", "Source": "MapBiomas"},
+        {"Function": "read_private_aerodromes", "Geography": "Private Aerodromes", "Years": "All", "Source": "MapBiomas"},
+        {"Function": "read_state_highways", "Geography": "State Highways", "Years": "All", "Source": "MapBiomas"},
+        {"Function": "read_federal_highways", "Geography": "Federal Highways", "Years": "All", "Source": "MapBiomas"},
+        {"Function": "read_railways", "Geography": "Railways", "Years": "All", "Source": "MapBiomas"},
+        {"Function": "read_waterways", "Geography": "Waterways", "Years": "All", "Source": "SNIRH"},
+        {"Function": "read_heliports", "Geography": "Heliports", "Years": "All", "Source": "MapBiomas"},
+        
+        # Land tenure and property datasets
+        {"Function": "read_snci_properties", "Geography": "SNCI Properties", "Years": "All", "Source": "INCRA"},
+        {"Function": "read_sigef_properties", "Geography": "SIGEF Properties", "Years": "All", "Source": "INCRA"},
+        {"Function": "read_quilombola_areas", "Geography": "Quilombola Areas", "Years": "All", "Source": "INCRA"}
+    ]
+    
+    # Create DataFrame
+    df = pd.DataFrame(datasets)
+    
+    # Display the table
+    print(tabulate(df, headers='keys', tablefmt='psql', showindex=False))
+    
+    # Return the DataFrame for further use
+    return df
 
-    try:
-        html_data = get("https://github.com/ipeaGIT/geobr/blob/master/README.md").text
-        find_emoji = html_data.index("👉")
-        html_data =  html_data[find_emoji:]
-        escaped_data = html_data.replace("\\u003c", "<").replace("\\u003e", ">")
-        tables = re.findall("<table>(.+?)</table>", escaped_data)
-        available_datasets = "<table>" + tables[0].replace("\\n", "") + "</table>"
-        df = pd.DataFrame(pd.read_html(StringIO(available_datasets))[0])
-
-    except HTTPError:
-        print(
-            "Geobr url functions list is broken"
-            'Please report an issue at "https://github.com/ipeaGIT/geobr/issues"'
-        )
-
-    for i in range(len(df)):
-        for each in df.columns:
-            print(f"{each}: {df.loc[i, each]}")
-
-        print("------------------------------")
+if __name__ == "__main__":
+    list_geobr()

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