tunned-geobr 0.1.2__py3-none-any.whl → 0.2.1__py3-none-any.whl

tunned_geobr/read_neighborhoods_2022.py

@@ -0,0 +1,99 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+import subprocess
+from io import BytesIO
+
+def read_neighborhoods_2022(simplified=False):
+    """Download Brazilian Neighborhoods data from IBGE (2022 Census).
+    
+    This function downloads and processes the Brazilian Neighborhoods data
+    from IBGE (Brazilian Institute of Geography and Statistics) for the 2022 Census.
+    Original source: IBGE - Instituto Brasileiro de Geografia e Estatística
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian neighborhoods data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_neighborhoods_2022
+    
+    # Read neighborhoods data
+    >>> neighborhoods = read_neighborhoods_2022()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_de_setores_censitarios__divisoes_intramunicipais/censo_2022/bairros/shp/BR/BR_bairros_CD2022.zip"
+    
+    try:
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Download the zip file to the temporary directory
+            zip_file_path = os.path.join(temp_dir, "neighborhoods.zip")
+            
+            # Download the file
+            response = requests.get(url)
+            if response.status_code != 200:
+                raise Exception("Failed to download neighborhoods data from IBGE")
+                
+            # Save the content to a file
+            with open(zip_file_path, 'wb') as f:
+                f.write(response.content)
+            
+            # Use unzip command line tool to extract the file (handles more compression methods)
+            try:
+                subprocess.run(['unzip', '-o', zip_file_path, '-d', temp_dir], 
+                              check=True, 
+                              stdout=subprocess.PIPE, 
+                              stderr=subprocess.PIPE)
+            except subprocess.CalledProcessError as e:
+                raise Exception(f"Failed to extract zip file: {e.stderr.decode()}")
+            
+            # 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])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names may need adjustment based on actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_BAIRRO',   # Neighborhood Code
+                    'NM_BAIRRO',   # Neighborhood Name
+                    'CD_MUN',      # Municipality Code
+                    'NM_MUN',      # Municipality Name
+                    'CD_UF',       # State Code
+                    'NM_UF',       # State Name
+                    'SIGLA_UF',    # State Abbreviation
+                    'AREA_KM2'     # Area in square kilometers
+                ]
+                
+                # 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 neighborhoods data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_neighborhoods_2022()

tunned_geobr/read_pan_strategic_areas.py

@@ -0,0 +1,89 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_pan_strategic_areas(simplified=False):
+    """Download Strategic Areas data from ICMBio's PAN.
+    
+    This function downloads and processes the Strategic Areas data from ICMBio's 
+    National Action Plans (PAN). These are areas of strategic importance for 
+    biodiversity conservation in Brazil.
+    Original source: ICMBio - Instituto Chico Mendes de Conservação da Biodiversidade
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with PAN strategic areas data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_pan_strategic_areas
+    
+    # Read PAN strategic areas data
+    >>> strategic_areas = read_pan_strategic_areas()
+    """
+    
+    url = "https://geoservicos.inde.gov.br/geoserver/ICMBio/ows?request=GetFeature&service=WFS&version=1.0.0&typeName=ICMBio:pan_icmbio_areas_estrat_052024_a&outputFormat=SHAPE-ZIP"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download strategic areas data from ICMBio")
+            
+        # 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])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names may need adjustment based on actual data
+                columns_to_keep = [
+                    'geometry',
+                    'nome',        # Area name
+                    'pan',         # PAN name
+                    'tipo',        # Type of strategic area
+                    'area_km2',    # Area in square kilometers
+                    'bioma',       # Biome
+                    'uf',          # State
+                    'municipio',   # Municipality
+                    'importancia', # Importance
+                    'descricao'    # Description
+                ]
+                
+                # 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 PAN strategic areas data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_pan_strategic_areas()

tunned_geobr/read_ports.py

@@ -0,0 +1,80 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_ports(simplified=False):
+    """Download Brazilian Ports data from SNIRH.
+    
+    This function downloads and processes ports data from SNIRH (Sistema Nacional de 
+    Informações sobre Recursos Hídricos). The data includes information about ports 
+    across Brazil.
+    Original source: SNIRH (Sistema Nacional de Informações sobre Recursos Hídricos)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian ports data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_ports
+    
+    # Read ports data
+    >>> ports = read_ports()
+    """
+    
+    url = "https://metadados.snirh.gov.br/geonetwork/srv/api/records/0afc9687-db93-4eb1-ab31-3bbd871ff303/attachments/GEOFT_PORTO.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from SNIRH")
+            
+        # 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',          # Port name
+                    'municipio',     # Municipality
+                    'uf',           # State
+                    'tipo',         # Port type
+                    'administra',   # Administration
+                    'situacao',     # Status
+                    'localizaca'    # Location details
+                ]
+                
+                # 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 ports data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_private_aerodromes.py

@@ -0,0 +1,81 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_private_aerodromes(simplified=False):
+    """Download Private Aerodromes data from MapBiomas.
+    
+    This function downloads and processes private aerodromes data from MapBiomas. 
+    The data includes information about private airports and aerodromes across Brazil.
+    Original source: MapBiomas
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with private aerodromes data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_private_aerodromes
+    
+    # Read private aerodromes data
+    >>> aerodromes = read_private_aerodromes()
+    """
+    
+    url = "https://brasil.mapbiomas.org/wp-content/uploads/sites/4/2023/08/Aerodromos_Privados.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MapBiomas")
+            
+        # 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',          # Aerodrome name
+                    'municipio',     # Municipality
+                    'uf',           # State
+                    'codigo_oaci',  # ICAO code
+                    'altitude',     # Altitude
+                    'tipo_uso',     # Usage type
+                    'compriment',   # Runway length
+                    'largura',      # Runway width
+                    'tipo_pista'    # Runway type
+                ]
+                
+                # 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 private aerodromes data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_public_aerodromes.py

@@ -0,0 +1,81 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_public_aerodromes(simplified=False):
+    """Download Public Aerodromes data from MapBiomas.
+    
+    This function downloads and processes public aerodromes data from MapBiomas. 
+    The data includes information about public airports and aerodromes across Brazil.
+    Original source: MapBiomas
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with public aerodromes data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_public_aerodromes
+    
+    # Read public aerodromes data
+    >>> aerodromes = read_public_aerodromes()
+    """
+    
+    url = "https://brasil.mapbiomas.org/wp-content/uploads/sites/4/2023/08/Aerodromos_publicos.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MapBiomas")
+            
+        # 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',          # Aerodrome name
+                    'municipio',     # Municipality
+                    'uf',           # State
+                    'codigo_oaci',  # ICAO code
+                    'altitude',     # Altitude
+                    'tipo_uso',     # Usage type
+                    'compriment',   # Runway length
+                    'largura',      # Runway width
+                    'tipo_pista'    # Runway type
+                ]
+                
+                # 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 public aerodromes data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_quilombola_areas.py

@@ -0,0 +1,85 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_settlements(simplified=False):
+    """Download official settlements data from INCRA.
+    
+    This function downloads and processes data about settlements (assentamentos) 
+    from INCRA (Instituto Nacional de Colonização e Reforma Agrária).
+    Original source: INCRA - Certificação de Imóveis Rurais
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with settlements data
+        
+    Example
+    -------
+    >>> from geobr import read_settlements
+    
+    # Read settlements data
+    >>> settlements = read_settlements()
+    """
+    
+    url = "https://certificacao.incra.gov.br/csv_shp/zip/Assentamento%20Brasil.zip"
+    
+    try:
+        # Download the zip file
+        # Disable SSL verification due to INCRA's certificate issues
+        response = requests.get(url, verify=False)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from INCRA")
+            
+        # Suppress the InsecureRequestWarning
+        import urllib3
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+            
+        # 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]))
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'NOME_PROJE',  # Nome do Projeto de Assentamento
+                    'MUNICIPIO',   # Município
+                    'UF',          # Estado
+                    'AREA_HA',     # Área em hectares
+                    'NUM_FAMILI',  # Número de famílias
+                    'CAPACIDADE',  # Capacidade de famílias
+                    'DT_CRIACAO',  # Data de criação
+                    'SITUACAO'     # Situação do assentamento
+                ]
+                
+                # 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 settlements data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    settlements = read_settlements()
+    print(settlements)

tunned_geobr/read_quilombola_areas_temp.py

@@ -0,0 +1,103 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+import urllib3
+import time
+from pathlib import Path
+
+def read_quilombola_areas(simplified=False, local_file=None):
+    """Download Quilombola Areas data from INCRA.
+    
+    This function downloads and processes data about Quilombola Areas (Áreas Quilombolas) 
+    in Brazil. These are territories recognized and titled to remaining quilombo communities.
+    Original source: INCRA - Instituto Nacional de Colonização e Reforma Agrária
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+    local_file : string, optional
+        Path to a local zip file containing the data, by default None
+        If provided, the function will use this file instead of downloading from INCRA
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Quilombola Areas data
+        Columns:
+        - geometry: Geometry of the area
+        - nome: Area name
+        - municipio: Municipality
+        - uf: State
+        - area_ha: Area in hectares
+        - fase: Current phase in the titling process
+        - familias: Number of families
+        - portaria: Ordinance number
+        - decreto: Decree number
+        - titulo: Title number
+        - data_titulo: Title date
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_quilombola_areas
+    
+    # Read Quilombola Areas data
+    >>> quilombos = read_quilombola_areas()
+    
+    # Or use a local file that was previously downloaded
+    >>> quilombos = read_quilombola_areas(local_file="path/to/Áreas de Quilombolas.zip")
+    """
+    
+    url = "https://certificacao.incra.gov.br/csv_shp/zip/Áreas%20de%20Quilombolas.zip"
+    
+    # If a local file is provided, use it instead of downloading
+    if local_file and os.path.exists(local_file):
+        print(f"Using local file: {local_file}")
+        try:
+            with tempfile.TemporaryDirectory() as temp_dir:
+                # Extract the zip file
+                with ZipFile(local_file) 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 local file")
+                
+                print(f"Found shapefile: {shp_files[0]}")
+                
+                # 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(f"Successfully loaded {len(gdf)} Quilombola Areas from local file")
+                
+                if simplified:
+                    # Keep only the most relevant columns
+                    columns_to_keep = [
+                        'geometry',
+                        'nome',       # Area name
+                        'municipio',  # Municipality
+                        'uf',        # State
+                        'area_ha',   # Area in hectares
+                        'fase'       # Current phase
+                    ]
+                    
+                    # 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]
+                
+                return gdf
+        except Exception as e:
+            raise Exception(f"Error processing local file: {str(e)}")
+    
+    # If no local file is provided, return a message with download instructions
+    # This is consistent with the approach in read_snci_properties as mentioned in the MEMORY
+    return "O download automático dos dados de Áreas Quilombolas está temporariamente indisponível.\nPor favor, faça o download manual através do link:\n" + url + "\n\nApós o download, você pode usar o parâmetro local_file:\nquilombos = read_quilombola_areas(local_file='caminho/para/Áreas de Quilombolas.zip')"
+
+if __name__ == '__main__':
+    quilombos = read_quilombola_areas()
+    print(quilombos)