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

tunned_geobr/read_railways.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_railways(simplified=False):
+    """Download Railways data from MapBiomas.
+    
+    This function downloads and processes railways data from MapBiomas. 
+    The data includes information about railway networks 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 railways data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_railways
+    
+    # Read railways data
+    >>> railways = read_railways()
+    """
+    
+    url = "https://brasil.mapbiomas.org/wp-content/uploads/sites/4/2023/08/ferrovia.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',         # Railway name
+                    'uf',           # State
+                    'operadora',    # Operating company
+                    'situacao',     # Status
+                    'extensao_km',  # Length in km
+                    'bitola',       # Track gauge
+                    'carga',        # Cargo type
+                    'eletrifica'    # Electrification
+                ]
+                
+                # 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 railways data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_rppn.py

@@ -0,0 +1,107 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_rppn(simplified=False):
+    """Download Private Natural Heritage Reserves (RPPN) data from ICMBio.
+    
+    This function downloads and processes data about Private Natural Heritage Reserves 
+    (Reservas Particulares do Patrimônio Natural - RPPN) in Brazil. RPPNs are private 
+    conservation units created by landowners to protect natural areas on their properties.
+    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 RPPN data
+        Columns:
+        - geometry: Geometry of the RPPN
+        - nome: RPPN name
+        - municipio: Municipality
+        - uf: State
+        - proprietar: Owner name
+        - area_ha: Area in hectares
+        - portaria: Ordinance number
+        - dt_criacao: Creation date
+        - bioma: Biome
+        - esfera: Administrative sphere (Federal/State)
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_rppn
+    
+    # Read RPPN data
+    >>> rppn = read_rppn()
+    """
+    
+    url = "https://sistemas.icmbio.gov.br/simrppn/publico/rppn/shp/"
+    
+    # Headers para simular um navegador
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
+        'Accept-Language': 'pt-BR,pt;q=0.9,en-US;q=0.8,en;q=0.7',
+        'Accept-Encoding': 'gzip, deflate, br',
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1',
+        'Sec-Fetch-Dest': 'document',
+        'Sec-Fetch-Mode': 'navigate',
+        'Sec-Fetch-Site': 'none',
+        'Sec-Fetch-User': '?1',
+        'Cache-Control': 'max-age=0'
+    }
+    
+    try:
+        # Download the zip file
+        response = requests.get(url, headers=headers, timeout=30, allow_redirects=True)
+        print(f"Status: {response.status_code}")
+        print(f"Headers: {dict(response.headers)}")
+        
+        if response.status_code != 200:
+            raise Exception(f"Failed to download data from ICMBio. Status code: {response.status_code}")
+            
+        # 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',
+                    'nome',       # RPPN name
+                    'municipio',  # Municipality
+                    'uf',         # State
+                    'area_ha',    # Area in hectares
+                    'bioma'       # Biome
+                ]
+                
+                # 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 RPPN data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_rppn()

tunned_geobr/read_sigef_properties.py

@@ -0,0 +1,83 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_sigef_properties(simplified=False):
+    """Download Certified Properties data from INCRA's SNCI.
+    
+    This function downloads and processes certified properties data from INCRA's 
+    National Property Certification System (Sistema Nacional de Certificação de Imóveis - SNCI). 
+    The data includes information about certified rural properties across Brazil.
+    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
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with certified properties data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_snci_properties
+    
+    # Read certified properties data
+    >>> properties = read_snci_properties()
+    """
+    
+    url = "https://certificacao.incra.gov.br/csv_shp/zip/Sigef%20Brasil.zip"
+    if 1==1:
+        return "Essa camada está muito pesada, baixe manualmente no link: " + url
+    try:
+        # Download the zip file
+        # Disable SSL verification due to INCRA's certificate issues
+        import urllib3
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        
+        response = requests.get(url, verify=False)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from INCRA")
+            
+        # 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',
+                    'parcela',      # Property ID
+                    'municipio',    # Municipality
+                    'uf',          # State
+                    'area_ha',     # Area in hectares
+                    'status',      # Certification status
+                    'data_cert',   # Certification date
+                    'cod_imovel',  # Property code
+                    'nome_imov'    # Property name
+                ]
+                
+                # 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 certified properties data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_snci_properties.py

@@ -0,0 +1,83 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_snci_properties(simplified=False):
+    """Download Certified Properties data from INCRA's SNCI.
+    
+    This function downloads and processes certified properties data from INCRA's 
+    National Property Certification System (Sistema Nacional de Certificação de Imóveis - SNCI). 
+    The data includes information about certified rural properties across Brazil.
+    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
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with certified properties data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_snci_properties
+    
+    # Read certified properties data
+    >>> properties = read_snci_properties()
+    """
+    
+    url = "https://certificacao.incra.gov.br/csv_shp/zip/Imóvel%20certificado%20SNCI%20Brasil.zip"
+    if 1==1:
+        return "Essa camada está muito pesada, baixe manualmente no link: " + url
+    try:
+        # Download the zip file
+        # Disable SSL verification due to INCRA's certificate issues
+        import urllib3
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        
+        response = requests.get(url, verify=False)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from INCRA")
+            
+        # 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',
+                    'parcela',      # Property ID
+                    'municipio',    # Municipality
+                    'uf',          # State
+                    'area_ha',     # Area in hectares
+                    'status',      # Certification status
+                    'data_cert',   # Certification date
+                    'cod_imovel',  # Property code
+                    'nome_imov'    # Property name
+                ]
+                
+                # 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 certified properties data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_state_direct.py

@@ -0,0 +1,103 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_state(code_state="all", simplified=True):
+    """Download shapefiles of Brazilian states as geopandas objects.
+
+    This function downloads and processes state data directly from IBGE (Brazilian Institute of Geography and Statistics).
+    Data uses Geodetic reference system "SIRGAS2000" and CRS(4674).
+    
+    Parameters
+    ----------
+    code_state : str, optional
+        The two-digit code of a state or a two-letter uppercase abbreviation
+        (e.g. 33 or "RJ"). If code_state="all", all states will be loaded (Default).
+    simplified : boolean, by default True
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with state boundaries
+
+    Example
+    -------
+    >>> from tunned_geobr import read_state
+
+    # Read all states
+    >>> states = read_state()
+
+    # Read specific state by code
+    >>> state = read_state(code_state=33)
+
+    # Read specific state by abbreviation
+    >>> state = read_state(code_state="RJ")
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_UF_2023.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download state data from IBGE")
+            
+        # 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)
+            
+            # Filter by code_state if not "all"
+            if code_state != "all":
+                if isinstance(code_state, int) or code_state.isdigit():
+                    # Filter by numeric code
+                    code = str(code_state).zfill(2)
+                    gdf = gdf[gdf['CD_UF'] == code]
+                elif isinstance(code_state, str) and len(code_state) == 2:
+                    # Filter by state abbreviation
+                    gdf = gdf[gdf['SIGLA_UF'] == code_state.upper()]
+                
+                if len(gdf) == 0:
+                    raise Exception(f"No data found for code_state={code_state}")
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'CD_UF',       # State code
+                    'SIGLA_UF',    # State abbreviation
+                    'NM_UF',       # State name
+                    '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 state data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_state()

tunned_geobr/read_state_highways.py

@@ -0,0 +1,79 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_state_highways(simplified=False):
+    """Download State Highways data from MapBiomas.
+    
+    This function downloads and processes state highways data from MapBiomas. 
+    The data includes information about state-managed highways 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 state highways data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_state_highways
+    
+    # Read state highways data
+    >>> highways = read_state_highways()
+    """
+    
+    url = "https://brasil.mapbiomas.org/wp-content/uploads/sites/4/2023/08/rodovia-estadual.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',
+                    'sigla',        # Highway code
+                    'uf',           # State
+                    'jurisdicao',   # Jurisdiction
+                    'superficie',   # Surface type
+                    'situacao',     # Status
+                    'extensao_km',  # Length in km
+                    'tipo_trecho'   # Section 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 state highways data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_transmission_lines_ons.py

@@ -0,0 +1,87 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_transmission_lines_ons(simplified=False):
+    """Download Brazilian Transmission Lines data from ONS.
+    
+    This function downloads and processes the Brazilian Transmission Lines data
+    from ONS (National Electric System Operator).
+    Original source: ONS - Operador Nacional do Sistema Elétrico
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian transmission lines data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_transmission_lines_ons
+    
+    # Read transmission lines data
+    >>> transmission_lines = read_transmission_lines_ons()
+    """
+    
+    # The URL provided is a blob URL which might be temporary
+    # This is the permanent URL to the ONS data portal
+    url = "https://sig.ons.org.br/download/LT_SIN.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download transmission lines data from ONS")
+            
+        # 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',        # Line name
+                    'TENSAO',      # Voltage
+                    'EXTENSAO',    # Length
+                    'CIRCUITO',    # Circuit
+                    'PROPRIETAR',  # Owner
+                    'STATUS'       # Status
+                ]
+                
+                # 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 transmission lines data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_transmission_lines_ons()