tunned-geobr 0.2.10__py3-none-any.whl → 1.0.1__py3-none-any.whl

tunned_geobr/__init__.py

@@ -18,7 +18,6 @@ from .read_meso_region import read_meso_region
 from .read_micro_region import read_micro_region
 from .read_municipality 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
 from .read_pop_arrangements import read_pop_arrangements
 from .lookup_muni import lookup_muni
@@ -65,7 +64,7 @@ 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_neighborhoods_2022 import read_neighborhoods_2022
+from .read_neighborhood import read_neighborhood
 from .read_baze_sites import read_baze_sites
 from .read_existent_eolic import read_existent_eolic
 from .read_planned_eolic import read_planned_eolic
@@ -125,3 +124,6 @@ from .read_natural_gas_processing_hub import read_natural_gas_processing_hub
 from .read_compression_stations import read_compression_stations
 from .read_natural_gas_delivery_points import read_natural_gas_delivery_points
 from .read_quilombola_areas import read_quilombola_areas
+from .read_icmbio_embargoes import read_icmbio_embargoes
+from .read_icmbio_infractions import read_icmbio_infractions
+from .read_ibama_embargoes import read_ibama_embargoes

tunned_geobr/list_geobr.py

@@ -168,7 +168,12 @@ def list_geobr():
         {"Function": "read_og_basement", "Geography": "Oil and Gas Basement", "Years": "All", "Source": "EPE"},
         {"Function": "read_hydroelectric_feasibility_studies", "Geography": "Hydroelectric Feasibility Studies", "Years": "All", "Source": "EPE"},
         {"Function": "read_hydroelectric_inventory_aai_studies", "Geography": "Hydroelectric Inventory and AAI Studies", "Years": "All", "Source": "EPE"},
-        {"Function": "read_ama_anemometric_towers", "Geography": "AMA Anemometric Towers", "Years": "All", "Source": "EPE"}
+        {"Function": "read_ama_anemometric_towers", "Geography": "AMA Anemometric Towers", "Years": "All", "Source": "EPE"},
+        
+        # Environmental Enforcement Data
+        {"Function": "read_icmbio_embargoes", "Geography": "ICMBio Embargoed Areas", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_icmbio_infractions", "Geography": "ICMBio Infraction Notices", "Years": "All", "Source": "ICMBio"},
+        {"Function": "read_ibama_embargoes", "Geography": "IBAMA Embargoed Areas", "Years": "All", "Source": "IBAMA"}
     ]
     
     # Create DataFrame

tunned_geobr/read_amazon.py

@@ -1,7 +1,7 @@
 from geobr.utils import select_metadata, download_gpkg
 
 
-def read_amazon(year=2012, simplified=True, verbose=False):
+def read_amazon(year=2012, simplified=False, verbose=False):
     """ Download official data of Brazil's Legal Amazon as an sf object.
     
      This data set covers the whole of Brazil's Legal Amazon as defined in the federal law n. 12.651/2012). The original

tunned_geobr/read_ibama_embargoes.py

@@ -0,0 +1,85 @@
+import geopandas as gpd
+import requests
+from io import BytesIO
+
+def read_ibama_embargoes(simplified=False, verbose=False):
+    """Download IBAMA Embargoes data.
+    
+    This function downloads and processes embargoes data from the Brazilian Institute 
+    of Environment and Renewable Natural Resources (IBAMA) through their WFS service.
+    Original source: IBAMA SISCOM
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+    verbose : boolean, by default False
+        If True, prints detailed information about the download process
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with IBAMA Embargoes data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_ibama_embargoes
+    
+    # Read IBAMA Embargoes data
+    >>> embargoes = read_ibama_embargoes()
+    """
+    
+    url = "https://siscom.ibama.gov.br/geoserver/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=publica:vw_brasil_adm_embargo_a&outputFormat=application/json"
+    
+    if verbose:
+        print("Downloading IBAMA Embargoes data...")
+    
+    try:
+        # Download the JSON data
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception(f"Failed to download data from IBAMA WFS service. Status code: {response.status_code}")
+        
+        if verbose:
+            print("Data downloaded successfully. Processing...")
+            
+        # Read the GeoJSON directly from the response content
+        gdf = gpd.read_file(BytesIO(response.content))
+        
+        # Convert to SIRGAS 2000 (EPSG:4674) if needed
+        if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+            if verbose:
+                print(f"Converting CRS from {gdf.crs} to SIRGAS 2000 (EPSG:4674)")
+            gdf = gdf.to_crs(4674)
+            
+        if simplified:
+            # Keep only the most relevant columns
+            # Adjust these based on the actual columns in the dataset
+            columns_to_keep = [
+                'geometry',
+                'nm_municipio',     # Municipality name
+                'sg_uf',            # State abbreviation
+                'nm_pessoa',        # Person/entity name
+                'nr_cpfcnpj',       # CPF/CNPJ number
+                'dt_embargo',       # Embargo date
+                'nr_processo',      # Process number
+                'nr_termo',         # Term number
+                'ar_embargada',     # Embargoed area
+                'tp_infracao',      # Infraction type
+                'ds_infracao'       # Infraction 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]
+            
+            if verbose:
+                print(f"Simplified dataset with {len(existing_columns)} columns")
+    
+    except Exception as e:
+        raise Exception(f"Error downloading IBAMA Embargoes data: {str(e)}")
+    
+    if verbose:
+        print(f"Download completed. Returning GeoDataFrame with {len(gdf)} records")
+        
+    return gdf

tunned_geobr/read_icmbio_embargoes.py

@@ -0,0 +1,83 @@
+import geopandas as gpd
+import requests
+from io import BytesIO
+
+def read_icmbio_embargoes(simplified=False, verbose=False):
+    """Download ICMBio Embargoes data.
+    
+    This function downloads and processes embargoes data from the Brazilian Institute 
+    of Environment and Renewable Natural Resources (ICMBio) through the National Spatial 
+    Data Infrastructure (INDE) WFS service.
+    Original source: ICMBio via INDE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+    verbose : boolean, by default False
+        If True, prints detailed information about the download process
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with ICMBio Embargoes data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_icmbio_embargoes
+    
+    # Read ICMBio Embargoes data
+    >>> embargoes = read_icmbio_embargoes()
+    """
+    
+    url = "https://geoservicos.inde.gov.br/geoserver/ICMBio/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=embargos_icmbio&outputFormat=application/json"
+    
+    if verbose:
+        print("Downloading ICMBio Embargoes data...")
+    
+    try:
+        # Download the JSON data
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception(f"Failed to download data from ICMBio WFS service. Status code: {response.status_code}")
+        
+        if verbose:
+            print("Data downloaded successfully. Processing...")
+            
+        # Read the GeoJSON directly from the response content
+        gdf = gpd.read_file(BytesIO(response.content))
+        
+        # Convert to SIRGAS 2000 (EPSG:4674) if needed
+        if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+            if verbose:
+                print(f"Converting CRS from {gdf.crs} to SIRGAS 2000 (EPSG:4674)")
+            gdf = gdf.to_crs(4674)
+            
+        if simplified:
+            # Keep only the most relevant columns
+            # Adjust these based on the actual columns in the dataset
+            columns_to_keep = [
+                'geometry',
+                'NOME_AREA',       # Area name
+                'MUNICIPIO',       # Municipality
+                'UF',              # State
+                'AREA_HA',         # Area in hectares
+                'TIPO_INFRA',      # Infraction type
+                'DATA_EMBARG',     # Embargo date
+                'TERMO_EMBG'       # Embargo term
+            ]
+            
+            # 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]
+            
+            if verbose:
+                print(f"Simplified dataset with {len(existing_columns)} columns")
+    
+    except Exception as e:
+        raise Exception(f"Error downloading ICMBio Embargoes data: {str(e)}")
+    
+    if verbose:
+        print(f"Download completed. Returning GeoDataFrame with {len(gdf)} records")
+        
+    return gdf

tunned_geobr/read_icmbio_infractions.py

@@ -0,0 +1,83 @@
+import geopandas as gpd
+import requests
+from io import BytesIO
+
+def read_icmbio_infractions(simplified=False, verbose=False):
+    """Download ICMBio Infraction Notices data.
+    
+    This function downloads and processes infraction notices data from the Brazilian Institute 
+    of Environment and Renewable Natural Resources (ICMBio) through the National Spatial 
+    Data Infrastructure (INDE) WFS service.
+    Original source: ICMBio via INDE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+    verbose : boolean, by default False
+        If True, prints detailed information about the download process
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with ICMBio Infraction Notices data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_icmbio_infractions
+    
+    # Read ICMBio Infraction Notices data
+    >>> infractions = read_icmbio_infractions()
+    """
+    
+    url = "https://geoservicos.inde.gov.br/geoserver/ICMBio/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=autos_infracao_icmbio&outputFormat=application/json"
+    
+    if verbose:
+        print("Downloading ICMBio Infraction Notices data...")
+    
+    try:
+        # Download the JSON data
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception(f"Failed to download data from ICMBio WFS service. Status code: {response.status_code}")
+        
+        if verbose:
+            print("Data downloaded successfully. Processing...")
+            
+        # Read the GeoJSON directly from the response content
+        gdf = gpd.read_file(BytesIO(response.content))
+        
+        # Convert to SIRGAS 2000 (EPSG:4674) if needed
+        if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+            if verbose:
+                print(f"Converting CRS from {gdf.crs} to SIRGAS 2000 (EPSG:4674)")
+            gdf = gdf.to_crs(4674)
+            
+        if simplified:
+            # Keep only the most relevant columns
+            # Adjust these based on the actual columns in the dataset
+            columns_to_keep = [
+                'geometry',
+                'MUNICIPIO',       # Municipality
+                'UF',              # State
+                'DATA_AUTO',       # Infraction date
+                'TIPO_INFRA',      # Infraction type
+                'AREA_PROTE',      # Protected area
+                'VALOR_AUTO',      # Fine value
+                'NUM_AUTO'         # Infraction number
+            ]
+            
+            # 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]
+            
+            if verbose:
+                print(f"Simplified dataset with {len(existing_columns)} columns")
+    
+    except Exception as e:
+        raise Exception(f"Error downloading ICMBio Infraction Notices data: {str(e)}")
+    
+    if verbose:
+        print(f"Download completed. Returning GeoDataFrame with {len(gdf)} records")
+        
+    return gdf

tunned_geobr/read_immediate_region.py

@@ -1,81 +1,69 @@
-from geobr.utils import select_metadata, download_gpkg, change_type_list, test_options
-
-
-def read_immediate_region(
-    code_immediate="all", year=2017, simplified=False, verbose=False
-):
-    """ Download shape files of Brazil's Immediate Geographic Areas as sf objects
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_immediate_region(simplified=False):
+    """Download official immediate region data from IBGE.
+    
+    This function downloads and processes immediate region data from IBGE (Brazilian Institute of Geography and Statistics).
+    The data includes immediate regions of Brazil for the year 2023.
+    Original source: IBGE
     
-     The Immediate Geographic Areas are part of the geographic division of 
-     Brazil created in 2017 by IBGE to replace the "Micro Regions" division. 
-     Data at scale 1:250,000, using Geodetic reference system "SIRGAS2000" 
-     and CRS(4674)
-
     Parameters
     ----------
-    code_immediate: 
-        6-digit code of an immediate region. If the two-digit code or a 
-        two-letter uppercase abbreviation of a state is passed, (e.g. 33 or 
-        "RJ") the function will load all immediate regions of that state. If 
-        code_immediate="all", all immediate regions of the country are loaded 
-        (defaults to "all").
-    year : int, optional
-        Year of the data, by default 2017
-    simplify: boolean, by default True
-        Data 'type', indicating whether the function returns the 'original' dataset 
-        with high resolution or a dataset with 'simplify' borders (Default)
-    verbose : bool, optional
-        by default False
-    
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
     Returns
     -------
     gpd.GeoDataFrame
-        Metadata and geopackage of selected states
-    
-    Raises
-    ------
-    Exception
-        If parameters are not found or not well defined
-
+        Geodataframe with immediate region data
+        
     Example
     -------
     >>> from geobr import read_immediate_region
-
-    # Read specific state at a given year
-    >>> df = read_immediate_region(year=2017)
+    
+    # Read immediate region data
+    >>> immediate_region = read_immediate_region()
     """
-
-    test_options(code_immediate, "code_immediate", not_allowed=[None])
-
-    metadata = select_metadata("immediate_regions", year=year, simplified=simplified)
-
-    gdf = download_gpkg(metadata)
-
-    # ensure type
-    code_immediate = str(code_immediate)
-
-    if code_immediate == "all":
-
-        if verbose:
-            print(
-                "Loading data for the whole country. "
-                "This might take a few minutes.\n"
-            )
-
-        return gdf
-
-    elif code_immediate in gdf["abbrev_state"].tolist():
-
-        return gdf.query(f'abbrev_state == "{code_immediate}"')
-
-    elif code_immediate in change_type_list(gdf["code_state"].tolist()):
-
-        return gdf.query(f'code_state == "{code_immediate}"')
-
-    elif code_immediate in change_type_list(gdf["code_immediate"].tolist()):
-
-        return gdf.query(f'code_immediate == "{code_immediate}"')
-
-    else:
-
-        raise Exception("Invalid Value to argument 'code_immediate'")
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_RG_Imediatas_2023.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from IBGE")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract zip content
+            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
+                # Note: These columns are based on typical immediate region data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_RGI',  # Immediate region code
+                    'NM_RGI',  # Immediate region name
+                ]
+                gdf = gdf[columns_to_keep]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading immediate region data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_indigenous_land.py

@@ -1,44 +1,77 @@
-from geobr.utils import select_metadata, download_gpkg
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
 
-
-def read_indigenous_land(date=201907, simplified=False, verbose=False):
-    """ Download official data of indigenous lands as an sf object.
+def read_indigenous_land(simplified=False):
+    """Download Indigenous Land data from FUNAI.
+    
+    This function downloads and processes data about indigenous lands in Brazil 
+    from FUNAI (Fundação Nacional dos Povos Indígenas). The data includes location 
+    and basic information about registered indigenous lands.
+    Original source: FUNAI - Fundação Nacional dos Povos Indígenas
     
-     The data set covers the whole of Brazil and it includes indigenous lands from all ethnicities and
- in different stages of demarcation. The original data comes from the National Indian Foundation (FUNAI)
- and can be found at http://www.funai.gov.br/index.php/shape. Although original data is updated monthly,
- the geobr package will only keep the data for a few months per year.
-
     Parameters
     ----------
-    date : int, optional
-        A date numer in YYYYMM format, by default 201907
-    simplified: boolean, by default True
-        Data 'type', indicating whether the function returns the 'original' dataset 
-        with high resolution or a dataset with 'simplified' borders (Default)
-    verbose : bool, optional
-        by default False
-    
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
     Returns
     -------
     gpd.GeoDataFrame
-        Metadata and geopackage of selected states
-    
-    Raises
-    ------
-    Exception
-        If parameters are not found or not well defined
-
+        Geodataframe with indigenous land data
+        Columns:
+        - geometry: Land boundaries
+        - nome: Land name
+        - municipio: Municipality
+        - uf: State
+        - etnia: Ethnicity
+        - fase: Legal status
+        - area_ha: Area in hectares
+        
     Example
     -------
-    >>> from geobr import read_indigenous_land
-
-    # Read specific state at a given year
-    >>> df = read_indigenous_land(date=201907)
+    >>> from tunned_geobr import read_indigenous_land
+    >>> lands = read_indigenous_land()
     """
-
-    metadata = select_metadata("indigenous_land", year=date, simplified=simplified)
-
-    gdf = download_gpkg(metadata)
-
+    
+    url = "https://geoserver.funai.gov.br/geoserver/Funai/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=Funai%3Atis_poligonais&maxFeatures=10000&outputFormat=SHAPE-ZIP"
+    
+    try:
+        # Download the zip file with a 60-second timeout
+        response = requests.get(url, timeout=60)
+        if response.status_code != 200:
+            raise Exception(f"Failed to download data from FUNAI. 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
+            
+            # Print columns for debugging
+            print("Available columns:", gdf.columns)
+            
+            if simplified:
+                columns_to_keep = ['geometry', 'nome', 'municipio', 'uf', 'etnia', 'fase', 'area_ha']
+                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 indigenous land data: {str(e)}")
+        
     return gdf
+
+if __name__ == '__main__':
+    read_indigenous_land()