tunned-geobr 1.0.0__tar.gz → 1.0.2__tar.gz

{tunned_geobr-1.0.0 → tunned_geobr-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tunned-geobr
-Version: 1.0.0
+Version: 1.0.2
 Summary: Fork personalizado do geobr com funcionalidades extras como download de dados da ANM
 Author: Anderson Stolfi
 License: MIT
@@ -23,6 +23,8 @@ Requires-Dist: patool>=1.15.0
 Requires-Dist: fiona>=1.10.1
 Requires-Dist: gdown>=5.2.0
 Requires-Dist: tabulate>=0.9.0
+Requires-Dist: build>=1.2.2.post1
+Requires-Dist: twine>=6.1.0
 Description-Content-Type: text/markdown
 
 # geobr: Download Official Spatial Data Sets of Brazil 

{tunned_geobr-1.0.0 → tunned_geobr-1.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tunned-geobr"
-version = "1.0.0"
+version = "1.0.2"
 description = "Fork personalizado do geobr com funcionalidades extras como download de dados da ANM"
 readme = "README.md"
 requires-python = "<4.0,>=3.9"
@@ -18,6 +18,8 @@ dependencies = [
     "fiona>=1.10.1",
     "gdown>=5.2.0",
     "tabulate>=0.9.0",
+    "build>=1.2.2.post1",
+    "twine>=6.1.0",
 ]
 classifiers = [
     "Intended Audience :: Science/Research",

{tunned_geobr-1.0.0 → tunned_geobr-1.0.2}/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

tunned_geobr-1.0.2/tunned_geobr/read_immediate_region.py

@@ -0,0 +1,69 @@
+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
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with immediate region data
+        
+    Example
+    -------
+    >>> from geobr import read_immediate_region
+    
+    # Read immediate region data
+    >>> immediate_region = read_immediate_region()
+    """
+    
+    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-1.0.2/tunned_geobr/read_indigenous_land.py

@@ -0,0 +1,77 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+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
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        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 tunned_geobr import read_indigenous_land
+    >>> lands = read_indigenous_land()
+    """
+    
+    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()

tunned_geobr-1.0.2/tunned_geobr/read_intermediate_region.py

@@ -0,0 +1,69 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_intermediate_region(simplified=False):
+    """Download official intermediate region data from IBGE.
+    
+    This function downloads and processes intermediate region data from IBGE (Brazilian Institute of Geography and Statistics).
+    The data includes intermediate regions of Brazil for the year 2023.
+    Original source: IBGE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with intermediate region data
+        
+    Example
+    -------
+    >>> from geobr import read_intermediate_region
+    
+    # Read intermediate region data
+    >>> intermediate_region = read_intermediate_region()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_RG_Intermediarias_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 intermediate region data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_RGINT',  # Intermediate region code
+                    'NM_RGINT',  # Intermediate region name
+                ]
+                gdf = gdf[columns_to_keep]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading intermediate region data: {str(e)}")
+        
+    return gdf

tunned_geobr-1.0.2/tunned_geobr/read_meso_region.py

@@ -0,0 +1,69 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_meso_region(simplified=False):
+    """Download official mesoregion data from IBGE.
+    
+    This function downloads and processes mesoregion data from IBGE (Brazilian Institute of Geography and Statistics).
+    The data includes mesoregions of Brazil for the year 2022.
+    Original source: IBGE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with mesoregion data
+        
+    Example
+    -------
+    >>> from geobr import read_meso_region
+    
+    # Read mesoregion data
+    >>> meso_region = read_meso_region()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2022/Brasil/BR/BR_Mesorregioes_2022.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 mesoregion data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_MESO',  # Mesoregion code
+                    'NM_MESO',  # Mesoregion name
+                ]
+                gdf = gdf[columns_to_keep]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading mesoregion data: {str(e)}")
+        
+    return gdf

tunned_geobr-1.0.2/tunned_geobr/read_micro_region.py

@@ -0,0 +1,69 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_micro_region(simplified=False):
+    """Download official microregion data from IBGE.
+    
+    This function downloads and processes microregion data from IBGE (Brazilian Institute of Geography and Statistics).
+    The data includes microregions of Brazil for the year 2022.
+    Original source: IBGE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with microregion data
+        
+    Example
+    -------
+    >>> from geobr import read_micro_region
+    
+    # Read microregion data
+    >>> micro_region = read_micro_region()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2022/Brasil/BR/BR_Microrregioes_2022.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 microregion data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_MICRO',  # Microregion code
+                    'NM_MICRO',  # Microregion name
+                ]
+                gdf = gdf[columns_to_keep]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading microregion data: {str(e)}")
+        
+    return gdf

tunned_geobr-1.0.0/tunned_geobr/read_neighborhoods_2022.py → tunned_geobr-1.0.2/tunned_geobr/read_neighborhood.py

@@ -5,7 +5,7 @@ import requests
 import subprocess
 from io import BytesIO
 
-def read_neighborhoods_2022(simplified=False):
+def read_neighborhood(simplified=False):
     """Download Brazilian Neighborhoods data from IBGE (2022 Census).
     
     This function downloads and processes the Brazilian Neighborhoods data

tunned_geobr-1.0.2/tunned_geobr/read_region.py

@@ -0,0 +1,69 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_region(simplified=False):
+    """Download official region data from IBGE.
+    
+    This function downloads and processes region data from IBGE (Brazilian Institute of Geography and Statistics).
+    The data includes regions of Brazil for the year 2022.
+    Original source: IBGE
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with region data
+        
+    Example
+    -------
+    >>> from geobr import read_region
+    
+    # Read region data
+    >>> region = read_region()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2022/Brasil/BR/BR_Regioes_2022.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 region data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'CD_RG',  # Region code
+                    'NM_RG',  # Region name
+                ]
+                gdf = gdf[columns_to_keep]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading region data: {str(e)}")
+        
+    return gdf

{tunned_geobr-1.0.0 → tunned_geobr-1.0.2}/tunned_geobr/read_sigef_properties.py

@@ -32,8 +32,6 @@ def read_sigef_properties(simplified=False):
     """
     
     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

tunned_geobr-1.0.0/tunned_geobr/read_immediate_region.py

@@ -1,81 +0,0 @@
-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
-    
-     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
-    
-    Returns
-    -------
-    gpd.GeoDataFrame
-        Metadata and geopackage of selected states
-    
-    Raises
-    ------
-    Exception
-        If parameters are not found or not well defined
-
-    Example
-    -------
-    >>> from geobr import read_immediate_region
-
-    # Read specific state at a given year
-    >>> df = read_immediate_region(year=2017)
-    """
-
-    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'")

tunned_geobr-1.0.0/tunned_geobr/read_indigenous_land.py

@@ -1,44 +0,0 @@
-from geobr.utils import select_metadata, download_gpkg
-
-
-def read_indigenous_land(date=201907, simplified=False, verbose=False):
-    """ Download official data of indigenous lands as an sf object.
-    
-     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
-    
-    Returns
-    -------
-    gpd.GeoDataFrame
-        Metadata and geopackage of selected states
-    
-    Raises
-    ------
-    Exception
-        If parameters are not found or not well defined
-
-    Example
-    -------
-    >>> from geobr import read_indigenous_land
-
-    # Read specific state at a given year
-    >>> df = read_indigenous_land(date=201907)
-    """
-
-    metadata = select_metadata("indigenous_land", year=date, simplified=simplified)
-
-    gdf = download_gpkg(metadata)
-
-    return gdf

tunned_geobr-1.0.0/tunned_geobr/read_intermediate_region.py

@@ -1,61 +0,0 @@
-from geobr.utils import select_metadata, download_gpkg
-
-
-def read_intermediate_region(
-    code_intermadiate="all", year=2019, simplified=False, verbose=False
-):
-    r"""Download spatial data of Brazil's Intermediate Geographic Areas
-
-    The intermediate Geographic Areas are part of the geographic division of
-    Brazil created in 2017 by IBGE. These regions were created to replace the
-    "Meso Regions" division. Data at scale 1:250,000, using Geodetic reference
-    system "SIRGAS2000" and CRS(4674)
-
-       Parameters
-       ----------
-       code_intermadiate: str or int, by default "all"
-            4-digit code of an intermediate 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 intermediate regions of that
-            state. If `code_intermediate="all"` (Default), all intermediate regions of
-            the country are loaded.
-       year : int, optional
-           Year of the data, by default 2019
-       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
-
-       Returns
-       -------
-       gpd.GeoDataFrame
-           Metadata and geopackage of selected states
-
-       Raises
-       ------
-       Exception
-           If parameters are not found or not well defined
-
-       Example
-       -------
-       >>> from geobr import read_intermediate_region
-
-       # Read specific state at a given year
-       >>> df = read_intermediate_region(year=2019)
-    """
-
-    metadata = select_metadata("intermediate_regions", year=year, simplified=simplified)
-
-    gdf = download_gpkg(metadata)
-
-    if code_intermadiate == "all":
-        return gdf
-
-    for col in ["abbrev_state", "code_state", "code_intermediate"]:
-        if code_intermadiate in gdf[col].unique():
-            return gdf[gdf[col] == code_intermadiate]
-    else:
-        raise ValueError(
-            f"Invalid value to argumet `code_intermadiate`: {code_intermadiate}"
-        )