tunned-geobr 0.2.6__tar.gz → 0.2.7__tar.gz

{tunned_geobr-0.2.6 → tunned_geobr-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tunned-geobr
-Version: 0.2.6
+Version: 0.2.7
 Summary: Fork personalizado do geobr com funcionalidades extras como download de dados da ANM
 Author: Anderson Stolfi
 License: MIT

{tunned_geobr-0.2.6 → tunned_geobr-0.2.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tunned-geobr"
-version = "0.2.6"
+version = "0.2.7"
 description = "Fork personalizado do geobr com funcionalidades extras como download de dados da ANM"
 readme = "README.md"
 requires-python = "<4.0,>=3.9"

tunned_geobr-0.2.7/tunned_geobr/read_municipality.py

@@ -0,0 +1,127 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_municipality(code_muni="all", simplified=False):
+    """Download shapefiles of Brazilian municipalities as geopandas objects.
+
+    This function downloads and processes municipality data directly from IBGE (Brazilian Institute of Geography and Statistics).
+    Data uses Geodetic reference system "SIRGAS2000" and CRS(4674).
+    
+    Parameters
+    ----------
+    code_muni : str, optional
+        The 7-digit code of a municipality. 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 municipalities of that state.
+        If code_muni="all", all municipalities of the country 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 municipality boundaries
+
+    Example
+    -------
+    >>> from tunned_geobr import read_municipality
+
+    # Read all municipalities
+    >>> municipalities = read_municipality()
+
+    # Read all municipalities in a state by code
+    >>> state_municipalities = read_municipality(code_muni=33)
+
+    # Read all municipalities in a state by abbreviation
+    >>> state_municipalities = read_municipality(code_muni="RJ")
+    
+    # Read specific municipality by code
+    >>> municipality = read_municipality(code_muni=3304557)
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_Municipios_2023.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download municipality 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_muni if not "all"
+            if code_muni != "all":
+                if isinstance(code_muni, int) or code_muni.isdigit():
+                    if len(str(code_muni)) == 7:
+                        # Filter by municipality code
+                        gdf = gdf[gdf['CD_MUN'] == str(code_muni)]
+                    elif len(str(code_muni)) == 2:
+                        # Filter by state code
+                        gdf = gdf[gdf['CD_MUN'].str.startswith(str(code_muni).zfill(2))]
+                elif isinstance(code_muni, str) and len(code_muni) == 2:
+                    # Filter by state abbreviation - need to get state code first
+                    state_url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_UF_2023.zip"
+                    state_response = requests.get(state_url)
+                    
+                    if state_response.status_code == 200:
+                        with tempfile.TemporaryDirectory() as state_temp_dir:
+                            with ZipFile(BytesIO(state_response.content)) as zip_ref:
+                                zip_ref.extractall(state_temp_dir)
+                            
+                            state_shp_files = []
+                            for root, dirs, files in os.walk(state_temp_dir):
+                                state_shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+                            
+                            if state_shp_files:
+                                state_gdf = gpd.read_file(state_shp_files[0])
+                                state_code = state_gdf[state_gdf['SIGLA_UF'] == code_muni.upper()]['CD_UF'].values
+                                
+                                if len(state_code) > 0:
+                                    gdf = gdf[gdf['CD_MUN'].str.startswith(state_code[0])]
+                
+                if len(gdf) == 0:
+                    raise Exception(f"No data found for code_muni={code_muni}")
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'CD_MUN',      # Municipality code
+                    'NM_MUN',      # Municipality 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 municipality data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_municipality()

tunned_geobr-0.2.7/tunned_geobr/read_state.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=False):
+    """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-0.2.6/tunned_geobr/read_municipality.py

@@ -1,83 +0,0 @@
-from geobr.utils import select_metadata, download_gpkg
-
-
-def read_municipality(code_muni="all", year=2010, simplified=False, verbose=False):
-    """Download shape files of Brazilian municipalities as sf objects.
-
-     Data at scale 1:250,000, using Geodetic reference system "SIRGAS2000" and CRS(4674)
-
-    Parameters
-    ----------
-    code_muni:
-        The 7-digit code of a municipality. 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 municipalities of that state.
-        If code_muni="all", all municipalities of the country will be loaded.
-    year : int, optional
-        Year of the data, by default 2010
-    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_municipality
-
-    # Read specific meso region at a given year
-    >>> df = read_municipality(code_muni=1200179, year=2018)
-
-    # Read all meso regions of a state at a given year
-    >>> df = read_municipality(code_muni=12, year=2017)
-    >>> df = read_municipality(code_muni="AM", year=2000)
-
-    # Read all meso regions of the country at a given year
-    >>> df = read_municipality(code_muni="all", year=2010)
-    """
-
-    metadata = select_metadata("municipality", year=year, simplified=simplified)
-
-    if year < 1992:
-
-        return download_gpkg(metadata)
-
-    if code_muni == "all":
-
-        if verbose:
-            print("Loading data for the whole country. This might take a few minutes.")
-
-        return download_gpkg(metadata)
-
-    metadata = metadata[
-        metadata[["code", "code_abbrev"]].apply(
-            lambda x: str(code_muni)[:2] in str(x["code"])
-            or str(code_muni)[:2]  # if number e.g. 12
-            in str(x["code_abbrev"]),  # if UF e.g. RO
-            1,
-        )
-    ]
-
-    if not len(metadata):
-        raise Exception("Invalid Value to argument code_muni.")
-
-    gdf = download_gpkg(metadata)
-
-    if len(str(code_muni)) == 2:
-        return gdf
-
-    elif code_muni in gdf["code_muni"].tolist():
-        return gdf.query(f"code_muni == {code_muni}")
-
-    else:
-        raise Exception("Invalid Value to argument code_muni.")
-    return gdf

tunned_geobr-0.2.6/tunned_geobr/read_state.py

@@ -1,88 +0,0 @@
-import geopandas as gpd
-
-from geobr.utils import select_metadata, download_gpkg
-
-
-def read_state(code_state="all", year=2010, simplified=False, verbose=False):
-    """Download shapefiles of Brazilian states as geopandas objects.
-
-     Data at scale 1:250,000, using 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).
-    year : int, optional
-        Year of the data, by default 2010
-    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_state
-
-    # Read specific state at a given year
-    >>> uf = read_state(code_state=12, year=2017)
-
-     # Read specific state at a given year with normal geopackages
-    >>> uf = read_state(code_state="SC", year=2000, tp='normal')
-
-     # Read all states at a given year
-    >>> ufs = read_state(code_state="all", year=2010)
-    """
-
-    metadata = select_metadata("state", year=year, simplified=simplified)
-
-    if code_state is None:
-        raise Exception("Value to argument 'code_state' cannot be None")
-
-    # From 1872 to 1991 and all
-    if (year < 1992) or (code_state == "all"):
-
-        if verbose:
-            print("Loading data for the whole country\n")
-
-        return download_gpkg(metadata)
-
-    # From 2000 onwards
-    else:
-
-        if (
-            str(code_state)[0:2] not in metadata["code"].unique()
-            and str(code_state)[0:2] not in metadata["code_abbrev"].unique()
-        ):
-
-            raise Exception("Error: Invalid Value to argument code_state.")
-
-        else:
-
-            if isinstance(code_state, int):
-                metadata = metadata.query(f'code == "{str(code_state)[0:2]}"')
-
-            if isinstance(code_state, str):
-                metadata = metadata.query(f'code_abbrev == "{code_state[0:2]}"')
-
-            gdf = download_gpkg(metadata)
-
-            if len(str(code_state)) == 2:
-                return gdf
-
-            elif code_state in list(gdf["code_state"]):
-                return gdf.query('code_state == "code_state"')
-
-            else:
-                raise Exception("Error: Invalid Value to argument code_state.")