tunned-geobr 0.1.0__py3-none-any.whl

tunned_geobr/__init__.py

@@ -0,0 +1,38 @@
+from .read_state import read_state
+from .read_amazon import read_amazon
+from .read_biomes import read_biomes
+from .read_country import read_country
+from .read_municipal_seat import read_municipal_seat
+from .read_region import read_region
+from .read_semiarid import read_semiarid
+from .read_disaster_risk_area import read_disaster_risk_area
+from .read_metro_area import read_metro_area
+from .read_conservation_units import read_conservation_units
+from .read_urban_area import read_urban_area
+from .read_health_facilities import read_health_facilities
+from .read_indigenous_land import read_indigenous_land
+from .read_immediate_region import read_immediate_region
+from .list_geobr import list_geobr
+from .read_census_tract import read_census_tract
+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
+from .read_intermediate_region import read_intermediate_region
+from .read_urban_concentrations import read_urban_concentrations
+from .read_schools import read_schools
+from .read_comparable_areas import read_comparable_areas
+from .read_biomes import read_biomes
+from .read_statistical_grid import read_statistical_grid
+from .read_mining_processes import read_mining_processes
+from .read_geology import read_geology
+from .read_geomorphology import read_geomorphology
+from .read_pedology import read_pedology
+from .read_climate_aggressiveness import read_climate_aggressiveness
+from .read_amazon_ibas import read_amazon_ibas
+from .read_atlantic_forest_ibas import read_atlantic_forest_ibas
+from .read_settlements import read_settlements

tunned_geobr/constants.py

@@ -0,0 +1,13 @@
+from enum import Enum
+
+
+class DataTypes(Enum):
+
+    code_muni = "float"
+    code_cnes = "float"
+    code_state = "float"
+    year_update = "float"
+    code_neighborhood = "float"
+    code_subdistrict = "float"
+    code_district = "float"
+    geo_bater = "float"

tunned_geobr/data/grid_state_correspondence_table.csv

@@ -0,0 +1,140 @@
+name_state,abbrev_state,code_grid
+Acre,AC,ID_50
+Acre,AC,ID_51
+Acre,AC,ID_60
+Acre,AC,ID_61
+Amazonas,AM,ID_51
+Amazonas,AM,ID_60
+Amazonas,AM,ID_61
+Amazonas,AM,ID_62
+Amazonas,AM,ID_63
+Amazonas,AM,ID_70
+Amazonas,AM,ID_71
+Amazonas,AM,ID_72
+Amazonas,AM,ID_73
+Amazonas,AM,ID_80
+Amazonas,AM,ID_81
+Amazonas,AM,ID_82
+Roraima,RR,ID_72
+Roraima,RR,ID_81
+Roraima,RR,ID_82
+Roraima,RR,ID_83
+Roraima,RR,ID_92
+Roraima,RR,ID_93
+Amap�,AP,ID_74
+Amap�,AP,ID_75
+Amap�,AP,ID_84
+Amap�,AP,ID_85
+Par�,PA,ID_53
+Par�,PA,ID_54
+Par�,PA,ID_55
+Par�,PA,ID_63
+Par�,PA,ID_64
+Par�,PA,ID_65
+Par�,PA,ID_73
+Par�,PA,ID_74
+Par�,PA,ID_75
+Par�,PA,ID_76
+Par�,PA,ID_83
+Par�,PA,ID_84
+Par�,PA,ID_85
+Maranh�o,MA,ID_55
+Maranh�o,MA,ID_56
+Maranh�o,MA,ID_65
+Maranh�o,MA,ID_66
+Maranh�o,MA,ID_75
+Maranh�o,MA,ID_76
+Maranh�o,MA,ID_77
+Piau�,PI,ID_56
+Piau�,PI,ID_57
+Piau�,PI,ID_66
+Piau�,PI,ID_67
+Piau�,PI,ID_76
+Piau�,PI,ID_77
+Cear�,CE,ID_67
+Cear�,CE,ID_68
+Cear�,CE,ID_77
+Rio Grande do Norte,RN,ID_67
+Rio Grande do Norte,RN,ID_68
+Para�ba,PB,ID_67
+Para�ba,PB,ID_68
+Pernambuco,PE,ID_57
+Pernambuco,PE,ID_58
+Pernambuco,PE,ID_67
+Pernambuco,PE,ID_68
+Pernambuco,PE,ID_69
+Alagoas,AL,ID_57
+Alagoas,AL,ID_58
+Sergipe,SE,ID_57
+Sergipe,SE,ID_58
+Bahia,BA,ID_37
+Bahia,BA,ID_46
+Bahia,BA,ID_47
+Bahia,BA,ID_56
+Bahia,BA,ID_57
+Esp�rito Santo,ES,ID_36
+Esp�rito Santo,ES,ID_37
+Esp�rito Santo,ES,ID_39
+Rio de Janeiro,RJ,ID_26
+Rio de Janeiro,RJ,ID_27
+Rio de Janeiro,RJ,ID_36
+Rio de Janeiro,RJ,ID_37
+S�o Paulo,SP,ID_24
+S�o Paulo,SP,ID_25
+S�o Paulo,SP,ID_26
+S�o Paulo,SP,ID_34
+S�o Paulo,SP,ID_35
+Paran�,PR,ID_24
+Paran�,PR,ID_25
+Santa Catarina,SC,ID_14
+Santa Catarina,SC,ID_15
+Santa Catarina,SC,ID_24
+Santa Catarina,SC,ID_25
+Rio Grande do Sul,RS,ID_4
+Rio Grande do Sul,RS,ID_13
+Rio Grande do Sul,RS,ID_14
+Rio Grande do Sul,RS,ID_15
+Mato Grosso do Sul,MS,ID_23
+Mato Grosso do Sul,MS,ID_24
+Mato Grosso do Sul,MS,ID_33
+Mato Grosso do Sul,MS,ID_34
+Mato Grosso do Sul,MS,ID_35
+Mato Grosso do Sul,MS,ID_43
+Mato Grosso do Sul,MS,ID_44
+Minas Gerais,MG,ID_25
+Minas Gerais,MG,ID_26
+Minas Gerais,MG,ID_35
+Minas Gerais,MG,ID_36
+Minas Gerais,MG,ID_37
+Minas Gerais,MG,ID_45
+Minas Gerais,MG,ID_46
+Minas Gerais,MG,ID_47
+Goi�s,GO,ID_34
+Goi�s,GO,ID_35
+Goi�s,GO,ID_44
+Goi�s,GO,ID_45
+Goi�s,GO,ID_46
+Goi�s,GO,ID_55
+Goi�s,GO,ID_56
+Distrito Federal,DF,ID_45
+Tocantins,TO,ID_45
+Tocantins,TO,ID_55
+Tocantins,TO,ID_56
+Tocantins,TO,ID_65
+Tocantins,TO,ID_66
+Mato Grosso,MT,ID_33
+Mato Grosso,MT,ID_34
+Mato Grosso,MT,ID_43
+Mato Grosso,MT,ID_44
+Mato Grosso,MT,ID_45
+Mato Grosso,MT,ID_52
+Mato Grosso,MT,ID_53
+Mato Grosso,MT,ID_54
+Mato Grosso,MT,ID_55
+Mato Grosso,MT,ID_63
+Rond�nia,RO,ID_42
+Rond�nia,RO,ID_43
+Rond�nia,RO,ID_51
+Rond�nia,RO,ID_52
+Rond�nia,RO,ID_53
+Rond�nia,RO,ID_62

tunned_geobr/list_geobr.py

@@ -0,0 +1,39 @@
+from requests import get
+import pandas as pd
+from io import StringIO
+from urllib.error import HTTPError
+import re
+
+def list_geobr():
+    """Prints available functions, according to latest README.md file
+
+    Example output
+    ------------------------------
+    Function: read_immediate_region
+    Geographies available: Immediate region
+    Years available: 2017
+    Source: IBGE
+    ------------------------------
+
+    """
+
+    try:
+        html_data = get("https://github.com/ipeaGIT/geobr/blob/master/README.md").text
+        find_emoji = html_data.index("👉")
+        html_data =  html_data[find_emoji:]
+        escaped_data = html_data.replace("\\u003c", "<").replace("\\u003e", ">")
+        tables = re.findall("<table>(.+?)</table>", escaped_data)
+        available_datasets = "<table>" + tables[0].replace("\\n", "") + "</table>"
+        df = pd.DataFrame(pd.read_html(StringIO(available_datasets))[0])
+
+    except HTTPError:
+        print(
+            "Geobr url functions list is broken"
+            'Please report an issue at "https://github.com/ipeaGIT/geobr/issues"'
+        )
+
+    for i in range(len(df)):
+        for each in df.columns:
+            print(f"{each}: {df.loc[i, each]}")
+
+        print("------------------------------")

tunned_geobr/lookup_muni.py

@@ -0,0 +1,111 @@
+from geobr import utils
+
+
+def lookup_muni(name_muni=None, code_muni=None, verbose=False):
+    """Lookup municipality codes and names.
+
+    By default, it looks for all municipalities. You can also use 'all' to in
+    `name_muni` or `code_muni` to get all municipalities.
+
+    Input a municipality NAME or CODE and get the names and codes of
+    the municipality's corresponding state, meso, micro, intermediate, and
+    immediate regions. You should not select both code_muni and name_muni
+
+    Parameters
+    ----------
+
+    name_muni : str, optional
+    The municipality name to be looked up
+
+    code_muni: str, optional
+    The municipality code to be looked up
+
+    verbose : bool, optional
+    by default False
+
+    Returns
+    -------
+    pd.DataFram
+    13 columns identifying the geographies information of that municipality
+
+    Details Only available from 2010 Census data so far
+
+    Raise
+    -------
+    Exception if code_muni or name_muni cannot be found
+
+    Example
+    -------
+    >>> import geobr
+
+    # Lookup table for municipality of Rio de Janeiro
+    >>> mun = lookup_muni('Rio de Janeiro)
+    or
+    >>> mun = lookup_muni(3304557)
+
+    # lookup table for all municipalities
+    >>> mun_all = lookup_muni()
+    """
+    # Get metadata with data url addresses
+    temp_meta = utils.select_metadata(geo="lookup_muni", year=2010)
+
+    # Read DataFrame available at provided url
+    lookup_table = utils.download_metadata(
+        temp_meta.loc[:, "download_path"].to_list()[0]
+    )
+    lookup_table["name_muni_format"] = lookup_table["name_muni_format"].str.lower()
+
+    # Search by inputs
+    if (
+        code_muni == "all"
+        or name_muni == "all"
+        or (code_muni is None and name_muni is None)
+    ):
+        if verbose:
+            print(f"Returning results for all municipalities")
+        return lookup_table.iloc[:, :-1]
+
+    elif code_muni is not None:
+        if name_muni is not None:
+            if verbose:
+                print("Ignoring argument name_muni")
+        try:
+            output = lookup_table[lookup_table["code_muni"] == int(code_muni)].iloc[
+                :, :-1
+            ]
+            if verbose:
+                print(
+                    "Returning results for municipality ",
+                    f'{output.loc[:, "name_muni"].to_list()[0]}',
+                )
+            return output
+
+        except KeyError:
+            raise Exception(
+                f"The `code_muni` argument {code_muni}",
+                "was not found in the database.",
+            )
+
+    elif name_muni is not None:
+        # Cleaning from accents and turning into lower cases without spaces
+        name_muni = utils.strip_accents(str(name_muni).lower().strip())
+        output = lookup_table[lookup_table["name_muni_format"] == name_muni]
+
+        if len(output) == 0:
+            if verbose:
+                print("Please insert a valid municipality name")
+            raise Exception(
+                f"The `name_muni` argument {name_muni} ",
+                "was not found in the database.",
+            )
+        else:
+            if verbose:
+                print(
+                    "Returning results for municipality"
+                    f'{output.loc[:, "name_muni"].to_list()[0]}'
+                )
+            return output.iloc[:, :-1]
+
+    elif code_muni == "all" and name_muni == "all":
+        if verbose:
+            print("Please insert either a municipality ", "name or a municipality code")

tunned_geobr/read_amazon.py

@@ -0,0 +1,42 @@
+from cursed_geobr.utils import select_metadata, download_gpkg
+
+
+def read_amazon(year=2012, simplified=True, 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
+ data comes from the Brazilian Ministry of Environment (MMA) and can be found at http://mapas.mma.gov.br/i3geo/datadownload.htm .
+
+    Parameters
+    ----------
+    year : int, optional
+        Year of the data, by default 2012
+    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 cursed_geobr import read_amazon
+
+    # Read specific state at a given year
+    >>> df = read_amazon(year=2012)
+    """
+
+    metadata = select_metadata("amazonia_legal", year=year, simplified=simplified)
+
+    gdf = download_gpkg(metadata)
+
+    return gdf

tunned_geobr/read_amazon_ibas.py

@@ -0,0 +1,92 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+import patoolib
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_amazon_ibas(simplified=False):
+    """Download Important Bird Areas (IBAs) data for the Amazon region.
+    
+    This function downloads and processes IBAs data from SAVE Brasil. The data includes 
+    important areas for bird conservation in the Amazon region.
+    Original source: SAVE Brasil
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Amazon IBAs data
+        
+    Example
+    -------
+    >>> from cursed_geobr import read_amazon_ibas
+    
+    # Read Amazon IBAs data
+    >>> ibas = read_amazon_ibas()
+    """
+    
+    url = "https://www.savebrasil.org.br/_files/archives/6d1e48_c03ae9708adf4d978220547eaf173103.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from SAVE Brasil")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # First extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            subfolder_path = os.path.join(temp_dir, "Shapefiles IBAs Amazônia e Mata Atlântica")
+            rar_files = [f for f in os.listdir(subfolder_path) if f.endswith('.rar')]
+
+            if not rar_files:
+                raise Exception("No RAR file found in the downloaded data")
+            
+            # Extract the RAR file using patoolib
+            rar_path = os.path.join(subfolder_path, rar_files[0])
+            patoolib.extract_archive(rar_path, outdir=temp_dir)
+                
+            # Path to the Amazon shapefile directory
+            amazon_dir = os.path.join(subfolder_path, "Amazônia", 'Final')
+            
+            # Find the shapefile
+            shp_files = [f for f in os.listdir(amazon_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(amazon_dir, shp_files[0]))
+            gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: These columns are based on typical IBAs data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'IBA_NAME',    # IBA name
+                    'IBA_CODE',    # IBA code
+                    'STATE',       # State
+                    'AREA_HA',     # Area in hectares
+                    'PRIORITY',    # Conservation priority
+                    'THREATS',     # Threats to the area
+                    'HABITATS',    # Main habitats
+                ]
+                
+                # 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 Amazon IBAs data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_atlantic_forest_ibas.py

@@ -0,0 +1,93 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+import patoolib
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_atlantic_forest_ibas(simplified=False):
+    """Download Important Bird Areas (IBAs) data for the Atlantic Forest region.
+    
+    This function downloads and processes IBAs data from SAVE Brasil. The data includes 
+    important areas for bird conservation in the Atlantic Forest region.
+    Original source: SAVE Brasil
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Atlantic Forest IBAs data
+        
+    Example
+    -------
+    >>> from cursed_geobr import read_atlantic_forest_ibas
+    
+    # Read Atlantic Forest IBAs data
+    >>> ibas = read_atlantic_forest_ibas()
+    """
+    
+    url = "https://www.savebrasil.org.br/_files/archives/6d1e48_c03ae9708adf4d978220547eaf173103.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from SAVE Brasil")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # First extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            subfolder_path = os.path.join(temp_dir, "Shapefiles IBAs Amazônia e Mata Atlântica")
+            rar_files = [f for f in os.listdir(subfolder_path) if f.endswith('.rar')]
+
+            if not rar_files:
+                raise Exception("No RAR file found in the downloaded data")
+            
+            # Extract the RAR file using patoolib
+            rar_path = os.path.join(subfolder_path, rar_files[0])
+            patoolib.extract_archive(rar_path, outdir=temp_dir)
+                
+            # Path to the Atlantic Forest shapefile directory
+            atlantic_dir = os.path.join(subfolder_path, "Mata Atlântica")
+            
+            # Find the shapefile
+            shp_files = [f for f in os.listdir(atlantic_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(atlantic_dir, shp_files[0]))
+            gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: These columns are based on typical IBAs data structure
+                # You may want to adjust these based on the actual data
+                columns_to_keep = [
+                    'geometry',
+                    'IBA_NAME',    # IBA name
+                    'IBA_CODE',    # IBA code
+                    'STATE',       # State
+                    'AREA_HA',     # Area in hectares
+                    'PRIORITY',    # Conservation priority
+                    'THREATS',     # Threats to the area
+                    'HABITATS',    # Main habitats
+                ]
+                
+                # 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 Atlantic Forest IBAs data: {str(e)}")
+        
+    return gdf
+

tunned_geobr/read_biomes.py

@@ -0,0 +1,43 @@
+from cursed_geobr.utils import select_metadata, download_gpkg
+
+
+def read_biomes(year=2019, simplified=True, verbose=False):
+    """ Download official data of Brazilian biomes as an sf object.
+    
+     This data set includes  polygons of all biomes present in Brazilian territory and coastal area.
+ The latest data set dates to 2019 and it is available at scale 1:250.000. The 2004 data set is at
+ the scale 1:5.000.000. The original data comes from IBGE. More information at https://www.ibge.gov.br/apps/biomas/
+
+    Parameters
+    ----------
+    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 cursed_geobr import read_biomes
+
+    # Read specific state at a given year
+    >>> df = read_biomes(year=2019)
+    """
+
+    metadata = select_metadata("biomes", year=year, simplified=simplified)
+
+    gdf = download_gpkg(metadata)
+
+    return gdf