tunned-geobr 0.2.2__py3-none-any.whl → 0.2.4__py3-none-any.whl

tunned_geobr/read_og_ipa_supply_infrastructure.py

@@ -0,0 +1,119 @@
+import geopandas as gpd
+import requests
+import zipfile
+import tempfile
+import os
+import warnings
+import shutil
+
+
+def read_og_ipa_supply_infrastructure(simplified=True, verbose=False):
+    """Download data for Oil and Gas IPA Supply Infrastructure in Brazil.
+
+    This function downloads, processes, and returns data for Oil and Gas IPA Supply Infrastructure
+    in Brazil as a geopandas GeoDataFrame.
+
+    Parameters
+    ----------
+    simplified : bool, optional
+        If True, returns a simplified version of the dataset with only essential columns.
+        If False, returns the complete dataset with all columns.
+        Default is True.
+    verbose : bool, optional
+        If True, prints detailed information about the data download and processing.
+        Default is False.
+
+    Returns
+    -------
+    geopandas.GeoDataFrame
+        A GeoDataFrame containing Oil and Gas IPA Supply Infrastructure data.
+
+    Examples
+    --------
+    >>> # Download Oil and Gas IPA Supply Infrastructure data
+    >>> df = read_og_ipa_supply_infrastructure()
+    >>> df.head()
+    """
+
+    url = "https://gisepeprd2.epe.gov.br/arcgis/rest/services/Download_Dados_Webmap_EPE/GPServer/Extract%20Data%20Task/execute?f=json&env%3AoutSR=102100&Layers_to_Clip=%5B%22IPA%20Infraestrutura%20de%20Abastecimento%22%5D&Area_of_Interest=%7B%22geometryType%22%3A%22esriGeometryPolygon%22%2C%22features%22%3A%5B%7B%22geometry%22%3A%7B%22rings%22%3A%5B%5B%5B-9237395.881983705%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C-4650539.310904562%5D%5D%5D%2C%22spatialReference%22%3A%7B%22wkid%22%3A102100%7D%7D%7D%5D%2C%22sr%22%3A%7B%22wkid%22%3A102100%7D%7D&Feature_Format=Shapefile%20-%20SHP%20-%20.shp&Raster_Format=Tagged%20Image%20File%20Format%20-%20TIFF%20-%20.tif"
+
+    if verbose:
+        print("Downloading data...")
+
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        response_json = response.json()
+
+        if "value" not in response_json or not response_json["value"]:
+            raise ValueError("No data found in the response")
+
+        download_url = response_json["value"]["itemUrl"]
+        
+        if verbose:
+            print(f"Download URL: {download_url}")
+            print("Downloading zip file...")
+
+        zip_response = requests.get(download_url)
+        zip_response.raise_for_status()
+
+        # Create a temporary directory to extract the files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            zip_path = os.path.join(temp_dir, "data.zip")
+            
+            # Save the zip file
+            with open(zip_path, "wb") as f:
+                f.write(zip_response.content)
+            
+            if verbose:
+                print(f"Zip file saved to {zip_path}")
+                print("Extracting files...")
+            
+            # Extract the zip file
+            with zipfile.ZipFile(zip_path, "r") 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 FileNotFoundError("No shapefile found in the downloaded zip file")
+            
+            shp_path = os.path.join(temp_dir, shp_files[0])
+            
+            if verbose:
+                print(f"Reading shapefile from {shp_path}")
+            
+            # Read the shapefile
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            gdf = gdf.to_crs(epsg=4674)
+            
+            if simplified:
+                # Select only essential columns
+                if verbose:
+                    print("Simplifying the dataset...")
+                
+                # Identify the essential columns
+                essential_cols = ["geometry"]
+                
+                # Add any other essential columns that exist in the dataset
+                for col in ["CLASSE", "NOME", "DESCRICAO", "AREA_KM2"]:
+                    if col in gdf.columns:
+                        essential_cols.append(col)
+                
+                # Select only the essential columns
+                gdf = gdf[essential_cols]
+            
+            return gdf
+    
+    except requests.exceptions.RequestException as e:
+        warnings.warn(f"Error downloading data: {e}")
+        return None
+    except (ValueError, FileNotFoundError, zipfile.BadZipFile) as e:
+        warnings.warn(f"Error processing data: {e}")
+        return None
+    except Exception as e:
+        warnings.warn(f"Unexpected error: {e}")
+        return None

tunned_geobr/read_og_legal_pre_salt_polygon.py

@@ -0,0 +1,119 @@
+import geopandas as gpd
+import requests
+import zipfile
+import tempfile
+import os
+import warnings
+import shutil
+
+
+def read_og_legal_pre_salt_polygon(simplified=True, verbose=False):
+    """Download data for Oil and Gas Legal Pre-Salt Polygon in Brazil.
+
+    This function downloads, processes, and returns data for Oil and Gas Legal Pre-Salt Polygon
+    in Brazil as a geopandas GeoDataFrame.
+
+    Parameters
+    ----------
+    simplified : bool, optional
+        If True, returns a simplified version of the dataset with only essential columns.
+        If False, returns the complete dataset with all columns.
+        Default is True.
+    verbose : bool, optional
+        If True, prints detailed information about the data download and processing.
+        Default is False.
+
+    Returns
+    -------
+    geopandas.GeoDataFrame
+        A GeoDataFrame containing Oil and Gas Legal Pre-Salt Polygon data.
+
+    Examples
+    --------
+    >>> # Download Oil and Gas Legal Pre-Salt Polygon data
+    >>> df = read_og_legal_pre_salt_polygon()
+    >>> df.head()
+    """
+
+    url = "https://gisepeprd2.epe.gov.br/arcgis/rest/services/Download_Dados_Webmap_EPE/GPServer/Extract%20Data%20Task/execute?f=json&env%3AoutSR=102100&Layers_to_Clip=%5B%22Pol%C3%ADgono%20do%20Pr%C3%A9%20Sal%20Legal%22%5D&Area_of_Interest=%7B%22geometryType%22%3A%22esriGeometryPolygon%22%2C%22features%22%3A%5B%7B%22geometry%22%3A%7B%22rings%22%3A%5B%5B%5B-9237395.881983705%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C-4650539.310904562%5D%5D%5D%2C%22spatialReference%22%3A%7B%22wkid%22%3A102100%7D%7D%7D%5D%2C%22sr%22%3A%7B%22wkid%22%3A102100%7D%7D&Feature_Format=Shapefile%20-%20SHP%20-%20.shp&Raster_Format=Tagged%20Image%20File%20Format%20-%20TIFF%20-%20.tif"
+
+    if verbose:
+        print("Downloading data...")
+
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        response_json = response.json()
+
+        if "value" not in response_json or not response_json["value"]:
+            raise ValueError("No data found in the response")
+
+        download_url = response_json["value"]["itemUrl"]
+        
+        if verbose:
+            print(f"Download URL: {download_url}")
+            print("Downloading zip file...")
+
+        zip_response = requests.get(download_url)
+        zip_response.raise_for_status()
+
+        # Create a temporary directory to extract the files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            zip_path = os.path.join(temp_dir, "data.zip")
+            
+            # Save the zip file
+            with open(zip_path, "wb") as f:
+                f.write(zip_response.content)
+            
+            if verbose:
+                print(f"Zip file saved to {zip_path}")
+                print("Extracting files...")
+            
+            # Extract the zip file
+            with zipfile.ZipFile(zip_path, "r") 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 FileNotFoundError("No shapefile found in the downloaded zip file")
+            
+            shp_path = os.path.join(temp_dir, shp_files[0])
+            
+            if verbose:
+                print(f"Reading shapefile from {shp_path}")
+            
+            # Read the shapefile
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            gdf = gdf.to_crs(epsg=4674)
+            
+            if simplified:
+                # Select only essential columns
+                if verbose:
+                    print("Simplifying the dataset...")
+                
+                # Identify the essential columns
+                essential_cols = ["geometry"]
+                
+                # Add any other essential columns that exist in the dataset
+                for col in ["NOME", "DESCRICAO", "AREA_KM2"]:
+                    if col in gdf.columns:
+                        essential_cols.append(col)
+                
+                # Select only the essential columns
+                gdf = gdf[essential_cols]
+            
+            return gdf
+    
+    except requests.exceptions.RequestException as e:
+        warnings.warn(f"Error downloading data: {e}")
+        return None
+    except (ValueError, FileNotFoundError, zipfile.BadZipFile) as e:
+        warnings.warn(f"Error processing data: {e}")
+        return None
+    except Exception as e:
+        warnings.warn(f"Unexpected error: {e}")
+        return None

tunned_geobr/read_og_predominant_fluid_type.py

@@ -0,0 +1,129 @@
+import geopandas as gpd
+import requests
+import shutil
+import zipfile
+import tempfile
+import warnings
+import os
+from shapely.geometry.point import Point
+
+
+def read_og_predominant_fluid_type(simplified=False, verbose=False):
+    """Download data of predominant fluid type areas in Brazil's oil and gas basins.
+
+    This function downloads and returns data of predominant fluid type areas
+    (Tipo de Fluido Predominante) in Brazil's oil and gas basins as a GeoPandas GeoDataFrame. 
+    The data comes from EPE (Energy Research Company).
+
+    Parameters
+    ----------
+    simplified : bool, optional
+        If True, returns a simplified version of the dataset with only the most
+        important columns. If False, returns the complete dataset. Default is False.
+    verbose : bool, optional
+        If True, displays detailed messages about the download and processing
+        steps. Default is False.
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        A GeoDataFrame containing data on predominant fluid type areas in Brazil's oil and gas basins.
+
+    Raises
+    ------
+    Exception
+        If the download or processing of the data fails.
+
+    Example
+    -------
+    >>> from tunned_geobr import read_og_predominant_fluid_type
+    >>> 
+    >>> # Read the data
+    >>> fluid_types = read_og_predominant_fluid_type()
+    >>> 
+    >>> # Plot the data
+    >>> fluid_types.plot()
+    """
+    
+    if verbose:
+        print("Downloading data of predominant fluid type areas in Brazil's oil and gas basins")
+    
+    # Define the URL for the API request
+    url = "https://gisepeprd2.epe.gov.br/arcgis/rest/services/Download_Dados_Webmap_EPE/GPServer/Extract%20Data%20Task/execute?f=json&env%3AoutSR=102100&Layers_to_Clip=%5B%22Tipo%20de%20Fluido%20Predominante%22%5D&Area_of_Interest=%7B%22geometryType%22%3A%22esriGeometryPolygon%22%2C%22features%22%3A%5B%7B%22geometry%22%3A%7B%22rings%22%3A%5B%5B%5B-9237395.881983705%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C-4650539.310904562%5D%5D%5D%2C%22spatialReference%22%3A%7B%22wkid%22%3A102100%7D%7D%7D%5D%2C%22sr%22%3A%7B%22wkid%22%3A102100%7D%7D&Feature_Format=Shapefile%20-%20SHP%20-%20.shp&Raster_Format=Tagged%20Image%20File%20Format%20-%20TIFF%20-%20.tif"
+    
+    try:
+        # Make the API request
+        response = requests.get(url)
+        response.raise_for_status()
+        
+        # Parse the JSON response
+        data = response.json()
+        
+        # Extract the URL for the zip file
+        if 'results' in data and len(data['results']) > 0 and 'value' in data['results'][0]:
+            download_url = data['results'][0]['value']['url']
+        else:
+            raise Exception("Failed to extract download URL from API response")
+        
+        # Create a temporary directory to store the downloaded files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Download the zip file
+            zip_path = os.path.join(temp_dir, "og_predominant_fluid_type.zip")
+            if verbose:
+                print("Downloading zip file")
+            
+            response = requests.get(download_url, stream=True)
+            response.raise_for_status()
+            
+            with open(zip_path, 'wb') as f:
+                response.raw.decode_content = True
+                shutil.copyfileobj(response.raw, f)
+            
+            # Extract the zip file
+            if verbose:
+                print("Extracting files")
+            
+            with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile in the extracted files
+            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 zip file")
+            
+            # Read the shapefile
+            if verbose:
+                print("Reading shapefile")
+            
+            shp_path = os.path.join(temp_dir, shp_files[0])
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            if verbose:
+                print("Converting to SIRGAS 2000 (EPSG:4674)")
+            
+            gdf = gdf.to_crs(epsg=4674)
+            
+            # Simplify the dataset if requested
+            if simplified:
+                if verbose:
+                    print("Simplifying the dataset")
+                
+                # Select only the most important columns
+                # Adjust these columns based on the actual data structure
+                cols_to_keep = ['TIPO', 'BACIA', 'UF', 'geometry']
+                cols_available = [col for col in cols_to_keep if col in gdf.columns]
+                
+                if not cols_available:
+                    warnings.warn("None of the specified columns for simplification are available. Returning the full dataset.")
+                else:
+                    gdf = gdf[cols_available]
+            
+            if verbose:
+                print("Finished processing predominant fluid type areas data")
+            
+            return gdf
+    
+    except Exception as e:
+        raise Exception(f"Failed to download or process predominant fluid type areas data: {str(e)}")

tunned_geobr/read_og_probabilistic_effective_basin.py

@@ -0,0 +1,129 @@
+import geopandas as gpd
+import requests
+import shutil
+import zipfile
+import tempfile
+import warnings
+import os
+from shapely.geometry.point import Point
+
+
+def read_og_probabilistic_effective_basin(simplified=False, verbose=False):
+    """Download data of oil and gas probabilistic effective basins in Brazil.
+
+    This function downloads and returns data of oil and gas probabilistic effective basins
+    (Bacia Efetiva Probabilística) in Brazil as a GeoPandas GeoDataFrame. 
+    The data comes from EPE (Energy Research Company).
+
+    Parameters
+    ----------
+    simplified : bool, optional
+        If True, returns a simplified version of the dataset with only the most
+        important columns. If False, returns the complete dataset. Default is False.
+    verbose : bool, optional
+        If True, displays detailed messages about the download and processing
+        steps. Default is False.
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        A GeoDataFrame containing data on oil and gas probabilistic effective basins in Brazil.
+
+    Raises
+    ------
+    Exception
+        If the download or processing of the data fails.
+
+    Example
+    -------
+    >>> from tunned_geobr import read_og_probabilistic_effective_basin
+    >>> 
+    >>> # Read the data
+    >>> prob_basins = read_og_probabilistic_effective_basin()
+    >>> 
+    >>> # Plot the data
+    >>> prob_basins.plot()
+    """
+    
+    if verbose:
+        print("Downloading data of oil and gas probabilistic effective basins in Brazil")
+    
+    # Define the URL for the API request
+    url = "https://gisepeprd2.epe.gov.br/arcgis/rest/services/Download_Dados_Webmap_EPE/GPServer/Extract%20Data%20Task/execute?f=json&env%3AoutSR=102100&Layers_to_Clip=%5B%22Bacia%20Efetiva%20Probabil%C3%ADstica%22%5D&Area_of_Interest=%7B%22geometryType%22%3A%22esriGeometryPolygon%22%2C%22features%22%3A%5B%7B%22geometry%22%3A%7B%22rings%22%3A%5B%5B%5B-9237395.881983705%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C-4650539.310904562%5D%5D%5D%2C%22spatialReference%22%3A%7B%22wkid%22%3A102100%7D%7D%7D%5D%2C%22sr%22%3A%7B%22wkid%22%3A102100%7D%7D&Feature_Format=Shapefile%20-%20SHP%20-%20.shp&Raster_Format=Tagged%20Image%20File%20Format%20-%20TIFF%20-%20.tif"
+    
+    try:
+        # Make the API request
+        response = requests.get(url)
+        response.raise_for_status()
+        
+        # Parse the JSON response
+        data = response.json()
+        
+        # Extract the URL for the zip file
+        if 'results' in data and len(data['results']) > 0 and 'value' in data['results'][0]:
+            download_url = data['results'][0]['value']['url']
+        else:
+            raise Exception("Failed to extract download URL from API response")
+        
+        # Create a temporary directory to store the downloaded files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Download the zip file
+            zip_path = os.path.join(temp_dir, "og_probabilistic_effective_basin.zip")
+            if verbose:
+                print("Downloading zip file")
+            
+            response = requests.get(download_url, stream=True)
+            response.raise_for_status()
+            
+            with open(zip_path, 'wb') as f:
+                response.raw.decode_content = True
+                shutil.copyfileobj(response.raw, f)
+            
+            # Extract the zip file
+            if verbose:
+                print("Extracting files")
+            
+            with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile in the extracted files
+            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 zip file")
+            
+            # Read the shapefile
+            if verbose:
+                print("Reading shapefile")
+            
+            shp_path = os.path.join(temp_dir, shp_files[0])
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            if verbose:
+                print("Converting to SIRGAS 2000 (EPSG:4674)")
+            
+            gdf = gdf.to_crs(epsg=4674)
+            
+            # Simplify the dataset if requested
+            if simplified:
+                if verbose:
+                    print("Simplifying the dataset")
+                
+                # Select only the most important columns
+                # Adjust these columns based on the actual data structure
+                cols_to_keep = ['NOME', 'TIPO', 'AMBIENTE', 'UF', 'geometry']
+                cols_available = [col for col in cols_to_keep if col in gdf.columns]
+                
+                if not cols_available:
+                    warnings.warn("None of the specified columns for simplification are available. Returning the full dataset.")
+                else:
+                    gdf = gdf[cols_available]
+            
+            if verbose:
+                print("Finished processing oil and gas probabilistic effective basins data")
+            
+            return gdf
+    
+    except Exception as e:
+        raise Exception(f"Failed to download or process oil and gas probabilistic effective basins data: {str(e)}")

tunned_geobr/read_og_total_ipa.py

@@ -0,0 +1,129 @@
+import geopandas as gpd
+import requests
+import shutil
+import zipfile
+import tempfile
+import warnings
+import os
+from shapely.geometry.point import Point
+
+
+def read_og_total_ipa(simplified=False, verbose=False):
+    """Download data of total IPA (Accumulated Productivity Index) for oil and gas in Brazil.
+
+    This function downloads and returns data of total IPA (Índice de Produtividade Acumulada)
+    for oil and gas areas in Brazil as a GeoPandas GeoDataFrame. 
+    The data comes from EPE (Energy Research Company).
+
+    Parameters
+    ----------
+    simplified : bool, optional
+        If True, returns a simplified version of the dataset with only the most
+        important columns. If False, returns the complete dataset. Default is False.
+    verbose : bool, optional
+        If True, displays detailed messages about the download and processing
+        steps. Default is False.
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        A GeoDataFrame containing data on total IPA for oil and gas areas in Brazil.
+
+    Raises
+    ------
+    Exception
+        If the download or processing of the data fails.
+
+    Example
+    -------
+    >>> from tunned_geobr import read_og_total_ipa
+    >>> 
+    >>> # Read the data
+    >>> total_ipa = read_og_total_ipa()
+    >>> 
+    >>> # Plot the data
+    >>> total_ipa.plot()
+    """
+    
+    if verbose:
+        print("Downloading data of total IPA for oil and gas areas in Brazil")
+    
+    # Define the URL for the API request
+    url = "https://gisepeprd2.epe.gov.br/arcgis/rest/services/Download_Dados_Webmap_EPE/GPServer/Extract%20Data%20Task/execute?f=json&env%3AoutSR=102100&Layers_to_Clip=%5B%22IPA%20Total%22%5D&Area_of_Interest=%7B%22geometryType%22%3A%22esriGeometryPolygon%22%2C%22features%22%3A%5B%7B%22geometry%22%3A%7B%22rings%22%3A%5B%5B%5B-9237395.881983705%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C1219824.4613954136%5D%2C%5B-2349502.3891517334%2C-4650539.310904562%5D%2C%5B-9237395.881983705%2C-4650539.310904562%5D%5D%5D%2C%22spatialReference%22%3A%7B%22wkid%22%3A102100%7D%7D%7D%5D%2C%22sr%22%3A%7B%22wkid%22%3A102100%7D%7D&Feature_Format=Shapefile%20-%20SHP%20-%20.shp&Raster_Format=Tagged%20Image%20File%20Format%20-%20TIFF%20-%20.tif"
+    
+    try:
+        # Make the API request
+        response = requests.get(url)
+        response.raise_for_status()
+        
+        # Parse the JSON response
+        data = response.json()
+        
+        # Extract the URL for the zip file
+        if 'results' in data and len(data['results']) > 0 and 'value' in data['results'][0]:
+            download_url = data['results'][0]['value']['url']
+        else:
+            raise Exception("Failed to extract download URL from API response")
+        
+        # Create a temporary directory to store the downloaded files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Download the zip file
+            zip_path = os.path.join(temp_dir, "og_total_ipa.zip")
+            if verbose:
+                print("Downloading zip file")
+            
+            response = requests.get(download_url, stream=True)
+            response.raise_for_status()
+            
+            with open(zip_path, 'wb') as f:
+                response.raw.decode_content = True
+                shutil.copyfileobj(response.raw, f)
+            
+            # Extract the zip file
+            if verbose:
+                print("Extracting files")
+            
+            with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile in the extracted files
+            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 zip file")
+            
+            # Read the shapefile
+            if verbose:
+                print("Reading shapefile")
+            
+            shp_path = os.path.join(temp_dir, shp_files[0])
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            if verbose:
+                print("Converting to SIRGAS 2000 (EPSG:4674)")
+            
+            gdf = gdf.to_crs(epsg=4674)
+            
+            # Simplify the dataset if requested
+            if simplified:
+                if verbose:
+                    print("Simplifying the dataset")
+                
+                # Select only the most important columns
+                # Adjust these columns based on the actual data structure
+                cols_to_keep = ['CLASSE', 'BACIA', 'UF', 'geometry']
+                cols_available = [col for col in cols_to_keep if col in gdf.columns]
+                
+                if not cols_available:
+                    warnings.warn("None of the specified columns for simplification are available. Returning the full dataset.")
+                else:
+                    gdf = gdf[cols_available]
+            
+            if verbose:
+                print("Finished processing total IPA data")
+            
+            return gdf
+    
+    except Exception as e:
+        raise Exception(f"Failed to download or process total IPA data: {str(e)}")