Added function which_countries_on_a_grid to GDE_TOOLS_create_ind...

GDE_TOOLS_create_industrial_cells.py

@@ -1632,3 +1632,81 @@ def export_cells_to_geodatafile(
 
     # Write to ShapeFile or other format (as per out_driver):
     shp_gdf.to_file(os.path.join(out_pathname, out_filename), driver=out_driver)
+
+
+def which_countries_on_a_grid(
+    metadata_filepath,
+    sheet_name="IND",
+    col_name="Variables",
+    var_name="Resolution",
+    target="30 arc seconds",
+    export=False,
+    out_pathname="",
+    out_filename="",
+):
+    """This function retrieves the list of countries for which the industrial exposure is
+    defined on a 30-arcsec grid in the SERA exposure model. This information is provided in the
+    EFEHR repository within an Excel spreadsheet called
+    "European_Exposure_Model_Data_Assumptions.xlsx". The default values of all input parameters
+    refer to the structure of this file.
+
+    Args:
+        metadata_filepath (str): Full path to the source metadata file, including file name and
+                                 extension. It needs to be an Excel spreadsheet (.xls or .xlsx).
+        sheet_name (str): Name of the sheet of metadata_filepath to read. Default: "IND".
+        col_name (str): Name of the column of sheet_name that contains the parameter names.
+                        Default: "Variables".
+        var_name (str): Name of the parameter to read. Default: "Resolution".
+        target (str): Target value of var_name (i.e. the code will seek for cases in which the
+                      value of var_name is target. Default: "30 arc seconds".
+        export (bool): If True, the resulting list of countries will be exported to a CSV file
+                       under the path out_pathname and the file name out_filename.
+                       Default: False.
+        out_pathname (str): Path where to export the output CSV to. Only needed if export is
+                            True. Default: "".
+        out_filename (str): Name of the file where to write the list of countries. Only needed
+                            if export is True. Default: "".
+
+    Returns:
+        countries (list of str): List of countries for which the var_name takes the value given
+                                 by target (the countries for which the industrial exposure is
+                                 defined on a 30-arcsec grid in the SERA exposure model.
+    """
+
+    # Check metadata_filepath exists and points at an Excel spreadsheet:
+    if not os.path.isfile(metadata_filepath):
+        print("ERROR in which_countries_on_a_grid: input file not found")
+        return []
+    if "xls" not in metadata_filepath.split(".")[-1]:
+        print("ERROR in which_countries_on_a_grid: input file is not an Excel spreadsheet")
+        return []
+
+    # Read the SERA metadata file:
+    metadata = pd.read_excel(metadata_filepath, sheet_name=sheet_name)
+
+    # Identify the row in which the variable var_name is given:
+    which_row = np.where(metadata[col_name].values == var_name)[0]
+
+    if len(which_row) != 1:  # This should not occur
+        print("ERROR READING %s: ROW NOT FOUND." % (metadata_filepath))
+        return []
+
+    # Retrieve the row in which the variable var_name is given:
+    whole_row = metadata.iloc[which_row[0], :]
+    # Columns in which var_name takes the value target:
+    which_cols = np.where(whole_row == target)[0]
+    # The names of those columns are the countries for which var_name takes the value target:
+    countries = list(whole_row.index[which_cols])
+
+    # Write a csv file with the list of countries:
+    if export:
+        # Create out_pathname if it does not exist:
+        if not os.path.exists(out_pathname):
+            os.makedirs(out_pathname)
+        # Write to file:
+        out_filepath = os.path.join(out_pathname, out_filename)
+        f = open(out_filepath, "w")
+        f.write(",".join(countries))
+        f.close()
+
+    return countries