Reduced number of parameters used to define building classes

GDE_TOOLS_read_SERA.py

@@ -397,20 +397,20 @@ def determine_unique_combinations_of_taxonomies_and_values_per_building(in_case,
     For example, for residential exposure a "unique" class will be defined by:
     taxonomy///settlement_type/occupancy_type/dwell_per_bdg/area_per_dwelling_sqm
     
-    This combination of parameters is referred to in brief as taxonomy*. The columns used for taxonomy* are not the same
+    This combination of parameters is referred to in brief as taxonomy*. The columns used for taxonomy* are not necessarily the same
     for Res, Com and Ind (see function get_list_for_grouping).
     
     This function will then define if there are repeated instances of taxonomy* within with_duplicates_df.
 
     For example, if with_duplicates_df is:
     taxonomy                        structural        night
-    RC/H:2///RURAL//2.00/125.00       2000.5          3.51
-    RC/H:2///RURAL//2.00/125.00       2000.5          3.51
-    RC/H:2///RURAL//1.00/150.00       1050.2          3.51
+    RC/H:2///RURAL//                  2000.5          3.51
+    RC/H:2///RURAL//                  2000.5          3.51
+    RC/H:2///RURAL//                  1050.2          3.51
     
     The result will be:
         there_are_duplicates= True
-        uniq_vals= array['RC/H:2///RURAL//2.00/125.00', 'RC/H:2///RURAL//1.00/150.00']
+        uniq_vals= array['RC/H:2///RURAL//', 'RC/H:2///RURAL//']
         uniq_inverse= array[0,0,1] (i.e. the positions of with_duplicates_df that correspond to each unique element in uniq_vals)
         groupby_crit= ['taxonomy', 'settlement_type', 'occupancy_type', 'dwell_per_bdg', 'area_per_dwelling_sqm']
    
@@ -456,17 +456,17 @@ def get_list_for_grouping(occupancy_case):
     """
     The columns enumerated in the out_list are those that will be used to identify the building class.
     The decision regarding on which columns to include here was based on the analysis carried out
-    using SERA_which_countries_have_duplicate_classes_include_settlement.py (March 2020).
+    in March 2020, May/June 2020 and November 2021.
     """
     if occupancy_case=='Res':
-        out_list= ['taxonomy', 'settlement_type', 'occupancy_type', 'dwell_per_bdg', 'area_per_dwelling_sqm']
-        round_by= ['', '', '', get_rounding_type('dwell_per_bdg'), get_rounding_type('area_per_dwelling_sqm')] # method for rounding floats
+        out_list= ['taxonomy', 'settlement_type', 'occupancy_type']
+        round_by= ['', '', ''] # method for rounding floats
     elif occupancy_case=='Com':
-        out_list= ['taxonomy', 'settlement_type', 'occupancy_type', 'area_per_dwelling_sqm']
-        round_by= ['', '', '', get_rounding_type('area_per_dwelling_sqm')] # method for rounding floats
+        out_list= ['taxonomy', 'settlement_type', 'occupancy_type']
+        round_by= ['', '', ''] # method for rounding floats
     elif occupancy_case=='Ind':
-        out_list= ['taxonomy', 'settlement_type', 'occupancy_type', 'cost_per_area_usd']
-        round_by= ['', '', '', get_rounding_type('cost_per_area_usd')] # method for rounding floats
+        out_list= ['taxonomy', 'settlement_type', 'occupancy_type']
+        round_by= ['', '', ''] # method for rounding floats
     else:
         out_list= []
         round_by= []
@@ -620,7 +620,7 @@ def group_same_taxonomies(in_df, in_array_unique_combis, in_position_of_unique,
     in_array_unique_combis= numpy array of unique combinations of taxonomy* (i.e. taxonomy considering all parameters enumerated in get_list_for_grouping)
     in_position_of_unique= its length is the same as the number of rows in in_df; for each row, it indicates the corresponding element of in_array_unique_taxonoms
     in_country_adm_ids= an array of strings with length equal to the number of rows in in_df. It indicates the country_admin_ID each row in in_df is coming from.
-                        
+
     out_df= Pandas DataFrame in which a certain combination of taxonomy* only exists once (the different rows of in_df for the same combination of taxonomy*
             have been grouped together). Note that the number of buildings (i.e. "number" or "buildings" column), number of dwellings and number of people
             ("occupants_per_asset") are the only values that are added, all other values (e.g. "dwell_per_bdg") are values per building or dwelling and are