Added feature to retrieve number of buildings, dwellings, people, costs

gdeimporter/aggregatedexposuremodel.py

@@ -50,6 +50,8 @@ class AggregatedExposureModel(abc.ABC):
         self.boundary_filename_pattern (str):
             Pattern of the names of the geodata files that contain the boundaries of the
             exposure entities of the input aggregated exposure model.
+        self.currency (str):
+            Currency used in the AggregatedExposureModel to express building replacement costs.
     """
 
     def __init__(self, configuration):
@@ -65,6 +67,7 @@ class AggregatedExposureModel(abc.ABC):
         self.exposure_entities = None
         self.filename_pattern = None
         self.boundary_filename_pattern = None
+        self.currency = None
 
     def retrieve_exposure_entities(self, configuration):
         """This function retrieves the exposure entities for which an input aggregated exposure
@@ -200,6 +203,10 @@ class ExposureModelESRM20(AggregatedExposureModel):
                     Relative path to the metadata .xlsx file.
                 CSVs (str):
                     Relative path to the folder that contains the CSV files per exposure entity.
+        self.csv_column_names
+            Names of columns of interest in the CSV files.
+        self.currency (str):
+            Currency used in ESRM20 to express building replacement costs.
         self.exposure_entities (dictionary of ExposureEntity):
             Dictionary of instances of ExposureEntity objects, each of which represent an
             exposure entity where the input aggregated exposure model is defined. See
@@ -240,6 +247,24 @@ class ExposureModelESRM20(AggregatedExposureModel):
             "metadata": "sources/European_Exposure_Model_Data_Inputs_Sources.xlsx",
             "CSVs": "_exposure_models",
         }
+        self.csv_column_names = {
+            "Buildings": "BUILDINGS",
+            "Dwellings": "DWELLINGS",
+            "People": {
+                "Census": "OCCUPANTS_PER_ASSET",
+                "Day": "OCCUPANTS_PER_ASSET_DAY",
+                "Night": "OCCUPANTS_PER_ASSET_NIGHT",
+                "Transit": "OCCUPANTS_PER_ASSET_TRANSIT",
+                "Average": "OCCUPANTS_PER_ASSET_AVERAGE",
+            },
+            "Cost": {
+                "Total": "TOTAL_REPL_COST_EUR",
+                "Structural": "COST_STRUCTURAL_EUR",
+                "Non-Structural": "COST_NONSTRUCTURAL_EUR",
+                "Contents": "COST_CONTENTS_EUR",
+            },
+        }
+        self.currency = "EUR"
         self.exposure_entities = self.retrieve_exposure_entities(configuration)
 
     def retrieve_exposure_entities(self, configuration):
@@ -382,14 +407,14 @@ class ExposureModelESRM20(AggregatedExposureModel):
         """
 
         # Read names of data units from ESRM20's CSV files
-        target_column_name = "ID_%s" % (
+        id_column_name_data = "ID_%s" % (
             str(
                 self.exposure_entities[exposure_entity_name].occupancy_cases[occupancy_case][
                     "data_units_level"
                 ]
             )
         )
-        datatypes = {target_column_name: str}
+        datatypes = {id_column_name_data: str}
         data_table = self._read_data_table(
             configuration,
             self.exposure_entities[exposure_entity_name],
@@ -397,12 +422,12 @@ class ExposureModelESRM20(AggregatedExposureModel):
             datatypes,
         )
         try:
-            data_units_names = list(data_table[target_column_name].unique())
+            data_units_ids = list(data_table[id_column_name_data].unique())
         except KeyError:
-            data_units_names = []
+            data_units_ids = []
             logger.critical(
-                "Error while retrieving 'data_units_names' of %s, %s: column `%s` not found"
-                % (exposure_entity_name, occupancy_case, target_column_name)
+                "Error while retrieving 'data_units_ids' of %s, %s: column `%s` not found"
+                % (exposure_entity_name, occupancy_case, id_column_name_data)
             )
 
         # Read geometries of data units from ESRM20's boundary files
@@ -410,7 +435,7 @@ class ExposureModelESRM20(AggregatedExposureModel):
             "data_units"
         ] = {}
 
-        target_column_name = "ID_%s" % (
+        id_column_name_geometries = "ID_%s" % (
             self.exposure_entities[exposure_entity_name].occupancy_cases[occupancy_case][
                 self.boundary_filename_pattern["first"]
             ]
@@ -422,10 +447,26 @@ class ExposureModelESRM20(AggregatedExposureModel):
             datatypes,
         )
 
-        for data_unit_name in data_units_names:
+        # Retrieve total number of buildings, dwellings, people and cost
+        results = self._retrieve_totals_all_data_units(
+            data_table, id_column_name_data, data_units_ids, exposure_entity_name
+        )
+        total_buildings, total_dwellings, total_people, total_cost = results
+
+        for data_unit_id in data_units_ids:
             self.exposure_entities[exposure_entity_name].occupancy_cases[occupancy_case][
                 "data_units"
-            ][data_unit_name] = DataUnit(data_unit_name, geometries_table, target_column_name)
+            ][data_unit_id] = DataUnit(
+                data_unit_id,
+                geometries_table,
+                id_column_name_geometries,
+                total_buildings[data_unit_id],
+                total_dwellings[data_unit_id],
+                total_people[data_unit_id],
+                total_cost[data_unit_id],
+                self.currency,
+            )
+
         return
 
     def _map_data_units_types(self, original_description):
@@ -584,3 +625,119 @@ class ExposureModelESRM20(AggregatedExposureModel):
             )
 
         return geometries_table
+
+    def _retrieve_totals_all_data_units(
+        self, data_table, ids_column_name, data_units_ids, exposure_entity_name
+    ):
+        """This function retrieves from data_table the total numbers of buildings, dwellings,
+        people and replacement costs in each data unit enumerated in data_units_ids.
+
+        Args:
+            data_table (Pandas DataFrame):
+                DataFrame with all contents of the ESRM20 CSV file for a specific
+                ExposureEntity and occupancy_case.
+            ids_column_name (str):
+                Name of the column of data_table where the data unit IDs are found.
+            data_units_ids (list of str):
+                List of IDs of data units assumed to be found in column ids_column_name of
+                data_table.
+            exposure_entity_name (str):
+                Name of the ExposureEntity to which data_units_ids belong.
+
+        Returns:
+            total_buildings (dict):
+                Dictionary containing the total number of buildings per data unit. The keys of
+                the dictionary are the data_units_ids. The values of total_buildings[key] are
+                floats.
+            total_dwellings (dict):
+                Dictionary containing the total number of dwellings per data unit. The keys of
+                the dictionary are the data_units_ids. The values of total_dwellings[key] are
+                floats.
+            total_people (dict):
+                Dictionary containing the total number of people per data unit. The keys of the
+                dictionary are the data_units_ids. The values of total_people[key] are
+                dictionaries themselves containing the following:
+                    Census (float):
+                        Total number of people expected to be inside all buildings in the
+                        DataUnit obtained from distributing the census population to the
+                        buildings, without consideration of the time of the day or distribution
+                        of the population across different economic/educational/recreational
+                        activities.
+                    Day (float):
+                        Total number of people expected to be inside all buildings in the
+                        DataUnit during the day (approx. 10 am to 6 pm).
+                    Night (float):
+                        Total number of people expected to be inside all buildings in the
+                        DataUnit during the night (approx. 10 pm to 6 am).
+                    Transit (float):
+                        Total number of people expected to be inside all buildings in the
+                        DataUnit during transit times (approx. 6 am to 10 am and 6 pm to 10 pm).
+                    Average (float):
+                        Average total number of people expected to be inside all buildings in
+                        the DataUnit at an undefined time of the day (average of Day, Night and
+                        Transit).
+            total_cost (dict):
+                Dictionary containing the monetary value of all the buildings per data unit
+                (cost of total_buildings). The keys of the dictionary are the data_units_ids.
+                The values of total_cost[key] are dictionaries themselves containing the
+                following:
+                    Total (float):
+                        Total replacement cost of all buildings, including structural and
+                        non-structural components, as well as contents.
+                    Structural (float):
+                        Replacement cost of the structural components of all buildings.
+                    Non-Structural (float):
+                        Replacement cost of the non-structural components of all buildings.
+                    Contents (float):
+                        Replacement cost of the contents of all buildings.
+        """
+
+        totals_of_data_units = {
+            "Buildings": {},
+            "Dwellings": {},
+            "People": {},  # Sub-keys will be retrieved from self.csv_column_names
+            "Cost": {},  # Sub-keys will be retrieved from self.csv_column_names
+        }
+
+        for data_unit_id in data_units_ids:
+            which = numpy.where(data_table[ids_column_name].values == data_unit_id)[0]
+            for parameter in totals_of_data_units.keys():
+                # Link this parameter with a column of data_table
+                aux_val = self.csv_column_names[parameter]
+                if isinstance(aux_val, str):  # Buildings, dwellings
+                    column = aux_val
+                    totals_of_data_units[parameter][data_unit_id] = (
+                        data_table[column].values[which].sum()
+                    )
+                if isinstance(aux_val, dict):  # People, cost
+                    totals_of_data_units[parameter][data_unit_id] = {}
+                    sub_dictionary = aux_val
+                    for key in sub_dictionary.keys():
+                        column = self.csv_column_names[parameter][key]
+                        totals_of_data_units[parameter][data_unit_id][key] = (
+                            data_table[column].values[which].sum()
+                        )
+
+        total_buildings = totals_of_data_units["Buildings"]
+        total_dwellings = totals_of_data_units["Dwellings"]
+        total_people = totals_of_data_units["People"]
+        total_cost = totals_of_data_units["Cost"]
+
+        # Check consistency of costs
+        for data_unit_id in data_units_ids:
+            total_cost_difference = abs(
+                total_cost[data_unit_id]["Total"]
+                - (
+                    total_cost[data_unit_id]["Structural"]
+                    + total_cost[data_unit_id]["Non-Structural"]
+                    + total_cost[data_unit_id]["Contents"]
+                )
+            )
+            if total_cost_difference > 1e-5:
+                logger.warning(
+                    "Data Unit with ID %s of Exposure Entity '%s': The sum of structural, "
+                    "non-structural and components' costs does not match the total cost."
+                    % (data_unit_id, exposure_entity_name)
+                )
+
+        return total_buildings, total_dwellings, total_people, total_cost

gdeimporter/dataunit.py

@@ -21,6 +21,21 @@ import numpy
 
 logger = logging.getLogger()
 
+_TOTAL_PEOPLE_DEFAULT = {
+    "Census": None,
+    "Day": None,
+    "Night": None,
+    "Transit": None,
+    "Average": None,
+}
+
+_TOTAL_COST_DEFAULT = {
+    "Total": None,
+    "Structural": None,
+    "Non-Structural": None,
+    "Contents": None,
+}
+
 
 class DataUnit:
     """This class represents the smallest geographical unit of an ExposureEntity, that is, the
@@ -32,6 +47,45 @@ class DataUnit:
             ID of the DataUnit (e.g. ID of the administrative unit it represents).
         self.geometry (Shapely polygon):
             Geometry of the data unit.
+        self.total_buildings (float):
+            Total number of buildings in the DataUnit.
+        self.total_dwellings (float):
+            Total number of dwellings in the DataUnit.
+        self.total_people (dict):
+            Dictionary with the total number of people in the DataUnit. The keys of the
+            dictionary are:
+                Census (float):
+                    Total number of people expected to be inside all buildings in the DataUnit
+                    obtained from distributing the census population to the buildings, without
+                    consideration of the time of the day or distribution of the population
+                    across different economic/educational/recreational activities.
+                Day (float):
+                    Total number of people expected to be inside all buildings in the DataUnit
+                    during the day (approx. 10 am to 6 pm).
+                Night (float):
+                    Total number of people expected to be inside all buildings in the DataUnit
+                    during the night (approx. 10 pm to 6 am).
+                Transit (float):
+                    Total number of people expected to be inside all buildings in the DataUnit
+                    during transit times (approx. 6 am to 10 am and 6 pm to 10 pm).
+                Average (float):
+                    Average total number of people expected to be inside all buildings in the
+                    DataUnit at an undefined time of the day (average of Day, Night and
+                    Transit).
+        self.total_cost (dict):
+            Dictionary with the monetary value of all the buildings in the DataUnit (cost of
+            self.total_buildings). The keys of the dictionary are:
+                Total (float):
+                    Total replacement cost of all buildings, including structural and
+                    non-structural components, as well as contents.
+                Structural (float):
+                    Replacement cost of the structural components of all buildings.
+                Non-Structural (float):
+                    Replacement cost of the non-structural components of all buildings.
+                Contents (float):
+                    Replacement cost of the contents of all buildings.
+        self.currency (str):
+            Currency used in self.total_cost to express building replacement costs.
         self.data_unit_tiles (GeoPandas GeoDataFrame):
             Definition of the data-unit tiles associated with the data unit. It is filled in by
             ExposureEntity.create_data_unit_tiles(), processing all the data units associated
@@ -43,7 +97,17 @@ class DataUnit:
                     Geometry of the data-unit tile.
     """
 
-    def __init__(self, dataunit_id, geometries_table, target_column_name):
+    def __init__(
+        self,
+        dataunit_id,
+        geometries_table,
+        target_column_name,
+        total_buildings=None,
+        total_dwellings=None,
+        total_people=_TOTAL_PEOPLE_DEFAULT,
+        total_cost=_TOTAL_COST_DEFAULT,
+        currency=None,
+    ):
         """
         Args:
             dataunit_id (str):
@@ -58,11 +122,43 @@ class DataUnit:
                         Geometry.
             target_column_name (str):
                 Name of the column in which the ID of the Data Unit will be sought.
+            total_buildings (float):
+                Total number of buildings in the DataUnit.
+            total_dwellings (float):
+                Total number of dwellings in the DataUnit.
+            total_people (dict of floats):
+                Dictionary with the total number of people in the DataUnit. The keys should be:
+                Census, Day, Night, Transit, Average. See definitions in the description of
+                DataUnit.total_people.
+            total_cost (dict of floats):
+                Dictionary with the monetary value of all the buildings in the DataUnit (cost of
+                total_buildings). The keys should be: Total, Structural, Non-Structural,
+                Contents. See definitions in the description of DataUnit.total_cost.
+            currency (str):
+                Currency used in total_cost to express building replacement costs.
         """
 
+        # Check that the keys of total_people are the expected ones
+        assert "Census" in total_people.keys()
+        assert "Day" in total_people.keys()
+        assert "Night" in total_people.keys()
+        assert "Transit" in total_people.keys()
+        assert "Average" in total_people.keys()
+
+        # Check that the keys of total_cost are the expected ones
+        assert "Total" in total_cost.keys()
+        assert "Structural" in total_cost.keys()
+        assert "Non-Structural" in total_cost.keys()
+        assert "Contents" in total_cost.keys()
+
         self.id = dataunit_id
         self.geometry = self.get_data_unit_geometry(geometries_table, target_column_name)
         self.data_unit_tiles = None
+        self.total_buildings = total_buildings
+        self.total_dwellings = total_dwellings
+        self.total_people = total_people
+        self.total_cost = total_cost
+        self.currency = currency
 
     def get_data_unit_geometry(self, geometries_table, target_column_name):
         """This function retrieves the geometry of the data unit, by reading it from

tests/data/ExposureModelESRM20_non_trivial/_exposure_models/Exposure_Model_Entity_1_Com.csv

-lon,lat,taxonomy,number,ID_1
-20.1,47.3,A,35.2,Unit_X
-20.1,47.3,B,12.7,Unit_X
-20.1,47.3,C,8.9,Unit_X
-20.1,47.3,C,5.7,Unit_X
-19.8,47.4,A,25.6,Unit_Y
-19.8,47.4,A,7.9,Unit_Y
-19.8,47.4,B,23.5,Unit_Y
-20.4,46.9,A,40.2,Unit_Z
-20.4,46.9,B,16.3,Unit_Z
-20.4,46.9,C,33.4,Unit_Z
+lon,lat,taxonomy,BUILDINGS,ID_1,DWELLINGS,TOTAL_REPL_COST_EUR,COST_STRUCTURAL_EUR,COST_NONSTRUCTURAL_EUR,COST_CONTENTS_EUR,OCCUPANTS_PER_ASSET,OCCUPANTS_PER_ASSET_DAY,OCCUPANTS_PER_ASSET_NIGHT,OCCUPANTS_PER_ASSET_TRANSIT,OCCUPANTS_PER_ASSET_AVERAGE
+20.1,47.3,A,35.2,Unit_X,35.2,316800000,126720000,63360000,126720000,1056,844.8,105.6,211.2,387.2
+20.1,47.3,B,12.7,Unit_X,12.7,114300000,45720000,22860000,45720000,381,304.8,38.1,76.2,139.7
+20.1,47.3,C,8.9,Unit_X,8.9,80100000,32040000,16020000,32040000,267,213.6,26.7,53.4,97.9
+20.1,47.3,C,5.7,Unit_X,5.7,51300000,20520000,10260000,20520000,171,136.8,17.1,34.2,62.7
+19.8,47.4,A,25.6,Unit_Y,25.6,230400000,92160000,46080000,92160000,768,614.4,76.8,153.6,281.6
+19.8,47.4,A,7.9,Unit_Y,7.9,71100000,28440000,14220000,28440000,237,189.6,23.7,47.4,86.9
+19.8,47.4,B,23.5,Unit_Y,23.5,211500000,84600000,42300000,84600000,705,564,70.5,141,258.5
+20.4,46.9,A,40.2,Unit_Z,40.2,361800000,144720000,72360000,144720000,1206,964.8,120.6,241.2,442.2
+20.4,46.9,B,16.3,Unit_Z,16.3,146700000,58680000,29340000,58680000,489,391.2,48.9,97.8,179.3
+20.4,46.9,C,33.4,Unit_Z,33.4,300600000,120240000,60120000,120240000,1002,801.6,100.2,200.4,367.4

tests/data/ExposureModelESRM20_non_trivial/_exposure_models/Exposure_Model_Entity_1_Res.csv

-lon,lat,taxonomy,number,ID_1
-20.1,47.3,A,35.2,Unit_1
-20.1,47.3,B,12.7,Unit_1
-20.1,47.3,C,8.9,Unit_1
-20.1,47.3,C,5.7,Unit_1
-19.8,47.4,A,25.6,Unit_2
-19.8,47.4,A,7.9,Unit_2
-19.8,47.4,B,23.5,Unit_2
-20.4,46.9,A,40.2,Unit_3
-20.4,46.9,B,16.3,Unit_3
-20.4,46.9,C,33.4,Unit_3
+lon,lat,taxonomy,BUILDINGS,ID_1,DWELLINGS,TOTAL_REPL_COST_EUR,COST_STRUCTURAL_EUR,COST_NONSTRUCTURAL_EUR,COST_CONTENTS_EUR,OCCUPANTS_PER_ASSET,OCCUPANTS_PER_ASSET_DAY,OCCUPANTS_PER_ASSET_NIGHT,OCCUPANTS_PER_ASSET_TRANSIT,OCCUPANTS_PER_ASSET_AVERAGE
+20.1,47.3,A,35.2,Unit_1,105.6,158400000,79200000,47520000,31680000,264,39.6,184.8,52.8,92.4
+20.1,47.3,B,12.7,Unit_1,38.1,57150000,28575000,17145000,11430000,95.25,14.2875,66.675,19.05,33.3375
+20.1,47.3,C,8.9,Unit_1,26.7,40050000,20025000,12015000,8010000,66.75,10.0125,46.725,13.35,23.3625
+20.1,47.3,C,5.7,Unit_1,17.1,25650000,12825000,7695000,5130000,42.75,6.4125,29.925,8.55,14.9625
+19.8,47.4,A,25.6,Unit_2,76.8,115200000,57600000,34560000,23040000,192,28.8,134.4,38.4,67.2
+19.8,47.4,A,7.9,Unit_2,23.7,35550000,17775000,10665000,7110000,59.25,8.8875,41.475,11.85,20.7375
+19.8,47.4,B,23.5,Unit_2,70.5,105750000,52875000,31725000,21150000,176.25,26.4375,123.375,35.25,61.6875
+20.4,46.9,A,40.2,Unit_3,120.6,180900000,90450000,54270000,36180000,301.5,45.225,211.05,60.3,105.525
+20.4,46.9,B,16.3,Unit_3,48.9,73350000,36675000,22005000,14670000,122.25,18.3375,85.575,24.45,42.7875
+20.4,46.9,C,33.4,Unit_3,100.2,150300000,75150000,45090000,30060000,250.5,37.575,175.35,50.1,87.675

tests/data/ExposureModelESRM20_non_trivial/_exposure_models/Exposure_Model_Entity_2_Com.csv

-lon,lat,taxonomy,number,ID_2
-20.6,46.8,A,38.72,Unit_A
-20.6,46.8,B,13.97,Unit_A
-20.6,46.8,B,9.79,Unit_A
-20.6,46.8,C,6.27,Unit_A
-20.3,46.9,A,28.16,Unit_B
-20.3,46.9,C,8.69,Unit_B
-20.3,46.9,C,25.85,Unit_B
-20.9,46.4,A,44.22,Unit_C
-20.9,46.4,B,17.93,Unit_C
-20.9,46.4,C,36.74,Unit_C
+lon,lat,taxonomy,BUILDINGS,ID_2,DWELLINGS,TOTAL_REPL_COST_EUR,COST_STRUCTURAL_EUR,COST_NONSTRUCTURAL_EUR,COST_CONTENTS_EUR,OCCUPANTS_PER_ASSET,OCCUPANTS_PER_ASSET_DAY,OCCUPANTS_PER_ASSET_NIGHT,OCCUPANTS_PER_ASSET_TRANSIT,OCCUPANTS_PER_ASSET_AVERAGE
+20.6,46.8,A,38.72,Unit_A,38.72,348480000,139392000,69696000,139392000,1161.6,929.28,116.16,232.32,425.92
+20.6,46.8,B,13.97,Unit_A,13.97,125730000,50292000,25146000,50292000,419.1,335.28,41.91,83.82,153.67
+20.6,46.8,B,9.79,Unit_A,9.79,88110000,35244000,17622000,35244000,293.7,234.96,29.37,58.74,107.69
+20.6,46.8,C,6.27,Unit_A,6.27,56430000,22572000,11286000,22572000,188.1,150.48,18.81,37.62,68.97
+20.3,46.9,A,28.16,Unit_B,28.16,253440000,101376000,50688000,101376000,844.8,675.84,84.48,168.96,309.76
+20.3,46.9,C,8.69,Unit_B,8.69,78210000,31284000,15642000,31284000,260.7,208.56,26.07,52.14,95.59
+20.3,46.9,C,25.85,Unit_B,25.85,232650000,93060000,46530000,93060000,775.5,620.4,77.55,155.1,284.35
+20.9,46.4,A,44.22,Unit_C,44.22,397980000,159192000,79596000,159192000,1326.6,1061.28,132.66,265.32,486.42
+20.9,46.4,B,17.93,Unit_C,17.93,161370000,64548000,32274000,64548000,537.9,430.32,53.79,107.58,197.23
+20.9,46.4,C,36.74,Unit_C,36.74,330660000,132264000,66132000,132264000,1102.2,881.76,110.22,220.44,404.14

tests/data/ExposureModelESRM20_non_trivial/_exposure_models/Exposure_Model_Entity_2_Res.csv

-lon,lat,taxonomy,number,ID_1
-20.6,46.8,A,38.72,Unit_1
-20.6,46.8,B,13.97,Unit_1
-20.6,46.8,B,9.79,Unit_1
-20.6,46.8,C,6.27,Unit_1
-20.3,46.9,A,28.16,Unit_2
-20.3,46.9,C,8.69,Unit_2
-20.3,46.9,C,25.85,Unit_2
-20.9,46.4,A,44.22,Unit_3
-20.9,46.4,B,17.93,Unit_3
-20.9,46.4,C,36.74,Unit_3
+lon,lat,taxonomy,BUILDINGS,ID_1,DWELLINGS,TOTAL_REPL_COST_EUR,COST_STRUCTURAL_EUR,COST_NONSTRUCTURAL_EUR,COST_CONTENTS_EUR,OCCUPANTS_PER_ASSET,OCCUPANTS_PER_ASSET_DAY,OCCUPANTS_PER_ASSET_NIGHT,OCCUPANTS_PER_ASSET_TRANSIT,OCCUPANTS_PER_ASSET_AVERAGE
+20.6,46.8,A,38.72,Unit_1,116.16,174240000,87120000,52272000,34848000,290.4,43.56,203.28,58.08,101.64
+20.6,46.8,B,13.97,Unit_1,41.91,62865000,31432500,18859500,12573000,104.775,15.71625,73.3425,20.955,36.67125
+20.6,46.8,B,9.79,Unit_1,29.37,44055000,22027500,13216500,8811000,73.425,11.01375,51.3975,14.685,25.69875
+20.6,46.8,C,6.27,Unit_1,18.81,28215000,14107500,8464500,5643000,47.025,7.05375,32.9175,9.405,16.45875
+20.3,46.9,A,28.16,Unit_2,84.48,126720000,63360000,38016000,25344000,211.2,31.68,147.84,42.24,73.92
+20.3,46.9,C,8.69,Unit_2,26.07,39105000,19552500,11731500,7821000,65.175,9.77625,45.6225,13.035,22.81125
+20.3,46.9,C,25.85,Unit_2,77.55,116325000,58162500,34897500,23265000,193.875,29.08125,135.7125,38.775,67.85625
+20.9,46.4,A,44.22,Unit_3,132.66,198990000,99495000,59697000,39798000,331.65,49.7475,232.155,66.33,116.0775
+20.9,46.4,B,17.93,Unit_3,53.79,80685000,40342500,24205500,16137000,134.475,20.17125,94.1325,26.895,47.06625
+20.9,46.4,C,36.74,Unit_3,110.22,165330000,82665000,49599000,33066000,275.55,41.3325,192.885,55.11,96.4425

tests/data/expected_results_test_ExposureModelESRM20.csv

+Col_0,Col_1,Col_2,Col_3,Col_4,Col_5,Col_6,Col_7,Col_8,Col_9,Col_10,Col_11,Col_12,Col_13
+entity_names,occupancy_names,Data_Unit_ID,total_buildings,total_dwellings,total_people,total_people,total_people,total_people,total_people,total_cost,total_cost,total_cost,total_cost
+entity_names,occupancy_names,Data_Unit_ID,total_buildings,total_dwellings,Census,Day,Night,Transit,Average,Total,Structural,Non-Structural,Contents
+Entity_1,residential,Unit_1,62.5,187.5,468.75,70.3125,328.125,93.75,164.0625,281250000,140625000,84375000,56250000
+Entity_1,residential,Unit_2,57,171,427.5,64.125,299.25,85.5,149.625,256500000,128250000,76950000,51300000
+Entity_1,residential,Unit_3,89.9,269.7,674.25,101.1375,471.975,134.85,235.9875,404550000,202275000,121365000,80910000
+Entity_1,commercial,Unit_X,62.5,62.5,1875,1500,187.5,375,687.5,562500000,225000000,112500000,225000000
+Entity_1,commercial,Unit_Y,57,57,1710,1368,171,342,627,513000000,205200000,102600000,205200000
+Entity_1,commercial,Unit_Z,89.9,89.9,2697,2157.6,269.7,539.4,988.9,809100000,323640000,161820000,323640000
+Entity_2,commercial,Unit_A,68.75,68.75,2062.5,1650,206.25,412.5,756.25,618750000,247500000,123750000,247500000
+Entity_2,commercial,Unit_B,62.7,62.7,1881,1504.8,188.1,376.2,689.7,564300000,225720000,112860000,225720000
+Entity_2,commercial,Unit_C,98.89,98.89,2966.7,2373.36,296.67,593.34,1087.79,890010000,356004000,178002000,356004000

tests/test_aggregatedexposuremodel.py

@@ -200,6 +200,14 @@ def test_ExposureModelESRM20():
         sep=",",
         dtype={"LonW": str, "LonE": str, "LatN": str, "LatS": str},
     )
+    expected_results_totals = pandas.read_csv(
+        os.path.join(
+            os.path.dirname(__file__),
+            "data",
+            "expected_results_test_ExposureModelESRM20.csv",
+        ),
+        sep=",",
+    )
 
     for i in range(len(entity_names)):
         # Check number of data units
@@ -208,6 +216,7 @@ def test_ExposureModelESRM20():
             .occupancy_cases[occupancy_names[i]]["data_units"]
             .keys()
         ) == len(unit_ids[i])
+
         # Check names of data units
         for unit_id in unit_ids[i]:
             assert (
@@ -216,6 +225,7 @@ def test_ExposureModelESRM20():
                     occupancy_names[i]
                 ]["data_units"]
             )
+
         # Check bounds of the geometries of data units
         for unit_id in unit_ids[i]:
             geometry = (
@@ -236,6 +246,56 @@ def test_ExposureModelESRM20():
             assert "{:.2f}".format(returned_lat_n) == expected_lat_n
             assert "{:.2f}".format(returned_lat_s) == expected_lat_s
 
+        # Rows of expected_results_totals associated with this entity and occupancy
+        rows_entity_occupancy = numpy.where(
+            numpy.logical_and(
+                expected_results_totals["Col_0"].values == entity_names[i],
+                expected_results_totals["Col_1"].values == occupancy_names[i],
+            )
+        )[0]
+
+        # Check total numbers of buildings, dwellings, people and costs per data unit
+        for unit_id in unit_ids[i]:
+            returned_data_unit = returned_aem.exposure_entities[
+                entity_names[i]
+            ].occupancy_cases[occupancy_names[i]]["data_units"][unit_id]
+
+            # Row of expected_results_totals associated with this data-unit ID
+            # (within rows_entity_occupancy)
+            row_data_unit = numpy.where(
+                expected_results_totals["Col_2"].values[rows_entity_occupancy] == unit_id
+            )[0][0]
+
+            for col_pos, col_name in enumerate(expected_results_totals.columns):
+                if col_name == "Col_0" or col_name == "Col_1" or col_name == "Col_2":
+                    continue
+                # pylint: disable=unsubscriptable-object
+                attr_name = expected_results_totals[col_name].values[0]
+                returned_attr_val = getattr(returned_data_unit, attr_name)
+
+                if isinstance(returned_attr_val, float):
+                    difference_returned_expected = abs(
+                        returned_attr_val
+                        - float(
+                            expected_results_totals[col_name].values[rows_entity_occupancy][
+                                row_data_unit
+                            ]
+                        )
+                    )
+
+                if isinstance(returned_attr_val, dict):
+                    sub_attr_name = expected_results_totals[col_name].values[1]
+                    difference_returned_expected = abs(
+                        returned_attr_val[sub_attr_name]
+                        - float(
+                            expected_results_totals[col_name].values[rows_entity_occupancy][
+                                row_data_unit
+                            ]
+                        )
+                    )
+
+                assert difference_returned_expected < 1e-5
+
     assert (
         "data_units"
         not in returned_aem.exposure_entities["Entity_1"].occupancy_cases["industrial"]

tests/test_dataunit.py

@@ -19,6 +19,7 @@
 import logging
 import geopandas
 import shapely
+import pytest
 from pyproj import CRS
 from gdeimporter.dataunit import DataUnit
 
@@ -34,16 +35,72 @@ def test_DataUnit():
         shapely.geometry.Polygon([(22.5, 13.7), (28.3, 14.2), (25.1, 16.7)]),
     ]
     geometry = geopandas.GeoSeries(geometries)
+    total_buildings = [1500.0, 740.6]
+    total_dwellings = [3000.0, 1851.5]
+    currency = "EUR"
     aux_data = {target_column_name: unit_ids, "geometry": geometry}
     geometries_table = geopandas.GeoDataFrame(aux_data)
     geometries_table.crs = CRS("epsg:4326")
 
     for i in range(len(unit_ids)):
-        returned_data_unit = DataUnit(unit_ids[i], geometries_table, target_column_name)
+        returned_data_unit = DataUnit(
+            unit_ids[i],
+            geometries_table,
+            target_column_name,
+            total_buildings=total_buildings[i],
+            total_dwellings=total_dwellings[i],
+            currency=currency,
+        )
         assert returned_data_unit.id == unit_ids[i]
         assert returned_data_unit.geometry == geometries[i]
+        assert returned_data_unit.total_buildings == total_buildings[i]
+        assert returned_data_unit.total_dwellings == total_dwellings[i]
+        assert returned_data_unit.currency == currency
 
     # Test case in which the ID is not found
     returned_data_unit = DataUnit("something", geometries_table, target_column_name)
     assert returned_data_unit.id == "something"
     assert returned_data_unit.geometry is None