Feature/reassign centr bydflt

climada/engine/forecast.py

@@ -297,7 +297,7 @@ def calc(self, force_reassign=False):
             if force_reassign:
                 self.exposure.assign_centroids(haz_i)
             self._impact[ind_i].calc(
-                self.exposure, self.vulnerability, haz_i, save_mat=True
+                self.exposure, self.vulnerability, haz_i, save_mat=True, reassign_centroids=False
             )
 
     def plot_imp_map(

climada/engine/impact.py

@@ -184,7 +184,7 @@ def __init__(self,
 
 
 
-    def calc(self, exposures, impact_funcs, hazard, save_mat=False):
+    def calc(self, exposures, impact_funcs, hazard, save_mat=False, reassign_centroids=True):
         """This function is deprecated, use ImpactCalc.impact
         and ImpactCalc.insured_impact instead.
         """
@@ -198,11 +198,11 @@ def calc(self, exposures, impact_funcs, hazard, save_mat=False):
                 " for insured impacts instead. For non-insured impacts "
                 "please use ImpactCalc().impact()"
                 )
-            self.__dict__ = impcalc.insured_impact(save_mat).__dict__
+            self.__dict__ = impcalc.insured_impact(save_mat, reassign_centroids).__dict__
         else:
             LOGGER.warning("The use of Impact().calc() is deprecated. "
                            "Use ImpactCalc().impact() instead.")
-            self.__dict__ = impcalc.impact(save_mat).__dict__
+            self.__dict__ = impcalc.impact(save_mat, reassign_centroids).__dict__
 
 #TODO: new name
     @classmethod
@@ -1029,7 +1029,7 @@ def video_direct_impact(exp, impf_set, haz_list, file_name='',
         imp_arr = np.zeros(len(exp.gdf))
         for i_time, _ in enumerate(haz_list):
             imp_tmp = Impact()
-            imp_tmp.calc(exp, impf_set, haz_list[i_time])
+            imp_tmp.calc(exp, impf_set, haz_list[i_time], reassign_centroids=False)
             imp_arr = np.maximum(imp_arr, imp_tmp.eai_exp)
             # remove not impacted exposures
             save_exp = imp_arr > imp_thresh

climada/engine/impact_calc.py

@@ -61,7 +61,8 @@ def __init__(self,
         self.exposures = exposures
         self.impfset = impfset
         self.hazard = hazard
-        self._orig_exp_idx = np.arange(self.exposures.gdf.shape[0]) #exposures index to use for matrix reconstruction
+        # exposures index to use for matrix reconstruction
+        self._orig_exp_idx = np.arange(self.exposures.gdf.shape[0])
 
     @property
     def n_exp_pnt(self):
@@ -101,13 +102,20 @@ def cover(self):
         if 'cover' in self.exposures.gdf.columns:
             return self.exposures.gdf['cover'].to_numpy()
 
-    def impact(self, save_mat=True):
+    def impact(self, save_mat=True, reassign_centroids=True):
         """Compute the impact of a hazard on exposures.
 
         Parameters
         ----------
-        save_mat : bool
+        save_mat : bool, optional
             if true, save the total impact matrix (events x exposures)
+            Default: True
+        reassign_centroids : bool, optional
+            indicates whether centroids are re-assigned to the self.exposures object
+            or kept from previous impact calculation with a hazard of the same hazard type.
+            Centroids assignment is an expensive operation, set this to true if you know that
+            the centroids are the same between two impact calculations.
+            Default: True
 
         Examples
         --------
@@ -126,7 +134,7 @@ def impact(self, save_mat=True):
         the column is added to the exposures geodataframe.
         """
         impf_col = self.exposures.get_impf_column(self.hazard.haz_type)
-        exp_gdf = self.minimal_exp_gdf(impf_col)
+        exp_gdf = self.minimal_exp_gdf(impf_col, reassign_centroids)
         if exp_gdf.size == 0:
             return self._return_empty(save_mat)
         LOGGER.info('Calculating impact for %s assets (>0) and %s events.',
@@ -136,7 +144,7 @@ def impact(self, save_mat=True):
 
 #TODO: make a better impact matrix generator for insured impacts when
 # the impact matrix is already present
-    def insured_impact(self, save_mat=False):
+    def insured_impact(self, save_mat=False, reassign_centroids=True):
         """Compute the impact of a hazard on exposures with a deductible and/or
         cover.
 
@@ -147,6 +155,12 @@ def insured_impact(self, save_mat=False):
         ----------
         save_mat : bool
             if true, save the total impact matrix (events x exposures)
+        reassign_centroids : bool, optional
+            indicates whether centroids are re-assigned to the self.exposures object
+            or kept from previous impact calculation with a hazard of the same hazard type.
+            Centroids assignment is an expensive operation, set this to true if you know that
+            the centroids are the same between two impact calculations.
+            Default: True
 
         Examples
         --------
@@ -169,7 +183,7 @@ def insured_impact(self, save_mat=False):
                                  "Please set exposures.gdf.cover"
                                  "and/or exposures.gdf.deductible")
         impf_col = self.exposures.get_impf_column(self.hazard.haz_type)
-        exp_gdf = self.minimal_exp_gdf(impf_col)
+        exp_gdf = self.minimal_exp_gdf(impf_col, reassign_centroids)
         if exp_gdf.size == 0:
             return self._return_empty(save_mat)
         LOGGER.info('Calculating impact for %s assets (>0) and %s events.',
@@ -238,18 +252,22 @@ def _return_empty(self, save_mat):
         return Impact.from_eih(self.exposures, self.impfset, self.hazard,
                         at_event, eai_exp, aai_agg, imp_mat)
 
-    def minimal_exp_gdf(self, impf_col):
+    def minimal_exp_gdf(self, impf_col, reassign_centroids):
         """Get minimal exposures geodataframe for impact computation
 
         Parameters
         ----------
         exposures : climada.entity.Exposures
         hazard : climada.Hazard
-        impf_col: str
-            name of the impact function column in exposures.gdf
-
-        """
-        self.exposures.assign_centroids(self.hazard, overwrite=False)
+        impf_col : str
+            Name of the impact function column in exposures.gdf
+        reassign_centroids : bool
+            Indicates whether centroids are re-assigned to the self.exposures object
+            or kept from previous impact calculation with a hazard of the same hazard type.
+            Centroids assignment is an expensive operation, set this to true if you know that
+            the centroids are the same between two impact calculations.
+        """
+        self.exposures.assign_centroids(self.hazard, overwrite=reassign_centroids)
         mask = (
             (self.exposures.gdf.value.values != 0)
             & (self.exposures.gdf[self.hazard.centr_exp_col].values >= 0)
@@ -260,7 +278,8 @@ def minimal_exp_gdf(self, impf_col):
             )
         if exp_gdf.size == 0:
             LOGGER.warning("No exposures with value >0 in the vicinity of the hazard.")
-        self._orig_exp_idx = mask.nonzero()[0]  #update index of kept exposures points in exp_gdf within the full exposures
+        self._orig_exp_idx = mask.nonzero()[0]  # update index of kept exposures points in exp_gdf
+                                                # within the full exposures
         return exp_gdf
 
     def imp_mat_gen(self, exp_gdf, impf_col):
@@ -381,10 +400,11 @@ def impact_matrix(self, exp_values, cent_idx, impf):
         scipy.sparse.csr_matrix
             Impact per event (rows) per exposure point (columns)
         """
-        n_exp_pnt = len(cent_idx) #implicitly checks in matrix assignement whether len(cent_idx) == len(exp_values)
+        n_exp_pnt = len(cent_idx)  # implicitly checks in matrix assignement whether
+                                   # len(cent_idx) == len(exp_values)
         mdr = self.hazard.get_mdr(cent_idx, impf)
         fract = self.hazard.get_fraction(cent_idx)
-        exp_values_csr = sparse.csr_matrix( #vector 1 x exp_size
+        exp_values_csr = sparse.csr_matrix(  # vector 1 x exp_size
             (exp_values, np.arange(n_exp_pnt), [0, n_exp_pnt]),
             shape=(1, n_exp_pnt))
         return fract.multiply(mdr).multiply(exp_values_csr)
@@ -393,7 +413,9 @@ def stitch_impact_matrix(self, imp_mat_gen):
         """
         Make an impact matrix from an impact sub-matrix generator
         """
-        data, row, col = np.hstack([  #rows=events index, cols=exposure point index within self.exposures
+        # rows: events index
+        # cols: exposure point index within self.exposures
+        data, row, col = np.hstack([
             (mat.data, mat.nonzero()[0], self._orig_exp_idx[idx][mat.nonzero()[1]])
             for mat, idx in imp_mat_gen
             ])

climada/engine/test/test_cost_benefit.py

@@ -820,7 +820,7 @@ def test_impact(self):
         hazard = Hazard.from_mat(HAZ_TEST_MAT)
         impact = Impact()
         ent.exposures.assign_centroids(hazard)
-        impact.calc(ent.exposures, ent.impact_funcs, hazard)
+        impact.calc(ent.exposures, ent.impact_funcs, hazard, reassign_centroids=False)
         return impact
 
     def test_risk_aai_agg_pass(self):

climada/engine/test/test_impact.py

@@ -298,7 +298,7 @@ def test_excel_io(self):
 
         imp_write = Impact()
         ent.exposures.assign_centroids(hazard)
-        imp_write.calc(ent.exposures, ent.impact_funcs, hazard)
+        imp_write.calc(ent.exposures, ent.impact_funcs, hazard, reassign_centroids=False)
         file_name = DATA_FOLDER.joinpath('test.xlsx')
         imp_write.write_excel(file_name)
 
@@ -351,7 +351,7 @@ def test_local_exceedance_imp_pass(self):
         # Assign centroids to exposures
         ent.exposures.assign_centroids(hazard)
         # Compute the impact over the whole exposures
-        impact.calc(ent.exposures, ent.impact_funcs, hazard, save_mat=True)
+        impact.calc(ent.exposures, ent.impact_funcs, hazard, save_mat=True, reassign_centroids=False)
         # Compute the impact per return period over the whole exposures
         impact_rp = impact.local_exceedance_imp(return_periods=(10, 40))
 
@@ -561,7 +561,7 @@ def test_select_event_identity_pass(self):
         ent.exposures.assign_centroids(hazard)
 
         # Compute the impact over the whole exposures
-        imp.calc(ent.exposures, ent.impact_funcs, hazard, save_mat=True)
+        imp.calc(ent.exposures, ent.impact_funcs, hazard, save_mat=True, reassign_centroids=False)
 
         sel_imp = imp.select(event_ids=imp.event_id,
                              event_names=imp.event_name,

climada/engine/test/test_impact_calc.py

@@ -133,7 +133,7 @@ def test_calc_impact_TC_pass(self):
         HAZf = deepcopy(HAZ)
         HAZf.fraction *= 0.6
         icalc = ImpactCalc(ENT.exposures, ENT.impact_funcs, HAZf)
-        impact = icalc.impact()
+        impact = icalc.impact(reassign_centroids=False)
         self.assertEqual(icalc.n_events, len(impact.at_event))
         self.assertEqual(0, impact.at_event[0])
         self.assertEqual(0, impact.at_event[7225])
@@ -152,7 +152,7 @@ def test_calc_impact_RF_pass(self):
         exp = Exposures.from_hdf5(get_test_file('test_exposure_US_flood_random_locations'))
         impf_set = ImpactFuncSet.from_excel(Path(__file__).parent / 'data' / 'flood_imp_func_set.xls')
         icalc = ImpactCalc(exp, impf_set, haz)
-        impact = icalc.impact()
+        impact = icalc.impact(reassign_centroids=False)
         aai_agg = 161436.05112960344
         eai_exp = np.array([
             1.61159701e+05, 1.33742847e+02, 0.00000000e+00, 4.21352988e-01,
@@ -181,17 +181,17 @@ def test_calc_impact_RF_pass(self):
         check_impact(self, impact, haz, exp, aai_agg, eai_exp, at_event, imp_mat_array)
 
     def test_empty_impact(self):
-        """Check that empty impact is returned if no centroids matching the exposures"""
+        """Check that empty impact is returned if no centroids match the exposures"""
         exp = ENT.exposures.copy()
         exp.gdf['centr_TC'] = -1
         icalc = ImpactCalc(exp, ENT.impact_funcs, HAZ)
-        impact = icalc.impact()
+        impact = icalc.impact(reassign_centroids=False)
         aai_agg = 0.0
         eai_exp = np.zeros(len(exp.gdf))
         at_event = np.zeros(HAZ.size)
         check_impact(self, impact, HAZ, exp, aai_agg, eai_exp, at_event, None)
 
-        impact = icalc.impact(save_mat=True)
+        impact = icalc.impact(save_mat=True, reassign_centroids=False)
         imp_mat_array = sparse.csr_matrix((HAZ.size, len(exp.gdf))).toarray()
         check_impact(self, impact, HAZ, exp, aai_agg, eai_exp, at_event, imp_mat_array)
 
@@ -204,7 +204,7 @@ def test_single_event_impact(self):
         eai_exp = np.zeros(len(ENT.exposures.gdf))
         at_event = np.array([0])
         check_impact(self, impact, haz, ENT.exposures, aai_agg, eai_exp, at_event, None)
-        impact = icalc.impact(save_mat=True)
+        impact = icalc.impact(save_mat=True, reassign_centroids=False)
         imp_mat_array = sparse.csr_matrix((haz.size, len(ENT.exposures.gdf))).toarray()
         check_impact(self, impact, haz, ENT.exposures, aai_agg, eai_exp, at_event, imp_mat_array)
 
@@ -299,7 +299,7 @@ def test_calc_insured_impact_fail(self):
     def test_minimal_exp_gdf(self):
         """Test obtain minimal exposures gdf"""
         icalc = ImpactCalc(ENT.exposures, ENT.impact_funcs, HAZ)
-        exp_min_gdf = icalc.minimal_exp_gdf('impf_TC')
+        exp_min_gdf = icalc.minimal_exp_gdf('impf_TC', False)
         self.assertSetEqual(
             set(exp_min_gdf.columns), set(['value', 'impf_TC', 'centr_TC'])
             )

climada/entity/exposures/base.py

@@ -417,7 +417,7 @@ def assign_centroids(self, hazard, distance='euclidean',
             if overwrite:
                 LOGGER.info('Existing centroids will be overwritten for %s', haz_type)
             else:
-                return None
+                return
 
         LOGGER.info('Matching %s exposures with %s centroids.',
                     str(self.gdf.shape[0]), str(hazard.centroids.size))

climada/test/test_calibration.py

@@ -18,6 +18,7 @@
 
 Test Calibration class.
 """
+import re
 import unittest
 from pathlib import Path
 import pandas as pd
@@ -69,7 +70,7 @@ def test_calib_instance(self):
                                        yearly_impact=True)
         # calc Impact as comparison
         impact = Impact()
-        impact.calc(ent.exposures, ent.impact_funcs, hazard)
+        impact.calc(ent.exposures, ent.impact_funcs, hazard, reassign_centroids=False)
         IYS = impact.calc_impact_year_set(all_years=True)
 
         # do the tests

climada/util/lines_polys_handler.py

@@ -124,7 +124,7 @@ def calc_geom_impact(
 
     # compute point impact
     impact_pnt = Impact()
-    impact_pnt.calc(exp_pnt, impf_set, haz, save_mat=True)
+    impact_pnt.calc(exp_pnt, impf_set, haz, save_mat=True, reassign_centroids=False)
 
     # re-aggregate impact to original exposure geometry
     impact_agg = impact_pnt_agg(impact_pnt, exp_pnt.gdf, agg_met)
@@ -295,7 +295,7 @@ def calc_grid_impact(
 
     # compute point impact
     impact_pnt = Impact()
-    impact_pnt.calc(exp_pnt, impf_set, haz, save_mat=True)
+    impact_pnt.calc(exp_pnt, impf_set, haz, save_mat=True, reassign_centroids=False)
 
     # re-aggregate impact to original exposure geometry
     impact_agg = impact_pnt_agg(impact_pnt, exp_pnt.gdf, agg_met)