adapt to new defaults

Author: ValentinGebhart

CHANGELOG.md

@@ -40,7 +40,7 @@ Removed:
 - `Exposures.write_hdf5` pickles geometry data in WKB format, which is faster and more sustainable. [#1051](https://github.com/CLIMADA-project/climada_python/pull/1051)
 - The online documentation has been completely overhauled, now uses PyData theme: [#977](https://github.com/CLIMADA-project/climada_python/pull/977)
 - Add `climada.hazard.xarray` module with helper structures for reading Hazard objects from `xarray` data [#1063](https://github.com/CLIMADA-project/climada_python/pull/1063)
-- The output of the `impact_yearset` was changed to only contain attributes corresponding to the yearly impact set. The default parameters of `impact_yearset`, `sample_events`, and `impact_yearset_from_sampling_vect` functions of the `climada.util.yearsets` module have been changed to sampling with replacement and not applying the correction factor to the impact yearsets. The application of the correction factor and the frequency of the resulting yearly impact object are corrected. [#1075](https://github.com/CLIMADA-project/climada_python/pull/1075)
+- The output of the `impact_yearset` was changed to only contain attributes corresponding to the yearly impact set. The application of the correction factor and the frequency of the resulting yearly impact object are corrected. [#1075](https://github.com/CLIMADA-project/climada_python/pull/1075)
 
 ### Fixed
 

climada/util/yearsets.py

@@ -25,7 +25,7 @@
 
 
 def impact_yearset(
-    imp, sampled_years, lam=None, correction_fac=False, with_replacement=True, seed=None
+    imp, sampled_years, lam=None, correction_fac=True, with_replacement=False, seed=None
 ):
     """Create a yearset of impacts (yimp) containing a probabilistic impact for each year
     in the sampled_years list by sampling events from the impact received as input with a
@@ -45,13 +45,13 @@ def impact_yearset(
             events per year. If no lambda value is given, the default lam = sum(imp.frequency)
             is used. Default is None.
         correction_fac : boolean, optional
-            If True a correction factor is applied to the resulting yimp. It is
+            If True, a correction factor is applied to the resulting yimp. It is
             scaled in such a way that the expected annual impact (eai) of the yimp
-            equals the eai of the input impact. Defaults to False.
+            equals the eai of the input impact. Defaults to True.
         with_replacement : bool, optional
             If True, impact events are sampled with replacement. If False, events are sampled
             without replacement. Sampling without replacement can yield distorted samples if
-            frequencies of different events are unqual. Defaults to True.
+            frequencies of different events are unqual. Defaults to False.
         seed : Any, optional
             seed for the default bit generator
             default: None
@@ -86,7 +86,7 @@ def impact_yearset(
 
 
 def impact_yearset_from_sampling_vect(
-    imp, sampled_years, sampling_vect, correction_fac=False
+    imp, sampled_years, sampling_vect, correction_fac=True
 ):
     """Create a yearset of impacts (yimp) containing a probabilistic impact for each year
     in the sampled_years list by sampling events from the impact received as input following
@@ -112,7 +112,7 @@ def impact_yearset_from_sampling_vect(
         correction_fac : boolean, optional
             If True a correction factor is applied to the resulting yimp. It is
             scaled in such a way that the expected annual impact (eai) of the yimp
-            equals the eai of the input impact. Defaults to False.
+            equals the eai of the input impact. Defaults to True.
 
     Returns
     -------
@@ -170,7 +170,7 @@ def sample_from_poisson(n_sampled_years, lam, seed=None):
     return np.round(np.random.poisson(lam=lam, size=n_sampled_years)).astype("int")
 
 
-def sample_events(events_per_year, freqs_orig, with_replacement=True, seed=None):
+def sample_events(events_per_year, freqs_orig, with_replacement=False, seed=None):
     """Sample events uniformely from an array (indices_orig) without replacement
     (if sum(events_per_year) > n_input_events the input events are repeated
     (tot_n_events/n_input_events) times, by ensuring that the same events doens't
@@ -185,7 +185,7 @@ def sample_events(events_per_year, freqs_orig, with_replacement=True, seed=None)
         with_replacement : bool, optional
             If True, impact events are sampled with replacement. If False, events are sampled
             without replacement. Sampling without replacement can yield distorted samples if
-            frequencies of different events are unqual. Defaults to True.
+            frequencies of different events are unqual. Defaults to False.
         seed : Any, optional
             seed for the default bit generator.
             Default: None
@@ -209,7 +209,7 @@ def sample_events(events_per_year, freqs_orig, with_replacement=True, seed=None)
             LOGGER.warning(
                 "The frequencies of the different events are not equal. This can lead to "
                 "distorted sampling if the frequencies vary significantly. To avoid this, "
-                "please set with_replacement=True to sample with replacement instead."
+                "please set `with_replacement=True` to sample with replacement instead."
             )
 
         indices = indices_orig
@@ -226,7 +226,7 @@ def sample_events(events_per_year, freqs_orig, with_replacement=True, seed=None)
                 )
 
             # if not enough events remaining, append original events
-            if len(indices) < amount_events or len(indices) == 0:
+            if len(np.unique(indices)) < amount_events or len(indices) == 0:
                 indices = np.append(indices, indices_orig)
                 freqs = np.append(freqs, freqs_orig)
 

doc/user-guide/climada_util_yearsets.ipynb

@@ -11,9 +11,9 @@
     "The function `impact_yearset` performs all these computational steps, taking an `imp` and the list of sampled_years (`sampled_years`) as input. The output of the function is the `yimp` object and the `sampling_vect`.\n",
     "Moreover, a `sampling_vect` (generated in a previous run) can be provided as optional input and the user can custom-define the Poisson parameter `lam`. Reapplying the same sampling_vect does not only allow to reproduce the generated `yimp`, but also for a physically consistent way of sampling impacts caused by different hazards. \n",
     "\n",
-    "*Sampling options.* Per default, impact events are sampled with replacement. When setting `with_replacement=False`, the impact events are sampled without replacement (given that the original impact object contains enough events). Note that sampling without replacement can lead to distorted sampling if the frequencies of the different impacts (`imp.frequency`) are not equal.\n",
+    "*Sampling options.* Per default, impact events are sampled without replacement (given that the original impact object contains enough events). When setting `with_replacement=True`, the impact events are sampled with replacement . Note that sampling without replacement can lead to distorted sampling if the frequencies of the different impacts (`imp.frequency`) are not equal.\n",
     "\n",
-    "*Correction factor.* By setting `correction_fac=False`, a correction factor is applied uniformly to all yearly impacts, such that the final `yimp` object has the same average annual impact than `imp`, the original impact object.\n",
+    "*Correction factor.* By default, a correction factor is applied uniformly to all yearly impacts, such that the final `yimp` object has the same average annual impact than `imp`, the original impact object. Applying the correction factor can be avoided by setting `correction_fac=False`.\n",
     "\n"
    ]
   },
@@ -64,7 +64,7 @@
     {
      "data": {
       "text/plain": [
-       "array([1, 2, 1, 0, 1, 0, 0, 2, 1, 2])"
+       "array([0, 1, 1, 0, 2, 3, 3, 0, 2, 3])"
       ]
      },
      "execution_count": 2,
@@ -90,16 +90,16 @@
     {
      "data": {
       "text/plain": [
-       "[array([2]),\n",
-       " array([1, 0]),\n",
-       " array([2]),\n",
+       "[array([], dtype=int64),\n",
+       " array([0]),\n",
+       " array([1]),\n",
        " array([], dtype=int64),\n",
-       " array([2]),\n",
+       " array([4, 2]),\n",
+       " array([2, 0, 4]),\n",
+       " array([5, 1, 3]),\n",
        " array([], dtype=int64),\n",
-       " array([], dtype=int64),\n",
-       " array([1, 4]),\n",
-       " array([2]),\n",
-       " array([4, 4])]"
+       " array([5, 3]),\n",
+       " array([5, 3, 1])]"
       ]
      },
      "execution_count": 3,
@@ -121,7 +121,7 @@
     {
      "data": {
       "text/plain": [
-       "array([  4,   2,   4,   0,   4,   0,   0,  62,   4, 120])"
+       "array([ 0,  0,  2,  0, 64, 64, 70,  0, 68, 70])"
       ]
      },
      "execution_count": 4,
@@ -143,7 +143,7 @@
     {
      "data": {
       "text/plain": [
-       "1.34"
+       "0.7928994082840237"
       ]
      },
      "execution_count": 5,
@@ -180,9 +180,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "yimp.at_event =  [  2   0   0 122  14   0   0 246   4 124]\n",
-      "imp_per_year =  [  2   0   0 122  14   0   0 246   4 124]\n",
-      "The expected annual impact 51.2 differs from the one of the original impact (26.8).\n"
+      "yimp.at_event =  [  2   0   0  70 130   0   0 128  68  62]\n",
+      "imp_per_year =  [  2   0   0  70 130   0   0 128  68  62]\n",
+      "The expected annual impact 46.0 differs from the one of the original impact (26.8).\n"
      ]
     }
    ],
@@ -228,9 +228,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2025-07-22 17:10:20,134 - climada.util.yearsets - INFO - The correction factor is 0.5234375.\n",
-      "yimp.at_event =  [  1.05   0.     0.    63.86   7.33   0.     0.   128.77   2.09  64.91]\n",
-      "imp_per_year =  [  1.05   0.     0.    63.86   7.33   0.     0.   128.77   2.09  64.91]\n",
+      "2025-09-19 15:39:54,743 - climada.util.yearsets - INFO - The correction factor is 0.5826086956521739.\n",
+      "yimp.at_event =  [ 1.17  0.    0.   40.78 75.74  0.    0.   74.57 39.62 36.12]\n",
+      "imp_per_year =  [ 1.17  0.    0.   40.78 75.74  0.    0.   74.57 39.62 36.12]\n",
       "The expected annual impact 26.8 is equal to the one of the original impact (26.8).\n"
      ]
     }
@@ -241,7 +241,7 @@
     "    imp, sampled_years, correction_fac=True, seed=example_seed\n",
     ")\n",
     "\n",
-    "# compute correction factor\n",
+    "# compute correction factor from imp_per_year computed above without correction factor\n",
     "correction_factor = yearsets.calculate_correction_fac(imp_per_year, imp)\n",
     "\n",
     "print(\"yimp.at_event = \", np.round(yimp.at_event, 2))\n",