Merge branch 'develop' into cross-calibrate-impact-functions

Author: emanuel-schmid

CHANGELOG.md

@@ -15,18 +15,27 @@ Removed:
 - `pandas-datareader`
 
 ### Added
+- Added optional parameter to `geo_im_from_array`, `plot_from_gdf`, `plot_rp_imp`, `plot_rp_intensity`,
+`plot_intensity`, `plot_fraction`, `_event_plot` to mask plotting when regions are too far from data points [#1047](https://github.com/CLIMADA-project/climada_python/pull/1047). To recreate previous plots (no masking), the parameter can be set to None.
 - Added instructions to install Climada petals on Euler cluster in `doc.guide.Guide_Euler.ipynb` [#1029](https://github.com/CLIMADA-project/climada_python/pull/1029)
 
+- `ImpactFunc` and `ImpactFuncSet` now support equality comparisons via `==` [#1027](https://github.com/CLIMADA-project/climada_python/pull/1027)
+
 ### Changed
+
 - `Hazard.local_exceedance_intensity`, `Hazard.local_return_period` and `Impact.local_exceedance_impact`, `Impact.local_return_period`, using the `climada.util.interpolation` module: New default (no binning), binning on decimals, and faster implementation [#1012](https://github.com/CLIMADA-project/climada_python/pull/1012)
 - World Bank indicator data is now downloaded directly from their API via the function `download_world_bank_indicator`, instead of relying on the `pandas-datareader` package [#1033](https://github.com/CLIMADA-project/climada_python/pull/1033)
+- `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)
 
 ### Fixed
+
 - NaN plotting issues in `geo_im_from_array`[#1038](https://github.com/CLIMADA-project/climada_python/pull/1038)
+- Broken ECMWF links in pydoc of `climada.hazard.storm_europe` relocated. [#944](https://github.com/CLIMADA-project/climada_python/pull/944)
 
 ### Deprecated
 
 ### Removed
+
 - `climada.util.interpolation.round_to_sig_digits` [#1012](https://github.com/CLIMADA-project/climada_python/pull/1012)
 
 ## 6.0.1

climada/engine/impact.py

@@ -1178,6 +1178,7 @@ def plot_rp_imp(
         return_periods=(25, 50, 100, 250),
         log10_scale=True,
         axis=None,
+        mask_distance=0.01,
         kwargs_local_exceedance_impact=None,
         **kwargs,
     ):
@@ -1194,6 +1195,11 @@ def plot_rp_imp(
             plot impact as log10(impact). Default: True
         smooth : bool, optional
             smooth plot to plot.RESOLUTIONxplot.RESOLUTION. Default: True
+        mask_distance: float, optional
+            Only regions are plotted that are closer to any of the data points than this distance,
+            relative to overall plot size. For instance, to only plot values
+            at the centroids, use mask_distance=0.01. If None, the plot is not masked.
+            Default is 0.01.
         kwargs_local_exceedance_impact: dict
             Dictionary of keyword arguments for the method impact.local_exceedance_impact.
         kwargs : dict, optional
@@ -1242,7 +1248,12 @@ def plot_rp_imp(
             )
 
         axis = u_plot.plot_from_gdf(
-            impacts_stats, title, column_labels, axis=axis, **kwargs
+            impacts_stats,
+            title,
+            column_labels,
+            axis=axis,
+            mask_distance=mask_distance,
+            **kwargs,
         )
         return axis, impacts_stats_vals
 

climada/entity/exposures/base.py

@@ -29,6 +29,7 @@
 
 import cartopy.crs as ccrs
 import contextily as ctx
+import geopandas as gpd
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
@@ -1131,10 +1132,8 @@ def write_hdf5(self, file_name):
         """
         LOGGER.info("Writing %s", file_name)
         store = pd.HDFStore(file_name, mode="w")
-        pandas_df = pd.DataFrame(self.gdf)
-        for col in pandas_df.columns:
-            if str(pandas_df[col].dtype) == "geometry":
-                pandas_df[col] = np.asarray(self.gdf[col])
+        geocols = self.data.columns[self.data.dtypes == "geometry"].to_list()
+        pandas_df = self.data.to_wkb()
 
         # Avoid pandas PerformanceWarning when writing HDF5 data
         with warnings.catch_warnings():
@@ -1146,6 +1145,7 @@ def write_hdf5(self, file_name):
         for var in type(self)._metadata:
             var_meta[var] = getattr(self, var)
         var_meta["crs"] = self.crs
+        var_meta["wkb_columns"] = geocols
         store.get_storer("exposures").attrs.metadata = var_meta
 
         store.close()
@@ -1184,7 +1184,15 @@ def from_hdf5(cls, file_name):
             crs = metadata.get("crs", metadata.get("_crs"))
             if crs is None and metadata.get("meta"):
                 crs = metadata["meta"].get("crs")
-            exp = cls(store["exposures"], crs=crs)
+            data = pd.DataFrame(store["exposures"])
+
+            wkb_columns = (
+                metadata.pop("wkb_columns") if "wkb_columns" in metadata else []
+            )
+            for col in wkb_columns:
+                data[col] = gpd.GeoSeries.from_wkb(data[col])
+
+            exp = cls(data, crs=crs)
             for key, val in metadata.items():
                 if key in type(exp)._metadata:  # pylint: disable=protected-access
                     setattr(exp, key, val)

climada/entity/exposures/test/test_base.py

@@ -378,11 +378,14 @@ def test_read_template_pass(self):
 
     def test_io_hdf5_pass(self):
         """write and read hdf5"""
-        exp_df = Exposures(pd.read_excel(ENT_TEMPLATE_XLS), crs="epsg:32632")
-        exp_df.check()
+        exp = Exposures(pd.read_excel(ENT_TEMPLATE_XLS), crs="epsg:32632")
+
         # set metadata
-        exp_df.ref_year = 2020
-        exp_df.value_unit = "XSD"
+        exp.ref_year = 2020
+        exp.value_unit = "XSD"
+
+        # add another geometry column
+        exp.data["geocol2"] = exp.data.geometry.copy(deep=True)
 
         file_name = DATA_DIR.joinpath("test_hdf5_exp.h5")
 
@@ -392,46 +395,51 @@ def test_io_hdf5_pass(self):
 
         with warnings.catch_warnings():
             warnings.simplefilter("error", category=pd.errors.PerformanceWarning)
-            exp_df.write_hdf5(file_name)
+            exp.write_hdf5(file_name=file_name)
 
         exp_read = Exposures.from_hdf5(file_name)
 
-        self.assertEqual(exp_df.ref_year, exp_read.ref_year)
-        self.assertEqual(exp_df.value_unit, exp_read.value_unit)
-        self.assertEqual(exp_df.description, exp_read.description)
-        np.testing.assert_array_equal(exp_df.latitude, exp_read.latitude)
-        np.testing.assert_array_equal(exp_df.longitude, exp_read.longitude)
-        np.testing.assert_array_equal(exp_df.value, exp_read.value)
+        self.assertEqual(exp.ref_year, exp_read.ref_year)
+        self.assertEqual(exp.value_unit, exp_read.value_unit)
+        self.assertEqual(exp.description, exp_read.description)
+        np.testing.assert_array_equal(exp.latitude, exp_read.latitude)
+        np.testing.assert_array_equal(exp.longitude, exp_read.longitude)
+        np.testing.assert_array_equal(exp.value, exp_read.value)
         np.testing.assert_array_equal(
-            exp_df.data["deductible"].values, exp_read.data["deductible"].values
+            exp.data["deductible"].values, exp_read.data["deductible"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["cover"].values, exp_read.data["cover"].values
+            exp.data["cover"].values, exp_read.data["cover"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["region_id"].values, exp_read.data["region_id"].values
+            exp.data["region_id"].values, exp_read.data["region_id"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["category_id"].values, exp_read.data["category_id"].values
+            exp.data["category_id"].values, exp_read.data["category_id"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["impf_TC"].values, exp_read.data["impf_TC"].values
+            exp.data["impf_TC"].values, exp_read.data["impf_TC"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["centr_TC"].values, exp_read.data["centr_TC"].values
+            exp.data["centr_TC"].values, exp_read.data["centr_TC"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["impf_FL"].values, exp_read.data["impf_FL"].values
+            exp.data["impf_FL"].values, exp_read.data["impf_FL"].values
         )
         np.testing.assert_array_equal(
-            exp_df.data["centr_FL"].values, exp_read.data["centr_FL"].values
+            exp.data["centr_FL"].values, exp_read.data["centr_FL"].values
         )
 
         self.assertTrue(
-            u_coord.equal_crs(exp_df.crs, exp_read.crs),
-            f"{exp_df.crs} and {exp_read.crs} are different",
+            u_coord.equal_crs(exp.crs, exp_read.crs),
+            f"{exp.crs} and {exp_read.crs} are different",
+        )
+        self.assertTrue(u_coord.equal_crs(exp.data.crs, exp_read.data.crs))
+
+        self.assertTrue(exp_read.data["geocol2"].dtype == "geometry")
+        np.testing.assert_array_equal(
+            exp.data["geocol2"].geometry, exp_read.data["geocol2"].values
         )
-        self.assertTrue(u_coord.equal_crs(exp_df.gdf.crs, exp_read.gdf.crs))
 
 
 class TestAddSea(unittest.TestCase):

climada/entity/impact_funcs/base.py

@@ -97,6 +97,19 @@ def __init__(
         self.mdd = mdd if mdd is not None else np.array([])
         self.paa = paa if paa is not None else np.array([])
 
+    def __eq__(self, value: object, /) -> bool:
+        if isinstance(value, ImpactFunc):
+            return (
+                self.haz_type == value.haz_type
+                and self.id == value.id
+                and self.name == value.name
+                and self.intensity_unit == value.intensity_unit
+                and np.array_equal(self.intensity, value.intensity)
+                and np.array_equal(self.mdd, value.mdd)
+                and np.array_equal(self.paa, value.paa)
+            )
+        return False
+
     def calc_mdr(self, inten: Union[float, np.ndarray]) -> np.ndarray:
         """Interpolate impact function to a given intensity.
 
@@ -177,7 +190,7 @@ def from_step_impf(
         mdd: tuple[float, float] = (0, 1),
         paa: tuple[float, float] = (1, 1),
         impf_id: int = 1,
-        **kwargs
+        **kwargs,
     ):
         """Step function type impact function.
 
@@ -218,7 +231,7 @@ def from_step_impf(
             intensity=intensity,
             mdd=mdd,
             paa=paa,
-            **kwargs
+            **kwargs,
         )
 
     def set_step_impf(self, *args, **kwargs):
@@ -238,7 +251,7 @@ def from_sigmoid_impf(
         x0: float,
         haz_type: str,
         impf_id: int = 1,
-        **kwargs
+        **kwargs,
     ):
         r"""Sigmoid type impact function hinging on three parameter.
 
@@ -287,7 +300,7 @@ def from_sigmoid_impf(
             intensity=intensity,
             paa=paa,
             mdd=mdd,
-            **kwargs
+            **kwargs,
         )
 
     def set_sigmoid_impf(self, *args, **kwargs):
@@ -308,7 +321,7 @@ def from_poly_s_shape(
         exponent: float,
         haz_type: str,
         impf_id: int = 1,
-        **kwargs
+        **kwargs,
     ):
         r"""S-shape polynomial impact function hinging on four parameter.
 

climada/entity/impact_funcs/impact_func_set.py

@@ -109,6 +109,12 @@ def __init__(self, impact_funcs: Optional[Iterable[ImpactFunc]] = None):
             for impf in impact_funcs:
                 self.append(impf)
 
+    def __eq__(self, value: object, /) -> bool:
+        if isinstance(value, ImpactFuncSet):
+            return self._data == value._data
+
+        return False
+
     def clear(self):
         """Reinitialize attributes."""
         self._data = dict()  # {hazard_type : {id:ImpactFunc}}

climada/entity/impact_funcs/test/test_base.py

@@ -26,6 +26,74 @@
 from climada.entity.impact_funcs.base import ImpactFunc
 
 
+class TestEquality(unittest.TestCase):
+    """Test equality method"""
+
+    def setUp(self):
+        self.impf1 = ImpactFunc(
+            haz_type="TC",
+            id=1,
+            intensity=np.array([1, 2, 3]),
+            mdd=np.array([0.1, 0.2, 0.3]),
+            paa=np.array([0.4, 0.5, 0.6]),
+            intensity_unit="m/s",
+            name="Test Impact",
+        )
+        self.impf2 = ImpactFunc(
+            haz_type="TC",
+            id=1,
+            intensity=np.array([1, 2, 3]),
+            mdd=np.array([0.1, 0.2, 0.3]),
+            paa=np.array([0.4, 0.5, 0.6]),
+            intensity_unit="m/s",
+            name="Test Impact",
+        )
+        self.impf3 = ImpactFunc(
+            haz_type="FL",
+            id=2,
+            intensity=np.array([4, 5, 6]),
+            mdd=np.array([0.7, 0.8, 0.9]),
+            paa=np.array([0.1, 0.2, 0.3]),
+            intensity_unit="m",
+            name="Another Impact",
+        )
+
+    def test_reflexivity(self):
+        self.assertEqual(self.impf1, self.impf1)
+
+    def test_symmetry(self):
+        self.assertEqual(self.impf1, self.impf2)
+        self.assertEqual(self.impf2, self.impf1)
+
+    def test_transitivity(self):
+        impf4 = ImpactFunc(
+            haz_type="TC",
+            id=1,
+            intensity=np.array([1, 2, 3]),
+            mdd=np.array([0.1, 0.2, 0.3]),
+            paa=np.array([0.4, 0.5, 0.6]),
+            intensity_unit="m/s",
+            name="Test Impact",
+        )
+        self.assertEqual(self.impf1, self.impf2)
+        self.assertEqual(self.impf2, impf4)
+        self.assertEqual(self.impf1, impf4)
+
+    def test_consistency(self):
+        self.assertEqual(self.impf1, self.impf2)
+        self.assertEqual(self.impf1, self.impf2)
+
+    def test_comparison_with_none(self):
+        self.assertNotEqual(self.impf1, None)
+
+    def test_different_types(self):
+        self.assertNotEqual(self.impf1, "Not an ImpactFunc")
+
+    def test_inequality(self):
+        self.assertNotEqual(self.impf1, self.impf3)
+        self.assertTrue(self.impf1 != self.impf3)
+
+
 class TestInterpolation(unittest.TestCase):
     """Impact function interpolation test"""
 
@@ -139,5 +207,8 @@ def test_aux_vars(impf):
 
 # Execute Tests
 if __name__ == "__main__":
-    TESTS = unittest.TestLoader().loadTestsFromTestCase(TestInterpolation)
-    unittest.TextTestRunner(verbosity=2).run(TESTS)
+    equality_tests = unittest.TestLoader().loadTestsFromTestCase(TestEquality)
+    interpolation_tests = unittest.TestLoader().loadTestsFromTestCase(TestInterpolation)
+    unittest.TextTestRunner(verbosity=2).run(
+        unittest.TestSuite([equality_tests, interpolation_tests])
+    )