error when adding info to gdf

[OnnoEbbens]

When I try to run the function bgt = nlmod.gwf.surface_water.add_stages_from_waterboards(bgt, la) on linux using pandas version 1.5.3 I get this error:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
Cell In[16], line 5
      2 bgt = nlmod.gwf.surface_water.add_min_ahn_to_gdf(bgt, ahn, buffer=5.0)
      4 # add information from level areas (la) to bgt
----> 5 bgt = nlmod.gwf.surface_water.add_stages_from_waterboards(bgt, la)
      7 # add information from watercources (wc) to bgt
      8 bgt = nlmod.gwf.surface_water.add_bottom_height_from_waterboards(bgt, wc)

File ~/.local/lib/python3.9/site-packages/nlmod/gwf/surface_water.py:711, in add_stages_from_waterboards(gdf, la, extent, columns, config, min_total_overlap)
    709         continue
    710     mask = gdf["bronhouder"] == config[wb]["bgt_code"]
--> 711     gdf[mask] = add_info_to_gdf(
    712         la[wb],
    713         gdf[mask],
    714         columns=columns,
    715         min_total_overlap=min_total_overlap,
    716         desc=f"Adding {columns} from {wb}",
    717     )
    718 return gdf

File /opt/tljh/user/lib/python3.9/site-packages/geopandas/geodataframe.py:1443, in GeoDataFrame.__setitem__(self, key, value)
   1441     except TypeError:
   1442         warnings.warn("Geometry column does not contain geometry.")
-> 1443 super().__setitem__(key, value)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/frame.py:3968, in DataFrame.__setitem__(self, key, value)
   3966     self._setitem_frame(key, value)
   3967 elif isinstance(key, (Series, np.ndarray, list, Index)):
-> 3968     self._setitem_array(key, value)
   3969 elif isinstance(value, DataFrame):
   3970     self._set_item_frame_value(key, value)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/frame.py:4003, in DataFrame._setitem_array(self, key, value)
   4000     if isinstance(value, DataFrame):
   4001         # GH#39931 reindex since iloc does not align
   4002         value = value.reindex(self.index.take(indexer))
-> 4003     self.iloc[indexer] = value
   4005 else:
   4006     # Note: unlike self.iloc[:, indexer] = value, this will
   4007     #  never try to overwrite values inplace
   4009     if isinstance(value, DataFrame):

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:818, in _LocationIndexer.__setitem__(self, key, value)
    815 self._has_valid_setitem_indexer(key)
    817 iloc = self if self.name == "iloc" else self.obj.iloc
--> 818 iloc._setitem_with_indexer(indexer, value, self.name)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1795, in _iLocIndexer._setitem_with_indexer(self, indexer, value, name)
   1792 # align and set the values
   1793 if take_split_path:
   1794     # We have to operate column-wise
-> 1795     self._setitem_with_indexer_split_path(indexer, value, name)
   1796 else:
   1797     self._setitem_single_block(indexer, value, name)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1831, in _iLocIndexer._setitem_with_indexer_split_path(self, indexer, value, name)
   1828 if is_list_like_indexer(value) and getattr(value, "ndim", 1) > 0:
   1830     if isinstance(value, ABCDataFrame):
-> 1831         self._setitem_with_indexer_frame_value(indexer, value, name)
   1833     elif np.ndim(value) == 2:
   1834         self._setitem_with_indexer_2d_value(indexer, value)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1922, in _iLocIndexer._setitem_with_indexer_frame_value(self, indexer, value, name)
   1920     for i, loc in enumerate(ilocs):
   1921         val = value.iloc[:, i]
-> 1922         self._setitem_single_column(loc, val, pi)
   1924 elif not unique_cols and value.columns.equals(self.obj.columns):
   1925     # We assume we are already aligned, see
   1926     # test_iloc_setitem_frame_duplicate_columns_multiple_blocks
   1927     for loc in ilocs:

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1985, in _iLocIndexer._setitem_single_column(self, loc, value, plane_indexer)
   1978 elif (
   1979     is_array_like(value)
   1980     and len(value.shape) > 0
   1981     and self.obj.shape[0] == value.shape[0]
   1982     and not is_empty_indexer(pi)
   1983 ):
   1984     if is_list_like(pi) and not is_bool_dtype(pi):
-> 1985         value = value[np.argsort(pi)]
   1986     else:
   1987         # in case of slice
   1988         value = value[pi]

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/series.py:1007, in Series.__getitem__(self, key)
   1004     key = np.asarray(key, dtype=bool)
   1005     return self._get_values(key)
-> 1007 return self._get_with(key)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/series.py:1042, in Series._get_with(self, key)
   1038 if key_type == "integer":
   1039     # We need to decide whether to treat this as a positional indexer
   1040     #  (i.e. self.iloc) or label-based (i.e. self.loc)
   1041     if not self.index._should_fallback_to_positional:
-> 1042         return self.loc[key]
   1043     else:
   1044         return self.iloc[key]

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1073, in _LocationIndexer.__getitem__(self, key)
   1070 axis = self.axis or 0
   1072 maybe_callable = com.apply_if_callable(key, self.obj)
-> 1073 return self._getitem_axis(maybe_callable, axis=axis)

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1301, in _LocIndexer._getitem_axis(self, key, axis)
   1298     if hasattr(key, "ndim") and key.ndim > 1:
   1299         raise ValueError("Cannot index with multidimensional key")
-> 1301     return self._getitem_iterable(key, axis=axis)
   1303 # nested tuple slicing
   1304 if is_nested_tuple(key, labels):

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1239, in _LocIndexer._getitem_iterable(self, key, axis)
   1236 self._validate_key(key, axis)
   1238 # A collection of keys
-> 1239 keyarr, indexer = self._get_listlike_indexer(key, axis)
   1240 return self.obj._reindex_with_indexers(
   1241     {axis: [keyarr, indexer]}, copy=True, allow_dups=True
   1242 )

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexing.py:1432, in _LocIndexer._get_listlike_indexer(self, key, axis)
   1429 ax = self.obj._get_axis(axis)
   1430 axis_name = self.obj._get_axis_name(axis)
-> 1432 keyarr, indexer = ax._get_indexer_strict(key, axis_name)
   1434 return keyarr, indexer

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexes/base.py:6070, in Index._get_indexer_strict(self, key, axis_name)
   6067 else:
   6068     keyarr, indexer, new_indexer = self._reindex_non_unique(keyarr)
-> 6070 self._raise_if_missing(keyarr, indexer, axis_name)
   6072 keyarr = self.take(indexer)
   6073 if isinstance(key, Index):
   6074     # GH 42790 - Preserve name from an Index

File /opt/tljh/user/lib/python3.9/site-packages/pandas/core/indexes/base.py:6133, in Index._raise_if_missing(self, key, indexer, axis_name)
   6130     raise KeyError(f"None of [{key}] are in the [{axis_name}]")
   6132 not_found = list(ensure_index(key)[missing_mask.nonzero()[0]].unique())
-> 6133 raise KeyError(f"{not_found} not in index")

KeyError: '[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 33, 34, 36, 40, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 55, 57, 58, 60, 61, 62, 63, 64, 65, 66, 67, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 83, 85, 86, 87, 88, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 127, 128, 132, 133, 134, 135, 138, 139] not in index'

When I use gdf.loc[mask] instead of gdf[mask] in the function add_stages_from_waterboards it works fine (see below). I think there is some pandas version thing involved.

gdf.loc[mask] = add_info_to_gdf(
    712         la[wb],
    713         gdf[mask],
    714         columns=columns,
    715         min_total_overlap=min_total_overlap,
    716         desc=f"Adding {columns} from {wb}",
    717     )

[OnnoEbbens]

closed by adding .loc as suggested