Complete NumPy 2.x compatibility fixes for p-value calculations

xskillscore/core/deterministic.py

@@ -465,7 +465,7 @@ def pearson_r_eff_p_value(
     <xarray.DataArray (x: 3, y: 3)> Size: 72B
     array([[0.82544245,        nan, 0.25734167],
            [0.78902959, 0.57503354, 0.8059353 ],
-           [0.79242625, 0.66792245,        nan]])
+           [0.79242625, 0.66792245, 1.        ]])
     Dimensions without coordinates: x, y
     """
     _fail_if_dim_empty(dim)

xskillscore/core/np_deterministic.py

@@ -143,7 +143,7 @@ def _effective_sample_size(a, b, axis, skipna):
     b = np.rollaxis(b, axis)
 
     # count total number of samples that are non-nan.
-    n = np.count_nonzero(~np.isnan(np.atleast_1d(a)), axis=0)
+    n = np.count_nonzero(~np.isnan(a), axis=0)
 
     # compute lag-1 autocorrelation.
     am, bm = __compute_anomalies(a, b, weights=None, axis=0, skipna=skipna)
@@ -347,7 +347,7 @@ def _pearson_r_p_value(a, b, weights, axis, skipna):
         a = np.rollaxis(a, axis)
         b = np.rollaxis(b, axis)
         # count non-nans
-        dof = np.count_nonzero(~np.isnan(np.atleast_1d(a)), axis=0) - 2
+        dof = np.count_nonzero(~np.isnan(a), axis=0) - 2
         with warnings.catch_warnings():
             warnings.simplefilter("ignore", RuntimeWarning)
             t_squared = r**2 * (dof / ((1.0 - r) * (1.0 + r)))
@@ -358,14 +358,7 @@ def _pearson_r_p_value(a, b, weights, axis, skipna):
         _b = 0.5
         res = special.betainc(_a, _b, _x)
         # reset masked values to nan
-        # raises  <__array_function__ internals>:5: DeprecationWarning: Calling nonzero
-        # on 0d arrays is deprecated, as it behaves surprisingly. Use
-        # `atleast_1d(cond).nonzero()` if the old behavior was intended. If the context
-        # of this warning is of the form `arr[nonzero(cond)]`, just use `arr[cond]`.
-        nan_locs = np.where(np.isnan(np.atleast_1d(r)))
-        if len(nan_locs[0]) > 0:
-            res[nan_locs] = np.nan
-        return res
+        return np.where(np.isnan(r), np.nan, res)
 
 
 def _pearson_r_eff_p_value(a, b, axis, skipna):
@@ -417,10 +410,7 @@ def _pearson_r_eff_p_value(a, b, axis, skipna):
         _b = 0.5
         res = special.betainc(_a, _b, _x)
         # reset masked values to nan
-        nan_locs = np.where(np.isnan(np.atleast_1d(r)))
-        if len(nan_locs[0]) > 0:
-            res[nan_locs] = np.nan
-        return res
+        return np.where(np.isnan(r), np.nan, res)
 
 
 def _spearman_r(a, b, weights, axis, skipna):
@@ -490,7 +480,7 @@ def _spearman_r_p_value(a, b, weights, axis, skipna):
     a = np.rollaxis(a, axis)
     b = np.rollaxis(b, axis)
     # count non-nans
-    dof = np.count_nonzero(~np.isnan(np.atleast_1d(a)), axis=0) - 2
+    dof = np.count_nonzero(~np.isnan(a), axis=0) - 2
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", RuntimeWarning)
         t = rs * np.sqrt((dof / ((rs + 1.0) * (1.0 - rs))).clip(0))

xskillscore/core/stattests.py

@@ -122,11 +122,11 @@ def multipletests(
             [ 0.1       ,  0.1       ,  0.1       ],
             [ 0.1       ,  0.1       ,  0.1       ]]])
     Coordinates:
+      * result                (result) <U15 240B 'reject' ... 'alphacBonf'
       * x                     (x) int64 24B 0 1 2
       * y                     (y) int64 24B 0 1 2
         multipletests_method  <U6 24B 'fdr_bh'
         multipletests_alpha   float64 8B 0.1
-      * result                (result) <U15 240B 'reject' ... 'alphacBonf'
     """
     MULTIPLE_TESTS = [
         "bonferroni",
@@ -182,10 +182,7 @@ def multipletests(
     ret = tuple(r.unstack("s").transpose(*p.dims, ...) for r in ret)
 
     def _add_kwargs_as_coords(r: XArray):
-        return r.assign_coords(
-            multipletests_method=method,
-            multipletests_alpha=alpha
-        )
+        return r.assign_coords(multipletests_method=method, multipletests_alpha=alpha)
 
     ret = tuple(_add_kwargs_as_coords(r) for r in ret)