MAINT: update sorting order of positional metadata

this seems to be a difference in how pd.concat is sorting the columns, and likely coming up because of the `odd_key` used here (an empty `frozendict`). this may be related to this pandas bug fix that went into pandas 1.5.0: pandas-dev/pandas#47331

Author: gregcaporaso

checklist.py

@@ -457,7 +457,7 @@ def _parse_file(self, fp, root):
                     if node.level > 0:
                         prefix = root
                         extra = node.level - 1
-                        while(extra > 0):
+                        while (extra > 0):
                             # Keep dropping...
                             prefix = os.path.split(prefix)[0]
                             extra -= 1

setup.py

@@ -151,7 +151,7 @@
           'matplotlib >= 1.4.3',
           'natsort >= 4.0.3',
           'numpy >= 1.9.2',
-          'pandas >= 1.0.0',
+          'pandas >= 1.5.0',
           'scipy >= 1.9.0',
           'h5py >= 2.9.0',
           'hdmedians >= 0.14.1',

skbio/diversity/alpha/_base.py

@@ -795,7 +795,7 @@ def pielou_e(counts):
 
 @experimental(as_of="0.4.0")
 def robbins(counts):
-    r"""Calculate Robbins' estimator for the probability of unobserved outcomes.
+    r"""Calculate Robbins' estimator for probability of unobserved outcomes.
 
     Robbins' estimator is defined as:
 

skbio/io/format/embl.py

@@ -1165,7 +1165,7 @@ def _serialize_reference(header, obj, cross_references, indent=5):
 
             # delete PUBMED key (already present in CROSS_REFERENCE)
             if "PUBMED" in data:
-                del(data["PUBMED"])
+                del (data["PUBMED"])
 
         else:
             # no cross reference, do I have PUBMED in data?

skbio/io/format/tests/test_clustal.py

@@ -163,27 +163,22 @@ def             CGAUCAGUCAGUCGAU---------- 34
 xyz             UGCUGCAUCA---------------- 33
                 *     ***""")
             ]
-        self.invalid_clustal_out = [StringIO('\n'.join(['dshfjsdfhdfsj',
-                                                        'hfsdjksdfhjsdf'])),
-                                    StringIO('\n'.join(['hfsdjksdfhjsdf'])),
-                                    StringIO('\n'.join(['dshfjsdfhdfsj',
-                                                        'dshfjsdfhdfsj',
-                                                        'hfsdjksdfhjsdf'])),
-                                    StringIO('\n'.join(['dshfjsdfhdfsj',
-                                                        '\t',
-                                                        'hfsdjksdfhjsdf'])),
-                                    StringIO('\n'.join(['dshfj\tdfhdfsj',
-                                                        'hfsdjksdfhjsdf'])),
-                                    StringIO('\n'.join(['dshfjsdfhdfsj',
-                                                        'hfsdjk\tdfhjsdf'])),
-                                    StringIO("""CLUSTAL W (1.74) multiple sequence alignment
+        self.invalid_clustal_out = [
+            StringIO('\n'.join(['dshfjsdfhdfsj', 'hfsdjksdfhjsdf'])),
+            StringIO('\n'.join(['hfsdjksdfhjsdf'])),
+            StringIO('\n'.join(['dshfjsdfhdfsj', 'dshfjsdfhdfsj',
+                                'hfsdjksdfhjsdf'])),
+            StringIO('\n'.join(['dshfjsdfhdfsj', '\t', 'hfsdjksdfhjsdf'])),
+            StringIO('\n'.join(['dshfj\tdfhdfsj', 'hfsdjksdfhjsdf'])),
+            StringIO('\n'.join(['dshfjsdfhdfsj', 'hfsdjk\tdfhjsdf'])),
+            StringIO("""CLUSTAL W (1.74) multiple sequence alignment
 
 
 adj GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA
 ------------------------------------------------------------
 adk -----GGGGGGG------------------------------------------------
 """),
-                                    StringIO("""CLUSTAL W (1.74) multiple sequence alignment
+            StringIO("""CLUSTAL W (1.74) multiple sequence alignment
 
 
 adj GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA
@@ -193,7 +188,7 @@ def             CGAUCAGUCAGUCGAU---------- 34
 adj GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA
 adk -----GGGGGGG---------------------------------------------
 """),
-                                    StringIO("""CLUSTAL W (1.74) multiple sequence alignment
+            StringIO("""CLUSTAL W (1.74) multiple sequence alignment
 
 
 adj GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA
@@ -204,15 +199,15 @@ def             CGAUCAGUCAGUCGAU---------- 34
 adk -----GGGGGGG---------------------------------------------
 """),
 
-                                    StringIO("""CLUSTAL W (1.74) multiple sequence alignment
+            StringIO("""CLUSTAL W (1.74) multiple sequence alignment
 
 
 adj GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA
 ------------------------------------------------------------
 adk -----GGGGGGG------------------------------------------------
 """),
 
-                                    StringIO("""CLUSTAL W (1.74) multiple sequence alignment
+            StringIO("""CLUSTAL W (1.74) multiple sequence alignment
 
 
 GCAUGCAUGCAUGAUCGUACGUCAGCAUGCUAGACUGCAUACGUACGUACGCAUGCAUCA

skbio/metadata/_interval.py

@@ -175,7 +175,7 @@ def __repr__(self):
 
     @experimental(as_of='0.5.1')
     def drop(self):
-        '''Drop this ``Interval`` object from the interval metadata it links to.
+        '''Drop this ``Interval`` object from interval metadata it links to.
 
         If the ``Interval`` object is dropped, you can still get values of
         ``bounds``, ``fuzzy``, and ``metadata`` attributes, but you

skbio/sequence/_sequence.py

@@ -2098,7 +2098,7 @@ def _constructor(self, **kwargs):
         return self.__class__(**kwargs)
 
     def _munge_to_index_array(self, sliceable):
-        r"""Return an index array from something isomorphic to a boolean vector.
+        r"""Return index array from something isomorphic to a boolean vector.
 
         """
         if isinstance(sliceable, str):

skbio/sequence/tests/test_sequence.py

@@ -169,8 +169,8 @@ def test_concat_strict_simple(self):
     def test_concat_strict_many(self):
         odd_key = frozenset()
         expected = Sequence("13579",
-                            positional_metadata={'a': list('skbio'),
-                                                 odd_key: [1, 2, 3, 4, 5]})
+                            positional_metadata={odd_key: [1, 2, 3, 4, 5],
+                                                 'a': list('skbio')})
         result = Sequence.concat([
                 Sequence("1", positional_metadata={'a': ['s'], odd_key: [1]}),
                 Sequence("3", positional_metadata={'a': ['k'], odd_key: [2]}),

skbio/stats/distance/_mantel.py

@@ -15,7 +15,6 @@
 from scipy.stats import kendalltau
 from scipy.stats import ConstantInputWarning
 from scipy.stats import NearConstantInputWarning
-from scipy.stats import ConstantInputWarning
 
 from skbio.stats.distance import DistanceMatrix
 from skbio.util._decorator import experimental

skbio/tree/_nj.py

@@ -118,7 +118,7 @@ def result_constructor(x):
 
     # while there are still more than three distances in the distance matrix,
     # join neighboring nodes.
-    while(dm.shape[0] > 3):
+    while (dm.shape[0] > 3):
         # compute the Q matrix
         q = _compute_q(dm)