Assorted cleanups

pandas/_libs/src/klib/khash_python.h

@@ -106,7 +106,7 @@ khint_t PANDAS_INLINE kh_put_str_starts_item(kh_str_starts_t* table, char* key,
     return result;
 }
 
-khint_t PANDAS_INLINE kh_get_str_starts_item(kh_str_starts_t* table, char* key) {
+khint_t PANDAS_INLINE kh_get_str_starts_item(const kh_str_starts_t* table, const char* key) {
     unsigned char ch = *key;
 	if (table->starts[ch]) {
 		if (ch == '\0' || kh_get_str(table->table, key) != table->table->n_buckets) return 1;

pandas/core/indexing.py

@@ -936,7 +936,7 @@ def _getitem_lowerdim(self, tup):
                         new_key = b, a
 
                     if len(new_key) == 1:
-                        new_key, = new_key
+                        new_key = new_key[0]
 
                 # Slices should return views, but calling iloc/loc with a null
                 # slice returns a new object.
@@ -1250,7 +1250,7 @@ def _convert_to_indexer(
                 # a positional
                 if obj >= self.obj.shape[axis] and not isinstance(labels, MultiIndex):
                     raise ValueError(
-                        "cannot set by positional indexing with " "enlargement"
+                        "cannot set by positional indexing with enlargement"
                     )
 
             return obj
@@ -1408,7 +1408,7 @@ def __getitem__(self, key):
             maybe_callable = com.apply_if_callable(key, self.obj)
             return self._getitem_axis(maybe_callable, axis=axis)
 
-    def _is_scalar_access(self, key):
+    def _is_scalar_access(self, key: tuple):
         raise NotImplementedError()
 
     def _getitem_scalar(self, key):
@@ -1709,14 +1709,11 @@ def _validate_key(self, key, axis: int):
         if not is_list_like_indexer(key):
             self._convert_scalar_indexer(key, axis)
 
-    def _is_scalar_access(self, key):
+    def _is_scalar_access(self, key: tuple):
         # this is a shortcut accessor to both .loc and .iloc
         # that provide the equivalent access of .at and .iat
         # a) avoid getting things via sections and (to minimize dtype changes)
         # b) provide a performant path
-        if not hasattr(key, "__len__"):
-            return False
-
         if len(key) != self.ndim:
             return False
 
@@ -2000,7 +1997,7 @@ def _validate_key(self, key, axis: int):
             # check that the key has a numeric dtype
             if not is_numeric_dtype(arr.dtype):
                 raise IndexError(
-                    ".iloc requires numeric indexers, got " "{arr}".format(arr=arr)
+                    ".iloc requires numeric indexers, got {arr}".format(arr=arr)
                 )
 
             # check that the key does not exceed the maximum size of the index
@@ -2015,14 +2012,11 @@ def _validate_key(self, key, axis: int):
     def _has_valid_setitem_indexer(self, indexer):
         self._has_valid_positional_setitem_indexer(indexer)
 
-    def _is_scalar_access(self, key):
+    def _is_scalar_access(self, key: tuple):
         # this is a shortcut accessor to both .loc and .iloc
         # that provide the equivalent access of .at and .iat
         # a) avoid getting things via sections and (to minimize dtype changes)
         # b) provide a performant path
-        if not hasattr(key, "__len__"):
-            return False
-
         if len(key) != self.ndim:
             return False
 
@@ -2131,9 +2125,7 @@ def _getitem_axis(self, key, axis: int):
         else:
             key = item_from_zerodim(key)
             if not is_integer(key):
-                raise TypeError(
-                    "Cannot index by location index with a " "non-integer key"
-                )
+                raise TypeError("Cannot index by location index with a non-integer key")
 
             # validate the location
             self._validate_integer(key, axis)
@@ -2191,7 +2183,7 @@ def __setitem__(self, key, value):
         if not isinstance(key, tuple):
             key = self._tuplify(key)
         if len(key) != self.obj.ndim:
-            raise ValueError("Not enough indexers for scalar access " "(setting)!")
+            raise ValueError("Not enough indexers for scalar access (setting)!")
         key = list(self._convert_key(key, is_setter=True))
         key.append(value)
         self.obj._set_value(*key, takeable=self._takeable)
@@ -2327,7 +2319,7 @@ def _convert_key(self, key, is_setter: bool = False):
         """ require integer args (and convert to label arguments) """
         for a, i in zip(self.obj.axes, key):
             if not is_integer(i):
-                raise ValueError("iAt based indexing can only have integer " "indexers")
+                raise ValueError("iAt based indexing can only have integer indexers")
         return key
 
 

pandas/core/internals/blocks.py

@@ -41,7 +41,6 @@
     is_integer_dtype,
     is_interval_dtype,
     is_list_like,
-    is_numeric_v_string_like,
     is_object_dtype,
     is_period_dtype,
     is_re,
@@ -1297,24 +1296,20 @@ def take_nd(self, indexer, axis, new_mgr_locs=None, fill_tuple=None):
 
         if fill_tuple is None:
             fill_value = self.fill_value
-            new_values = algos.take_nd(
-                values, indexer, axis=axis, allow_fill=False, fill_value=fill_value
-            )
+            allow_fill = False
         else:
             fill_value = fill_tuple[0]
-            new_values = algos.take_nd(
-                values, indexer, axis=axis, allow_fill=True, fill_value=fill_value
-            )
+            allow_fill = True
 
+        new_values = algos.take_nd(
+            values, indexer, axis=axis, allow_fill=allow_fill, fill_value=fill_value
+        )
+
+        # Called from three places in managers, all of which satisfy
+        #  this assertion
+        assert not (axis == 0 and new_mgr_locs is None)
         if new_mgr_locs is None:
-            if axis == 0:
-                slc = libinternals.indexer_as_slice(indexer)
-                if slc is not None:
-                    new_mgr_locs = self.mgr_locs[slc]
-                else:
-                    new_mgr_locs = self.mgr_locs[indexer]
-            else:
-                new_mgr_locs = self.mgr_locs
+            new_mgr_locs = self.mgr_locs
 
         if not is_dtype_equal(new_values.dtype, self.dtype):
             return self.make_block(new_values, new_mgr_locs)
@@ -1858,11 +1853,11 @@ def take_nd(self, indexer, axis=0, new_mgr_locs=None, fill_tuple=None):
         # if its REALLY axis 0, then this will be a reindex and not a take
         new_values = self.values.take(indexer, fill_value=fill_value, allow_fill=True)
 
-        if self.ndim == 1 and new_mgr_locs is None:
-            new_mgr_locs = [0]
-        else:
-            if new_mgr_locs is None:
-                new_mgr_locs = self.mgr_locs
+        # Called from three places in managers, all of which satisfy
+        #  this assertion
+        assert not (self.ndim == 1 and new_mgr_locs is None)
+        if new_mgr_locs is None:
+            new_mgr_locs = self.mgr_locs
 
         return self.make_block_same_class(new_values, new_mgr_locs)
 
@@ -3366,10 +3361,6 @@ def _putmask_smart(v, m, n):
         # if we have nulls
         if not _isna_compat(v, nn[0]):
             pass
-        elif is_numeric_v_string_like(nn, v):
-            # avoid invalid dtype comparisons
-            # between numbers & strings
-            pass
         elif not (is_float_dtype(nn.dtype) or is_integer_dtype(nn.dtype)):
             # only compare integers/floats
             pass

pandas/core/internals/construction.py

@@ -355,7 +355,7 @@ def extract_index(data):
                 raw_lengths.append(len(val))
 
         if not indexes and not raw_lengths:
-            raise ValueError("If using all scalar values, you must pass" " an index")
+            raise ValueError("If using all scalar values, you must pass an index")
 
         if have_series:
             index = _union_indexes(indexes)
@@ -369,7 +369,7 @@ def extract_index(data):
 
             if have_dicts:
                 raise ValueError(
-                    "Mixing dicts with non-Series may lead to " "ambiguous ordering."
+                    "Mixing dicts with non-Series may lead to ambiguous ordering."
                 )
 
             if have_series:

pandas/core/internals/managers.py

@@ -1061,7 +1061,7 @@ def value_getitem(placement):
 
             if value.shape[1:] != self.shape[1:]:
                 raise AssertionError(
-                    "Shape of new values must be compatible " "with manager shape"
+                    "Shape of new values must be compatible with manager shape"
                 )
 
         try:
@@ -1154,7 +1154,7 @@ def value_getitem(placement):
             # Newly created block's dtype may already be present.
             self._known_consolidated = False
 
-    def insert(self, loc, item, value, allow_duplicates=False):
+    def insert(self, loc: int, item, value, allow_duplicates: bool = False):
         """
         Insert item at selected position.
 
@@ -1389,9 +1389,7 @@ def take(self, indexer, axis=1, verify=True, convert=True):
 
         if verify:
             if ((indexer == -1) | (indexer >= n)).any():
-                raise Exception(
-                    "Indices must be nonzero and less than " "the axis length"
-                )
+                raise Exception("Indices must be nonzero and less than the axis length")
 
         new_labels = self.axes[axis].take(indexer)
         return self.reindex_indexer(
@@ -1478,7 +1476,7 @@ def __init__(
         if isinstance(axis, list):
             if len(axis) != 1:
                 raise ValueError(
-                    "cannot create SingleBlockManager with more " "than 1 axis"
+                    "cannot create SingleBlockManager with more than 1 axis"
                 )
             axis = axis[0]
 
@@ -1492,7 +1490,7 @@ def __init__(
                     block = [np.array([])]
                 elif len(block) != 1:
                     raise ValueError(
-                        "Cannot create SingleBlockManager with " "more than 1 block"
+                        "Cannot create SingleBlockManager with more than 1 block"
                     )
                 block = block[0]
         else:
@@ -1509,7 +1507,7 @@ def __init__(
 
                 if len(block) != 1:
                     raise ValueError(
-                        "Cannot create SingleBlockManager with " "more than 1 block"
+                        "Cannot create SingleBlockManager with more than 1 block"
                     )
                 block = block[0]