CLN: Assorted cleanups (pandas-dev#30260)

Author: jbrockmendel

pandas/core/dtypes/cast.py

@@ -244,13 +244,13 @@ def maybe_upcast_putmask(result: np.ndarray, mask: np.ndarray, other):
         necessary.
     mask : boolean ndarray
     other : scalar
-        The source value
+        The source value.
 
     Returns
     -------
     result : ndarray
-    changed : boolean
-        Set to true if the result array was upcasted
+    changed : bool
+        Set to true if the result array was upcasted.
 
     Examples
     --------
@@ -337,6 +337,21 @@ def changeit():
 
 
 def maybe_promote(dtype, fill_value=np.nan):
+    """
+    Find the minimal dtype that can hold both the given dtype and fill_value.
+
+    Parameters
+    ----------
+    dtype : np.dtype or ExtensionDtype
+    fill_value : scalar, default np.nan
+
+    Returns
+    -------
+    dtype
+        Upcasted from dtype argument if necessary.
+    fill_value
+        Upcasted from fill_value argument if necessary.
+    """
     if not is_scalar(fill_value) and not is_object_dtype(dtype):
         # with object dtype there is nothing to promote, and the user can
         #  pass pretty much any weird fill_value they like
@@ -592,11 +607,11 @@ def infer_dtype_from_scalar(val, pandas_dtype: bool = False):
 
 def infer_dtype_from_array(arr, pandas_dtype: bool = False):
     """
-    Infer the dtype from a scalar or array.
+    Infer the dtype from an array.
 
     Parameters
     ----------
-    arr : scalar or array
+    arr : array
     pandas_dtype : bool, default False
         whether to infer dtype including pandas extension types.
         If False, array belongs to pandas extension types
@@ -622,7 +637,6 @@ def infer_dtype_from_array(arr, pandas_dtype: bool = False):
 
     >>> infer_dtype_from_array([1, '1'])
     (numpy.object_, [1, '1'])
-
     """
 
     if isinstance(arr, np.ndarray):
@@ -686,10 +700,12 @@ def maybe_upcast(values, fill_value=np.nan, dtype=None, copy: bool = False):
 
     Parameters
     ----------
-    values : the ndarray that we want to maybe upcast
+    values : ndarray or ExtensionArray
+        The array that we want to maybe upcast.
     fill_value : what we want to fill with
     dtype : if None, then use the dtype of the values, else coerce to this type
-    copy : if True always make a copy even if no upcast is required
+    copy : bool, default True
+        If True always make a copy even if no upcast is required.
     """
     if not is_scalar(fill_value) and not is_object_dtype(values.dtype):
         # We allow arbitrary fill values for object dtype

pandas/core/frame.py

@@ -4354,7 +4354,7 @@ def _maybe_casted_values(index, labels=None):
                         values = values._data
 
                     if mask.any():
-                        values, changed = maybe_upcast_putmask(values, mask, np.nan)
+                        values, _ = maybe_upcast_putmask(values, mask, np.nan)
 
                     if issubclass(values_type, DatetimeLikeArray):
                         values = values_type(values, dtype=values_dtype)

pandas/core/indexes/base.py

@@ -331,11 +331,12 @@ def __new__(
 
         # extension dtype
         elif is_extension_array_dtype(data) or is_extension_array_dtype(dtype):
-            data = np.asarray(data)
             if not (dtype is None or is_object_dtype(dtype)):
                 # coerce to the provided dtype
                 ea_cls = dtype.construct_array_type()
                 data = ea_cls._from_sequence(data, dtype=dtype, copy=False)
+            else:
+                data = np.asarray(data, dtype=object)
 
             # coerce to the object dtype
             data = data.astype(object)

pandas/core/nanops.py

@@ -314,7 +314,7 @@ def _get_values(
 
         # promote if needed
         else:
-            values, changed = maybe_upcast_putmask(values, mask, fill_value)
+            values, _ = maybe_upcast_putmask(values, mask, fill_value)
 
     # return a platform independent precision dtype
     dtype_max = dtype

pandas/core/ops/array_ops.py

@@ -110,7 +110,7 @@ def masked_arith_op(x, y, op):
             with np.errstate(all="ignore"):
                 result[mask] = op(xrav[mask], y)
 
-    result, changed = maybe_upcast_putmask(result, ~mask, np.nan)
+    result, _ = maybe_upcast_putmask(result, ~mask, np.nan)
     result = result.reshape(x.shape)  # 2D compat
     return result
 

pandas/core/strings.py

@@ -74,10 +74,12 @@ def cat_core(list_of_columns: List, sep: str):
     """
     if sep == "":
         # no need to interleave sep if it is empty
-        return np.sum(list_of_columns, axis=0)
+        arr_of_cols = np.asarray(list_of_columns, dtype=object)
+        return np.sum(arr_of_cols, axis=0)
     list_with_sep = [sep] * (2 * len(list_of_columns) - 1)
     list_with_sep[::2] = list_of_columns
-    return np.sum(list_with_sep, axis=0)
+    arr_with_sep = np.asarray(list_with_sep)
+    return np.sum(arr_with_sep, axis=0)
 
 
 def cat_safe(list_of_columns: List, sep: str):