REF: handle non-list_like cases upfront in sanitize_array (pandas-dev#38563)

Author: jbrockmendel

pandas/core/construction.py

@@ -449,6 +449,11 @@ def sanitize_array(
     # extract ndarray or ExtensionArray, ensure we have no PandasArray
     data = extract_array(data, extract_numpy=True)
 
+    if isinstance(data, np.ndarray) and data.ndim == 0:
+        if dtype is None:
+            dtype = data.dtype
+        data = lib.item_from_zerodim(data)
+
     # GH#846
     if isinstance(data, np.ndarray):
 
@@ -462,7 +467,7 @@ def sanitize_array(
                 else:
                     subarr = np.array(data, copy=False)
         else:
-            # we will try to copy be-definition here
+            # we will try to copy by-definition here
             subarr = _try_cast(data, dtype, copy, raise_cast_failure)
 
     elif isinstance(data, ABCExtensionArray):
@@ -491,30 +496,16 @@ def sanitize_array(
         # GH#16804
         arr = np.arange(data.start, data.stop, data.step, dtype="int64")
         subarr = _try_cast(arr, dtype, copy, raise_cast_failure)
-    elif lib.is_scalar(data) and index is not None and dtype is not None:
+
+    elif not is_list_like(data):
+        if index is None:
+            raise ValueError("index must be specified when data is not list-like")
         subarr = construct_1d_arraylike_from_scalar(data, len(index), dtype)
+
     else:
         subarr = _try_cast(data, dtype, copy, raise_cast_failure)
 
-    # scalar like, GH
-    if getattr(subarr, "ndim", 0) == 0:
-        if isinstance(data, list):  # pragma: no cover
-            subarr = np.array(data, dtype=object)
-        elif index is not None:
-            subarr = construct_1d_arraylike_from_scalar(data, len(index), dtype)
-
-        else:
-            return subarr.item()
-
-    # the result that we want
-    elif subarr.ndim == 1:
-        subarr = _maybe_repeat(subarr, index)
-
-    elif subarr.ndim > 1:
-        if isinstance(data, np.ndarray):
-            raise ValueError("Data must be 1-dimensional")
-        else:
-            subarr = com.asarray_tuplesafe(data, dtype=dtype)
+    subarr = _sanitize_ndim(subarr, data, dtype, index)
 
     if not (is_extension_array_dtype(subarr.dtype) or is_extension_array_dtype(dtype)):
         subarr = _sanitize_str_dtypes(subarr, data, dtype, copy)
@@ -528,6 +519,27 @@ def sanitize_array(
     return subarr
 
 
+def _sanitize_ndim(
+    result: ArrayLike, data, dtype: Optional[DtypeObj], index: Optional[Index]
+) -> ArrayLike:
+    """
+    Ensure we have a 1-dimensional result array.
+    """
+    if getattr(result, "ndim", 0) == 0:
+        raise ValueError("result should be arraylike with ndim > 0")
+
+    elif result.ndim == 1:
+        # the result that we want
+        result = _maybe_repeat(result, index)
+
+    elif result.ndim > 1:
+        if isinstance(data, np.ndarray):
+            raise ValueError("Data must be 1-dimensional")
+        else:
+            result = com.asarray_tuplesafe(data, dtype=dtype)
+    return result
+
+
 def _sanitize_str_dtypes(
     result: np.ndarray, data, dtype: Optional[DtypeObj], copy: bool
 ) -> np.ndarray:
@@ -565,7 +577,7 @@ def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bo
 
     Parameters
     ----------
-    arr : ndarray, scalar, list, tuple, iterator (catchall)
+    arr : ndarray, list, tuple, iterator (catchall)
         Excludes: ExtensionArray, Series, Index.
     dtype : np.dtype, ExtensionDtype or None
     copy : bool

pandas/core/dtypes/cast.py

@@ -1543,7 +1543,10 @@ def construct_1d_arraylike_from_scalar(
     """
 
     if dtype is None:
-        dtype, value = infer_dtype_from_scalar(value, pandas_dtype=True)
+        try:
+            dtype, value = infer_dtype_from_scalar(value, pandas_dtype=True)
+        except OutOfBoundsDatetime:
+            dtype = np.dtype(object)
 
     if is_extension_array_dtype(dtype):
         cls = dtype.construct_array_type()