BUG: permit str dtype -> IntegerDtype conversions

Resolves #25472, resolves #25288.

Author: alexreg

pandas/core/arrays/integer.py

@@ -1,6 +1,9 @@
 from __future__ import annotations
 
-from typing import overload
+from typing import (
+    Optional,
+    overload,
+)
 import warnings
 
 import numpy as np
@@ -32,6 +35,7 @@
     is_integer_dtype,
     is_list_like,
     is_object_dtype,
+    is_string_dtype,
     pandas_dtype,
 )
 from pandas.core.dtypes.missing import isna
@@ -119,17 +123,20 @@ def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
         return None
 
 
-def safe_cast(values, dtype, copy: bool):
+def safe_cast(values, dtype, inferred_type: str | None, copy: bool):
     """
     Safely cast the values to the dtype if they
     are equivalent, meaning floats must be equivalent to the
     ints.
-
     """
+    if inferred_type in ("string", "unicode"):
+        # casts from str are always safe since they raise
+        # a ValueError if the str cannot be parsed into an int
+        return values.astype(dtype, copy=copy)
+
     try:
         return values.astype(dtype, casting="safe", copy=copy)
     except TypeError as err:
-
         casted = values.astype(dtype, copy=copy)
         if (casted == values).all():
             return casted
@@ -143,7 +150,7 @@ def coerce_to_array(
     values, dtype, mask=None, copy: bool = False
 ) -> tuple[np.ndarray, np.ndarray]:
     """
-    Coerce the input values array to numpy arrays with a mask
+    Coerce the input values array to numpy arrays with a mask.
 
     Parameters
     ----------
@@ -187,7 +194,9 @@ def coerce_to_array(
         return values, mask
 
     values = np.array(values, copy=copy)
-    if is_object_dtype(values):
+    inferred_type = None
+    # note that `is_string_dtype` subsumes `is_object_dtype`
+    if is_string_dtype(values):
         inferred_type = lib.infer_dtype(values, skipna=True)
         if inferred_type == "empty":
             values = np.empty(len(values))
@@ -198,6 +207,8 @@ def coerce_to_array(
             "mixed-integer",
             "integer-na",
             "mixed-integer-float",
+            "string",
+            "unicode",
         ]:
             raise TypeError(f"{values.dtype} cannot be converted to an IntegerDtype")
 
@@ -230,9 +241,7 @@ def coerce_to_array(
     if mask.any():
         values = values.copy()
         values[mask] = 1
-        values = safe_cast(values, dtype, copy=False)
-    else:
-        values = safe_cast(values, dtype, copy=False)
+    values = safe_cast(values, dtype, inferred_type, copy=False)
 
     return values, mask
 

pandas/core/dtypes/common.py

@@ -143,14 +143,14 @@ def ensure_python_int(value: int | np.integer) -> int:
 
 
 def classes(*klasses) -> Callable:
-    """evaluate if the tipo is a subclass of the klasses"""
+    """Evaluate if the tipo is a subclass of the klasses."""
     return lambda tipo: issubclass(tipo, klasses)
 
 
 def classes_and_not_datetimelike(*klasses) -> Callable:
     """
-    evaluate if the tipo is a subclass of the klasses
-    and not a datetimelike
+    Evaluate if the tipo is a subclass of the klasses
+    and not a datetimelike.
     """
     return lambda tipo: (
         issubclass(tipo, klasses)
@@ -674,7 +674,7 @@ def is_integer_dtype(arr_or_dtype) -> bool:
     """
     Check whether the provided array or dtype is of an integer dtype.
 
-    Unlike in `in_any_int_dtype`, timedelta64 instances will return False.
+    Unlike in `is_any_int_dtype`, timedelta64 instances will return False.
 
     The nullable Integer dtypes (e.g. pandas.Int64Dtype) are also considered
     as integer by this function.
@@ -726,7 +726,7 @@ def is_signed_integer_dtype(arr_or_dtype) -> bool:
     """
     Check whether the provided array or dtype is of a signed integer dtype.
 
-    Unlike in `in_any_int_dtype`, timedelta64 instances will return False.
+    Unlike in `is_any_int_dtype`, timedelta64 instances will return False.
 
     The nullable Integer dtypes (e.g. pandas.Int64Dtype) are also considered
     as integer by this function.
@@ -1521,7 +1521,7 @@ def is_complex_dtype(arr_or_dtype) -> bool:
 
 def _is_dtype(arr_or_dtype, condition) -> bool:
     """
-    Return a boolean if the condition is satisfied for the arr_or_dtype.
+    Return true if the condition is satisfied for the arr_or_dtype.
 
     Parameters
     ----------
@@ -1580,7 +1580,7 @@ def get_dtype(arr_or_dtype) -> DtypeObj:
 
 def _is_dtype_type(arr_or_dtype, condition) -> bool:
     """
-    Return a boolean if the condition is satisfied for the arr_or_dtype.
+    Return true if the condition is satisfied for the arr_or_dtype.
 
     Parameters
     ----------