PERF: lib.Validator iteration (#44495)

Author: jbrockmendel

pandas/_libs/lib.pyx

@@ -1704,10 +1704,15 @@ cdef class Validator:
     cdef bint _validate(self, ndarray values) except -1:
         cdef:
             Py_ssize_t i
-            Py_ssize_t n = self.n
+            Py_ssize_t n = values.size
+            flatiter it = PyArray_IterNew(values)
 
         for i in range(n):
-            if not self.is_valid(values[i]):
+            # The PyArray_GETITEM and PyArray_ITER_NEXT are faster
+            #  equivalents to `val = values[i]`
+            val = PyArray_GETITEM(values, PyArray_ITER_DATA(it))
+            PyArray_ITER_NEXT(it)
+            if not self.is_valid(val):
                 return False
 
         return True
@@ -1717,10 +1722,15 @@ cdef class Validator:
     cdef bint _validate_skipna(self, ndarray values) except -1:
         cdef:
             Py_ssize_t i
-            Py_ssize_t n = self.n
+            Py_ssize_t n = values.size
+            flatiter it = PyArray_IterNew(values)
 
         for i in range(n):
-            if not self.is_valid_skipna(values[i]):
+            # The PyArray_GETITEM and PyArray_ITER_NEXT are faster
+            #  equivalents to `val = values[i]`
+            val = PyArray_GETITEM(values, PyArray_ITER_DATA(it))
+            PyArray_ITER_NEXT(it)
+            if not self.is_valid_skipna(val):
                 return False
 
         return True

pandas/core/arrays/string_.py

@@ -318,9 +318,7 @@ def __init__(self, values, copy=False):
 
     def _validate(self):
         """Validate that we only store NA or strings."""
-        if len(self._ndarray) and not lib.is_string_array(
-            self._ndarray.ravel("K"), skipna=True
-        ):
+        if len(self._ndarray) and not lib.is_string_array(self._ndarray, skipna=True):
             raise ValueError("StringArray requires a sequence of strings or pandas.NA")
         if self._ndarray.dtype != "object":
             raise ValueError(

pandas/core/dtypes/inference.py

@@ -447,5 +447,5 @@ def is_inferred_bool_dtype(arr: ArrayLike) -> bool:
     if dtype == np.dtype(bool):
         return True
     elif dtype == np.dtype("object"):
-        return lib.is_bool_array(arr.ravel("K"))
+        return lib.is_bool_array(arr)
     return False

pandas/tests/dtypes/test_inference.py

@@ -1429,9 +1429,11 @@ def test_other_dtypes_for_array(self, func):
         func = getattr(lib, func)
         arr = np.array(["foo", "bar"])
         assert not func(arr)
+        assert not func(arr.reshape(2, 1))
 
         arr = np.array([1, 2])
         assert not func(arr)
+        assert not func(arr.reshape(2, 1))
 
     def test_date(self):