Merge remote-tracking branch 'upstream/main' into read-csv-from-directory

Author: fangchenli

doc/source/whatsnew/v3.0.0.rst

@@ -725,6 +725,7 @@ Timezones
 
 Numeric
 ^^^^^^^
+- Bug in :func:`api.types.infer_dtype` returning "mixed-integer-float" for float and ``pd.NA`` mix (:issue:`61621`)
 - Bug in :meth:`DataFrame.corr` where numerical precision errors resulted in correlations above ``1.0`` (:issue:`61120`)
 - Bug in :meth:`DataFrame.cov` raises a ``TypeError`` instead of returning potentially incorrect results or other errors (:issue:`53115`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)

pandas/_libs/lib.pyi

@@ -60,7 +60,7 @@ def is_time_array(values: np.ndarray, skipna: bool = ...): ...
 def is_date_array(values: np.ndarray, skipna: bool = ...): ...
 def is_datetime_array(values: np.ndarray, skipna: bool = ...): ...
 def is_string_array(values: np.ndarray, skipna: bool = ...): ...
-def is_float_array(values: np.ndarray): ...
+def is_float_array(values: np.ndarray, skipna: bool = ...): ...
 def is_integer_array(values: np.ndarray, skipna: bool = ...): ...
 def is_bool_array(values: np.ndarray, skipna: bool = ...): ...
 def fast_multiget(

pandas/_libs/lib.pyx

@@ -1752,7 +1752,7 @@ def infer_dtype(value: object, skipna: bool = True) -> str:
             return "complex"
 
     elif util.is_float_object(val):
-        if is_float_array(values):
+        if is_float_array(values, skipna=skipna):
             return "floating"
         elif is_integer_float_array(values, skipna=skipna):
             if is_integer_na_array(values, skipna=skipna):
@@ -1954,9 +1954,11 @@ cdef class FloatValidator(Validator):
 
 
 # Note: only python-exposed for tests
-cpdef bint is_float_array(ndarray values):
+cpdef bint is_float_array(ndarray values, bint skipna=True):
     cdef:
-        FloatValidator validator = FloatValidator(values.size, values.dtype)
+        FloatValidator validator = FloatValidator(values.size,
+                                                  values.dtype,
+                                                  skipna=skipna)
     return validator.validate(values)
 
 

pandas/core/dtypes/cast.py

@@ -1086,10 +1086,7 @@ def convert_dtypes(
             elif (
                 infer_objects
                 and input_array.dtype == object
-                and (
-                    isinstance(inferred_dtype, str)
-                    and inferred_dtype == "mixed-integer-float"
-                )
+                and (isinstance(inferred_dtype, str) and inferred_dtype == "floating")
             ):
                 inferred_dtype = pandas_dtype_func("Float64")
 

pandas/tests/dtypes/test_inference.py

@@ -1396,6 +1396,15 @@ def test_infer_dtype_period_with_na(self, na_value):
         arr = np.array([na_value, Period("2011-01", freq="D"), na_value])
         assert lib.infer_dtype(arr, skipna=True) == "period"
 
+    @pytest.mark.parametrize("na_value", [pd.NA, np.nan])
+    def test_infer_dtype_numeric_with_na(self, na_value):
+        # GH61621
+        ser = Series([1, 2, na_value], dtype=object)
+        assert lib.infer_dtype(ser, skipna=True) == "integer"
+
+        ser = Series([1.0, 2.0, na_value], dtype=object)
+        assert lib.infer_dtype(ser, skipna=True) == "floating"
+
     def test_infer_dtype_all_nan_nat_like(self):
         arr = np.array([np.nan, np.nan])
         assert lib.infer_dtype(arr, skipna=True) == "floating"

pandas/tests/extension/test_arrow.py

@@ -3081,7 +3081,7 @@ def test_infer_dtype_pyarrow_dtype(data, request):
     res = lib.infer_dtype(data)
     assert res != "unknown-array"
 
-    if data._hasna and res in ["floating", "datetime64", "timedelta64"]:
+    if data._hasna and res in ["datetime64", "timedelta64"]:
         mark = pytest.mark.xfail(
             reason="in infer_dtype pd.NA is not ignored in these cases "
             "even with skipna=True in the list(data) check below"