CLN: enforce the deprecation of the Series.argsort NA behavior (pandas-dev#58232)

* enforce deprecation of the Series.argsort NA behavior

* remove comments

* add a note to v3.0.0

* correct def argsort and tests

* correct def argsort/tests

* fix pre-commit error

* Restore numpy test

---------

Co-authored-by: Matthew Roeschke <[email protected]>

Author: 2 people

das as pd.py

@@ -0,0 +1,15 @@
+import pandas as pd
+
+# 데이터 프레임 생성
+data = {
+    "항목": ["Initial Cost", "Annual Operating Cost", "Annual Revenue", "Proud Number"],
+    "값": [1000000, 200000, 400000, "=B4/(B2+B3)"]
+}
+
+df = pd.DataFrame(data)
+
+# 엑셀 파일로 저장
+file_path = "/mnt/data/Proud_Number_Calculation.xlsx"
+df.to_excel(file_path, index=False)
+
+import ace_tools as tools; tools.display_dataframe_to_user(name="Proud Number Calculation", dataframe=df)

doc/source/whatsnew/v3.0.0.rst

@@ -382,6 +382,7 @@ Other Removals
 - Enforced deprecation of strings ``T``, ``L``, ``U``, and ``N`` denoting units in :class:`Timedelta` (:issue:`57627`)
 - Enforced deprecation of the behavior of :func:`concat` when ``len(keys) != len(objs)`` would truncate to the shorter of the two. Now this raises a ``ValueError`` (:issue:`43485`)
 - Enforced deprecation of the behavior of :meth:`DataFrame.replace` and :meth:`Series.replace` with :class:`CategoricalDtype` that would introduce new categories. (:issue:`58270`)
+- Enforced deprecation of the behavior of :meth:`Series.argsort` in the presence of NA values (:issue:`58232`)
 - Enforced deprecation of values "pad", "ffill", "bfill", and "backfill" for :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` (:issue:`57869`)
 - Enforced deprecation removing :meth:`Categorical.to_list`, use ``obj.tolist()`` instead (:issue:`51254`)
 - Enforced silent-downcasting deprecation for :ref:`all relevant methods <whatsnew_220.silent_downcasting>` (:issue:`54710`)

import pandas as pd.py

@@ -0,0 +1,15 @@
+import pandas as pd
+
+# 데이터 프레임 생성
+data = {
+    "Component": ["Displacement (lbs)", "Waterline Length (Lwl) (ft)", "Displacement/Length Ratio"],
+    "Value": [20000, 35, "=(B2/2240)/((B3/100)^3)"]
+}
+
+df = pd.DataFrame(data)
+
+# 엑셀 파일로 저장
+file_path = "/mnt/data/Displacement_Length_Ratio_Calculation.xlsx"
+df.to_excel(file_path, index=False)
+
+import ace_tools as tools; tools.display_dataframe_to_user(name="Displacement/Length Ratio Calculation", dataframe=df)

pandas/core/series.py

@@ -49,7 +49,6 @@
     deprecate_nonkeyword_arguments,
     doc,
 )
-from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import (
     validate_ascending,
     validate_bool_kwarg,
@@ -3722,25 +3721,7 @@ def argsort(
             # GH#54257 We allow -1 here so that np.argsort(series) works
             self._get_axis_number(axis)
 
-        values = self._values
-        mask = isna(values)
-
-        if mask.any():
-            # TODO(3.0): once this deprecation is enforced we can call
-            #  self.array.argsort directly, which will close GH#43840 and
-            #  GH#12694
-            warnings.warn(
-                "The behavior of Series.argsort in the presence of NA values is "
-                "deprecated. In a future version, NA values will be ordered "
-                "last instead of set to -1.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-            result = np.full(len(self), -1, dtype=np.intp)
-            notmask = ~mask
-            result[notmask] = np.argsort(values[notmask], kind=kind)
-        else:
-            result = np.argsort(values, kind=kind)
+        result = self.array.argsort(kind=kind)
 
         res = self._constructor(
             result, index=self.index, name=self.name, dtype=np.intp, copy=False

pandas/tests/extension/base/methods.py

@@ -116,10 +116,8 @@ def test_argsort_missing_array(self, data_missing_for_sorting):
         tm.assert_numpy_array_equal(result, expected)
 
     def test_argsort_missing(self, data_missing_for_sorting):
-        msg = "The behavior of Series.argsort in the presence of NA values"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
-            result = pd.Series(data_missing_for_sorting).argsort()
-        expected = pd.Series(np.array([1, -1, 0], dtype=np.intp))
+        result = pd.Series(data_missing_for_sorting).argsort()
+        expected = pd.Series(np.array([2, 0, 1], dtype=np.intp))
         tm.assert_series_equal(result, expected)
 
     def test_argmin_argmax(self, data_for_sorting, data_missing_for_sorting, na_value):

pandas/tests/series/methods/test_argsort.py

@@ -20,21 +20,15 @@ def test_argsort_axis(self):
 
     def test_argsort_numpy(self, datetime_series):
         ser = datetime_series
-
         res = np.argsort(ser).values
         expected = np.argsort(np.array(ser))
         tm.assert_numpy_array_equal(res, expected)
 
-        # with missing values
-        ts = ser.copy()
-        ts[::2] = np.nan
-
-        msg = "The behavior of Series.argsort in the presence of NA values"
-        with tm.assert_produces_warning(
-            FutureWarning, match=msg, check_stacklevel=False
-        ):
-            result = np.argsort(ts)[1::2]
-        expected = np.argsort(np.array(ts.dropna()))
+    def test_argsort_numpy_missing(self):
+        data = [0.1, np.nan, 0.2, np.nan, 0.3]
+        ser = Series(data)
+        result = np.argsort(ser)
+        expected = np.argsort(np.array(data))
 
         tm.assert_numpy_array_equal(result.values, expected)
 
@@ -56,10 +50,8 @@ def test_argsort_dt64(self, unit):
         expected = Series(range(5), dtype=np.intp)
         tm.assert_series_equal(result, expected)
 
-        msg = "The behavior of Series.argsort in the presence of NA values"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
-            result = shifted.argsort()
-        expected = Series(list(range(4)) + [-1], dtype=np.intp)
+        result = shifted.argsort()
+        expected = Series(list(range(4)) + [4], dtype=np.intp)
         tm.assert_series_equal(result, expected)
 
     def test_argsort_stable(self):

sdtesdg.txt

@@ -0,0 +1,23 @@
+import pandas as pd
+
+# 데이터 프레임 생성
+data = {
+    "Component": [
+        "Length Overall (LOA) (ft)", "Beam (ft)", "Draft (ft)", "Displacement (lbs)", 
+        "Waterline Length (Lwl) (ft)", "Speed (knots)", "Fuel Consumption (gallons/hour)", 
+        "Length-to-Beam Ratio", "Beam-to-Draft Ratio", "Displacement/Length Ratio", 
+        "Prismatic Coefficient (Cp)", "Speed-to-Length Ratio", "Fuel Consumption per Mile"
+    ],
+    "Value": [
+        40, 12, 4, 20000, 35, 10, 20, "=B2/B3", "=B3/B4", 
+        "=(B5/2240)/((B6/100)^3)", "=0.6", "=B7/SQRT(B6)", "=B8/B7"
+    ]
+}
+
+df = pd.DataFrame(data)
+
+# 엑셀 파일로 저장
+file_path = "/mnt/data/Powerboat_Coastal_Cruising_Ratio_Calculation.xlsx"
+df.to_excel(file_path, index=False)
+
+import pandas as pd; tools.display_dataframe_to_user(name="Powerboat Coastal Cruising Ratio Calculation", dataframe=df)