TST (string dtype): Adjust indexing string tests (#59541)

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: phofl

pandas/core/arrays/string_.py

@@ -713,6 +713,10 @@ def __setitem__(self, key, value) -> None:
         else:
             if not is_array_like(value):
                 value = np.asarray(value, dtype=object)
+            else:
+                # cast categories and friends to arrays to see if values are
+                # compatible, compatibility with arrow backed strings
+                value = np.asarray(value)
             if len(value) and not lib.is_string_array(value, skipna=True):
                 raise TypeError("Must provide strings.")
 

pandas/core/arrays/string_arrow.py

@@ -231,7 +231,7 @@ def _maybe_convert_setitem_value(self, value):
             value[isna(value)] = None
             for v in value:
                 if not (v is None or isinstance(v, str)):
-                    raise TypeError("Scalar must be NA or str")
+                    raise TypeError("Must provide strings")
         return super()._maybe_convert_setitem_value(value)
 
     def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:

pandas/tests/arrays/string_/test_string.py

@@ -101,10 +101,7 @@ def test_setitem_validates(cls, dtype):
     with pytest.raises(TypeError, match=msg):
         arr[0] = 10
 
-    if dtype.storage == "python":
-        msg = "Must provide strings."
-    else:
-        msg = "Scalar must be NA or str"
+    msg = "Must provide strings"
     with pytest.raises(TypeError, match=msg):
         arr[:] = np.array([1, 2])
 

pandas/tests/indexing/test_iloc.py

@@ -6,8 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.errors import IndexingError
 import pandas.util._test_decorators as td
 
@@ -1218,22 +1216,25 @@ def test_iloc_getitem_int_single_ea_block_view(self):
         arr[2] = arr[-1]
         assert ser[0] == arr[-1]
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
-    def test_iloc_setitem_multicolumn_to_datetime(self):
+    def test_iloc_setitem_multicolumn_to_datetime(self, using_infer_string):
         # GH#20511
         df = DataFrame({"A": ["2022-01-01", "2022-01-02"], "B": ["2021", "2022"]})
 
-        df.iloc[:, [0]] = DataFrame({"A": to_datetime(["2021", "2022"])})
-        expected = DataFrame(
-            {
-                "A": [
-                    Timestamp("2021-01-01 00:00:00"),
-                    Timestamp("2022-01-01 00:00:00"),
-                ],
-                "B": ["2021", "2022"],
-            }
-        )
-        tm.assert_frame_equal(df, expected, check_dtype=False)
+        if using_infer_string:
+            with pytest.raises(TypeError, match="Invalid value"):
+                df.iloc[:, [0]] = DataFrame({"A": to_datetime(["2021", "2022"])})
+        else:
+            df.iloc[:, [0]] = DataFrame({"A": to_datetime(["2021", "2022"])})
+            expected = DataFrame(
+                {
+                    "A": [
+                        Timestamp("2021-01-01 00:00:00"),
+                        Timestamp("2022-01-01 00:00:00"),
+                    ],
+                    "B": ["2021", "2022"],
+                }
+            )
+            tm.assert_frame_equal(df, expected, check_dtype=False)
 
 
 class TestILocErrors:

pandas/tests/indexing/test_indexing.py

@@ -8,8 +8,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.errors import IndexingError
 
 from pandas.core.dtypes.common import (
@@ -563,12 +561,12 @@ def test_string_slice_empty(self):
         with pytest.raises(KeyError, match="^0$"):
             df.loc["2011", 0]
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_astype_assignment(self, using_infer_string):
         # GH4312 (iloc)
         df_orig = DataFrame(
             [["1", "2", "3", ".4", 5, 6.0, "foo"]], columns=list("ABCDEFG")
         )
+        df_orig[list("ABCDG")] = df_orig[list("ABCDG")].astype(object)
 
         df = df_orig.copy()
 
@@ -578,9 +576,9 @@ def test_astype_assignment(self, using_infer_string):
         expected = DataFrame(
             [[1, 2, "3", ".4", 5, 6.0, "foo"]], columns=list("ABCDEFG")
         )
-        if not using_infer_string:
-            expected["A"] = expected["A"].astype(object)
-            expected["B"] = expected["B"].astype(object)
+        expected[list("CDG")] = expected[list("CDG")].astype(object)
+        expected["A"] = expected["A"].astype(object)
+        expected["B"] = expected["B"].astype(object)
         tm.assert_frame_equal(df, expected)
 
         # GH5702 (loc)
@@ -589,18 +587,16 @@ def test_astype_assignment(self, using_infer_string):
         expected = DataFrame(
             [[1, "2", "3", ".4", 5, 6.0, "foo"]], columns=list("ABCDEFG")
         )
-        if not using_infer_string:
-            expected["A"] = expected["A"].astype(object)
+        expected[list("ABCDG")] = expected[list("ABCDG")].astype(object)
         tm.assert_frame_equal(df, expected)
 
         df = df_orig.copy()
+
         df.loc[:, ["B", "C"]] = df.loc[:, ["B", "C"]].astype(np.int64)
         expected = DataFrame(
             [["1", 2, 3, ".4", 5, 6.0, "foo"]], columns=list("ABCDEFG")
         )
-        if not using_infer_string:
-            expected["B"] = expected["B"].astype(object)
-            expected["C"] = expected["C"].astype(object)
+        expected[list("ABCDG")] = expected[list("ABCDG")].astype(object)
         tm.assert_frame_equal(df, expected)
 
     def test_astype_assignment_full_replacements(self):

pandas/tests/indexing/test_loc.py

@@ -1,5 +1,6 @@
 """ test label based indexing with loc """
 from collections import namedtuple
+import contextlib
 from datetime import (
     date,
     datetime,
@@ -648,8 +649,9 @@ def test_loc_setitem_consistency_empty(self):
         expected["x"] = expected["x"].astype(np.int64)
         tm.assert_frame_equal(df, expected)
 
+    # incompatible dtype warning
     @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
-    def test_loc_setitem_consistency_slice_column_len(self):
+    def test_loc_setitem_consistency_slice_column_len(self, using_infer_string):
         # .loc[:,column] setting with slice == len of the column
         # GH10408
         levels = [
@@ -673,13 +675,24 @@ def test_loc_setitem_consistency_slice_column_len(self):
         ]
         df = DataFrame(values, index=mi, columns=cols)
 
-        df.loc[:, ("Respondent", "StartDate")] = to_datetime(
-            df.loc[:, ("Respondent", "StartDate")]
-        )
-        df.loc[:, ("Respondent", "EndDate")] = to_datetime(
-            df.loc[:, ("Respondent", "EndDate")]
-        )
-        df = df.infer_objects(copy=False)
+        ctx = contextlib.nullcontext()
+        if using_infer_string:
+            ctx = pytest.raises(TypeError, match="Invalid value")
+
+        with ctx:
+            df.loc[:, ("Respondent", "StartDate")] = to_datetime(
+                df.loc[:, ("Respondent", "StartDate")]
+            )
+        with ctx:
+            df.loc[:, ("Respondent", "EndDate")] = to_datetime(
+                df.loc[:, ("Respondent", "EndDate")]
+            )
+
+        if using_infer_string:
+            # infer-objects won't infer stuff anymore
+            return
+
+        df = df.infer_objects()
 
         # Adding a new key
         df.loc[:, ("Respondent", "Duration")] = (
@@ -1269,20 +1282,23 @@ def test_loc_reverse_assignment(self):
 
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="can't set int into string")
-    def test_loc_setitem_str_to_small_float_conversion_type(self):
+    def test_loc_setitem_str_to_small_float_conversion_type(self, using_infer_string):
         # GH#20388
 
         col_data = [str(np.random.default_rng(2).random() * 1e-12) for _ in range(5)]
         result = DataFrame(col_data, columns=["A"])
-        expected = DataFrame(col_data, columns=["A"], dtype=object)
+        expected = DataFrame(col_data, columns=["A"])
         tm.assert_frame_equal(result, expected)
 
         # assigning with loc/iloc attempts to set the values inplace, which
         #  in this case is successful
-        result.loc[result.index, "A"] = [float(x) for x in col_data]
-        expected = DataFrame(col_data, columns=["A"], dtype=float).astype(object)
-        tm.assert_frame_equal(result, expected)
+        if using_infer_string:
+            with pytest.raises(TypeError, match="Must provide strings"):
+                result.loc[result.index, "A"] = [float(x) for x in col_data]
+        else:
+            result.loc[result.index, "A"] = [float(x) for x in col_data]
+            expected = DataFrame(col_data, columns=["A"], dtype=float).astype(object)
+            tm.assert_frame_equal(result, expected)
 
         # assigning the entire column using __setitem__ swaps in the new array
         # GH#???
@@ -1458,9 +1474,6 @@ def test_loc_setitem_categorical_values_partial_column_slice(self):
             df.loc[2:3, "b"] = Categorical(["b", "b"], categories=["a", "b"])
         tm.assert_frame_equal(df, exp)
 
-    @pytest.mark.xfail(
-        using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
-    )
     def test_loc_setitem_single_row_categorical(self, using_infer_string):
         # GH#25495
         df = DataFrame({"Alpha": ["a"], "Numeric": [0]})