TST: run python-dev CI on 3.14-dev (#61950)

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

Author: ngoldbaum

.github/workflows/unit-tests.yml

@@ -313,7 +313,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    if: false
+    # if: false
     defaults:
       run:
         shell: bash -eou pipefail {0}
@@ -345,7 +345,7 @@ jobs:
       - name: Set up Python Dev Version
         uses: actions/setup-python@v6
         with:
-          python-version: '3.13-dev'
+          python-version: '3.14-dev'
 
       - name: Build Environment
         run: |
@@ -358,6 +358,8 @@ jobs:
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
+        # TEMP allow this to fail until we fixed all test failures (related to chained assignment warnings)
+        continue-on-error: true
 
   # NOTE: this job must be kept in sync with the Pyodide build job in wheels.yml
   emscripten:

pandas/compat/__init__.py

@@ -19,6 +19,7 @@
     IS64,
     ISMUSL,
     PY312,
+    PY314,
     PYPY,
     WASM,
 )
@@ -154,6 +155,7 @@ def is_ci_environment() -> bool:
     "IS64",
     "ISMUSL",
     "PY312",
+    "PY314",
     "PYARROW_MIN_VERSION",
     "PYPY",
     "WASM",

pandas/compat/_constants.py

@@ -14,6 +14,7 @@
 IS64 = sys.maxsize > 2**32
 
 PY312 = sys.version_info >= (3, 12)
+PY314 = sys.version_info >= (3, 14)
 PYPY = platform.python_implementation() == "PyPy"
 WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
@@ -23,6 +24,7 @@
     "IS64",
     "ISMUSL",
     "PY312",
+    "PY314",
     "PYPY",
     "WASM",
 ]

pandas/tests/frame/test_query_eval.py

@@ -168,7 +168,7 @@ def test_query_duplicate_column_name(self, engine, parser):
             }
         ).rename(columns={"B": "A"})
 
-        res = df.query('C == 1', engine=engine, parser=parser)
+        res = df.query("C == 1", engine=engine, parser=parser)
 
         expect = DataFrame(
             [[1, 1, 1]],
@@ -1411,7 +1411,7 @@ def test_expr_with_column_name_with_backtick_and_hash(self):
     def test_expr_with_column_name_with_backtick(self):
         # GH 59285
         df = DataFrame({"a`b": (1, 2, 3), "ab": (4, 5, 6)})
-        result = df.query("`a``b` < 2")  # noqa
+        result = df.query("`a``b` < 2")
         # Note: Formatting checks may wrongly consider the above ``inline code``.
         expected = df[df["a`b"] < 2]
         tm.assert_frame_equal(result, expected)

pandas/tests/indexes/test_indexing.py

@@ -18,6 +18,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY314
 from pandas.errors import InvalidIndexError
 
 from pandas.core.dtypes.common import (
@@ -160,13 +161,19 @@ def test_contains_requires_hashable_raises(self, index):
         with pytest.raises(TypeError, match=msg):
             [] in index
 
+        if PY314:
+            container_or_iterable = "a container or iterable"
+        else:
+            container_or_iterable = "iterable"
+
         msg = "|".join(
             [
                 r"unhashable type: 'dict'",
                 r"must be real number, not dict",
                 r"an integer is required",
                 r"\{\}",
-                r"pandas\._libs\.interval\.IntervalTree' is not iterable",
+                r"pandas\._libs\.interval\.IntervalTree' is not "
+                f"{container_or_iterable}",
             ]
         )
         with pytest.raises(TypeError, match=msg):

pandas/tests/io/parser/test_quoting.py

@@ -8,6 +8,7 @@
 
 import pytest
 
+from pandas.compat import PY314
 from pandas.errors import ParserError
 
 from pandas import DataFrame
@@ -20,15 +21,24 @@
 skip_pyarrow = pytest.mark.usefixtures("pyarrow_skip")
 
 
+if PY314:
+    # TODO: write a regex that works with all new possitibilities here
+    MSG1 = ""
+    MSG2 = r"[\s\S]*"
+else:
+    MSG1 = "a(n)? 1-character string"
+    MSG2 = "string( or None)?"
+
+
 @pytest.mark.parametrize(
     "kwargs,msg",
     [
-        ({"quotechar": "foo"}, '"quotechar" must be a(n)? 1-character string'),
+        ({"quotechar": "foo"}, f'"quotechar" must be {MSG1}'),
         (
             {"quotechar": None, "quoting": csv.QUOTE_MINIMAL},
             "quotechar must be set if quoting enabled",
         ),
-        ({"quotechar": 2}, '"quotechar" must be string( or None)?, not int'),
+        ({"quotechar": 2}, f'"quotechar" must be {MSG2}, not int'),
     ],
 )
 @skip_pyarrow  # ParserError: CSV parse error: Empty CSV file or block
@@ -87,8 +97,12 @@ def test_null_quote_char(all_parsers, quoting, quote_char):
 
     if quoting != csv.QUOTE_NONE:
         # Sanity checking.
+        if not PY314:
+            msg = "1-character string"
+        else:
+            msg = "unicode character or None"
         msg = (
-            '"quotechar" must be a 1-character string'
+            f'"quotechar" must be a {msg}'
             if all_parsers.engine == "python" and quote_char == ""
             else "quotechar must be set if quoting enabled"
         )

pandas/tests/reshape/merge/test_merge.py

@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY314
+
 from pandas.core.dtypes.common import (
     is_object_dtype,
     is_string_dtype,
@@ -2420,10 +2422,18 @@ def test_merge_suffix_raises(suffixes):
         merge(a, b, left_index=True, right_index=True, suffixes=suffixes)
 
 
+TWO_GOT_THREE = "2, got 3" if PY314 else "2"
+
+
 @pytest.mark.parametrize(
     "col1, col2, suffixes, msg",
     [
-        ("a", "a", ("a", "b", "c"), r"too many values to unpack \(expected 2\)"),
+        (
+            "a",
+            "a",
+            ("a", "b", "c"),
+            (rf"too many values to unpack \(expected {TWO_GOT_THREE}\)"),
+        ),
         ("a", "a", tuple("a"), r"not enough values to unpack \(expected 2, got 1\)"),
     ],
 )

pandas/tests/scalar/period/test_period.py

@@ -16,6 +16,7 @@
 from pandas._libs.tslibs.np_datetime import OutOfBoundsDatetime
 from pandas._libs.tslibs.parsing import DateParseError
 from pandas._libs.tslibs.period import INVALID_FREQ_ERR_MSG
+from pandas.compat import PY314
 from pandas.errors import Pandas4Warning
 
 from pandas import (
@@ -347,7 +348,10 @@ def test_invalid_arguments(self):
         msg = '^Given date string "-2000" not likely a datetime$'
         with pytest.raises(ValueError, match=msg):
             Period("-2000", "Y")
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "day 0 must be in range 1..31 for month 1 in year 1: 0"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(DateParseError, match=msg):
             Period("0", "Y")
         msg = "Unknown datetime string format, unable to parse"

pandas/tests/scalar/timestamp/test_constructors.py

@@ -17,6 +17,7 @@
 import pytest
 
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
+from pandas.compat import PY314
 from pandas.errors import (
     OutOfBoundsDatetime,
     Pandas4Warning,
@@ -221,7 +222,10 @@ def test_constructor_positional(self):
         with pytest.raises(ValueError, match=msg):
             Timestamp(2000, 13, 1)
 
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "must be in range 1..31 for month 1 in year 2000"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(ValueError, match=msg):
             Timestamp(2000, 1, 0)
         with pytest.raises(ValueError, match=msg):
@@ -245,7 +249,10 @@ def test_constructor_keyword(self):
         with pytest.raises(ValueError, match=msg):
             Timestamp(year=2000, month=13, day=1)
 
-        msg = "day is out of range for month"
+        if PY314:
+            msg = "must be in range 1..31 for month 1 in year 2000"
+        else:
+            msg = "day is out of range for month"
         with pytest.raises(ValueError, match=msg):
             Timestamp(year=2000, month=1, day=0)
         with pytest.raises(ValueError, match=msg):

pandas/tests/tools/test_to_datetime.py

@@ -21,7 +21,10 @@
     iNaT,
     parsing,
 )
-from pandas.compat import WASM
+from pandas.compat import (
+    PY314,
+    WASM,
+)
 from pandas.errors import (
     OutOfBoundsDatetime,
     OutOfBoundsTimedelta,
@@ -57,6 +60,16 @@
     r"alongside this."
 )
 
+if PY314:
+    NOT_99 = ", not 99"
+    DAY_IS_OUT_OF_RANGE = (
+        r"day \d{1,2} must be in range 1\.\.\d{1,2} for "
+        r"month \d{1,2} in year \d{4}"
+    )
+else:
+    NOT_99 = ""
+    DAY_IS_OUT_OF_RANGE = "day is out of range for month"
+
 
 class TestTimeConversionFormats:
     def test_to_datetime_readonly(self, writable):
@@ -1378,7 +1391,7 @@ def test_datetime_invalid_scalar(self, value, format):
                 r'^Given date string "a" not likely a datetime$',
                 r'^unconverted data remains when parsing with format "%H:%M:%S": "9". '
                 f"{PARSING_ERR_MSG}$",
-                r"^second must be in 0..59: 00:01:99$",
+                rf"^second must be in 0..59{NOT_99}: 00:01:99$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -1430,7 +1443,7 @@ def test_datetime_invalid_index(self, values, format):
                 f"{PARSING_ERR_MSG}$",
                 r'^unconverted data remains when parsing with format "%H:%M:%S": "9". '
                 f"{PARSING_ERR_MSG}$",
-                r"^second must be in 0..59: 00:01:99$",
+                rf"^second must be in 0..59{NOT_99}: 00:01:99$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -2857,7 +2870,10 @@ def test_day_not_in_month_coerce(self, cache, arg, format):
         assert isna(to_datetime(arg, errors="coerce", format=format, cache=cache))
 
     def test_day_not_in_month_raise(self, cache):
-        msg = "day is out of range for month: 2015-02-29"
+        if PY314:
+            msg = "day 29 must be in range 1..28 for month 2 in year 2015: 2015-02-29"
+        else:
+            msg = "day is out of range for month: 2015-02-29"
         with pytest.raises(ValueError, match=msg):
             to_datetime("2015-02-29", errors="raise", cache=cache)
 
@@ -2867,12 +2883,12 @@ def test_day_not_in_month_raise(self, cache):
             (
                 "2015-02-29",
                 "%Y-%m-%d",
-                f"^day is out of range for month. {PARSING_ERR_MSG}$",
+                f"^{DAY_IS_OUT_OF_RANGE}. {PARSING_ERR_MSG}$",
             ),
             (
                 "2015-29-02",
                 "%Y-%d-%m",
-                f"^day is out of range for month. {PARSING_ERR_MSG}$",
+                f"^{DAY_IS_OUT_OF_RANGE}. {PARSING_ERR_MSG}$",
             ),
             (
                 "2015-02-32",
@@ -2889,12 +2905,12 @@ def test_day_not_in_month_raise(self, cache):
             (
                 "2015-04-31",
                 "%Y-%m-%d",
-                f"^day is out of range for month. {PARSING_ERR_MSG}$",
+                f"^{DAY_IS_OUT_OF_RANGE}. {PARSING_ERR_MSG}$",
             ),
             (
                 "2015-31-04",
                 "%Y-%d-%m",
-                f"^day is out of range for month. {PARSING_ERR_MSG}$",
+                f"^{DAY_IS_OUT_OF_RANGE}. {PARSING_ERR_MSG}$",
             ),
         ],
     )