From c338620fdce13ed59776192096e57bf78d65a32b Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Sun, 21 Sep 2025 17:28:12 -0700
Subject: [PATCH 1/3] Reduce extensionarray data length from 100 to 10

---
 .../tests/arrays/boolean/test_arithmetic.py   |  2 +-
 .../tests/arrays/boolean/test_comparison.py   |  2 +-
 pandas/tests/arrays/boolean/test_reduction.py |  2 +-
 pandas/tests/arrays/floating/conftest.py      |  7 +---
 pandas/tests/arrays/integer/conftest.py       |  2 +-
 pandas/tests/extension/base/getitem.py        |  2 +-
 pandas/tests/extension/base/interface.py      |  4 +--
 pandas/tests/extension/base/methods.py        |  3 +-
 pandas/tests/extension/base/ops.py            |  4 +--
 pandas/tests/extension/conftest.py            |  4 +--
 pandas/tests/extension/decimal/array.py       |  4 +--
 .../tests/extension/decimal/test_decimal.py   | 10 +++---
 pandas/tests/extension/json/array.py          |  4 +--
 pandas/tests/extension/json/test_json.py      |  6 ++--
 pandas/tests/extension/list/array.py          |  6 ++--
 pandas/tests/extension/list/test_list.py      |  6 ++--
 pandas/tests/extension/test_arrow.py          | 34 +++++++++----------
 pandas/tests/extension/test_categorical.py    |  6 ++--
 pandas/tests/extension/test_datetime.py       |  2 +-
 pandas/tests/extension/test_interval.py       | 11 +++---
 pandas/tests/extension/test_masked.py         | 16 +++------
 pandas/tests/extension/test_numpy.py          |  6 ++--
 pandas/tests/extension/test_period.py         |  2 +-
 pandas/tests/extension/test_sparse.py         | 14 ++++----
 pandas/tests/extension/test_string.py         |  4 +--
 25 files changed, 74 insertions(+), 89 deletions(-)

diff --git a/pandas/tests/arrays/boolean/test_arithmetic.py b/pandas/tests/arrays/boolean/test_arithmetic.py
index 9ff690cdc914d..9553c4cf7ce5f 100644
--- a/pandas/tests/arrays/boolean/test_arithmetic.py
+++ b/pandas/tests/arrays/boolean/test_arithmetic.py
@@ -11,7 +11,7 @@
 def data():
     """Fixture returning boolean array with valid and missing values."""
     return pd.array(
-        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/boolean/test_comparison.py b/pandas/tests/arrays/boolean/test_comparison.py
index 2eeb9da574b1e..8c35a77253494 100644
--- a/pandas/tests/arrays/boolean/test_comparison.py
+++ b/pandas/tests/arrays/boolean/test_comparison.py
@@ -11,7 +11,7 @@
 def data():
     """Fixture returning boolean array with valid and missing data"""
     return pd.array(
-        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/boolean/test_reduction.py b/pandas/tests/arrays/boolean/test_reduction.py
index 7071c6f8844e4..8cb5035e264f6 100644
--- a/pandas/tests/arrays/boolean/test_reduction.py
+++ b/pandas/tests/arrays/boolean/test_reduction.py
@@ -8,7 +8,7 @@
 def data():
     """Fixture returning boolean array, with valid and missing values."""
     return pd.array(
-        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/floating/conftest.py b/pandas/tests/arrays/floating/conftest.py
index fc29e3bfd9962..9b6f65275ae2e 100644
--- a/pandas/tests/arrays/floating/conftest.py
+++ b/pandas/tests/arrays/floating/conftest.py
@@ -1,4 +1,3 @@
-import numpy as np
 import pytest
 
 import pandas as pd
@@ -18,11 +17,7 @@ def dtype(request):
 def data(dtype):
     """Fixture returning 'data' array according to parametrized float 'dtype'"""
     return pd.array(
-        list(np.arange(0.1, 0.9, 0.1))
-        + [pd.NA]
-        + list(np.arange(1, 9.8, 0.1))
-        + [pd.NA]
-        + [9.9, 10.0],
+        [0.1, 0.2] + [pd.NA] + [1.0, 1.1, 1.2, 1.3] + [pd.NA] + [9.9, 10.0],
         dtype=dtype,
     )
 
diff --git a/pandas/tests/arrays/integer/conftest.py b/pandas/tests/arrays/integer/conftest.py
index 79275522d49f5..8b1ae06d4aafc 100644
--- a/pandas/tests/arrays/integer/conftest.py
+++ b/pandas/tests/arrays/integer/conftest.py
@@ -39,7 +39,7 @@ def data(dtype):
     Used to test dtype conversion with and without missing values.
     """
     return pd.array(
-        list(range(8)) + [pd.NA] + list(range(10, 98)) + [pd.NA] + [99, 100],
+        [0, 1] + [pd.NA] + [10, 11, 12, 13] + [pd.NA] + [99, 100],
         dtype=dtype,
     )
 
diff --git a/pandas/tests/extension/base/getitem.py b/pandas/tests/extension/base/getitem.py
index 1f3680bf67e90..09e8d8ba93092 100644
--- a/pandas/tests/extension/base/getitem.py
+++ b/pandas/tests/extension/base/getitem.py
@@ -408,7 +408,7 @@ def test_take_series(self, data):
         result = s.take([0, -1])
         expected = pd.Series(
             data._from_sequence([data[0], data[len(data) - 1]], dtype=s.dtype),
-            index=range(0, 198, 99),
+            index=s.index.take([0, -1]),
         )
         tm.assert_series_equal(result, expected)
 
diff --git a/pandas/tests/extension/base/interface.py b/pandas/tests/extension/base/interface.py
index 79eb64b5a654f..883c0ba8e35b6 100644
--- a/pandas/tests/extension/base/interface.py
+++ b/pandas/tests/extension/base/interface.py
@@ -19,10 +19,10 @@ class BaseInterfaceTests:
     # ------------------------------------------------------------------------
 
     def test_len(self, data):
-        assert len(data) == 100
+        assert len(data) == 10
 
     def test_size(self, data):
-        assert data.size == 100
+        assert data.size == 10
 
     def test_ndim(self, data):
         assert data.ndim == 1
diff --git a/pandas/tests/extension/base/methods.py b/pandas/tests/extension/base/methods.py
index 90ec84a30a129..084ee61243fd0 100644
--- a/pandas/tests/extension/base/methods.py
+++ b/pandas/tests/extension/base/methods.py
@@ -39,7 +39,6 @@ def test_value_counts_default_dropna(self, data):
 
     @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
-        all_data = all_data[:10]
         if dropna:
             other = all_data[~all_data.isna()]
         else:
@@ -52,7 +51,7 @@ def test_value_counts(self, all_data, dropna):
 
     def test_value_counts_with_normalize(self, data):
         # GH 33172
-        data = data[:10].unique()
+        data = data.unique()
         values = np.array(data[~data.isna()])
         ser = pd.Series(data, dtype=data.dtype)
 
diff --git a/pandas/tests/extension/base/ops.py b/pandas/tests/extension/base/ops.py
index 222ff42d45052..583435b674ba1 100644
--- a/pandas/tests/extension/base/ops.py
+++ b/pandas/tests/extension/base/ops.py
@@ -250,9 +250,7 @@ class BaseUnaryOpsTests(BaseOpsUtil):
     def test_invert(self, data):
         ser = pd.Series(data, name="name")
         try:
-            # 10 is an arbitrary choice here, just avoid iterating over
-            #  the whole array to trim test runtime
-            [~x for x in data[:10]]
+            [~x for x in data]
         except TypeError:
             # scalars don't support invert -> we don't expect the vectorized
             #  operation to succeed
diff --git a/pandas/tests/extension/conftest.py b/pandas/tests/extension/conftest.py
index 97fb5a0bc5066..1376af5e51a6b 100644
--- a/pandas/tests/extension/conftest.py
+++ b/pandas/tests/extension/conftest.py
@@ -14,7 +14,7 @@ def dtype():
 @pytest.fixture
 def data():
     """
-    Length-100 array for this type.
+    Length-10 array for this type.
 
     * data[0] and data[1] should both be non missing
     * data[0] and data[1] should not be equal
@@ -25,7 +25,7 @@ def data():
 @pytest.fixture
 def data_for_twos(dtype):
     """
-    Length-100 array in which all the elements are two.
+    Length-10 array in which all the elements are two.
 
     Call pytest.skip in your fixture if the dtype does not support divmod.
     """
diff --git a/pandas/tests/extension/decimal/array.py b/pandas/tests/extension/decimal/array.py
index 6f7733ad7693e..aaba6295e5815 100644
--- a/pandas/tests/extension/decimal/array.py
+++ b/pandas/tests/extension/decimal/array.py
@@ -301,8 +301,8 @@ def to_decimal(values, context=None):
     return DecimalArray([decimal.Decimal(x) for x in values], context=context)
 
 
-def make_data():
-    return [decimal.Decimal(val) for val in np.random.default_rng(2).random(100)]
+def make_data(n: int):
+    return [decimal.Decimal(val) for val in np.random.default_rng(2).random(n)]
 
 
 DecimalArray._add_arithmetic_ops()
diff --git a/pandas/tests/extension/decimal/test_decimal.py b/pandas/tests/extension/decimal/test_decimal.py
index 39ce93d37da45..538c025546426 100644
--- a/pandas/tests/extension/decimal/test_decimal.py
+++ b/pandas/tests/extension/decimal/test_decimal.py
@@ -25,12 +25,12 @@ def dtype():
 
 @pytest.fixture
 def data():
-    return DecimalArray(make_data())
+    return DecimalArray(make_data(10))
 
 
 @pytest.fixture
 def data_for_twos():
-    return DecimalArray([decimal.Decimal(2) for _ in range(100)])
+    return DecimalArray([decimal.Decimal(2) for _ in range(10)])
 
 
 @pytest.fixture
@@ -340,7 +340,7 @@ def test_groupby_agg():
     # Ensure that the result of agg is inferred to be decimal dtype
     # https://github.com/pandas-dev/pandas/issues/29141
 
-    data = make_data()[:5]
+    data = make_data(5)
     df = pd.DataFrame(
         {"id1": [0, 0, 0, 1, 1], "id2": [0, 1, 0, 1, 1], "decimals": DecimalArray(data)}
     )
@@ -377,7 +377,7 @@ def DecimalArray__my_sum(self):
 
     monkeypatch.setattr(DecimalArray, "my_sum", DecimalArray__my_sum, raising=False)
 
-    data = make_data()[:5]
+    data = make_data(5)
     df = pd.DataFrame({"id": [0, 0, 0, 1, 1], "decimals": DecimalArray(data)})
     expected = pd.Series(to_decimal([data[0] + data[1] + data[2], data[3] + data[4]]))
 
@@ -399,7 +399,7 @@ def DecimalArray__array__(self, dtype=None):
 
     monkeypatch.setattr(DecimalArray, "__array__", DecimalArray__array__, raising=False)
 
-    data = make_data()
+    data = make_data(10)
     s = pd.Series(DecimalArray(data))
     df = pd.DataFrame({"a": s, "b": range(len(s))})
 
diff --git a/pandas/tests/extension/json/array.py b/pandas/tests/extension/json/array.py
index bc30ba4ef7769..828e4415bd295 100644
--- a/pandas/tests/extension/json/array.py
+++ b/pandas/tests/extension/json/array.py
@@ -255,7 +255,7 @@ def _pad_or_backfill(self, *, method, limit=None, copy=True):
         return super()._pad_or_backfill(method=method, limit=limit, copy=copy)
 
 
-def make_data():
+def make_data(n: int):
     # TODO: Use a regular dict. See _NDFrameIndexer._setitem_with_indexer
     rng = np.random.default_rng(2)
     return [
@@ -265,5 +265,5 @@ def make_data():
                 for _ in range(rng.integers(0, 10))
             ]
         )
-        for _ in range(100)
+        for _ in range(n)
     ]
diff --git a/pandas/tests/extension/json/test_json.py b/pandas/tests/extension/json/test_json.py
index 5e1980c202f62..0d3b4e1a7cde6 100644
--- a/pandas/tests/extension/json/test_json.py
+++ b/pandas/tests/extension/json/test_json.py
@@ -26,8 +26,8 @@ def dtype():
 
 @pytest.fixture
 def data():
-    """Length-100 PeriodArray for semantics test."""
-    data = make_data()
+    """Length-10 JSONArray for semantics test."""
+    data = make_data(10)
 
     # Why the while loop? NumPy is unable to construct an ndarray from
     # equal-length ndarrays. Many of our operations involve coercing the
@@ -36,7 +36,7 @@ def data():
     # the first two elements, so that's what we'll check.
 
     while len(data[0]) == len(data[1]):
-        data = make_data()
+        data = make_data(10)
 
     return JSONArray(data)
 
diff --git a/pandas/tests/extension/list/array.py b/pandas/tests/extension/list/array.py
index 009462a1406ec..6da5d1cf25fad 100644
--- a/pandas/tests/extension/list/array.py
+++ b/pandas/tests/extension/list/array.py
@@ -125,12 +125,12 @@ def _concat_same_type(cls, to_concat):
         return cls(data)
 
 
-def make_data():
+def make_data(n: int):
     # TODO: Use a regular dict. See _NDFrameIndexer._setitem_with_indexer
     rng = np.random.default_rng(2)
-    data = np.empty(100, dtype=object)
+    data = np.empty(n, dtype=object)
     data[:] = [
         [rng.choice(list(string.ascii_letters)) for _ in range(rng.integers(0, 10))]
-        for _ in range(100)
+        for _ in range(n)
     ]
     return data
diff --git a/pandas/tests/extension/list/test_list.py b/pandas/tests/extension/list/test_list.py
index ac396cd3c60d4..3cb1c1916492c 100644
--- a/pandas/tests/extension/list/test_list.py
+++ b/pandas/tests/extension/list/test_list.py
@@ -15,11 +15,11 @@ def dtype():
 
 @pytest.fixture
 def data():
-    """Length-100 ListArray for semantics test."""
-    data = make_data()
+    """Length-10 ListArray for semantics test."""
+    data = make_data(10)
 
     while len(data[0]) == len(data[1]):
-        data = make_data()
+        data = make_data(10)
 
     return ListArray(data)
 
diff --git a/pandas/tests/extension/test_arrow.py b/pandas/tests/extension/test_arrow.py
index 36dd91195d241..66f17c147ff71 100644
--- a/pandas/tests/extension/test_arrow.py
+++ b/pandas/tests/extension/test_arrow.py
@@ -93,57 +93,57 @@ def dtype(request):
 def data(dtype):
     pa_dtype = dtype.pyarrow_dtype
     if pa.types.is_boolean(pa_dtype):
-        data = [True, False] * 4 + [None] + [True, False] * 44 + [None] + [True, False]
+        data = [True, False] + [None] + [True, False] * 2 + [None] + [True, False]
     elif pa.types.is_floating(pa_dtype):
-        data = [1.0, 0.0] * 4 + [None] + [-2.0, -1.0] * 44 + [None] + [0.5, 99.5]
+        data = [1.0, 0.0] + [None] + [-2.0, -1.0] * 2 + [None] + [0.5, 99.5]
     elif pa.types.is_signed_integer(pa_dtype):
-        data = [1, 0] * 4 + [None] + [-2, -1] * 44 + [None] + [1, 99]
+        data = [1, 0] + [None] + [-2, -1] * 2 + [None] + [1, 99]
     elif pa.types.is_unsigned_integer(pa_dtype):
-        data = [1, 0] * 4 + [None] + [2, 1] * 44 + [None] + [1, 99]
+        data = [1, 0] + [None] + [2, 1] * 2 + [None] + [1, 99]
     elif pa.types.is_decimal(pa_dtype):
         data = (
-            [Decimal("1"), Decimal("0.0")] * 4
+            [Decimal("1"), Decimal("0.0")]
             + [None]
-            + [Decimal("-2.0"), Decimal("-1.0")] * 44
+            + [Decimal("-2.0"), Decimal("-1.0")] * 2
             + [None]
             + [Decimal("0.5"), Decimal("33.123")]
         )
     elif pa.types.is_date(pa_dtype):
         data = (
-            [date(2022, 1, 1), date(1999, 12, 31)] * 4
+            [date(2022, 1, 1), date(1999, 12, 31)]
             + [None]
-            + [date(2022, 1, 1), date(2022, 1, 1)] * 44
+            + [date(2022, 1, 1), date(2022, 1, 1)] * 2
             + [None]
             + [date(1999, 12, 31), date(1999, 12, 31)]
         )
     elif pa.types.is_timestamp(pa_dtype):
         data = (
-            [datetime(2020, 1, 1, 1, 1, 1, 1), datetime(1999, 1, 1, 1, 1, 1, 1)] * 4
+            [datetime(2020, 1, 1, 1, 1, 1, 1), datetime(1999, 1, 1, 1, 1, 1, 1)]
             + [None]
-            + [datetime(2020, 1, 1, 1), datetime(1999, 1, 1, 1)] * 44
+            + [datetime(2020, 1, 1, 1), datetime(1999, 1, 1, 1)] * 2
             + [None]
             + [datetime(2020, 1, 1), datetime(1999, 1, 1)]
         )
     elif pa.types.is_duration(pa_dtype):
         data = (
-            [timedelta(1), timedelta(1, 1)] * 4
+            [timedelta(1), timedelta(1, 1)]
             + [None]
-            + [timedelta(-1), timedelta(0)] * 44
+            + [timedelta(-1), timedelta(0)] * 2
             + [None]
             + [timedelta(-10), timedelta(10)]
         )
     elif pa.types.is_time(pa_dtype):
         data = (
-            [time(12, 0), time(0, 12)] * 4
+            [time(12, 0), time(0, 12)]
             + [None]
-            + [time(0, 0), time(1, 1)] * 44
+            + [time(0, 0), time(1, 1)] * 2
             + [None]
             + [time(0, 5), time(5, 0)]
         )
     elif pa.types.is_string(pa_dtype):
-        data = ["a", "b"] * 4 + [None] + ["1", "2"] * 44 + [None] + ["!", ">"]
+        data = ["a", "b"] + [None] + ["1", "2"] * 2 + [None] + ["!", ">"]
     elif pa.types.is_binary(pa_dtype):
-        data = [b"a", b"b"] * 4 + [None] + [b"1", b"2"] * 44 + [None] + [b"!", b">"]
+        data = [b"a", b"b"] + [None] + [b"1", b"2"] * 2 + [None] + [b"!", b">"]
     else:
         raise NotImplementedError
     return pd.array(data, dtype=dtype)
@@ -264,7 +264,7 @@ def data_for_twos(data):
         or pa.types.is_decimal(pa_dtype)
         or pa.types.is_duration(pa_dtype)
     ):
-        return pd.array([2] * 100, dtype=data.dtype)
+        return pd.array([2] * 10, dtype=data.dtype)
     # tests will be xfailed where 2 is not a valid scalar for pa_dtype
     return data
     # TODO: skip otherwise?
diff --git a/pandas/tests/extension/test_categorical.py b/pandas/tests/extension/test_categorical.py
index 8f8af607585df..275f8e2f859a4 100644
--- a/pandas/tests/extension/test_categorical.py
+++ b/pandas/tests/extension/test_categorical.py
@@ -28,9 +28,9 @@
 from pandas.tests.extension import base
 
 
-def make_data():
+def make_data(n: int):
     while True:
-        values = np.random.default_rng(2).choice(list(string.ascii_letters), size=100)
+        values = np.random.default_rng(2).choice(list(string.ascii_letters), size=n)
         # ensure we meet the requirements
         # 1. first two not null
         # 2. first and second are different
@@ -51,7 +51,7 @@ def data():
     * data[0] and data[1] should both be non missing
     * data[0] and data[1] should not be equal
     """
-    return Categorical(make_data())
+    return Categorical(make_data(10))
 
 
 @pytest.fixture
diff --git a/pandas/tests/extension/test_datetime.py b/pandas/tests/extension/test_datetime.py
index 356d5352f41f4..ab9eff220914d 100644
--- a/pandas/tests/extension/test_datetime.py
+++ b/pandas/tests/extension/test_datetime.py
@@ -33,7 +33,7 @@ def dtype():
 @pytest.fixture
 def data(dtype):
     data = DatetimeArray._from_sequence(
-        pd.date_range("2000", periods=100, tz=dtype.tz), dtype=dtype
+        pd.date_range("2000", periods=10, tz=dtype.tz), dtype=dtype
     )
     return data
 
diff --git a/pandas/tests/extension/test_interval.py b/pandas/tests/extension/test_interval.py
index 8d437fc5d238b..c457d702ba043 100644
--- a/pandas/tests/extension/test_interval.py
+++ b/pandas/tests/extension/test_interval.py
@@ -31,10 +31,9 @@
     import pandas as pd
 
 
-def make_data():
-    N = 100
-    left_array = np.random.default_rng(2).uniform(size=N).cumsum()
-    right_array = left_array + np.random.default_rng(2).uniform(size=N)
+def make_data(n: int):
+    left_array = np.random.default_rng(2).uniform(size=n).cumsum()
+    right_array = left_array + np.random.default_rng(2).uniform(size=n)
     return [Interval(left, right) for left, right in zip(left_array, right_array)]
 
 
@@ -45,8 +44,8 @@ def dtype():
 
 @pytest.fixture
 def data():
-    """Length-100 PeriodArray for semantics test."""
-    return IntervalArray(make_data())
+    """Length-10 IntervalArray for semantics test."""
+    return IntervalArray(make_data(10))
 
 
 @pytest.fixture
diff --git a/pandas/tests/extension/test_masked.py b/pandas/tests/extension/test_masked.py
index e3764b2514680..073f4e63a422b 100644
--- a/pandas/tests/extension/test_masked.py
+++ b/pandas/tests/extension/test_masked.py
@@ -61,21 +61,15 @@
 
 
 def make_data():
-    return list(range(1, 9)) + [pd.NA] + list(range(10, 98)) + [pd.NA] + [99, 100]
+    return [0, 1] + [pd.NA] + [10, 11, 12, 13] + [pd.NA] + [99, 100]
 
 
 def make_float_data():
-    return (
-        list(np.arange(0.1, 0.9, 0.1))
-        + [pd.NA]
-        + list(np.arange(1, 9.8, 0.1))
-        + [pd.NA]
-        + [9.9, 10.0]
-    )
+    return [0.1, 0.2] + [pd.NA] + [1.0, 1.1, 1.2, 1.3] + [pd.NA] + [9.9, 10.0]
 
 
 def make_bool_data():
-    return [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False]
+    return [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False]
 
 
 @pytest.fixture(
@@ -111,8 +105,8 @@ def data(dtype):
 @pytest.fixture
 def data_for_twos(dtype):
     if dtype.kind == "b":
-        return pd.array(np.ones(100), dtype=dtype)
-    return pd.array(np.ones(100) * 2, dtype=dtype)
+        return pd.array(np.ones(10), dtype=dtype)
+    return pd.array(np.ones(10) * 2, dtype=dtype)
 
 
 @pytest.fixture
diff --git a/pandas/tests/extension/test_numpy.py b/pandas/tests/extension/test_numpy.py
index 5fe761cd702b1..691ce9341b788 100644
--- a/pandas/tests/extension/test_numpy.py
+++ b/pandas/tests/extension/test_numpy.py
@@ -77,8 +77,8 @@ def allow_in_pandas(monkeypatch):
 @pytest.fixture
 def data(allow_in_pandas, dtype):
     if dtype.numpy_dtype == "object":
-        return pd.Series([(i,) for i in range(100)]).array
-    return NumpyExtensionArray(np.arange(1, 101, dtype=dtype._dtype))
+        return pd.Series([(i,) for i in range(10)]).array
+    return NumpyExtensionArray(np.arange(1, 11, dtype=dtype._dtype))
 
 
 @pytest.fixture
@@ -143,7 +143,7 @@ def data_for_grouping(allow_in_pandas, dtype):
 def data_for_twos(dtype):
     if dtype.kind == "O":
         pytest.skip(f"{dtype} is not a numeric dtype")
-    arr = np.ones(100) * 2
+    arr = np.ones(10) * 2
     return NumpyExtensionArray._from_sequence(arr, dtype=dtype)
 
 
diff --git a/pandas/tests/extension/test_period.py b/pandas/tests/extension/test_period.py
index 31496c1b7db3d..a3be4e2b4420a 100644
--- a/pandas/tests/extension/test_period.py
+++ b/pandas/tests/extension/test_period.py
@@ -43,7 +43,7 @@ def dtype(request):
 
 @pytest.fixture
 def data(dtype):
-    return PeriodArray(np.arange(1970, 2070), dtype=dtype)
+    return PeriodArray(np.arange(1970, 1980), dtype=dtype)
 
 
 @pytest.fixture
diff --git a/pandas/tests/extension/test_sparse.py b/pandas/tests/extension/test_sparse.py
index b7685a61d4937..72f9a13910cc2 100644
--- a/pandas/tests/extension/test_sparse.py
+++ b/pandas/tests/extension/test_sparse.py
@@ -24,12 +24,12 @@
 from pandas.tests.extension import base
 
 
-def make_data(fill_value):
+def make_data(fill_value, n: int):
     rng = np.random.default_rng(2)
     if np.isnan(fill_value):
-        data = rng.uniform(size=100)
+        data = rng.uniform(size=n)
     else:
-        data = rng.integers(1, 100, size=100, dtype=int)
+        data = rng.integers(1, 100, size=n, dtype=int)
         if data[0] == data[1]:
             data[0] += 1
 
@@ -44,14 +44,14 @@ def dtype():
 
 @pytest.fixture(params=[0, np.nan])
 def data(request):
-    """Length-100 PeriodArray for semantics test."""
-    res = SparseArray(make_data(request.param), fill_value=request.param)
+    """Length-10 SparseArray for semantics test."""
+    res = SparseArray(make_data(request.param, 10), fill_value=request.param)
     return res
 
 
 @pytest.fixture
 def data_for_twos():
-    return SparseArray(np.ones(100) * 2)
+    return SparseArray(np.ones(10) * 2)
 
 
 @pytest.fixture(params=[0, np.nan])
@@ -66,7 +66,7 @@ def data_repeated(request):
 
     def gen(count):
         for _ in range(count):
-            yield SparseArray(make_data(request.param), fill_value=request.param)
+            yield SparseArray(make_data(request.param, 10), fill_value=request.param)
 
     return gen
 
diff --git a/pandas/tests/extension/test_string.py b/pandas/tests/extension/test_string.py
index c49063a5a9a68..e373ff12c4086 100644
--- a/pandas/tests/extension/test_string.py
+++ b/pandas/tests/extension/test_string.py
@@ -65,9 +65,9 @@ def dtype(string_dtype_arguments):
 
 @pytest.fixture
 def data(dtype, chunked):
-    strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=100)
+    strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=10)
     while strings[0] == strings[1]:
-        strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=100)
+        strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=10)
 
     arr = dtype.construct_array_type()._from_sequence(strings, dtype=dtype)
     return maybe_split_array(arr, chunked)

From fca462e1455cc5e1f70a312d434b7f2f33cddd3b Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 22 Sep 2025 13:39:43 -0700
Subject: [PATCH 2/3] Adjust where the nulls should be, generalize some tests

---
 .../tests/arrays/boolean/test_arithmetic.py   |  2 +-
 .../tests/arrays/boolean/test_comparison.py   |  2 +-
 pandas/tests/arrays/boolean/test_reduction.py |  2 +-
 pandas/tests/arrays/floating/conftest.py      |  2 +-
 pandas/tests/arrays/integer/conftest.py       |  2 +-
 pandas/tests/extension/base/casting.py        | 10 +++++-
 pandas/tests/extension/base/printing.py       |  2 +-
 pandas/tests/extension/base/reshaping.py      |  4 ++-
 pandas/tests/extension/base/setitem.py        | 14 ++++----
 pandas/tests/extension/json/test_json.py      |  5 ++-
 pandas/tests/extension/test_arrow.py          | 32 +++++++++----------
 pandas/tests/extension/test_masked.py         |  6 ++--
 12 files changed, 46 insertions(+), 37 deletions(-)

diff --git a/pandas/tests/arrays/boolean/test_arithmetic.py b/pandas/tests/arrays/boolean/test_arithmetic.py
index 9553c4cf7ce5f..312dfb72e0950 100644
--- a/pandas/tests/arrays/boolean/test_arithmetic.py
+++ b/pandas/tests/arrays/boolean/test_arithmetic.py
@@ -11,7 +11,7 @@
 def data():
     """Fixture returning boolean array with valid and missing values."""
     return pd.array(
-        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
+        [True, False] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/boolean/test_comparison.py b/pandas/tests/arrays/boolean/test_comparison.py
index 8c35a77253494..ed1d4414cb03c 100644
--- a/pandas/tests/arrays/boolean/test_comparison.py
+++ b/pandas/tests/arrays/boolean/test_comparison.py
@@ -11,7 +11,7 @@
 def data():
     """Fixture returning boolean array with valid and missing data"""
     return pd.array(
-        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
+        [True, False] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/boolean/test_reduction.py b/pandas/tests/arrays/boolean/test_reduction.py
index 8cb5035e264f6..696ae1df4c9fd 100644
--- a/pandas/tests/arrays/boolean/test_reduction.py
+++ b/pandas/tests/arrays/boolean/test_reduction.py
@@ -8,7 +8,7 @@
 def data():
     """Fixture returning boolean array, with valid and missing values."""
     return pd.array(
-        [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],
+        [True, False] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 
diff --git a/pandas/tests/arrays/floating/conftest.py b/pandas/tests/arrays/floating/conftest.py
index 9b6f65275ae2e..21dae4123814a 100644
--- a/pandas/tests/arrays/floating/conftest.py
+++ b/pandas/tests/arrays/floating/conftest.py
@@ -17,7 +17,7 @@ def dtype(request):
 def data(dtype):
     """Fixture returning 'data' array according to parametrized float 'dtype'"""
     return pd.array(
-        [0.1, 0.2] + [pd.NA] + [1.0, 1.1, 1.2, 1.3] + [pd.NA] + [9.9, 10.0],
+        [0.1, 0.2, 0.3, 0.4] + [pd.NA] + [1.0, 1.1] + [pd.NA] + [9.9, 10.0],
         dtype=dtype,
     )
 
diff --git a/pandas/tests/arrays/integer/conftest.py b/pandas/tests/arrays/integer/conftest.py
index 8b1ae06d4aafc..f9371cf648fc0 100644
--- a/pandas/tests/arrays/integer/conftest.py
+++ b/pandas/tests/arrays/integer/conftest.py
@@ -39,7 +39,7 @@ def data(dtype):
     Used to test dtype conversion with and without missing values.
     """
     return pd.array(
-        [0, 1] + [pd.NA] + [10, 11, 12, 13] + [pd.NA] + [99, 100],
+        [0, 1, 2, 3] + [pd.NA] + [10, 11] + [pd.NA] + [99, 100],
         dtype=dtype,
     )
 
diff --git a/pandas/tests/extension/base/casting.py b/pandas/tests/extension/base/casting.py
index 8e3f21e1a4f56..8e1d6109e2119 100644
--- a/pandas/tests/extension/base/casting.py
+++ b/pandas/tests/extension/base/casting.py
@@ -57,9 +57,17 @@ def test_astype_str(self, data):
     )
     def test_astype_string(self, data, nullable_string_dtype):
         # GH-33465, GH#45326 as of 2.0 we decode bytes instead of calling str(obj)
+        def as_str(x):
+            if isinstance(x, bytes):
+                return x.decode()
+            elif x is data.dtype.na_value:
+                return x
+            else:
+                return str(x)
+
         result = pd.Series(data[:5]).astype(nullable_string_dtype)
         expected = pd.Series(
-            [str(x) if not isinstance(x, bytes) else x.decode() for x in data[:5]],
+            [as_str(x) for x in data[:5]],
             dtype=nullable_string_dtype,
         )
         tm.assert_series_equal(result, expected)
diff --git a/pandas/tests/extension/base/printing.py b/pandas/tests/extension/base/printing.py
index b20236ec107b0..f963c21ceea37 100644
--- a/pandas/tests/extension/base/printing.py
+++ b/pandas/tests/extension/base/printing.py
@@ -13,7 +13,7 @@ def test_array_repr(self, data, size):
         if size == "small":
             data = data[:5]
         else:
-            data = type(data)._concat_same_type([data] * 5)
+            data = type(data)._concat_same_type([data] * 20)
 
         result = repr(data)
         assert type(data).__name__ in result
diff --git a/pandas/tests/extension/base/reshaping.py b/pandas/tests/extension/base/reshaping.py
index a760cbc3995b3..6bddaaddff88e 100644
--- a/pandas/tests/extension/base/reshaping.py
+++ b/pandas/tests/extension/base/reshaping.py
@@ -303,7 +303,9 @@ def test_stack(self, data, columns, future_stack):
     )
     @pytest.mark.parametrize("obj", ["series", "frame"])
     def test_unstack(self, data, index, obj):
-        data = data[: len(index)]
+        final_length = min(len(index), len(data))
+        index = index[:final_length]
+        data = data[:final_length]
         if obj == "series":
             ser = pd.Series(data, index=index)
         else:
diff --git a/pandas/tests/extension/base/setitem.py b/pandas/tests/extension/base/setitem.py
index b4dbe04b04374..b273c9b9f092a 100644
--- a/pandas/tests/extension/base/setitem.py
+++ b/pandas/tests/extension/base/setitem.py
@@ -136,13 +136,13 @@ def test_setitem_iloc_scalar_mixed(self, data):
 
     def test_setitem_iloc_scalar_single(self, data):
         df = pd.DataFrame({"B": data})
-        df.iloc[10, 0] = data[1]
-        assert df.loc[10, "B"] == data[1]
+        df.iloc[9, 0] = data[1]
+        assert df.loc[9, "B"] == data[1]
 
     def test_setitem_iloc_scalar_multiple_homogoneous(self, data):
         df = pd.DataFrame({"A": data, "B": data})
-        df.iloc[10, 1] = data[1]
-        assert df.loc[10, "B"] == data[1]
+        df.iloc[9, 1] = data[1]
+        assert df.loc[9, "B"] == data[1]
 
     @pytest.mark.parametrize(
         "mask",
@@ -281,9 +281,9 @@ def test_setitem_mask_broadcast(self, data, setter):
         else:  # __setitem__
             target = ser
 
-        target[mask] = data[10]
-        assert ser[0] == data[10]
-        assert ser[1] == data[10]
+        target[mask] = data[9]
+        assert ser[0] == data[9]
+        assert ser[1] == data[9]
 
     def test_setitem_expand_columns(self, data):
         df = pd.DataFrame({"A": data})
diff --git a/pandas/tests/extension/json/test_json.py b/pandas/tests/extension/json/test_json.py
index 0d3b4e1a7cde6..cdb98c5342ecb 100644
--- a/pandas/tests/extension/json/test_json.py
+++ b/pandas/tests/extension/json/test_json.py
@@ -190,9 +190,8 @@ def test_ffill_limit_area(
             )
 
     def test_value_counts(self, all_data, dropna, request):
-        if len(all_data) == 100 or dropna:
-            mark = pytest.mark.xfail(reason="unhashable")
-            request.applymarker(mark)
+        if len(all_data) == 10 or dropna:
+            request.applymarker(unhashable)
         super().test_value_counts(all_data, dropna)
 
     @unhashable
diff --git a/pandas/tests/extension/test_arrow.py b/pandas/tests/extension/test_arrow.py
index 66f17c147ff71..1863771dff593 100644
--- a/pandas/tests/extension/test_arrow.py
+++ b/pandas/tests/extension/test_arrow.py
@@ -93,57 +93,57 @@ def dtype(request):
 def data(dtype):
     pa_dtype = dtype.pyarrow_dtype
     if pa.types.is_boolean(pa_dtype):
-        data = [True, False] + [None] + [True, False] * 2 + [None] + [True, False]
+        data = [True, False] * 2 + [None] + [True, False] + [None] + [True, False]
     elif pa.types.is_floating(pa_dtype):
-        data = [1.0, 0.0] + [None] + [-2.0, -1.0] * 2 + [None] + [0.5, 99.5]
+        data = [1.0, 0.0] * 2 + [None] + [-2.0, -1.0] + [None] + [0.5, 99.5]
     elif pa.types.is_signed_integer(pa_dtype):
-        data = [1, 0] + [None] + [-2, -1] * 2 + [None] + [1, 99]
+        data = [1, 0] * 2 + [None] + [-2, -1] + [None] + [1, 99]
     elif pa.types.is_unsigned_integer(pa_dtype):
-        data = [1, 0] + [None] + [2, 1] * 2 + [None] + [1, 99]
+        data = [1, 0] * 2 + [None] + [2, 1] + [None] + [1, 99]
     elif pa.types.is_decimal(pa_dtype):
         data = (
-            [Decimal("1"), Decimal("0.0")]
+            [Decimal("1"), Decimal("0.0")] * 2
             + [None]
-            + [Decimal("-2.0"), Decimal("-1.0")] * 2
+            + [Decimal("-2.0"), Decimal("-1.0")]
             + [None]
             + [Decimal("0.5"), Decimal("33.123")]
         )
     elif pa.types.is_date(pa_dtype):
         data = (
-            [date(2022, 1, 1), date(1999, 12, 31)]
+            [date(2022, 1, 1), date(1999, 12, 31)] * 2
             + [None]
-            + [date(2022, 1, 1), date(2022, 1, 1)] * 2
+            + [date(2022, 1, 1), date(2022, 1, 1)]
             + [None]
             + [date(1999, 12, 31), date(1999, 12, 31)]
         )
     elif pa.types.is_timestamp(pa_dtype):
         data = (
-            [datetime(2020, 1, 1, 1, 1, 1, 1), datetime(1999, 1, 1, 1, 1, 1, 1)]
+            [datetime(2020, 1, 1, 1, 1, 1, 1), datetime(1999, 1, 1, 1, 1, 1, 1)] * 2
             + [None]
-            + [datetime(2020, 1, 1, 1), datetime(1999, 1, 1, 1)] * 2
+            + [datetime(2020, 1, 1, 1), datetime(1999, 1, 1, 1)]
             + [None]
             + [datetime(2020, 1, 1), datetime(1999, 1, 1)]
         )
     elif pa.types.is_duration(pa_dtype):
         data = (
-            [timedelta(1), timedelta(1, 1)]
+            [timedelta(1), timedelta(1, 1)] * 2
             + [None]
-            + [timedelta(-1), timedelta(0)] * 2
+            + [timedelta(-1), timedelta(0)]
             + [None]
             + [timedelta(-10), timedelta(10)]
         )
     elif pa.types.is_time(pa_dtype):
         data = (
-            [time(12, 0), time(0, 12)]
+            [time(12, 0), time(0, 12)] * 2
             + [None]
-            + [time(0, 0), time(1, 1)] * 2
+            + [time(0, 0), time(1, 1)]
             + [None]
             + [time(0, 5), time(5, 0)]
         )
     elif pa.types.is_string(pa_dtype):
-        data = ["a", "b"] + [None] + ["1", "2"] * 2 + [None] + ["!", ">"]
+        data = ["a", "b"] * 2 + [None] + ["1", "2"] + [None] + ["!", ">"]
     elif pa.types.is_binary(pa_dtype):
-        data = [b"a", b"b"] + [None] + [b"1", b"2"] * 2 + [None] + [b"!", b">"]
+        data = [b"a", b"b"] * 2 + [None] + [b"1", b"2"] + [None] + [b"!", b">"]
     else:
         raise NotImplementedError
     return pd.array(data, dtype=dtype)
diff --git a/pandas/tests/extension/test_masked.py b/pandas/tests/extension/test_masked.py
index 073f4e63a422b..a288a4438aeec 100644
--- a/pandas/tests/extension/test_masked.py
+++ b/pandas/tests/extension/test_masked.py
@@ -61,15 +61,15 @@
 
 
 def make_data():
-    return [0, 1] + [pd.NA] + [10, 11, 12, 13] + [pd.NA] + [99, 100]
+    return [1, 2, 3, 4] + [pd.NA] + [10, 11] + [pd.NA] + [99, 100]
 
 
 def make_float_data():
-    return [0.1, 0.2] + [pd.NA] + [1.0, 1.1, 1.2, 1.3] + [pd.NA] + [9.9, 10.0]
+    return [0.1, 0.2, 0.3, 0.4] + [pd.NA] + [1.0, 1.1] + [pd.NA] + [9.9, 10.0]
 
 
 def make_bool_data():
-    return [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False]
+    return [True, False] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False]
 
 
 @pytest.fixture(

From 6ceec252c4d054c2336559f80616bfa7d012dbcf Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 22 Sep 2025 14:02:10 -0700
Subject: [PATCH 3/3] Fix test_groupby_agg_err_catching

---
 pandas/tests/groupby/aggregate/test_other.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/tests/groupby/aggregate/test_other.py b/pandas/tests/groupby/aggregate/test_other.py
index 1c016143d50c3..3b9f18456c559 100644
--- a/pandas/tests/groupby/aggregate/test_other.py
+++ b/pandas/tests/groupby/aggregate/test_other.py
@@ -647,7 +647,7 @@ def test_groupby_agg_err_catching(err_cls):
         to_decimal,
     )
 
-    data = make_data()[:5]
+    data = make_data(5)
     df = DataFrame(
         {"id1": [0, 0, 0, 1, 1], "id2": [0, 1, 0, 1, 1], "decimals": DecimalArray(data)}
     )