Reduce extensionarray data length from 100 to 10

mroeschke · mroeschke · commit c338620fdce1 · 2025-09-21T17:28:12.000-07:00
diff --git 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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
diff --git a/pandas/tests/extension/test_numpy.py b/pandas/tests/extension/test_numpy.py
diff --git a/pandas/tests/extension/test_period.py b/pandas/tests/extension/test_period.py
diff --git a/pandas/tests/extension/test_sparse.py b/pandas/tests/extension/test_sparse.py
diff --git a/pandas/tests/extension/test_string.py b/pandas/tests/extension/test_string.py

Original file line number	Diff line number	Diff line change
`@@ -11,7 +11,7 @@`
`11`	`11`	`def data():`
`12`	`12`	`"""Fixture returning boolean array with valid and missing values."""`
`13`	`13`	`return pd.array(`
`14`		`- [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],`
	`14`	`+ [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],`
`15`	`15`	`dtype="boolean",`
`16`	`16`	`)`
`17`	`17`
Original file line number	Diff line number	Diff line change
`@@ -8,7 +8,7 @@`
`8`	`8`	`def data():`
`9`	`9`	`"""Fixture returning boolean array, with valid and missing values."""`
`10`	`10`	`return pd.array(`
`11`		`- [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],`
	`11`	`+ [True, False] + [np.nan] + [True, False] * 2 + [np.nan] + [True, False],`
`12`	`12`	`dtype="boolean",`
`13`	`13`	`)`
`14`	`14`
Original file line number	Diff line number	Diff line change
`@@ -39,7 +39,7 @@ def data(dtype):`
`39`	`39`	`Used to test dtype conversion with and without missing values.`
`40`	`40`	`"""`
`41`	`41`	`return pd.array(`
`42`		`- list(range(8)) + [pd.NA] + list(range(10, 98)) + [pd.NA] + [99, 100],`
	`42`	`+ [0, 1] + [pd.NA] + [10, 11, 12, 13] + [pd.NA] + [99, 100],`
`43`	`43`	`dtype=dtype,`
`44`	`44`	`)`
`45`	`45`
Original file line number	Diff line number	Diff line change
`@@ -408,7 +408,7 @@ def test_take_series(self, data):`
`408`	`408`	`result = s.take([0, -1])`
`409`	`409`	`expected = pd.Series(`
`410`	`410`	`data._from_sequence([data[0], data[len(data) - 1]], dtype=s.dtype),`
`411`		`- index=range(0, 198, 99),`
	`411`	`+ index=s.index.take([0, -1]),`
`412`	`412`	`)`
`413`	`413`	`tm.assert_series_equal(result, expected)`
`414`	`414`