TST: Reduce ExtensionArray data testing length from 100 to 10

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] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 

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] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 

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] * 2 + [np.nan] + [True, False] + [np.nan] + [True, False],
         dtype="boolean",
     )
 

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, 0.3, 0.4] + [pd.NA] + [1.0, 1.1] + [pd.NA] + [9.9, 10.0],
         dtype=dtype,
     )
 

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, 2, 3] + [pd.NA] + [10, 11] + [pd.NA] + [99, 100],
         dtype=dtype,
     )
 

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)

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)
 

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

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)
 

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

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

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:

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})

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.
     """

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()

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))})
 

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)
     ]

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)
 
@@ -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

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

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)