TST: Clean pytest fixtures (#56088)

* TST: Clean/moved unused/sparsely use fixtures

* Refactor xml_data_path

* More fixture fixes

* inline tsframe

* Simplify ext fixtures

Author: mroeschke

pandas/conftest.py

@@ -30,7 +30,6 @@
 from decimal import Decimal
 import operator
 import os
-from pathlib import Path
 from typing import (
     TYPE_CHECKING,
     Callable,
@@ -775,23 +774,6 @@ def series_with_simple_index(index) -> Series:
     return _create_series(index)
 
 
-@pytest.fixture
-def series_with_multilevel_index() -> Series:
-    """
-    Fixture with a Series with a 2-level MultiIndex.
-    """
-    arrays = [
-        ["bar", "bar", "baz", "baz", "qux", "qux", "foo", "foo"],
-        ["one", "two", "one", "two", "one", "two", "one", "two"],
-    ]
-    tuples = zip(*arrays)
-    index = MultiIndex.from_tuples(tuples)
-    data = np.random.default_rng(2).standard_normal(8)
-    ser = Series(data, index=index)
-    ser.iloc[3] = np.nan
-    return ser
-
-
 _narrow_series = {
     f"{dtype.__name__}-series": tm.make_rand_series(name="a", dtype=dtype)
     for dtype in tm.NARROW_NP_DTYPES
@@ -865,35 +847,6 @@ def int_frame() -> DataFrame:
     return DataFrame(tm.getSeriesData()).astype("int64")
 
 
-@pytest.fixture
-def datetime_frame() -> DataFrame:
-    """
-    Fixture for DataFrame of floats with DatetimeIndex
-
-    Columns are ['A', 'B', 'C', 'D']
-
-                       A         B         C         D
-    2000-01-03 -1.122153  0.468535  0.122226  1.693711
-    2000-01-04  0.189378  0.486100  0.007864 -1.216052
-    2000-01-05  0.041401 -0.835752 -0.035279 -0.414357
-    2000-01-06  0.430050  0.894352  0.090719  0.036939
-    2000-01-07 -0.620982 -0.668211 -0.706153  1.466335
-    2000-01-10 -0.752633  0.328434 -0.815325  0.699674
-    2000-01-11 -2.236969  0.615737 -0.829076 -1.196106
-    ...              ...       ...       ...       ...
-    2000-02-03  1.642618 -0.579288  0.046005  1.385249
-    2000-02-04 -0.544873 -1.160962 -0.284071 -1.418351
-    2000-02-07 -2.656149 -0.601387  1.410148  0.444150
-    2000-02-08 -1.201881 -1.289040  0.772992 -1.445300
-    2000-02-09  1.377373  0.398619  1.008453 -0.928207
-    2000-02-10  0.473194 -0.636677  0.984058  0.511519
-    2000-02-11 -0.965556  0.408313 -1.312844 -0.381948
-
-    [30 rows x 4 columns]
-    """
-    return DataFrame(tm.getTimeSeriesData())
-
-
 @pytest.fixture
 def float_frame() -> DataFrame:
     """
@@ -923,24 +876,6 @@ def float_frame() -> DataFrame:
     return DataFrame(tm.getSeriesData())
 
 
-@pytest.fixture
-def mixed_type_frame() -> DataFrame:
-    """
-    Fixture for DataFrame of float/int/string columns with RangeIndex
-    Columns are ['a', 'b', 'c', 'float32', 'int32'].
-    """
-    return DataFrame(
-        {
-            "a": 1.0,
-            "b": 2,
-            "c": "foo",
-            "float32": np.array([1.0] * 10, dtype="float32"),
-            "int32": np.array([1] * 10, dtype="int32"),
-        },
-        index=np.arange(10),
-    )
-
-
 @pytest.fixture
 def rand_series_with_duplicate_datetimeindex() -> Series:
     """
@@ -1174,16 +1109,6 @@ def strict_data_files(pytestconfig):
     return pytestconfig.getoption("--no-strict-data-files")
 
 
-@pytest.fixture
-def tests_path() -> Path:
-    return Path(__file__).parent / "tests"
-
-
-@pytest.fixture
-def tests_io_data_path(tests_path) -> Path:
-    return tests_path / "io" / "data"
-
-
 @pytest.fixture
 def datapath(strict_data_files: str) -> Callable[..., str]:
     """
@@ -1218,14 +1143,6 @@ def deco(*args):
     return deco
 
 
-@pytest.fixture
-def iris(datapath) -> DataFrame:
-    """
-    The iris dataset as a DataFrame.
-    """
-    return pd.read_csv(datapath("io", "data", "csv", "iris.csv"))
-
-
 # ----------------------------------------------------------------
 # Time zones
 # ----------------------------------------------------------------
@@ -1905,28 +1822,6 @@ def sort_by_key(request):
     return request.param
 
 
-@pytest.fixture()
-def fsspectest():
-    pytest.importorskip("fsspec")
-    from fsspec import register_implementation
-    from fsspec.implementations.memory import MemoryFileSystem
-    from fsspec.registry import _registry as registry
-
-    class TestMemoryFS(MemoryFileSystem):
-        protocol = "testmem"
-        test = [None]
-
-        def __init__(self, **kwargs) -> None:
-            self.test[0] = kwargs.pop("test", None)
-            super().__init__(**kwargs)
-
-    register_implementation("testmem", TestMemoryFS, clobber=True)
-    yield TestMemoryFS()
-    registry.pop("testmem", None)
-    TestMemoryFS.test[0] = None
-    TestMemoryFS.store.clear()
-
-
 @pytest.fixture(
     params=[
         ("foo", None, None),

pandas/tests/apply/conftest.py

@@ -18,6 +18,27 @@
 from pandas.tests.frame.common import zip_frames
 
 
+@pytest.fixture
+def int_frame_const_col():
+    """
+    Fixture for DataFrame of ints which are constant per column
+
+    Columns are ['A', 'B', 'C'], with values (per column): [1, 2, 3]
+    """
+    df = DataFrame(
+        np.tile(np.arange(3, dtype="int64"), 6).reshape(6, -1) + 1,
+        columns=["A", "B", "C"],
+    )
+    return df
+
+
+@pytest.fixture(params=["python", pytest.param("numba", marks=pytest.mark.single_cpu)])
+def engine(request):
+    if request.param == "numba":
+        pytest.importorskip("numba")
+    return request.param
+
+
 def test_apply(float_frame, engine, request):
     if engine == "numba":
         mark = pytest.mark.xfail(reason="numba engine not supporting numpy ufunc yet")
@@ -269,7 +290,7 @@ def test_apply_raw_float_frame_no_reduction(float_frame, engine):
 
 
 @pytest.mark.parametrize("axis", [0, 1])
-def test_apply_raw_mixed_type_frame(mixed_type_frame, axis, engine):
+def test_apply_raw_mixed_type_frame(axis, engine):
     if engine == "numba":
         pytest.skip("isinstance check doesn't work with numba")
 
@@ -278,7 +299,17 @@ def _assert_raw(x):
         assert x.ndim == 1
 
     # Mixed dtype (GH-32423)
-    mixed_type_frame.apply(_assert_raw, axis=axis, engine=engine, raw=True)
+    df = DataFrame(
+        {
+            "a": 1.0,
+            "b": 2,
+            "c": "foo",
+            "float32": np.array([1.0] * 10, dtype="float32"),
+            "int32": np.array([1] * 10, dtype="int32"),
+        },
+        index=np.arange(10),
+    )
+    df.apply(_assert_raw, axis=axis, engine=engine, raw=True)
 
 
 def test_apply_axis1(float_frame):

pandas/tests/apply/test_frame_apply.py

@@ -24,9 +24,12 @@
 
 
 @pytest.mark.parametrize("result_type", ["foo", 1])
-def test_result_type_error(result_type, int_frame_const_col):
+def test_result_type_error(result_type):
     # allowed result_type
-    df = int_frame_const_col
+    df = DataFrame(
+        np.tile(np.arange(3, dtype="int64"), 6).reshape(6, -1) + 1,
+        columns=["A", "B", "C"],
+    )
 
     msg = (
         "invalid value for result_type, must be one of "
@@ -282,8 +285,11 @@ def test_transform_none_to_type():
         lambda x: Series([1, 2]),
     ],
 )
-def test_apply_broadcast_error(int_frame_const_col, func):
-    df = int_frame_const_col
+def test_apply_broadcast_error(func):
+    df = DataFrame(
+        np.tile(np.arange(3, dtype="int64"), 6).reshape(6, -1) + 1,
+        columns=["A", "B", "C"],
+    )
 
     # > 1 ndim
     msg = "too many dims to broadcast|cannot broadcast result"

pandas/tests/apply/test_invalid_arg.py

@@ -12,6 +12,11 @@
 pytestmark = [td.skip_if_no("numba"), pytest.mark.single_cpu]
 
 
+@pytest.fixture(params=[0, 1])
+def apply_axis(request):
+    return request.param
+
+
 def test_numba_vs_python_noop(float_frame, apply_axis):
     func = lambda x: x
     result = float_frame.apply(func, engine="numba", axis=apply_axis)

pandas/tests/apply/test_numba.py

@@ -2,11 +2,7 @@
 import pytest
 
 import pandas as pd
-from pandas import (
-    Index,
-    RangeIndex,
-)
-import pandas._testing as tm
+from pandas import Index
 
 
 @pytest.fixture(params=[1, np.array(1, dtype=np.int64)])
@@ -63,27 +59,6 @@ def zero(request):
     return request.param
 
 
-# ------------------------------------------------------------------
-# Vector Fixtures
-
-
-@pytest.fixture(
-    params=[
-        # TODO: add more  dtypes here
-        Index(np.arange(5, dtype="float64")),
-        Index(np.arange(5, dtype="int64")),
-        Index(np.arange(5, dtype="uint64")),
-        RangeIndex(5),
-    ],
-    ids=lambda x: type(x).__name__,
-)
-def numeric_idx(request):
-    """
-    Several types of numeric-dtypes Index objects
-    """
-    return request.param
-
-
 # ------------------------------------------------------------------
 # Scalar Fixtures
 
@@ -148,22 +123,6 @@ def two_hours(request):
 ]
 
 
-@pytest.fixture(
-    params=[
-        pd.Timedelta(minutes=30).to_pytimedelta(),
-        np.timedelta64(30, "s"),
-        pd.Timedelta(seconds=30),
-    ]
-    + _common_mismatch
-)
-def not_hourly(request):
-    """
-    Several timedelta-like and DateOffset instances that are _not_
-    compatible with Hourly frequencies.
-    """
-    return request.param
-
-
 @pytest.fixture(
     params=[
         np.timedelta64(4, "h"),
@@ -178,33 +137,3 @@ def not_daily(request):
     compatible with Daily frequencies.
     """
     return request.param
-
-
-@pytest.fixture(
-    params=[
-        np.timedelta64(365, "D"),
-        pd.Timedelta(days=365).to_pytimedelta(),
-        pd.Timedelta(days=365),
-    ]
-    + _common_mismatch
-)
-def mismatched_freq(request):
-    """
-    Several timedelta-like and DateOffset instances that are _not_
-    compatible with Monthly or Annual frequencies.
-    """
-    return request.param
-
-
-# ------------------------------------------------------------------
-
-
-@pytest.fixture(
-    params=[Index, pd.Series, tm.to_array, np.array, list], ids=lambda x: x.__name__
-)
-def box_1d_array(request):
-    """
-    Fixture to test behavior for Index, Series, tm.to_array, numpy Array and list
-    classes
-    """
-    return request.param