TST: de-duplicate fixtures (#44699)

Author: jbrockmendel

pandas/conftest.py

@@ -440,13 +440,21 @@ def multiindex_year_month_day_dataframe_random_data():
 
 
 @pytest.fixture
-def multiindex_dataframe_random_data():
-    """DataFrame with 2 level MultiIndex with random data"""
-    index = MultiIndex(
+def lexsorted_two_level_string_multiindex():
+    """
+    2-level MultiIndex, lexsorted, with string names.
+    """
+    return MultiIndex(
         levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
         codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
         names=["first", "second"],
     )
+
+
+@pytest.fixture
+def multiindex_dataframe_random_data(lexsorted_two_level_string_multiindex):
+    """DataFrame with 2 level MultiIndex with random data"""
+    index = lexsorted_two_level_string_multiindex
     return DataFrame(
         np.random.randn(10, 3), index=index, columns=Index(["A", "B", "C"], name="exp")
     )

pandas/tests/arithmetic/conftest.py

@@ -22,18 +22,6 @@ def switch_numexpr_min_elements(request):
     expr._MIN_ELEMENTS = _MIN_ELEMENTS
 
 
-# ------------------------------------------------------------------
-# Helper Functions
-
-
-def id_func(x):
-    if isinstance(x, tuple):
-        assert len(x) == 2
-        return x[0].__name__ + "-" + str(x[1])
-    else:
-        return x.__name__
-
-
 # ------------------------------------------------------------------
 
 
@@ -228,7 +216,9 @@ def mismatched_freq(request):
 # ------------------------------------------------------------------
 
 
-@pytest.fixture(params=[pd.Index, pd.Series, pd.DataFrame, pd.array], ids=id_func)
+@pytest.fixture(
+    params=[pd.Index, pd.Series, pd.DataFrame, pd.array], ids=lambda x: x.__name__
+)
 def box_with_array(request):
     """
     Fixture to test behavior for Index, Series, DataFrame, and pandas Array
@@ -237,7 +227,9 @@ def box_with_array(request):
     return request.param
 
 
-@pytest.fixture(params=[pd.Index, pd.Series, tm.to_array, np.array, list], ids=id_func)
+@pytest.fixture(
+    params=[pd.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

pandas/tests/frame/methods/test_drop.py

@@ -381,17 +381,8 @@ def test_drop_nonunique(self):
 
         tm.assert_frame_equal(result, expected)
 
-    def test_drop_level(self):
-        index = MultiIndex(
-            levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-            codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-            names=["first", "second"],
-        )
-        frame = DataFrame(
-            np.random.randn(10, 3),
-            index=index,
-            columns=Index(["A", "B", "C"], name="exp"),
-        )
+    def test_drop_level(self, multiindex_dataframe_random_data):
+        frame = multiindex_dataframe_random_data
 
         result = frame.drop(["bar", "qux"], level="first")
         expected = frame.iloc[[0, 1, 2, 5, 6]]

pandas/tests/frame/methods/test_sort_index.py

@@ -6,7 +6,6 @@
     CategoricalDtype,
     CategoricalIndex,
     DataFrame,
-    Index,
     IntervalIndex,
     MultiIndex,
     RangeIndex,
@@ -591,17 +590,8 @@ def test_sort_index_and_reconstruction(self):
         assert result.columns.is_monotonic
 
     # TODO: better name, de-duplicate with test_sort_index_level above
-    def test_sort_index_level2(self):
-        mi = MultiIndex(
-            levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-            codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-            names=["first", "second"],
-        )
-        frame = DataFrame(
-            np.random.randn(10, 3),
-            index=mi,
-            columns=Index(["A", "B", "C"], name="exp"),
-        )
+    def test_sort_index_level2(self, multiindex_dataframe_random_data):
+        frame = multiindex_dataframe_random_data
 
         df = frame.copy()
         df.index = np.arange(len(df))
@@ -639,34 +629,16 @@ def test_sort_index_level_large_cardinality(self):
         assert (result.dtypes.values == df.dtypes.values).all()
         assert result.index._lexsort_depth == 3
 
-    def test_sort_index_level_by_name(self):
-        mi = MultiIndex(
-            levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-            codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-            names=["first", "second"],
-        )
-        frame = DataFrame(
-            np.random.randn(10, 3),
-            index=mi,
-            columns=Index(["A", "B", "C"], name="exp"),
-        )
+    def test_sort_index_level_by_name(self, multiindex_dataframe_random_data):
+        frame = multiindex_dataframe_random_data
 
         frame.index.names = ["first", "second"]
         result = frame.sort_index(level="second")
         expected = frame.sort_index(level=1)
         tm.assert_frame_equal(result, expected)
 
-    def test_sort_index_level_mixed(self):
-        mi = MultiIndex(
-            levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-            codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-            names=["first", "second"],
-        )
-        frame = DataFrame(
-            np.random.randn(10, 3),
-            index=mi,
-            columns=Index(["A", "B", "C"], name="exp"),
-        )
+    def test_sort_index_level_mixed(self, multiindex_dataframe_random_data):
+        frame = multiindex_dataframe_random_data
 
         sorted_before = frame.sort_index(level=1)
 

pandas/tests/groupby/conftest.py

@@ -1,10 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas import (
-    DataFrame,
-    MultiIndex,
-)
+from pandas import DataFrame
 import pandas._testing as tm
 from pandas.core.groupby.base import (
     reduction_kernels,
@@ -23,13 +20,8 @@ def as_index(request):
 
 
 @pytest.fixture
-def mframe():
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["first", "second"],
-    )
-    return DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
+def mframe(multiindex_dataframe_random_data):
+    return multiindex_dataframe_random_data
 
 
 @pytest.fixture

pandas/tests/groupby/test_allowlist.py

@@ -10,8 +10,6 @@
 
 from pandas import (
     DataFrame,
-    Index,
-    MultiIndex,
     Series,
     date_range,
 )
@@ -89,16 +87,6 @@ def s_allowlist_fixture(request):
     return request.param
 
 
-@pytest.fixture
-def mframe():
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["first", "second"],
-    )
-    return DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
-
-
 @pytest.fixture
 def df():
     return DataFrame(
@@ -174,18 +162,11 @@ def test_groupby_frame_allowlist(df_letters, df_allowlist_fixture):
 
 
 @pytest.fixture
-def raw_frame():
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["first", "second"],
-    )
-    raw_frame = DataFrame(
-        np.random.randn(10, 3), index=index, columns=Index(["A", "B", "C"], name="exp")
-    )
-    raw_frame.iloc[1, [1, 2]] = np.nan
-    raw_frame.iloc[7, [0, 1]] = np.nan
-    return raw_frame
+def raw_frame(multiindex_dataframe_random_data):
+    df = multiindex_dataframe_random_data
+    df.iloc[1, [1, 2]] = np.nan
+    df.iloc[7, [0, 1]] = np.nan
+    return df
 
 
 @pytest.mark.parametrize("op", AGG_FUNCTIONS)

pandas/tests/indexes/multi/test_monotonic.py

@@ -7,6 +7,15 @@
 )
 
 
+def test_is_monotonic_increasing_lexsorted(lexsorted_two_level_string_multiindex):
+    # string ordering
+    mi = lexsorted_two_level_string_multiindex
+    assert mi.is_monotonic is False
+    assert Index(mi.values).is_monotonic is False
+    assert mi._is_strictly_monotonic_increasing is False
+    assert Index(mi.values)._is_strictly_monotonic_increasing is False
+
+
 def test_is_monotonic_increasing():
     i = MultiIndex.from_product([np.arange(10), np.arange(10)], names=["one", "two"])
     assert i.is_monotonic is True
@@ -36,17 +45,6 @@ def test_is_monotonic_increasing():
     assert Index(i.values).is_monotonic is False
     assert Index(i.values)._is_strictly_monotonic_increasing is False
 
-    # string ordering
-    i = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["first", "second"],
-    )
-    assert i.is_monotonic is False
-    assert Index(i.values).is_monotonic is False
-    assert i._is_strictly_monotonic_increasing is False
-    assert Index(i.values)._is_strictly_monotonic_increasing is False
-
     i = MultiIndex(
         levels=[["bar", "baz", "foo", "qux"], ["mom", "next", "zenith"]],
         codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],

pandas/tests/indexes/test_common.py

@@ -49,15 +49,14 @@ def test_to_frame(self, name, index_flat):
         df = idx.to_frame(index=False, name=idx_name)
         assert df.index is not idx
 
-    def test_droplevel(self, index):
+    def test_droplevel(self, index_flat):
         # GH 21115
-        if isinstance(index, MultiIndex):
-            # Tested separately in test_multi.py
-            return
+        # MultiIndex is tested separately in test_multi.py
+        index = index_flat
 
         assert index.droplevel([]).equals(index)
 
-        for level in index.name, [index.name]:
+        for level in [index.name, [index.name]]:
             if isinstance(index.name, tuple) and level is index.name:
                 # GH 21121 : droplevel with tuple name
                 continue
@@ -174,8 +173,6 @@ def test_copy_name(self, index_flat):
     def test_copy_name2(self, index_flat):
         # GH#35592
         index = index_flat
-        if isinstance(index, MultiIndex):
-            return
 
         assert index.copy(name="mario").name == "mario"
 
@@ -192,7 +189,7 @@ def test_unique_level(self, index_flat):
 
         # GH 17896
         expected = index.drop_duplicates()
-        for level in 0, index.name, None:
+        for level in [0, index.name, None]:
             result = index.unique(level=level)
             tm.assert_index_equal(result, expected)
 

pandas/tests/io/formats/test_series_info.py

@@ -37,15 +37,11 @@ def test_info_categorical():
 
 
 @pytest.mark.parametrize("verbose", [True, False])
-def test_info_series(verbose):
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["first", "second"],
-    )
-    s = Series(range(len(index)), index=index, name="sth")
+def test_info_series(lexsorted_two_level_string_multiindex, verbose):
+    index = lexsorted_two_level_string_multiindex
+    ser = Series(range(len(index)), index=index, name="sth")
     buf = StringIO()
-    s.info(verbose=verbose, buf=buf)
+    ser.info(verbose=verbose, buf=buf)
     result = buf.getvalue()
 
     expected = textwrap.dedent(
@@ -66,7 +62,7 @@ def test_info_series(verbose):
     expected += textwrap.dedent(
         f"""\
         dtypes: int64(1)
-        memory usage: {s.memory_usage()}.0+ bytes
+        memory usage: {ser.memory_usage()}.0+ bytes
         """
     )
     assert result == expected

pandas/tests/io/pytables/test_append.py

@@ -12,7 +12,6 @@
 import pandas as pd
 from pandas import (
     DataFrame,
-    MultiIndex,
     Series,
     _testing as tm,
     concat,
@@ -638,13 +637,9 @@ def check_col(key, name, size):
         tm.assert_frame_equal(result, expected)
 
 
-def test_append_hierarchical(setup_path):
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["foo", "bar"],
-    )
-    df = DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
+def test_append_hierarchical(setup_path, multiindex_dataframe_random_data):
+    df = multiindex_dataframe_random_data
+    df.columns.name = None
 
     with ensure_clean_store(setup_path) as store:
         store.append("mi", df)

pandas/tests/io/pytables/test_round_trip.py

@@ -15,7 +15,6 @@
 from pandas import (
     DataFrame,
     Index,
-    MultiIndex,
     Series,
     _testing as tm,
     bdate_range,
@@ -419,13 +418,8 @@ def test_can_serialize_dates(setup_path):
     _check_roundtrip(frame, tm.assert_frame_equal, path=setup_path)
 
 
-def test_store_hierarchical(setup_path):
-    index = MultiIndex(
-        levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
-        codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
-        names=["foo", "bar"],
-    )
-    frame = DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
+def test_store_hierarchical(setup_path, multiindex_dataframe_random_data):
+    frame = multiindex_dataframe_random_data
 
     _check_roundtrip(frame, tm.assert_frame_equal, path=setup_path)
     _check_roundtrip(frame.T, tm.assert_frame_equal, path=setup_path)