TST: address TODOs/FIXMES/noqas (pandas-dev#44960)

Author: jbrockmendel

pandas/__init__.py

@@ -23,13 +23,15 @@
 
 try:
     from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
-except ImportError as e:  # pragma: no cover
-    module = e.name
+except ImportError as err:  # pragma: no cover
+    module = err.name
     raise ImportError(
         f"C extension: {module} not built. If you want to import "
         "pandas from the source directory, you may need to run "
         "'python setup.py build_ext --force' to build the C extensions first."
-    ) from e
+    ) from err
+else:
+    del _tslib, _lib, _hashtable
 
 from pandas._config import (
     get_option,

pandas/tests/api/test_api.py

@@ -188,12 +188,9 @@ class TestPDApi(Base):
     # private modules in pandas namespace
     private_modules = [
         "_config",
-        "_hashtable",
-        "_lib",
         "_libs",
         "_is_numpy_dev",
         "_testing",
-        "_tslib",
         "_typing",
         "_version",
     ]

pandas/tests/internals/test_internals.py

@@ -494,16 +494,13 @@ def test_copy(self, mgr):
 
     def test_sparse(self):
         mgr = create_mgr("a: sparse-1; b: sparse-2")
-        # what to test here?
         assert mgr.as_array().dtype == np.float64
 
     def test_sparse_mixed(self):
         mgr = create_mgr("a: sparse-1; b: sparse-2; c: f8")
         assert len(mgr.blocks) == 3
         assert isinstance(mgr, BlockManager)
 
-        # TODO: what to test here?
-
     @pytest.mark.parametrize(
         "mgr_string, dtype",
         [("c: f4; d: f2", np.float32), ("c: f4; d: f2; e: f8", np.float64)],

pandas/tests/io/formats/test_to_html.py

@@ -452,43 +452,59 @@ def test_to_html_invalid_justify(justify):
         df.to_html(justify=justify)
 
 
-def test_to_html_index(datapath):
-    # TODO: split this test
-    index = ["foo", "bar", "baz"]
-    df = DataFrame(
-        {"A": [1, 2, 3], "B": [1.2, 3.4, 5.6], "C": ["one", "two", np.nan]},
-        columns=["A", "B", "C"],
-        index=index,
-    )
-    expected_with_index = expected_html(datapath, "index_1")
-    assert df.to_html() == expected_with_index
-
-    expected_without_index = expected_html(datapath, "index_2")
-    result = df.to_html(index=False)
-    for i in index:
-        assert i not in result
-    assert result == expected_without_index
-    df.index = Index(["foo", "bar", "baz"], name="idx")
-    expected_with_index = expected_html(datapath, "index_3")
-    assert df.to_html() == expected_with_index
-    assert df.to_html(index=False) == expected_without_index
-
-    tuples = [("foo", "car"), ("foo", "bike"), ("bar", "car")]
-    df.index = MultiIndex.from_tuples(tuples)
-
-    expected_with_index = expected_html(datapath, "index_4")
-    assert df.to_html() == expected_with_index
+class TestHTMLIndex:
+    @pytest.fixture
+    def df(self):
+        index = ["foo", "bar", "baz"]
+        df = DataFrame(
+            {"A": [1, 2, 3], "B": [1.2, 3.4, 5.6], "C": ["one", "two", np.nan]},
+            columns=["A", "B", "C"],
+            index=index,
+        )
+        return df
 
-    result = df.to_html(index=False)
-    for i in ["foo", "bar", "car", "bike"]:
-        assert i not in result
-    # must be the same result as normal index
-    assert result == expected_without_index
-
-    df.index = MultiIndex.from_tuples(tuples, names=["idx1", "idx2"])
-    expected_with_index = expected_html(datapath, "index_5")
-    assert df.to_html() == expected_with_index
-    assert df.to_html(index=False) == expected_without_index
+    @pytest.fixture
+    def expected_without_index(self, datapath):
+        return expected_html(datapath, "index_2")
+
+    def test_to_html_flat_index_without_name(
+        self, datapath, df, expected_without_index
+    ):
+        expected_with_index = expected_html(datapath, "index_1")
+        assert df.to_html() == expected_with_index
+
+        result = df.to_html(index=False)
+        for i in df.index:
+            assert i not in result
+        assert result == expected_without_index
+
+    def test_to_html_flat_index_with_name(self, datapath, df, expected_without_index):
+        df.index = Index(["foo", "bar", "baz"], name="idx")
+        expected_with_index = expected_html(datapath, "index_3")
+        assert df.to_html() == expected_with_index
+        assert df.to_html(index=False) == expected_without_index
+
+    def test_to_html_multiindex_without_names(
+        self, datapath, df, expected_without_index
+    ):
+        tuples = [("foo", "car"), ("foo", "bike"), ("bar", "car")]
+        df.index = MultiIndex.from_tuples(tuples)
+
+        expected_with_index = expected_html(datapath, "index_4")
+        assert df.to_html() == expected_with_index
+
+        result = df.to_html(index=False)
+        for i in ["foo", "bar", "car", "bike"]:
+            assert i not in result
+        # must be the same result as normal index
+        assert result == expected_without_index
+
+    def test_to_html_multiindex_with_names(self, datapath, df, expected_without_index):
+        tuples = [("foo", "car"), ("foo", "bike"), ("bar", "car")]
+        df.index = MultiIndex.from_tuples(tuples, names=["idx1", "idx2"])
+        expected_with_index = expected_html(datapath, "index_5")
+        assert df.to_html() == expected_with_index
+        assert df.to_html(index=False) == expected_without_index
 
 
 @pytest.mark.parametrize("classes", ["sortable draggable", ["sortable", "draggable"]])

pandas/tests/io/json/test_json_table_schema.py

@@ -185,14 +185,11 @@ def test_as_json_table_type_date_dtypes(self, date_dtype):
     def test_as_json_table_type_timedelta_dtypes(self, td_dtype):
         assert as_json_table_type(td_dtype) == "duration"
 
-    @pytest.mark.parametrize("str_dtype", [object])  # TODO
+    @pytest.mark.parametrize("str_dtype", [object])  # TODO(GH#14904) flesh out dtypes?
     def test_as_json_table_type_string_dtypes(self, str_dtype):
         assert as_json_table_type(str_dtype) == "string"
 
     def test_as_json_table_type_categorical_dtypes(self):
-        # TODO: I think before is_categorical_dtype(Categorical)
-        # returned True, but now it's False. Figure out why or
-        # if it matters
         assert as_json_table_type(pd.Categorical(["a"]).dtype) == "any"
         assert as_json_table_type(CategoricalDtype()) == "any"
 

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -28,7 +28,6 @@
 
 @tm.network
 def test_url(all_parsers, csv_dir_path):
-    # TODO: FTP testing
     parser = all_parsers
     kwargs = {"sep": "\t"}
 

pandas/tests/io/pytables/test_store.py

@@ -972,7 +972,8 @@ def test_columns_multiindex_modified(setup_path):
         )
         cols2load = list("BCD")
         cols2load_original = list(cols2load)
-        df_loaded = read_hdf(path, "df", columns=cols2load)  # noqa
+        # GH#10055 make sure read_hdf call does not alter cols2load inplace
+        read_hdf(path, "df", columns=cols2load)
         assert cols2load_original == cols2load
 
 

pandas/tests/io/test_sql.py

@@ -2128,7 +2128,7 @@ def test_get_engine_auto_error_message(self):
         # Expect different error messages from get_engine(engine="auto")
         # if engines aren't installed vs. are installed but bad version
         pass
-        # TODO fill this in when we add more engines
+        # TODO(GH#36893) fill this in when we add more engines
 
 
 class _TestSQLAlchemyConn(_EngineToConnMixin, _TestSQLAlchemy):

pandas/tests/reductions/test_stat_reductions.py

@@ -43,15 +43,14 @@ def test_dt64_mean(self, tz_naive_fixture, box):
         assert obj.mean(skipna=False) is pd.NaT
 
     @pytest.mark.parametrize("box", [Series, pd.Index, PeriodArray])
-    def test_period_mean(self, box):
+    @pytest.mark.parametrize("freq", ["S", "H", "D", "W", "B"])
+    def test_period_mean(self, box, freq):
         # GH#24757
         dti = pd.date_range("2001-01-01", periods=11)
         # shuffle so that we are not just working with monotone-increasing
         dti = dti.take([4, 1, 3, 10, 9, 7, 8, 5, 0, 2, 6])
 
-        # use hourly frequency to avoid rounding errors in expected results
-        #  TODO: flesh this out with different frequencies
-        parr = dti._data.to_period("H")
+        parr = dti._data.to_period(freq)
         obj = box(parr)
         with pytest.raises(TypeError, match="ambiguous"):
             obj.mean()