STYLE: Inconsistent namespace - groupby (#39992) (#40056)

Author: alexprincel

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -127,7 +127,7 @@ def test_groupby_aggregation_multi_level_column():
     ]
     df = DataFrame(
         data=lst,
-        columns=pd.MultiIndex.from_tuples([("A", 0), ("A", 1), ("B", 0), ("B", 1)]),
+        columns=MultiIndex.from_tuples([("A", 0), ("A", 1), ("B", 0), ("B", 1)]),
     )
 
     result = df.groupby(level=1, axis=1).sum()
@@ -310,7 +310,7 @@ def test_agg_multiple_functions_same_name_with_ohlc_present():
         {"A": ["ohlc", partial(np.quantile, q=0.9999), partial(np.quantile, q=0.1111)]}
     )
     expected_index = pd.date_range("1/1/2012", freq="3T", periods=6)
-    expected_columns = pd.MultiIndex.from_tuples(
+    expected_columns = MultiIndex.from_tuples(
         [
             ("A", "ohlc", "open"),
             ("A", "ohlc", "high"),
@@ -484,7 +484,7 @@ def test_func_duplicates_raises():
         pd.CategoricalIndex(list("abc")),
         pd.interval_range(0, 3),
         pd.period_range("2020", periods=3, freq="D"),
-        pd.MultiIndex.from_tuples([("a", 0), ("a", 1), ("b", 0)]),
+        MultiIndex.from_tuples([("a", 0), ("a", 1), ("b", 0)]),
     ],
 )
 def test_agg_index_has_complex_internals(index):
@@ -665,7 +665,7 @@ def test_duplicate_no_raises(self):
     def test_agg_relabel_with_level(self):
         df = DataFrame(
             {"A": [0, 0, 1, 1], "B": [1, 2, 3, 4]},
-            index=pd.MultiIndex.from_product([["A", "B"], ["a", "b"]]),
+            index=MultiIndex.from_product([["A", "B"], ["a", "b"]]),
         )
         result = df.groupby(level=0).agg(
             aa=("A", "max"), bb=("A", "min"), cc=("B", "mean")
@@ -745,7 +745,7 @@ def test_agg_relabel_multiindex_column(
     df = DataFrame(
         {"group": ["a", "a", "b", "b"], "A": [0, 1, 2, 3], "B": [5, 6, 7, 8]}
     )
-    df.columns = pd.MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
+    df.columns = MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
     idx = Index(["a", "b"], name=("x", "group"))
 
     result = df.groupby(("x", "group")).agg(a_max=(("y", "A"), "max"))
@@ -766,7 +766,7 @@ def test_agg_relabel_multiindex_raises_not_exist():
     df = DataFrame(
         {"group": ["a", "a", "b", "b"], "A": [0, 1, 2, 3], "B": [5, 6, 7, 8]}
     )
-    df.columns = pd.MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
+    df.columns = MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
 
     with pytest.raises(KeyError, match="do not exist"):
         df.groupby(("x", "group")).agg(a=(("Y", "a"), "max"))
@@ -779,7 +779,7 @@ def test_agg_relabel_multiindex_duplicates():
     df = DataFrame(
         {"group": ["a", "a", "b", "b"], "A": [0, 1, 2, 3], "B": [5, 6, 7, 8]}
     )
-    df.columns = pd.MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
+    df.columns = MultiIndex.from_tuples([("x", "group"), ("y", "A"), ("y", "B")])
 
     result = df.groupby(("x", "group")).agg(
         a=(("y", "A"), "min"), b=(("y", "A"), "min")
@@ -797,7 +797,7 @@ def test_groupby_aggregate_empty_key(kwargs):
     expected = DataFrame(
         [1, 4],
         index=Index([1, 2], dtype="int64", name="a"),
-        columns=pd.MultiIndex.from_tuples([["c", "min"]]),
+        columns=MultiIndex.from_tuples([["c", "min"]]),
     )
     tm.assert_frame_equal(result, expected)
 
@@ -806,7 +806,7 @@ def test_groupby_aggregate_empty_key_empty_return():
     # GH: 32580 Check if everything works, when return is empty
     df = DataFrame({"a": [1, 1, 2], "b": [1, 2, 3], "c": [1, 2, 4]})
     result = df.groupby("a").agg({"b": []})
-    expected = DataFrame(columns=pd.MultiIndex(levels=[["b"], []], codes=[[], []]))
+    expected = DataFrame(columns=MultiIndex(levels=[["b"], []], codes=[[], []]))
     tm.assert_frame_equal(result, expected)
 
 
@@ -851,7 +851,7 @@ def test_grouby_agg_loses_results_with_as_index_false_relabel_multiindex():
 def test_multiindex_custom_func(func):
     # GH 31777
     data = [[1, 4, 2], [5, 7, 1]]
-    df = DataFrame(data, columns=pd.MultiIndex.from_arrays([[1, 1, 2], [3, 4, 3]]))
+    df = DataFrame(data, columns=MultiIndex.from_arrays([[1, 1, 2], [3, 4, 3]]))
     result = df.groupby(np.array([0, 1])).agg(func)
     expected_dict = {(1, 3): {0: 1, 1: 5}, (1, 4): {0: 4, 1: 7}, (2, 3): {0: 2, 1: 1}}
     expected = DataFrame(expected_dict)
@@ -1150,7 +1150,7 @@ def test_groupby_combined_aggs_cat_cols(grp_col_dict, exp_data):
                 multi_index_list.append([k, value])
         else:
             multi_index_list.append([k, v])
-    multi_index = pd.MultiIndex.from_tuples(tuple(multi_index_list))
+    multi_index = MultiIndex.from_tuples(tuple(multi_index_list))
 
     expected_df = DataFrame(data=exp_data, columns=multi_index, index=cat_index)
 

pandas/tests/groupby/aggregate/test_other.py

@@ -439,7 +439,7 @@ def test_agg_over_numpy_arrays():
 def test_agg_tzaware_non_datetime_result(as_period):
     # discussed in GH#29589, fixed in GH#29641, operating on tzaware values
     #  with function that is not dtype-preserving
-    dti = pd.date_range("2012-01-01", periods=4, tz="UTC")
+    dti = date_range("2012-01-01", periods=4, tz="UTC")
     if as_period:
         dti = dti.tz_localize(None).to_period("D")
 

pandas/tests/groupby/test_apply.py

@@ -930,7 +930,7 @@ def test_groupby_apply_datetime_result_dtypes():
         pd.CategoricalIndex(list("abc")),
         pd.interval_range(0, 3),
         pd.period_range("2020", periods=3, freq="D"),
-        pd.MultiIndex.from_tuples([("a", 0), ("a", 1), ("b", 0)]),
+        MultiIndex.from_tuples([("a", 0), ("a", 1), ("b", 0)]),
     ],
 )
 def test_apply_index_has_complex_internals(index):
@@ -1070,7 +1070,7 @@ def test_apply_with_date_in_multiindex_does_not_convert_to_timestamp():
 
     expected = df.iloc[[0, 2, 3]]
     expected = expected.reset_index()
-    expected.index = pd.MultiIndex.from_frame(expected[["A", "B", "idx"]])
+    expected.index = MultiIndex.from_frame(expected[["A", "B", "idx"]])
     expected = expected.drop(columns="idx")
 
     tm.assert_frame_equal(result, expected)
@@ -1086,7 +1086,7 @@ def test_apply_by_cols_equals_apply_by_rows_transposed():
 
     df = DataFrame(
         np.random.random([6, 4]),
-        columns=pd.MultiIndex.from_product([["A", "B"], [1, 2]]),
+        columns=MultiIndex.from_product([["A", "B"], [1, 2]]),
     )
 
     by_rows = df.T.groupby(axis=0, level=0).apply(

pandas/tests/groupby/test_categorical.py

@@ -1568,7 +1568,7 @@ def test_aggregate_categorical_with_isnan():
     df = df.astype({"categorical_col": "category"})
 
     result = df.groupby(["A", "B"]).agg(lambda df: df.isna().sum())
-    index = pd.MultiIndex.from_arrays([[1, 1], [1, 2]], names=("A", "B"))
+    index = MultiIndex.from_arrays([[1, 1], [1, 2]], names=("A", "B"))
     expected = DataFrame(
         data={
             "numerical_col": [1.0, 0.0],
@@ -1640,7 +1640,7 @@ def test_series_groupby_first_on_categorical_col_grouped_on_2_categoricals(
     df = DataFrame({"a": cat, "b": cat, "c": val})
 
     cat2 = Categorical([0, 1])
-    idx = pd.MultiIndex.from_product([cat2, cat2], names=["a", "b"])
+    idx = MultiIndex.from_product([cat2, cat2], names=["a", "b"])
     expected_dict = {
         "first": Series([0, np.NaN, np.NaN, 1], idx, name="c"),
         "last": Series([1, np.NaN, np.NaN, 0], idx, name="c"),
@@ -1665,7 +1665,7 @@ def test_df_groupby_first_on_categorical_col_grouped_on_2_categoricals(
     df = DataFrame({"a": cat, "b": cat, "c": val})
 
     cat2 = Categorical([0, 1])
-    idx = pd.MultiIndex.from_product([cat2, cat2], names=["a", "b"])
+    idx = MultiIndex.from_product([cat2, cat2], names=["a", "b"])
     expected_dict = {
         "first": Series([0, np.NaN, np.NaN, 1], idx, name="c"),
         "last": Series([1, np.NaN, np.NaN, 0], idx, name="c"),

pandas/tests/groupby/test_function.py

@@ -370,7 +370,7 @@ def test_mad(self, gb, gni):
     def test_describe(self, df, gb, gni):
         # describe
         expected_index = Index([1, 3], name="A")
-        expected_col = pd.MultiIndex(
+        expected_col = MultiIndex(
             levels=[["B"], ["count", "mean", "std", "min", "25%", "50%", "75%", "max"]],
             codes=[[0] * 8, list(range(8))],
         )
@@ -566,7 +566,7 @@ def test_idxmin_idxmax_axis1():
 
     tm.assert_series_equal(alt[indexer], res.droplevel("A"))
 
-    df["E"] = pd.date_range("2016-01-01", periods=10)
+    df["E"] = date_range("2016-01-01", periods=10)
     gb2 = df.groupby("A")
 
     msg = "reduction operation 'argmax' not allowed for this dtype"
@@ -958,7 +958,7 @@ def test_frame_describe_multikey(tsframe):
     for col in tsframe:
         group = grouped[col].describe()
         # GH 17464 - Remove duplicate MultiIndex levels
-        group_col = pd.MultiIndex(
+        group_col = MultiIndex(
             levels=[[col], group.columns],
             codes=[[0] * len(group.columns), range(len(group.columns))],
         )

pandas/tests/groupby/test_groupby.py

@@ -1234,7 +1234,7 @@ def test_groupby_list_infer_array_like(df):
 def test_groupby_keys_same_size_as_index():
     # GH 11185
     freq = "s"
-    index = pd.date_range(
+    index = date_range(
         start=Timestamp("2015-09-29T11:34:44-0700"), periods=2, freq=freq
     )
     df = DataFrame([["A", 10], ["B", 15]], columns=["metric", "values"], index=index)
@@ -1704,7 +1704,7 @@ def test_pivot_table_values_key_error():
     # This test is designed to replicate the error in issue #14938
     df = DataFrame(
         {
-            "eventDate": pd.date_range(datetime.today(), periods=20, freq="M").tolist(),
+            "eventDate": date_range(datetime.today(), periods=20, freq="M").tolist(),
             "thename": range(0, 20),
         }
     )
@@ -1793,7 +1793,7 @@ def test_groupby_agg_ohlc_non_first():
     df = DataFrame(
         [[1], [1]],
         columns=["foo"],
-        index=pd.date_range("2018-01-01", periods=2, freq="D"),
+        index=date_range("2018-01-01", periods=2, freq="D"),
     )
 
     expected = DataFrame(
@@ -1807,7 +1807,7 @@ def test_groupby_agg_ohlc_non_first():
                 ("foo", "ohlc", "close"),
             )
         ),
-        index=pd.date_range("2018-01-01", periods=2, freq="D"),
+        index=date_range("2018-01-01", periods=2, freq="D"),
     )
 
     result = df.groupby(Grouper(freq="D")).agg(["sum", "ohlc"])

pandas/tests/groupby/test_grouping.py

@@ -611,7 +611,7 @@ def test_grouping_labels(self, mframe):
 
     def test_list_grouper_with_nat(self):
         # GH 14715
-        df = DataFrame({"date": pd.date_range("1/1/2011", periods=365, freq="D")})
+        df = DataFrame({"date": date_range("1/1/2011", periods=365, freq="D")})
         df.iloc[-1] = pd.NaT
         grouper = pd.Grouper(key="date", freq="AS")
 

pandas/tests/groupby/test_timegrouper.py

@@ -228,7 +228,7 @@ def test_timegrouper_with_reg_groups(self):
 
             # multi names
             df = df.copy()
-            df["Date"] = df.index + pd.offsets.MonthEnd(2)
+            df["Date"] = df.index + offsets.MonthEnd(2)
             result = df.groupby([Grouper(freq="1M", key="Date"), "Buyer"]).sum()
             expected = DataFrame(
                 {
@@ -434,7 +434,7 @@ def sumfunc_value(x):
     def test_groupby_groups_datetimeindex(self):
         # GH#1430
         periods = 1000
-        ind = pd.date_range(start="2012/1/1", freq="5min", periods=periods)
+        ind = date_range(start="2012/1/1", freq="5min", periods=periods)
         df = DataFrame(
             {"high": np.arange(periods), "low": np.arange(periods)}, index=ind
         )
@@ -445,7 +445,7 @@ def test_groupby_groups_datetimeindex(self):
         assert isinstance(list(groups.keys())[0], datetime)
 
         # GH#11442
-        index = pd.date_range("2015/01/01", periods=5, name="date")
+        index = date_range("2015/01/01", periods=5, name="date")
         df = DataFrame({"A": [5, 6, 7, 8, 9], "B": [1, 2, 3, 4, 5]}, index=index)
         result = df.groupby(level="date").groups
         dates = ["2015-01-05", "2015-01-04", "2015-01-03", "2015-01-02", "2015-01-01"]
@@ -672,9 +672,7 @@ def test_groupby_with_timezone_selection(self):
         df = DataFrame(
             {
                 "factor": np.random.randint(0, 3, size=60),
-                "time": pd.date_range(
-                    "01/01/2000 00:00", periods=60, freq="s", tz="UTC"
-                ),
+                "time": date_range("01/01/2000 00:00", periods=60, freq="s", tz="UTC"),
             }
         )
         df1 = df.groupby("factor").max()["time"]
@@ -693,7 +691,7 @@ def test_timezone_info(self):
 
     def test_datetime_count(self):
         df = DataFrame(
-            {"a": [1, 2, 3] * 2, "dates": pd.date_range("now", periods=6, freq="T")}
+            {"a": [1, 2, 3] * 2, "dates": date_range("now", periods=6, freq="T")}
         )
         result = df.groupby("a").dates.count()
         expected = Series([2, 2, 2], index=Index([1, 2, 3], name="a"), name="dates")

pandas/tests/groupby/transform/test_transform.py

@@ -101,7 +101,7 @@ def test_transform_fast():
         {
             "grouping": [0, 1, 1, 3],
             "f": [1.1, 2.1, 3.1, 4.5],
-            "d": pd.date_range("2014-1-1", "2014-1-4"),
+            "d": date_range("2014-1-1", "2014-1-4"),
             "i": [1, 2, 3, 4],
         },
         columns=["grouping", "f", "i", "d"],
@@ -347,7 +347,7 @@ def test_transform_transformation_func(request, transformation_func):
             "A": ["foo", "foo", "foo", "foo", "bar", "bar", "baz"],
             "B": [1, 2, np.nan, 3, 3, np.nan, 4],
         },
-        index=pd.date_range("2020-01-01", "2020-01-07"),
+        index=date_range("2020-01-01", "2020-01-07"),
     )
 
     if transformation_func == "cumcount":
@@ -413,7 +413,7 @@ def test_transform_function_aliases(df):
 def test_series_fast_transform_date():
     # GH 13191
     df = DataFrame(
-        {"grouping": [np.nan, 1, 1, 3], "d": pd.date_range("2014-1-1", "2014-1-4")}
+        {"grouping": [np.nan, 1, 1, 3], "d": date_range("2014-1-1", "2014-1-4")}
     )
     result = df.groupby("grouping")["d"].transform("first")
     dates = [
@@ -649,7 +649,7 @@ def test_cython_transform_frame(op, args, targop):
             "float": s,
             "float_missing": s_missing,
             "int": [1, 1, 1, 1, 2] * 200,
-            "datetime": pd.date_range("1990-1-1", periods=1000),
+            "datetime": date_range("1990-1-1", periods=1000),
             "timedelta": pd.timedelta_range(1, freq="s", periods=1000),
             "string": strings * 50,
             "string_missing": strings_missing * 50,
@@ -667,7 +667,7 @@ def test_cython_transform_frame(op, args, targop):
     df["cat"] = df["string"].astype("category")
 
     df2 = df.copy()
-    df2.index = pd.MultiIndex.from_product([range(100), range(10)])
+    df2.index = MultiIndex.from_product([range(100), range(10)])
 
     # DataFrame - Single and MultiIndex,
     # group by values, index level, columns
@@ -691,7 +691,7 @@ def test_cython_transform_frame(op, args, targop):
                 # to apply separately and concat
                 i = gb[["int"]].apply(targop)
                 f = gb[["float", "float_missing"]].apply(targop)
-                expected = pd.concat([f, i], axis=1)
+                expected = concat([f, i], axis=1)
             else:
                 expected = gb.apply(targop)
 
@@ -715,7 +715,7 @@ def test_cython_transform_frame(op, args, targop):
 
 def test_transform_with_non_scalar_group():
     # GH 10165
-    cols = pd.MultiIndex.from_tuples(
+    cols = MultiIndex.from_tuples(
         [
             ("syn", "A"),
             ("mis", "A"),
@@ -761,7 +761,7 @@ def test_transform_numeric_ret(cols, exp, comp_func, agg_func, request):
 
     # GH 19200
     df = DataFrame(
-        {"a": pd.date_range("2018-01-01", periods=3), "b": range(3), "c": range(7, 10)}
+        {"a": date_range("2018-01-01", periods=3), "b": range(3), "c": range(7, 10)}
     )
 
     result = df.groupby("b")[cols].transform(agg_func)
@@ -958,7 +958,7 @@ def test_groupby_transform_rename():
     def demean_rename(x):
         result = x - x.mean()
 
-        if isinstance(x, pd.Series):
+        if isinstance(x, Series):
             return result
 
         result = result.rename(columns={c: "{c}_demeaned" for c in result.columns})
@@ -993,7 +993,7 @@ def test_groupby_transform_timezone_column(func):
 )
 def test_groupby_transform_with_datetimes(func, values):
     # GH 15306
-    dates = pd.date_range("1/1/2011", periods=10, freq="D")
+    dates = date_range("1/1/2011", periods=10, freq="D")
 
     stocks = DataFrame({"price": np.arange(10.0)}, index=dates)
     stocks["week_id"] = dates.isocalendar().week