Move inconsistent namespace check to pre-commit, fixup more files (#37662)

* check for inconsistent namespace usage

* doc

* typos

* verbose regex

* use verbose flag

* use verbose flag

* match both directions

* add test

* don't import annotations from future

* update extra couple of cases

* 🚚 rename

* typing

* don't use subprocess

* don't type tests

* use pathlib

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -119,6 +119,12 @@ repos:
         entry: python scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module"
         types: [python]
         exclude: ^(asv_bench|pandas/tests|doc)/
+    -   id: inconsistent-namespace-usage
+        name: 'Check for inconsistent use of pandas namespace in tests'
+        entry: python scripts/check_for_inconsistent_pandas_namespace.py
+        language: python
+        types: [python]
+        files: ^pandas/tests/
     -   id: FrameOrSeriesUnion
         name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
         entry: Union\[.*(Series.*DataFrame|DataFrame.*Series).*\]

ci/code_checks.sh

@@ -37,12 +37,6 @@ function invgrep {
     return $((! $EXIT_STATUS))
 }
 
-function check_namespace {
-    local -r CLASS=${1}
-    grep -R -l --include "*.py" " ${CLASS}(" pandas/tests | xargs grep -n "pd\.${CLASS}[(\.]"
-    test $? -gt 0
-}
-
 if [[ "$GITHUB_ACTIONS" == "true" ]]; then
     FLAKE8_FORMAT="##[error]%(path)s:%(row)s:%(col)s:%(code)s:%(text)s"
     INVGREP_PREPEND="##[error]"
@@ -120,13 +114,6 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     MSG='Check for use of {foo!r} instead of {repr(foo)}' ; echo $MSG
     invgrep -R --include=*.{py,pyx} '!r}' pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    # -------------------------------------------------------------------------
-    MSG='Check for inconsistent use of pandas namespace in tests' ; echo $MSG
-    for class in "Series" "DataFrame" "Index" "MultiIndex" "Timestamp" "Timedelta" "TimedeltaIndex" "DatetimeIndex" "Categorical"; do
-        check_namespace ${class}
-        RET=$(($RET + $?))
-    done
     echo $MSG "DONE"
 fi
 

pandas/tests/dtypes/test_inference.py

@@ -862,7 +862,7 @@ def test_infer_dtype_datetime_with_na(self, na_value, time_stamp):
     @pytest.mark.parametrize(
         "arr",
         [
-            np.array([pd.Timedelta("1 days"), pd.Timedelta("2 days")]),
+            np.array([Timedelta("1 days"), Timedelta("2 days")]),
             np.array([np.timedelta64(1, "D"), np.timedelta64(2, "D")], dtype=object),
             np.array([timedelta(1), timedelta(2)]),
         ],

pandas/tests/extension/test_categorical.py

@@ -192,7 +192,7 @@ def test_cast_category_to_extension_dtype(self, expected):
             (
                 "datetime64[ns, MET]",
                 pd.DatetimeIndex(
-                    [pd.Timestamp("2015-01-01 00:00:00+0100", tz="MET")]
+                    [Timestamp("2015-01-01 00:00:00+0100", tz="MET")]
                 ).array,
             ),
         ],
@@ -254,7 +254,7 @@ def _compare_other(self, s, data, op_name, other):
 
     @pytest.mark.parametrize(
         "categories",
-        [["a", "b"], [0, 1], [pd.Timestamp("2019"), pd.Timestamp("2020")]],
+        [["a", "b"], [0, 1], [Timestamp("2019"), Timestamp("2020")]],
     )
     def test_not_equal_with_na(self, categories):
         # https://github.com/pandas-dev/pandas/issues/32276

pandas/tests/groupby/aggregate/test_other.py

@@ -425,7 +425,7 @@ def test_agg_over_numpy_arrays():
     result = df.groupby("category").agg(sum)
 
     expected_data = [[np.array([50, 70, 90])], [np.array([20, 30, 40])]]
-    expected_index = pd.Index([1, 2], name="category")
+    expected_index = Index([1, 2], name="category")
     expected_column = ["arraydata"]
     expected = DataFrame(expected_data, index=expected_index, columns=expected_column)
 
@@ -497,7 +497,7 @@ def test_sum_uint64_overflow():
     df = DataFrame([[1, 2], [3, 4], [5, 6]], dtype=object)
     df = df + 9223372036854775807
 
-    index = pd.Index(
+    index = Index(
         [9223372036854775808, 9223372036854775810, 9223372036854775812], dtype=np.uint64
     )
     expected = DataFrame(
@@ -596,7 +596,7 @@ def test_agg_lambda_with_timezone():
     result = df.groupby("tag").agg({"date": lambda e: e.head(1)})
     expected = DataFrame(
         [pd.Timestamp("2018-01-01", tz="UTC")],
-        index=pd.Index([1], name="tag"),
+        index=Index([1], name="tag"),
         columns=["date"],
     )
     tm.assert_frame_equal(result, expected)

pandas/tests/groupby/test_counting.py

@@ -4,7 +4,6 @@
 import numpy as np
 import pytest
 
-import pandas as pd
 from pandas import (
     DataFrame,
     Index,
@@ -260,7 +259,7 @@ def test_groupby_timedelta_cython_count():
     df = DataFrame(
         {"g": list("ab" * 2), "delt": np.arange(4).astype("timedelta64[ns]")}
     )
-    expected = Series([2, 2], index=pd.Index(["a", "b"], name="g"), name="delt")
+    expected = Series([2, 2], index=Index(["a", "b"], name="g"), name="delt")
     result = df.groupby("g").delt.count()
     tm.assert_series_equal(expected, result)
 
@@ -317,12 +316,12 @@ def test_count_non_nulls():
 def test_count_object():
     df = DataFrame({"a": ["a"] * 3 + ["b"] * 3, "c": [2] * 3 + [3] * 3})
     result = df.groupby("c").a.count()
-    expected = Series([3, 3], index=pd.Index([2, 3], name="c"), name="a")
+    expected = Series([3, 3], index=Index([2, 3], name="c"), name="a")
     tm.assert_series_equal(result, expected)
 
     df = DataFrame({"a": ["a", np.nan, np.nan] + ["b"] * 3, "c": [2] * 3 + [3] * 3})
     result = df.groupby("c").a.count()
-    expected = Series([1, 3], index=pd.Index([2, 3], name="c"), name="a")
+    expected = Series([1, 3], index=Index([2, 3], name="c"), name="a")
     tm.assert_series_equal(result, expected)
 
 
@@ -354,7 +353,7 @@ def test_lower_int_prec_count():
     )
     result = df.groupby("grp").count()
     expected = DataFrame(
-        {"a": [2, 2], "b": [2, 2], "c": [2, 2]}, index=pd.Index(list("ab"), name="grp")
+        {"a": [2, 2], "b": [2, 2], "c": [2, 2]}, index=Index(list("ab"), name="grp")
     )
     tm.assert_frame_equal(result, expected)
 
@@ -374,5 +373,5 @@ def __eq__(self, other):
 
     df = DataFrame({"a": [RaisingObject() for _ in range(4)], "grp": list("ab" * 2)})
     result = df.groupby("grp").count()
-    expected = DataFrame({"a": [2, 2]}, index=pd.Index(list("ab"), name="grp"))
+    expected = DataFrame({"a": [2, 2]}, index=Index(list("ab"), name="grp"))
     tm.assert_frame_equal(result, expected)

pandas/tests/groupby/test_grouping.py

@@ -614,12 +614,12 @@ def test_list_grouper_with_nat(self):
 
         # Grouper in a list grouping
         result = df.groupby([grouper])
-        expected = {pd.Timestamp("2011-01-01"): Index(list(range(364)))}
+        expected = {Timestamp("2011-01-01"): Index(list(range(364)))}
         tm.assert_dict_equal(result.groups, expected)
 
         # Test case without a list
         result = df.groupby(grouper)
-        expected = {pd.Timestamp("2011-01-01"): 365}
+        expected = {Timestamp("2011-01-01"): 365}
         tm.assert_dict_equal(result.groups, expected)
 
     @pytest.mark.parametrize(
@@ -938,12 +938,12 @@ def test_groupby_with_small_elem(self):
         grouped = df.groupby([pd.Grouper(freq="M"), "event"])
         assert len(grouped.groups) == 2
         assert grouped.ngroups == 2
-        assert (pd.Timestamp("2014-09-30"), "start") in grouped.groups
-        assert (pd.Timestamp("2013-10-31"), "start") in grouped.groups
+        assert (Timestamp("2014-09-30"), "start") in grouped.groups
+        assert (Timestamp("2013-10-31"), "start") in grouped.groups
 
-        res = grouped.get_group((pd.Timestamp("2014-09-30"), "start"))
+        res = grouped.get_group((Timestamp("2014-09-30"), "start"))
         tm.assert_frame_equal(res, df.iloc[[0], :])
-        res = grouped.get_group((pd.Timestamp("2013-10-31"), "start"))
+        res = grouped.get_group((Timestamp("2013-10-31"), "start"))
         tm.assert_frame_equal(res, df.iloc[[1], :])
 
         df = DataFrame(
@@ -953,12 +953,12 @@ def test_groupby_with_small_elem(self):
         grouped = df.groupby([pd.Grouper(freq="M"), "event"])
         assert len(grouped.groups) == 2
         assert grouped.ngroups == 2
-        assert (pd.Timestamp("2014-09-30"), "start") in grouped.groups
-        assert (pd.Timestamp("2013-10-31"), "start") in grouped.groups
+        assert (Timestamp("2014-09-30"), "start") in grouped.groups
+        assert (Timestamp("2013-10-31"), "start") in grouped.groups
 
-        res = grouped.get_group((pd.Timestamp("2014-09-30"), "start"))
+        res = grouped.get_group((Timestamp("2014-09-30"), "start"))
         tm.assert_frame_equal(res, df.iloc[[0, 2], :])
-        res = grouped.get_group((pd.Timestamp("2013-10-31"), "start"))
+        res = grouped.get_group((Timestamp("2013-10-31"), "start"))
         tm.assert_frame_equal(res, df.iloc[[1], :])
 
         # length=3
@@ -969,15 +969,15 @@ def test_groupby_with_small_elem(self):
         grouped = df.groupby([pd.Grouper(freq="M"), "event"])
         assert len(grouped.groups) == 3
         assert grouped.ngroups == 3
-        assert (pd.Timestamp("2014-09-30"), "start") in grouped.groups
-        assert (pd.Timestamp("2013-10-31"), "start") in grouped.groups
-        assert (pd.Timestamp("2014-08-31"), "start") in grouped.groups
+        assert (Timestamp("2014-09-30"), "start") in grouped.groups
+        assert (Timestamp("2013-10-31"), "start") in grouped.groups
+        assert (Timestamp("2014-08-31"), "start") in grouped.groups
 
-        res = grouped.get_group((pd.Timestamp("2014-09-30"), "start"))
+        res = grouped.get_group((Timestamp("2014-09-30"), "start"))
         tm.assert_frame_equal(res, df.iloc[[0], :])
-        res = grouped.get_group((pd.Timestamp("2013-10-31"), "start"))
+        res = grouped.get_group((Timestamp("2013-10-31"), "start"))
         tm.assert_frame_equal(res, df.iloc[[1], :])
-        res = grouped.get_group((pd.Timestamp("2014-08-31"), "start"))
+        res = grouped.get_group((Timestamp("2014-08-31"), "start"))
         tm.assert_frame_equal(res, df.iloc[[2], :])
 
     def test_grouping_string_repr(self):

pandas/tests/groupby/test_missing.py

@@ -11,11 +11,11 @@ def test_groupby_column_index_name_lost_fill_funcs(func):
     # GH: 29764 groupby loses index sometimes
     df = DataFrame(
         [[1, 1.0, -1.0], [1, np.nan, np.nan], [1, 2.0, -2.0]],
-        columns=pd.Index(["type", "a", "b"], name="idx"),
+        columns=Index(["type", "a", "b"], name="idx"),
     )
     df_grouped = df.groupby(["type"])[["a", "b"]]
     result = getattr(df_grouped, func)().columns
-    expected = pd.Index(["a", "b"], name="idx")
+    expected = Index(["a", "b"], name="idx")
     tm.assert_index_equal(result, expected)
 
 

pandas/tests/groupby/test_quantile.py

@@ -194,7 +194,7 @@ def test_quantile_missing_group_values_correct_results(
     df = DataFrame({"key": key, "val": val})
 
     expected = DataFrame(
-        expected_val, index=pd.Index(expected_key, name="key"), columns=["val"]
+        expected_val, index=Index(expected_key, name="key"), columns=["val"]
     )
 
     grp = df.groupby("key")
@@ -223,7 +223,7 @@ def test_groupby_quantile_nullable_array(values, q):
         idx = pd.MultiIndex.from_product((["x", "y"], q), names=["a", None])
         true_quantiles = [0.0, 0.5, 1.0]
     else:
-        idx = pd.Index(["x", "y"], name="a")
+        idx = Index(["x", "y"], name="a")
         true_quantiles = [0.5]
 
     expected = pd.Series(true_quantiles * 2, index=idx, name="b")
@@ -251,6 +251,6 @@ def test_groupby_timedelta_quantile():
                 pd.Timedelta("0 days 00:00:02.990000"),
             ]
         },
-        index=pd.Index([1, 2], name="group"),
+        index=Index([1, 2], name="group"),
     )
     tm.assert_frame_equal(result, expected)

pandas/tests/groupby/test_timegrouper.py

@@ -452,15 +452,15 @@ def test_groupby_groups_datetimeindex(self):
         result = df.groupby(level="date").groups
         dates = ["2015-01-05", "2015-01-04", "2015-01-03", "2015-01-02", "2015-01-01"]
         expected = {
-            Timestamp(date): pd.DatetimeIndex([date], name="date") for date in dates
+            Timestamp(date): DatetimeIndex([date], name="date") for date in dates
         }
         tm.assert_dict_equal(result, expected)
 
         grouped = df.groupby(level="date")
         for date in dates:
             result = grouped.get_group(date)
             data = [[df.loc[date, "A"], df.loc[date, "B"]]]
-            expected_index = pd.DatetimeIndex([date], name="date", freq="D")
+            expected_index = DatetimeIndex([date], name="date", freq="D")
             expected = DataFrame(data, columns=list("AB"), index=expected_index)
             tm.assert_frame_equal(result, expected)
 
@@ -484,7 +484,7 @@ def test_groupby_groups_datetimeindex_tz(self):
         )
         df["datetime"] = df["datetime"].apply(lambda d: Timestamp(d, tz="US/Pacific"))
 
-        exp_idx1 = pd.DatetimeIndex(
+        exp_idx1 = DatetimeIndex(
             [
                 "2011-07-19 07:00:00",
                 "2011-07-19 07:00:00",
@@ -508,13 +508,13 @@ def test_groupby_groups_datetimeindex_tz(self):
         tm.assert_frame_equal(result, expected)
 
         # by level
-        didx = pd.DatetimeIndex(dates, tz="Asia/Tokyo")
+        didx = DatetimeIndex(dates, tz="Asia/Tokyo")
         df = DataFrame(
             {"value1": np.arange(6, dtype="int64"), "value2": [1, 2, 3, 1, 2, 3]},
             index=didx,
         )
 
-        exp_idx = pd.DatetimeIndex(
+        exp_idx = DatetimeIndex(
             ["2011-07-19 07:00:00", "2011-07-19 08:00:00", "2011-07-19 09:00:00"],
             tz="Asia/Tokyo",
         )