use ast.parse to fixup inconsistencies in namespace

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -138,7 +138,8 @@ repos:
         entry: python scripts/check_for_inconsistent_pandas_namespace.py
         language: python
         types: [python]
-        files: ^pandas/tests/
+        files: ^pandas/tests/frame/
+        additional_dependencies: [tokenize-rt]
     -   id: FrameOrSeriesUnion
         name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
         entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]

pandas/tests/frame/indexing/test_indexing.py

@@ -212,7 +212,7 @@ def test_setitem_multi_index(self):
         it = ["jim", "joe", "jolie"], ["first", "last"], ["left", "center", "right"]
 
         cols = MultiIndex.from_product(it)
-        index = pd.date_range("20141006", periods=20)
+        index = date_range("20141006", periods=20)
         vals = np.random.randint(1, 1000, (len(index), len(cols)))
         df = DataFrame(vals, columns=cols, index=index)
 
@@ -1349,7 +1349,7 @@ def test_loc_duplicates(self):
         # gh-17105
 
         # insert a duplicate element to the index
-        trange = pd.date_range(
+        trange = date_range(
             start=Timestamp(year=2017, month=1, day=1),
             end=Timestamp(year=2017, month=1, day=5),
         )
@@ -1413,7 +1413,7 @@ def test_setitem_with_unaligned_tz_aware_datetime_column(self):
         # GH 12981
         # Assignment of unaligned offset-aware datetime series.
         # Make sure timezone isn't lost
-        column = Series(pd.date_range("2015-01-01", periods=3, tz="utc"), name="dates")
+        column = Series(date_range("2015-01-01", periods=3, tz="utc"), name="dates")
         df = DataFrame({"dates": column})
         df["dates"] = column[[1, 0, 2]]
         tm.assert_series_equal(df["dates"], column)
@@ -1737,7 +1737,7 @@ def test_object_casting_indexing_wraps_datetimelike():
     df = DataFrame(
         {
             "A": [1, 2],
-            "B": pd.date_range("2000", periods=2),
+            "B": date_range("2000", periods=2),
             "C": pd.timedelta_range("1 Day", periods=2),
         }
     )

pandas/tests/frame/methods/test_describe.py

@@ -277,7 +277,7 @@ def test_describe_tz_values(self, tz_naive_fixture):
         tm.assert_frame_equal(result, expected)
 
     def test_datetime_is_numeric_includes_datetime(self):
-        df = DataFrame({"a": pd.date_range("2012", periods=3), "b": [1, 2, 3]})
+        df = DataFrame({"a": date_range("2012", periods=3), "b": [1, 2, 3]})
         result = df.describe(datetime_is_numeric=True)
         expected = DataFrame(
             {

pandas/tests/frame/methods/test_diff.py

@@ -75,7 +75,7 @@ def test_diff_datetime_axis0_with_nat(self, tz):
     @pytest.mark.parametrize("tz", [None, "UTC"])
     def test_diff_datetime_with_nat_zero_periods(self, tz):
         # diff on NaT values should give NaT, not timedelta64(0)
-        dti = pd.date_range("2016-01-01", periods=4, tz=tz)
+        dti = date_range("2016-01-01", periods=4, tz=tz)
         ser = Series(dti)
         df = ser.to_frame()
 
@@ -173,7 +173,7 @@ def test_diff_axis(self):
 
     def test_diff_period(self):
         # GH#32995 Don't pass an incorrect axis
-        pi = pd.date_range("2016-01-01", periods=3).to_period("D")
+        pi = date_range("2016-01-01", periods=3).to_period("D")
         df = DataFrame({"A": pi})
 
         result = df.diff(1, axis=1)

pandas/tests/frame/methods/test_drop.py

@@ -21,7 +21,7 @@
 def test_drop_raise_exception_if_labels_not_in_level(msg, labels, level):
     # GH 8594
     mi = MultiIndex.from_arrays([[1, 2, 3], [4, 5, 6]], names=["a", "b"])
-    s = pd.Series([10, 20, 30], index=mi)
+    s = Series([10, 20, 30], index=mi)
     df = DataFrame([10, 20, 30], index=mi)
 
     with pytest.raises(KeyError, match=msg):
@@ -34,7 +34,7 @@ def test_drop_raise_exception_if_labels_not_in_level(msg, labels, level):
 def test_drop_errors_ignore(labels, level):
     # GH 8594
     mi = MultiIndex.from_arrays([[1, 2, 3], [4, 5, 6]], names=["a", "b"])
-    s = pd.Series([10, 20, 30], index=mi)
+    s = Series([10, 20, 30], index=mi)
     df = DataFrame([10, 20, 30], index=mi)
 
     expected_s = s.drop(labels, level=level, errors="ignore")

pandas/tests/frame/methods/test_join.py

@@ -304,7 +304,7 @@ def test_join_multiindex_leftright(self):
         tm.assert_frame_equal(df1.join(df2, how="left"), exp)
         tm.assert_frame_equal(df2.join(df1, how="right"), exp[["value2", "value1"]])
 
-        exp_idx = pd.MultiIndex.from_product(
+        exp_idx = MultiIndex.from_product(
             [["a", "b"], ["x", "y", "z"]], names=["first", "second"]
         )
         exp = DataFrame(

pandas/tests/frame/methods/test_reset_index.py

@@ -423,7 +423,7 @@ def test_reset_index_multiindex_columns(self):
     def test_reset_index_datetime(self, tz_naive_fixture):
         # GH#3950
         tz = tz_naive_fixture
-        idx1 = pd.date_range("1/1/2011", periods=5, freq="D", tz=tz, name="idx1")
+        idx1 = date_range("1/1/2011", periods=5, freq="D", tz=tz, name="idx1")
         idx2 = Index(range(5), name="idx2", dtype="int64")
         idx = MultiIndex.from_arrays([idx1, idx2])
         df = DataFrame(
@@ -450,7 +450,7 @@ def test_reset_index_datetime(self, tz_naive_fixture):
 
         tm.assert_frame_equal(df.reset_index(), expected)
 
-        idx3 = pd.date_range(
+        idx3 = date_range(
             "1/1/2012", periods=5, freq="MS", tz="Europe/Paris", name="idx3"
         )
         idx = MultiIndex.from_arrays([idx1, idx2, idx3])
@@ -489,7 +489,7 @@ def test_reset_index_datetime(self, tz_naive_fixture):
 
         # GH#7793
         idx = MultiIndex.from_product(
-            [["a", "b"], pd.date_range("20130101", periods=3, tz=tz)]
+            [["a", "b"], date_range("20130101", periods=3, tz=tz)]
         )
         df = DataFrame(
             np.arange(6, dtype="int64").reshape(6, 1), columns=["a"], index=idx

pandas/tests/frame/methods/test_to_csv.py

@@ -12,6 +12,7 @@
     DataFrame,
     Index,
     MultiIndex,
+    NaT,
     Series,
     Timestamp,
     date_range,
@@ -41,7 +42,7 @@ def read_csv(self, path, **kwargs):
         params = {"index_col": 0, "parse_dates": True}
         params.update(**kwargs)
 
-        return pd.read_csv(path, **params)
+        return read_csv(path, **params)
 
     def test_to_csv_from_csv1(self, float_frame, datetime_frame):
 
@@ -123,7 +124,7 @@ def test_to_csv_from_csv3(self):
             df1.to_csv(path)
             df2.to_csv(path, mode="a", header=False)
             xp = pd.concat([df1, df2])
-            rs = pd.read_csv(path, index_col=0)
+            rs = read_csv(path, index_col=0)
             rs.columns = [int(label) for label in rs.columns]
             xp.columns = [int(label) for label in xp.columns]
             tm.assert_frame_equal(xp, rs)
@@ -139,7 +140,7 @@ def test_to_csv_from_csv4(self):
             )
             df.to_csv(path)
 
-            result = pd.read_csv(path, index_col="dt_index")
+            result = read_csv(path, index_col="dt_index")
             result.index = pd.to_timedelta(result.index)
             # TODO: remove renaming when GH 10875 is solved
             result.index = result.index.rename("dt_index")
@@ -153,7 +154,7 @@ def test_to_csv_from_csv5(self, timezone_frame):
         with tm.ensure_clean("__tmp_to_csv_from_csv5__") as path:
 
             timezone_frame.to_csv(path)
-            result = pd.read_csv(path, index_col=0, parse_dates=["A"])
+            result = read_csv(path, index_col=0, parse_dates=["A"])
 
             converter = (
                 lambda c: to_datetime(result[c])
@@ -166,8 +167,6 @@ def test_to_csv_from_csv5(self, timezone_frame):
 
     def test_to_csv_cols_reordering(self):
         # GH3454
-        import pandas as pd
-
         chunksize = 5
         N = int(chunksize * 2.5)
 
@@ -177,17 +176,15 @@ def test_to_csv_cols_reordering(self):
 
         with tm.ensure_clean() as path:
             df.to_csv(path, columns=cols, chunksize=chunksize)
-            rs_c = pd.read_csv(path, index_col=0)
+            rs_c = read_csv(path, index_col=0)
 
         tm.assert_frame_equal(df[cols], rs_c, check_names=False)
 
     def test_to_csv_new_dupe_cols(self):
-        import pandas as pd
-
         def _check_df(df, cols=None):
             with tm.ensure_clean() as path:
                 df.to_csv(path, columns=cols, chunksize=chunksize)
-                rs_c = pd.read_csv(path, index_col=0)
+                rs_c = read_csv(path, index_col=0)
 
                 # we wrote them in a different order
                 # so compare them in that order
@@ -227,8 +224,6 @@ def _check_df(df, cols=None):
     @pytest.mark.slow
     def test_to_csv_dtnat(self):
         # GH3437
-        from pandas import NaT
-
         def make_dtnat_arr(n, nnat=None):
             if nnat is None:
                 nnat = int(n * 0.1)  # 10%
@@ -999,7 +994,7 @@ def test_to_csv_path_is_none(self, float_frame):
         # Series.to_csv()
         csv_str = float_frame.to_csv(path_or_buf=None)
         assert isinstance(csv_str, str)
-        recons = pd.read_csv(StringIO(csv_str), index_col=0)
+        recons = read_csv(StringIO(csv_str), index_col=0)
         tm.assert_frame_equal(float_frame, recons)
 
     @pytest.mark.parametrize(
@@ -1040,7 +1035,7 @@ def test_to_csv_compression(self, df, encoding, compression):
                 df.to_csv(handles.handle, encoding=encoding)
                 assert not handles.handle.closed
 
-            result = pd.read_csv(
+            result = read_csv(
                 filename,
                 compression=compression,
                 encoding=encoding,
@@ -1122,7 +1117,7 @@ def test_to_csv_with_dst_transitions(self):
 
         with tm.ensure_clean("csv_date_format_with_dst") as path:
             # make sure we are not failing on transitions
-            times = pd.date_range(
+            times = date_range(
                 "2013-10-26 23:00",
                 "2013-10-27 01:00",
                 tz="Europe/London",
@@ -1144,7 +1139,7 @@ def test_to_csv_with_dst_transitions(self):
                 tm.assert_frame_equal(result, df)
 
         # GH11619
-        idx = pd.date_range("2015-01-01", "2015-12-31", freq="H", tz="Europe/Paris")
+        idx = date_range("2015-01-01", "2015-12-31", freq="H", tz="Europe/Paris")
         idx = idx._with_freq(None)  # freq does not round-trip
         idx._data._freq = None  # otherwise there is trouble on unpickle
         df = DataFrame({"values": 1, "idx": idx}, index=idx)
@@ -1250,7 +1245,7 @@ def test_to_csv_quoting(self):
         # presents with encoding?
         text_rows = ["a,b,c", '1,"test \r\n",3']
         text = tm.convert_rows_list_to_csv_str(text_rows)
-        df = pd.read_csv(StringIO(text))
+        df = read_csv(StringIO(text))
 
         buf = StringIO()
         df.to_csv(buf, encoding="utf-8", index=False)
@@ -1286,7 +1281,7 @@ def test_period_index_date_overflow(self):
         assert result == expected
 
         # Overflow with pd.NaT
-        dates = ["1990-01-01", pd.NaT, "3005-01-01"]
+        dates = ["1990-01-01", NaT, "3005-01-01"]
         index = pd.PeriodIndex(dates, freq="D")
 
         df = DataFrame([4, 5, 6], index=index)
@@ -1298,7 +1293,7 @@ def test_period_index_date_overflow(self):
 
     def test_multi_index_header(self):
         # see gh-5539
-        columns = pd.MultiIndex.from_tuples([("a", 1), ("a", 2), ("b", 1), ("b", 2)])
+        columns = MultiIndex.from_tuples([("a", 1), ("a", 2), ("b", 1), ("b", 2)])
         df = DataFrame([[1, 2, 3, 4], [5, 6, 7, 8]])
         df.columns = columns
 

pandas/tests/frame/test_api.py

@@ -65,7 +65,7 @@ def test_tab_completion(self):
         df = DataFrame([list("abcd"), list("efgh")], columns=list("ABCD"))
         for key in list("ABCD"):
             assert key in dir(df)
-        assert isinstance(df.__getitem__("A"), pd.Series)
+        assert isinstance(df.__getitem__("A"), Series)
 
         # DataFrame whose first-level columns are identifiers shall have
         # them in __dir__.
@@ -77,7 +77,7 @@ def test_tab_completion(self):
             assert key in dir(df)
         for key in list("EFGH"):
             assert key not in dir(df)
-        assert isinstance(df.__getitem__("A"), pd.DataFrame)
+        assert isinstance(df.__getitem__("A"), DataFrame)
 
     def test_not_hashable(self):
         empty_frame = DataFrame()

pandas/tests/frame/test_constructors.py

@@ -33,6 +33,7 @@
 )
 import pandas._testing as tm
 from pandas.arrays import IntervalArray, PeriodArray, SparseArray
+from pandas.core.construction import array as pd_array
 
 MIXED_FLOAT_DTYPES = ["float16", "float32", "float64"]
 MIXED_INT_DTYPES = [
@@ -753,7 +754,7 @@ def test_constructor_extension_scalar_data(self, data, dtype):
         assert df["a"].dtype == dtype
         assert df["b"].dtype == dtype
 
-        arr = pd.array([data] * 2, dtype=dtype)
+        arr = pd_array([data] * 2, dtype=dtype)
         expected = DataFrame({"a": arr, "b": arr})
 
         tm.assert_frame_equal(df, expected)
@@ -2179,7 +2180,7 @@ class DatetimeSubclass(datetime):
 
     def test_with_mismatched_index_length_raises(self):
         # GH#33437
-        dti = pd.date_range("2016-01-01", periods=3, tz="US/Pacific")
+        dti = date_range("2016-01-01", periods=3, tz="US/Pacific")
         with pytest.raises(ValueError, match="Shape of passed values"):
             DataFrame(dti, index=range(4))
 

pandas/tests/frame/test_query_eval.py

@@ -713,7 +713,7 @@ def test_inf(self):
     def test_check_tz_aware_index_query(self, tz_aware_fixture):
         # https://github.com/pandas-dev/pandas/issues/29463
         tz = tz_aware_fixture
-        df_index = pd.date_range(
+        df_index = date_range(
             start="2019-01-01", freq="1d", periods=10, tz=tz, name="time"
         )
         expected = DataFrame(index=df_index)