Updated script to check inconsistent pandas namespace (#37848)

Author: mohdkashif93

pandas/tests/arithmetic/conftest.py

@@ -81,7 +81,7 @@ def zero(request):
 
     Examples
     --------
-    >>> arr = pd.RangeIndex(5)
+    >>> arr = RangeIndex(5)
     >>> arr / zeros
     Float64Index([nan, inf, inf, inf, inf], dtype='float64')
     """

pandas/tests/arithmetic/test_timedelta64.py

@@ -465,7 +465,7 @@ def test_addition_ops(self):
             tdi + pd.Int64Index([1, 2, 3])
 
         # this is a union!
-        # pytest.raises(TypeError, lambda : Int64Index([1,2,3]) + tdi)
+        # pytest.raises(TypeError, lambda : pd.Int64Index([1,2,3]) + tdi)
 
         result = tdi + dti  # name will be reset
         expected = DatetimeIndex(["20130102", pd.NaT, "20130105"])

pandas/tests/arrays/categorical/test_constructors.py

@@ -677,7 +677,7 @@ def test_interval(self):
         tm.assert_index_equal(cat.categories, idx)
 
         # overlapping
-        idx = pd.IntervalIndex([pd.Interval(0, 2), pd.Interval(0, 1)])
+        idx = IntervalIndex([Interval(0, 2), Interval(0, 1)])
         cat = Categorical(idx, categories=idx)
         expected_codes = np.array([0, 1], dtype="int8")
         tm.assert_numpy_array_equal(cat.codes, expected_codes)

pandas/tests/frame/test_constructors.py

@@ -720,8 +720,8 @@ def test_constructor_period_dict(self):
     @pytest.mark.parametrize(
         "data,dtype",
         [
-            (pd.Period("2012-01", freq="M"), "period[M]"),
-            (pd.Period("2012-02-01", freq="D"), "period[D]"),
+            (Period("2012-01", freq="M"), "period[M]"),
+            (Period("2012-02-01", freq="D"), "period[D]"),
             (Interval(left=0, right=5), IntervalDtype("int64")),
             (Interval(left=0.1, right=0.5), IntervalDtype("float64")),
         ],
@@ -2577,7 +2577,7 @@ def test_from_records_series_list_dict(self):
     def test_from_records_series_categorical_index(self):
         # GH 32805
         index = CategoricalIndex(
-            [pd.Interval(-20, -10), pd.Interval(-10, 0), pd.Interval(0, 10)]
+            [Interval(-20, -10), Interval(-10, 0), Interval(0, 10)]
         )
         series_of_dicts = Series([{"a": 1}, {"a": 2}, {"b": 3}], index=index)
         frame = DataFrame.from_records(series_of_dicts, index=index)
@@ -2628,7 +2628,7 @@ class List(list):
         [
             Categorical(list("aabbc")),
             SparseArray([1, np.nan, np.nan, np.nan]),
-            IntervalArray([pd.Interval(0, 1), pd.Interval(1, 5)]),
+            IntervalArray([Interval(0, 1), Interval(1, 5)]),
             PeriodArray(pd.period_range(start="1/1/2017", end="1/1/2018", freq="M")),
         ],
     )
@@ -2648,12 +2648,10 @@ def test_datetime_date_tuple_columns_from_dict(self):
 
     def test_construct_with_two_categoricalindex_series(self):
         # GH 14600
-        s1 = Series(
-            [39, 6, 4], index=pd.CategoricalIndex(["female", "male", "unknown"])
-        )
+        s1 = Series([39, 6, 4], index=CategoricalIndex(["female", "male", "unknown"]))
         s2 = Series(
             [2, 152, 2, 242, 150],
-            index=pd.CategoricalIndex(["f", "female", "m", "male", "unknown"]),
+            index=CategoricalIndex(["f", "female", "m", "male", "unknown"]),
         )
         result = DataFrame([s1, s2])
         expected = DataFrame(
@@ -2717,7 +2715,7 @@ def test_dataframe_constructor_infer_multiindex(self):
             (["1", "2"]),
             (list(date_range("1/1/2011", periods=2, freq="H"))),
             (list(date_range("1/1/2011", periods=2, freq="H", tz="US/Eastern"))),
-            ([pd.Interval(left=0, right=5)]),
+            ([Interval(left=0, right=5)]),
         ],
     )
     def test_constructor_list_str(self, input_vals, string_dtype):

pandas/tests/indexes/interval/test_interval.py

@@ -228,7 +228,7 @@ def test_is_unique_interval(self, closed):
         assert idx.is_unique is True
 
         # unique overlapping - shared endpoints
-        idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
+        idx = IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
         assert idx.is_unique is True
 
         # unique nested
@@ -279,14 +279,14 @@ def test_monotonic(self, closed):
         assert idx._is_strictly_monotonic_decreasing is False
 
         # increasing overlapping shared endpoints
-        idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
+        idx = IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
         assert idx.is_monotonic is True
         assert idx._is_strictly_monotonic_increasing is True
         assert idx.is_monotonic_decreasing is False
         assert idx._is_strictly_monotonic_decreasing is False
 
         # decreasing overlapping shared endpoints
-        idx = pd.IntervalIndex.from_tuples([(2, 3), (1, 3), (1, 2)], closed=closed)
+        idx = IntervalIndex.from_tuples([(2, 3), (1, 3), (1, 2)], closed=closed)
         assert idx.is_monotonic is False
         assert idx._is_strictly_monotonic_increasing is False
         assert idx.is_monotonic_decreasing is True
@@ -872,7 +872,7 @@ def test_is_all_dates(self):
         year_2017 = Interval(
             Timestamp("2017-01-01 00:00:00"), Timestamp("2018-01-01 00:00:00")
         )
-        year_2017_index = pd.IntervalIndex([year_2017])
+        year_2017_index = IntervalIndex([year_2017])
         assert not year_2017_index._is_all_dates
 
     @pytest.mark.parametrize("key", [[5], (2, 3)])

pandas/tests/indexes/test_numeric.py

@@ -522,7 +522,7 @@ def test_constructor_coercion_signed_to_unsigned(self, uint_dtype):
 
     def test_constructor_unwraps_index(self):
         idx = Index([1, 2])
-        result = pd.Int64Index(idx)
+        result = Int64Index(idx)
         expected = np.array([1, 2], dtype="int64")
         tm.assert_numpy_array_equal(result._data, expected)
 
@@ -614,8 +614,8 @@ def test_int_float_union_dtype(dtype):
     # https://github.com/pandas-dev/pandas/issues/26778
     # [u]int | float -> float
     index = Index([0, 2, 3], dtype=dtype)
-    other = pd.Float64Index([0.5, 1.5])
-    expected = pd.Float64Index([0.0, 0.5, 1.5, 2.0, 3.0])
+    other = Float64Index([0.5, 1.5])
+    expected = Float64Index([0.0, 0.5, 1.5, 2.0, 3.0])
     result = index.union(other)
     tm.assert_index_equal(result, expected)
 
@@ -626,9 +626,9 @@ def test_int_float_union_dtype(dtype):
 def test_range_float_union_dtype():
     # https://github.com/pandas-dev/pandas/issues/26778
     index = pd.RangeIndex(start=0, stop=3)
-    other = pd.Float64Index([0.5, 1.5])
+    other = Float64Index([0.5, 1.5])
     result = index.union(other)
-    expected = pd.Float64Index([0.0, 0.5, 1, 1.5, 2.0])
+    expected = Float64Index([0.0, 0.5, 1, 1.5, 2.0])
     tm.assert_index_equal(result, expected)
 
     result = other.union(index)

pandas/tests/series/test_constructors.py

@@ -1040,7 +1040,7 @@ def test_construction_consistency(self):
         "data_constructor", [list, np.array], ids=["list", "ndarray[object]"]
     )
     def test_constructor_infer_period(self, data_constructor):
-        data = [pd.Period("2000", "D"), pd.Period("2001", "D"), None]
+        data = [Period("2000", "D"), Period("2001", "D"), None]
         result = Series(data_constructor(data))
         expected = Series(period_array(data))
         tm.assert_series_equal(result, expected)
@@ -1057,7 +1057,7 @@ def test_construct_from_ints_including_iNaT_scalar_period_dtype(self):
         assert isna(series[2])
 
     def test_constructor_period_incompatible_frequency(self):
-        data = [pd.Period("2000", "D"), pd.Period("2001", "A")]
+        data = [Period("2000", "D"), Period("2001", "A")]
         result = Series(data)
         assert result.dtype == object
         assert result.tolist() == data
@@ -1539,7 +1539,7 @@ def test_constructor_list_of_periods_infers_period_dtype(self):
         assert series.dtype == "Period[D]"
 
         series = Series(
-            [pd.Period("2011-01-01", freq="D"), pd.Period("2011-02-01", freq="D")]
+            [Period("2011-01-01", freq="D"), Period("2011-02-01", freq="D")]
         )
         assert series.dtype == "Period[D]"
 

scripts/check_for_inconsistent_pandas_namespace.py

@@ -16,29 +16,18 @@
 
 PATTERN = r"""
     (
-        (?<!pd\.)(?<!\w)    # check class_name start with pd. or character
-        {class_name}\(      # match DataFrame but not pd.DataFrame or tm.makeDataFrame
+        (?<!pd\.)(?<!\w)    # check class_name doesn't start with pd. or character
+        ([A-Z]\w+)\(        # match DataFrame but not pd.DataFrame or tm.makeDataFrame
         .*                  # match anything
-        pd\.{class_name}\(  # only match e.g. pd.DataFrame
+        pd\.\2\(            # only match e.g. pd.DataFrame
     )|
     (
-        pd\.{class_name}\(  # only match e.g. pd.DataFrame
+        pd\.([A-Z]\w+)\(    # only match e.g. pd.DataFrame
         .*                  # match anything
-        (?<!pd\.)(?<!\w)    # check class_name start with pd. or character
-        {class_name}\(      # match DataFrame but not pd.DataFrame or tm.makeDataFrame
+        (?<!pd\.)(?<!\w)    # check class_name doesn't start with pd. or character
+        \4\(                # match DataFrame but not pd.DataFrame or tm.makeDataFrame
     )
     """
-CLASS_NAMES = (
-    "Series",
-    "DataFrame",
-    "Index",
-    "MultiIndex",
-    "Timestamp",
-    "Timedelta",
-    "TimedeltaIndex",
-    "DatetimeIndex",
-    "Categorical",
-)
 ERROR_MESSAGE = "Found both `pd.{class_name}` and `{class_name}` in {path}"
 
 
@@ -47,16 +36,22 @@ def main(argv: Optional[Sequence[str]] = None) -> None:
     parser.add_argument("paths", nargs="*", type=Path)
     args = parser.parse_args(argv)
 
-    for class_name in CLASS_NAMES:
-        pattern = re.compile(
-            PATTERN.format(class_name=class_name).encode(),
-            flags=re.MULTILINE | re.DOTALL | re.VERBOSE,
-        )
-        for path in args.paths:
-            contents = path.read_bytes()
-            match = pattern.search(contents)
-            assert match is None, ERROR_MESSAGE.format(
-                class_name=class_name, path=str(path)
+    pattern = re.compile(
+        PATTERN.encode(),
+        flags=re.MULTILINE | re.DOTALL | re.VERBOSE,
+    )
+    for path in args.paths:
+        contents = path.read_bytes()
+        match = pattern.search(contents)
+        if match is None:
+            continue
+        if match.group(2) is not None:
+            raise AssertionError(
+                ERROR_MESSAGE.format(class_name=match.group(2).decode(), path=str(path))
+            )
+        if match.group(4) is not None:
+            raise AssertionError(
+                ERROR_MESSAGE.format(class_name=match.group(4).decode(), path=str(path))
             )