TST: collect .insert tests (#32909)

Author: jbrockmendel

pandas/tests/frame/indexing/test_insert.py

@@ -0,0 +1,68 @@
+"""
+test_insert is specifically for the DataFrame.insert method; not to be
+confused with tests with "insert" in their names that are really testing
+__setitem__.
+"""
+import numpy as np
+import pytest
+
+from pandas import DataFrame, Index
+import pandas._testing as tm
+
+
+class TestDataFrameInsert:
+    def test_insert(self):
+        df = DataFrame(
+            np.random.randn(5, 3), index=np.arange(5), columns=["c", "b", "a"]
+        )
+
+        df.insert(0, "foo", df["a"])
+        tm.assert_index_equal(df.columns, Index(["foo", "c", "b", "a"]))
+        tm.assert_series_equal(df["a"], df["foo"], check_names=False)
+
+        df.insert(2, "bar", df["c"])
+        tm.assert_index_equal(df.columns, Index(["foo", "c", "bar", "b", "a"]))
+        tm.assert_almost_equal(df["c"], df["bar"], check_names=False)
+
+        with pytest.raises(ValueError, match="already exists"):
+            df.insert(1, "a", df["b"])
+
+        msg = "cannot insert c, already exists"
+        with pytest.raises(ValueError, match=msg):
+            df.insert(1, "c", df["b"])
+
+        df.columns.name = "some_name"
+        # preserve columns name field
+        df.insert(0, "baz", df["c"])
+        assert df.columns.name == "some_name"
+
+    def test_insert_column_bug_4032(self):
+
+        # GH#4032, inserting a column and renaming causing errors
+        df = DataFrame({"b": [1.1, 2.2]})
+
+        df = df.rename(columns={})
+        df.insert(0, "a", [1, 2])
+        result = df.rename(columns={})
+
+        str(result)
+        expected = DataFrame([[1, 1.1], [2, 2.2]], columns=["a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+        df.insert(0, "c", [1.3, 2.3])
+        result = df.rename(columns={})
+
+        str(result)
+        expected = DataFrame([[1.3, 1, 1.1], [2.3, 2, 2.2]], columns=["c", "a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+    def test_insert_with_columns_dups(self):
+        # GH#14291
+        df = DataFrame()
+        df.insert(0, "A", ["g", "h", "i"], allow_duplicates=True)
+        df.insert(0, "A", ["d", "e", "f"], allow_duplicates=True)
+        df.insert(0, "A", ["a", "b", "c"], allow_duplicates=True)
+        exp = DataFrame(
+            [["a", "d", "g"], ["b", "e", "h"], ["c", "f", "i"]], columns=["A", "A", "A"]
+        )
+        tm.assert_frame_equal(df, exp)

pandas/tests/frame/test_mutate_columns.py

@@ -3,14 +3,14 @@
 import numpy as np
 import pytest
 
-from pandas import DataFrame, Index, MultiIndex, Series
+from pandas import DataFrame, MultiIndex, Series
 import pandas._testing as tm
 
 # Column add, remove, delete.
 
 
 class TestDataFrameMutateColumns:
-    def test_insert_error_msmgs(self):
+    def test_setitem_error_msmgs(self):
 
         # GH 7432
         df = DataFrame(
@@ -30,7 +30,7 @@ def test_insert_error_msmgs(self):
         with pytest.raises(TypeError, match=msg):
             df["gr"] = df.groupby(["b", "c"]).count()
 
-    def test_insert_benchmark(self):
+    def test_setitem_benchmark(self):
         # from the vb_suite/frame_methods/frame_insert_columns
         N = 10
         K = 5
@@ -41,18 +41,12 @@ def test_insert_benchmark(self):
         expected = DataFrame(np.repeat(new_col, K).reshape(N, K), index=range(N))
         tm.assert_frame_equal(df, expected)
 
-    def test_insert(self):
+    def test_setitem_different_dtype(self):
         df = DataFrame(
             np.random.randn(5, 3), index=np.arange(5), columns=["c", "b", "a"]
         )
-
         df.insert(0, "foo", df["a"])
-        tm.assert_index_equal(df.columns, Index(["foo", "c", "b", "a"]))
-        tm.assert_series_equal(df["a"], df["foo"], check_names=False)
-
         df.insert(2, "bar", df["c"])
-        tm.assert_index_equal(df.columns, Index(["foo", "c", "bar", "b", "a"]))
-        tm.assert_almost_equal(df["c"], df["bar"], check_names=False)
 
         # diff dtype
 
@@ -82,17 +76,7 @@ def test_insert(self):
         )
         tm.assert_series_equal(result, expected)
 
-        with pytest.raises(ValueError, match="already exists"):
-            df.insert(1, "a", df["b"])
-        msg = "cannot insert c, already exists"
-        with pytest.raises(ValueError, match=msg):
-            df.insert(1, "c", df["b"])
-
-        df.columns.name = "some_name"
-        # preserve columns name field
-        df.insert(0, "baz", df["c"])
-        assert df.columns.name == "some_name"
-
+    def test_setitem_empty_columns(self):
         # GH 13522
         df = DataFrame(index=["A", "B", "C"])
         df["X"] = df.index
@@ -165,22 +149,3 @@ def test_pop_non_unique_cols(self):
         assert "b" in df.columns
         assert "a" not in df.columns
         assert len(df.index) == 2
-
-    def test_insert_column_bug_4032(self):
-
-        # GH4032, inserting a column and renaming causing errors
-        df = DataFrame({"b": [1.1, 2.2]})
-        df = df.rename(columns={})
-        df.insert(0, "a", [1, 2])
-
-        result = df.rename(columns={})
-        str(result)
-        expected = DataFrame([[1, 1.1], [2, 2.2]], columns=["a", "b"])
-        tm.assert_frame_equal(result, expected)
-        df.insert(0, "c", [1.3, 2.3])
-
-        result = df.rename(columns={})
-        str(result)
-
-        expected = DataFrame([[1.3, 1, 1.1], [2.3, 2, 2.2]], columns=["c", "a", "b"])
-        tm.assert_frame_equal(result, expected)

pandas/tests/frame/test_nonunique_indexes.py

@@ -513,14 +513,3 @@ def test_set_value_by_index(self):
 
         df.iloc[:, 0] = 3
         tm.assert_series_equal(df.iloc[:, 1], expected)
-
-    def test_insert_with_columns_dups(self):
-        # GH 14291
-        df = pd.DataFrame()
-        df.insert(0, "A", ["g", "h", "i"], allow_duplicates=True)
-        df.insert(0, "A", ["d", "e", "f"], allow_duplicates=True)
-        df.insert(0, "A", ["a", "b", "c"], allow_duplicates=True)
-        exp = pd.DataFrame(
-            [["a", "d", "g"], ["b", "e", "h"], ["c", "f", "i"]], columns=["A", "A", "A"]
-        )
-        tm.assert_frame_equal(df, exp)

pandas/tests/indexes/timedeltas/test_indexing.py

@@ -189,97 +189,6 @@ def test_take_fill_value(self):
 
 
 class TestTimedeltaIndex:
-    def test_insert_empty(self):
-        # Corner case inserting with length zero doesnt raise IndexError
-        idx = timedelta_range("1 Day", periods=3)
-        td = idx[0]
-
-        idx[:0].insert(0, td)
-        idx[:0].insert(1, td)
-        idx[:0].insert(-1, td)
-
-    def test_insert(self):
-
-        idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
-
-        result = idx.insert(2, timedelta(days=5))
-        exp = TimedeltaIndex(["4day", "1day", "5day", "2day"], name="idx")
-        tm.assert_index_equal(result, exp)
-
-        # insertion of non-datetime should coerce to object index
-        result = idx.insert(1, "inserted")
-        expected = Index(
-            [Timedelta("4day"), "inserted", Timedelta("1day"), Timedelta("2day")],
-            name="idx",
-        )
-        assert not isinstance(result, TimedeltaIndex)
-        tm.assert_index_equal(result, expected)
-        assert result.name == expected.name
-
-        idx = timedelta_range("1day 00:00:01", periods=3, freq="s", name="idx")
-
-        # preserve freq
-        expected_0 = TimedeltaIndex(
-            ["1day", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"],
-            name="idx",
-            freq="s",
-        )
-        expected_3 = TimedeltaIndex(
-            ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:04"],
-            name="idx",
-            freq="s",
-        )
-
-        # reset freq to None
-        expected_1_nofreq = TimedeltaIndex(
-            ["1day 00:00:01", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"],
-            name="idx",
-            freq=None,
-        )
-        expected_3_nofreq = TimedeltaIndex(
-            ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:05"],
-            name="idx",
-            freq=None,
-        )
-
-        cases = [
-            (0, Timedelta("1day"), expected_0),
-            (-3, Timedelta("1day"), expected_0),
-            (3, Timedelta("1day 00:00:04"), expected_3),
-            (1, Timedelta("1day 00:00:01"), expected_1_nofreq),
-            (3, Timedelta("1day 00:00:05"), expected_3_nofreq),
-        ]
-
-        for n, d, expected in cases:
-            result = idx.insert(n, d)
-            tm.assert_index_equal(result, expected)
-            assert result.name == expected.name
-            assert result.freq == expected.freq
-
-    @pytest.mark.parametrize(
-        "null", [None, np.nan, np.timedelta64("NaT"), pd.NaT, pd.NA]
-    )
-    def test_insert_nat(self, null):
-        # GH 18295 (test missing)
-        idx = timedelta_range("1day", "3day")
-        result = idx.insert(1, null)
-        expected = TimedeltaIndex(["1day", pd.NaT, "2day", "3day"])
-        tm.assert_index_equal(result, expected)
-
-    def test_insert_invalid_na(self):
-        idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
-        with pytest.raises(TypeError, match="incompatible label"):
-            idx.insert(0, np.datetime64("NaT"))
-
-    def test_insert_dont_cast_strings(self):
-        # To match DatetimeIndex and PeriodIndex behavior, dont try to
-        #  parse strings to Timedelta
-        idx = timedelta_range("1day", "3day")
-
-        result = idx.insert(0, "1 Day")
-        assert result.dtype == object
-        assert result[0] == "1 Day"
-
     def test_delete(self):
         idx = timedelta_range(start="1 Days", periods=5, freq="D", name="idx")
 

pandas/tests/indexes/timedeltas/test_insert.py

@@ -0,0 +1,101 @@
+from datetime import timedelta
+
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import Index, Timedelta, TimedeltaIndex, timedelta_range
+import pandas._testing as tm
+
+
+class TestTimedeltaIndexInsert:
+    def test_insert(self):
+
+        idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
+
+        result = idx.insert(2, timedelta(days=5))
+        exp = TimedeltaIndex(["4day", "1day", "5day", "2day"], name="idx")
+        tm.assert_index_equal(result, exp)
+
+        # insertion of non-datetime should coerce to object index
+        result = idx.insert(1, "inserted")
+        expected = Index(
+            [Timedelta("4day"), "inserted", Timedelta("1day"), Timedelta("2day")],
+            name="idx",
+        )
+        assert not isinstance(result, TimedeltaIndex)
+        tm.assert_index_equal(result, expected)
+        assert result.name == expected.name
+
+        idx = timedelta_range("1day 00:00:01", periods=3, freq="s", name="idx")
+
+        # preserve freq
+        expected_0 = TimedeltaIndex(
+            ["1day", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"],
+            name="idx",
+            freq="s",
+        )
+        expected_3 = TimedeltaIndex(
+            ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:04"],
+            name="idx",
+            freq="s",
+        )
+
+        # reset freq to None
+        expected_1_nofreq = TimedeltaIndex(
+            ["1day 00:00:01", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"],
+            name="idx",
+            freq=None,
+        )
+        expected_3_nofreq = TimedeltaIndex(
+            ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:05"],
+            name="idx",
+            freq=None,
+        )
+
+        cases = [
+            (0, Timedelta("1day"), expected_0),
+            (-3, Timedelta("1day"), expected_0),
+            (3, Timedelta("1day 00:00:04"), expected_3),
+            (1, Timedelta("1day 00:00:01"), expected_1_nofreq),
+            (3, Timedelta("1day 00:00:05"), expected_3_nofreq),
+        ]
+
+        for n, d, expected in cases:
+            result = idx.insert(n, d)
+            tm.assert_index_equal(result, expected)
+            assert result.name == expected.name
+            assert result.freq == expected.freq
+
+    @pytest.mark.parametrize(
+        "null", [None, np.nan, np.timedelta64("NaT"), pd.NaT, pd.NA]
+    )
+    def test_insert_nat(self, null):
+        # GH 18295 (test missing)
+        idx = timedelta_range("1day", "3day")
+        result = idx.insert(1, null)
+        expected = TimedeltaIndex(["1day", pd.NaT, "2day", "3day"])
+        tm.assert_index_equal(result, expected)
+
+    def test_insert_invalid_na(self):
+        idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
+        with pytest.raises(TypeError, match="incompatible label"):
+            idx.insert(0, np.datetime64("NaT"))
+
+    def test_insert_dont_cast_strings(self):
+        # To match DatetimeIndex and PeriodIndex behavior, dont try to
+        #  parse strings to Timedelta
+        idx = timedelta_range("1day", "3day")
+
+        result = idx.insert(0, "1 Day")
+        assert result.dtype == object
+        assert result[0] == "1 Day"
+
+    def test_insert_empty(self):
+        # Corner case inserting with length zero doesnt raise IndexError
+        idx = timedelta_range("1 Day", periods=3)
+        td = idx[0]
+
+        idx[:0].insert(0, td)
+        idx[:0].insert(1, td)
+        idx[:0].insert(-1, td)