Skip to content

CLN: Simplify groupby head/tail tests #37702

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 9, 2020
Merged

CLN: Simplify groupby head/tail tests #37702

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
69 changes: 23 additions & 46 deletions pandas/tests/groupby/test_nth.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,53 +487,30 @@ def test_nth_multi_index_as_expected():
tm.assert_frame_equal(result, expected)


def test_groupby_head_tail():
@pytest.mark.parametrize(
"op, n, expected_rows",
[
("head", -1, []),
("head", 0, []),
("head", 1, [0, 2]),
("head", 7, [0, 1, 2]),
("tail", -1, []),
("tail", 0, []),
("tail", 1, [1, 2]),
("tail", 7, [0, 1, 2]),
],
)
@pytest.mark.parametrize("columns", [None, [], ["A"], ["B"], ["A", "B"]])
@pytest.mark.parametrize("as_index", [True, False])
def test_groupby_head_tail(op, n, expected_rows, columns, as_index):
df = DataFrame([[1, 2], [1, 4], [5, 6]], columns=["A", "B"])
g_as = df.groupby("A", as_index=True)
g_not_as = df.groupby("A", as_index=False)

# as_index= False, much easier
tm.assert_frame_equal(df.loc[[0, 2]], g_not_as.head(1))
tm.assert_frame_equal(df.loc[[1, 2]], g_not_as.tail(1))

empty_not_as = DataFrame(columns=df.columns, index=Index([], dtype=df.index.dtype))
empty_not_as["A"] = empty_not_as["A"].astype(df.A.dtype)
empty_not_as["B"] = empty_not_as["B"].astype(df.B.dtype)
tm.assert_frame_equal(empty_not_as, g_not_as.head(0))
tm.assert_frame_equal(empty_not_as, g_not_as.tail(0))
tm.assert_frame_equal(empty_not_as, g_not_as.head(-1))
tm.assert_frame_equal(empty_not_as, g_not_as.tail(-1))

tm.assert_frame_equal(df, g_not_as.head(7)) # contains all
tm.assert_frame_equal(df, g_not_as.tail(7))

# as_index=True, (used to be different)
df_as = df

tm.assert_frame_equal(df_as.loc[[0, 2]], g_as.head(1))
tm.assert_frame_equal(df_as.loc[[1, 2]], g_as.tail(1))

empty_as = DataFrame(index=df_as.index[:0], columns=df.columns)
empty_as["A"] = empty_not_as["A"].astype(df.A.dtype)
empty_as["B"] = empty_not_as["B"].astype(df.B.dtype)
tm.assert_frame_equal(empty_as, g_as.head(0))
tm.assert_frame_equal(empty_as, g_as.tail(0))
tm.assert_frame_equal(empty_as, g_as.head(-1))
tm.assert_frame_equal(empty_as, g_as.tail(-1))

tm.assert_frame_equal(df_as, g_as.head(7)) # contains all
tm.assert_frame_equal(df_as, g_as.tail(7))

# test with selection
tm.assert_frame_equal(g_as[[]].head(1), df_as.loc[[0, 2], []])
tm.assert_frame_equal(g_as[["A"]].head(1), df_as.loc[[0, 2], ["A"]])
tm.assert_frame_equal(g_as[["B"]].head(1), df_as.loc[[0, 2], ["B"]])
tm.assert_frame_equal(g_as[["A", "B"]].head(1), df_as.loc[[0, 2]])

tm.assert_frame_equal(g_not_as[[]].head(1), df_as.loc[[0, 2], []])
tm.assert_frame_equal(g_not_as[["A"]].head(1), df_as.loc[[0, 2], ["A"]])
tm.assert_frame_equal(g_not_as[["B"]].head(1), df_as.loc[[0, 2], ["B"]])
tm.assert_frame_equal(g_not_as[["A", "B"]].head(1), df_as.loc[[0, 2]])
g = df.groupby("A", as_index=as_index)
expected = df.iloc[expected_rows]
if columns is not None:
g = g[columns]
expected = expected[columns]
result = getattr(g, op)(n)
tm.assert_frame_equal(result, expected)


def test_group_selection_cache():
Expand Down