Skip to content

CLN: Clean groupby/test_function.py #32027

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 17 commits into from
Feb 20, 2020
Merged

CLN: Clean groupby/test_function.py #32027

Changes from 9 commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
803a166
CLN: Clean test_function.py
Feb 15, 2020
5f56e75
Move into params
Feb 15, 2020
cc6b42c
Merge branch 'master' into clean-test
Feb 15, 2020
507bad8
Merge branch 'master' into clean-test
Feb 15, 2020
761c7e6
Break into two tests
Feb 15, 2020
bac1eb5
Remove some more loops
Feb 16, 2020
23ad133
Break into own test, parametrize
Feb 16, 2020
7b2cfcb
Revert "Break into own test, parametrize"
Feb 16, 2020
e8b37c1
Revert "Remove some more loops"
Feb 16, 2020
fd84996
Call functions directly
Feb 16, 2020
c3bc093
Make fixture and split out more tests
Feb 16, 2020
6a01a6d
Fix
Feb 16, 2020
4e02e07
Update fixture
Feb 16, 2020
20c1aa7
Merge branch 'master' into clean-test
Feb 16, 2020
a00df9a
xfail not strict
Feb 17, 2020
7cf1ae7
Update fixture
Feb 17, 2020
b923f5e
Merge branch 'master' into clean-test
Feb 17, 2020
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
166 changes: 97 additions & 69 deletions pandas/tests/groupby/test_function.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,13 +223,13 @@ def test_arg_passthru():
tm.assert_index_equal(result.columns, expected_columns)

expected_columns = Index(["int", "float", "string", "category_int", "timedelta"])
for attr in ["sum"]:
f = getattr(df.groupby("group"), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)

result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
f = getattr(df.groupby("group"), "sum")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just call this directly
df.groupby('group').sum()

result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)

result = f(numeric_only=False)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done, I think it's a bit easier to read / understand if we just call these functions directly instead of assigning to f then calling, so changed that as well

tm.assert_index_equal(result.columns, expected_columns)

expected_columns = Index(["int", "float", "category_int"])
for attr in ["prod", "cumprod"]:
Expand All @@ -254,13 +254,13 @@ def test_arg_passthru():
tm.assert_index_equal(result.columns, expected_columns)

expected_columns = Index(["int", "float", "category_int", "timedelta"])
for attr in ["cumsum"]:
f = getattr(df.groupby("group"), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)

result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
f = getattr(df.groupby("group"), "cumsum")
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)

result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)


def test_non_cython_api():
Expand Down Expand Up @@ -686,62 +686,40 @@ def test_numpy_compat(func):
getattr(g, func)(foo=1)


@pytest.mark.parametrize(
"dtype, min_val, max_val",
[
(np.int32, np.iinfo(np.int32).min, np.iinfo(np.int32).max),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

min_val, max_val can all be computed inside the function

(np.int64, np.iinfo(np.int64).min, np.iinfo(np.int64).max),
(np.float32, np.finfo(np.float32).min, np.finfo(np.float32).max),
(np.float64, np.finfo(np.float64).min, np.finfo(np.float64).max),
],
)
@pytest.mark.xfail(
_is_numpy_dev, reason="https://github.com/pandas-dev/pandas/issues/31992"
)
def test_cummin_cummax():
def test_cummin(dtype, min_val, max_val):
# GH 15048
num_types = [np.int32, np.int64, np.float32, np.float64]
num_mins = [
np.iinfo(np.int32).min,
np.iinfo(np.int64).min,
np.finfo(np.float32).min,
np.finfo(np.float64).min,
]
num_max = [
np.iinfo(np.int32).max,
np.iinfo(np.int64).max,
np.finfo(np.float32).max,
np.finfo(np.float64).max,
]
base_df = pd.DataFrame(
{"A": [1, 1, 1, 1, 2, 2, 2, 2], "B": [3, 4, 3, 2, 2, 3, 2, 1]}
)
expected_mins = [3, 3, 3, 2, 2, 2, 2, 1]
expected_maxs = [3, 4, 4, 4, 2, 3, 3, 3]

for dtype, min_val, max_val in zip(num_types, num_mins, num_max):
df = base_df.astype(dtype)

# cummin
expected = pd.DataFrame({"B": expected_mins}).astype(dtype)
result = df.groupby("A").cummin()
tm.assert_frame_equal(result, expected)
result = df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(result, expected)

# Test cummin w/ min value for dtype
df.loc[[2, 6], "B"] = min_val
expected.loc[[2, 3, 6, 7], "B"] = min_val
result = df.groupby("A").cummin()
tm.assert_frame_equal(result, expected)
expected = df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(result, expected)
df = base_df.astype(dtype)

# cummax
expected = pd.DataFrame({"B": expected_maxs}).astype(dtype)
result = df.groupby("A").cummax()
tm.assert_frame_equal(result, expected)
result = df.groupby("A").B.apply(lambda x: x.cummax()).to_frame()
tm.assert_frame_equal(result, expected)
expected = pd.DataFrame({"B": expected_mins}).astype(dtype)
result = df.groupby("A").cummin()
tm.assert_frame_equal(result, expected)
result = df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(result, expected)

# Test cummax w/ max value for dtype
df.loc[[2, 6], "B"] = max_val
expected.loc[[2, 3, 6, 7], "B"] = max_val
result = df.groupby("A").cummax()
tm.assert_frame_equal(result, expected)
expected = df.groupby("A").B.apply(lambda x: x.cummax()).to_frame()
tm.assert_frame_equal(result, expected)
# Test w/ min value for dtype
df.loc[[2, 6], "B"] = min_val
expected.loc[[2, 3, 6, 7], "B"] = min_val
result = df.groupby("A").cummin()
tm.assert_frame_equal(result, expected)
expected = df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(result, expected)

# Test nan in some values
base_df.loc[[0, 2, 4, 6], "B"] = np.nan
Expand All @@ -751,6 +729,65 @@ def test_cummin_cummax():
expected = base_df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(result, expected)

# Test nan in entire column
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you split to another test rather than make this test very long

base_df["B"] = np.nan
expected = pd.DataFrame({"B": [np.nan] * 8})
result = base_df.groupby("A").cummin()
tm.assert_frame_equal(expected, result)
result = base_df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(expected, result)

# GH 15561
df = pd.DataFrame(dict(a=[1], b=pd.to_datetime(["2001"])))
expected = pd.Series(pd.to_datetime("2001"), index=[0], name="b")

result = df.groupby("a")["b"].cummin()
tm.assert_series_equal(expected, result)

# GH 15635
df = pd.DataFrame(dict(a=[1, 2, 1], b=[1, 2, 2]))
result = df.groupby("a").b.cummin()
expected = pd.Series([1, 2, 1], name="b")
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

simply make this a fixture at the top of the file rather than repeating

"dtype, min_val, max_val",
[
(np.int32, np.iinfo(np.int32).min, np.iinfo(np.int32).max),
(np.int64, np.iinfo(np.int64).min, np.iinfo(np.int64).max),
(np.float32, np.finfo(np.float32).min, np.finfo(np.float32).max),
(np.float64, np.finfo(np.float64).min, np.finfo(np.float64).max),
],
)
@pytest.mark.xfail(
_is_numpy_dev, reason="https://github.com/pandas-dev/pandas/issues/31992"
)
def test_cummax(dtype, min_val, max_val):
# GH 15048
base_df = pd.DataFrame(
{"A": [1, 1, 1, 1, 2, 2, 2, 2], "B": [3, 4, 3, 2, 2, 3, 2, 1]}
)
expected_maxs = [3, 4, 4, 4, 2, 3, 3, 3]

df = base_df.astype(dtype)

expected = pd.DataFrame({"B": expected_maxs}).astype(dtype)
result = df.groupby("A").cummax()
tm.assert_frame_equal(result, expected)
result = df.groupby("A").B.apply(lambda x: x.cummax()).to_frame()
tm.assert_frame_equal(result, expected)

# Test w/ max value for dtype
df.loc[[2, 6], "B"] = max_val
expected.loc[[2, 3, 6, 7], "B"] = max_val
result = df.groupby("A").cummax()
tm.assert_frame_equal(result, expected)
expected = df.groupby("A").B.apply(lambda x: x.cummax()).to_frame()
tm.assert_frame_equal(result, expected)

# Test nan in some values
base_df.loc[[0, 2, 4, 6], "B"] = np.nan
expected = pd.DataFrame({"B": [np.nan, 4, np.nan, 4, np.nan, 3, np.nan, 3]})
result = base_df.groupby("A").cummax()
tm.assert_frame_equal(result, expected)
Expand All @@ -760,10 +797,6 @@ def test_cummin_cummax():
# Test nan in entire column
base_df["B"] = np.nan
expected = pd.DataFrame({"B": [np.nan] * 8})
result = base_df.groupby("A").cummin()
tm.assert_frame_equal(expected, result)
result = base_df.groupby("A").B.apply(lambda x: x.cummin()).to_frame()
tm.assert_frame_equal(expected, result)
result = base_df.groupby("A").cummax()
tm.assert_frame_equal(expected, result)
result = base_df.groupby("A").B.apply(lambda x: x.cummax()).to_frame()
Expand All @@ -772,21 +805,16 @@ def test_cummin_cummax():
# GH 15561
df = pd.DataFrame(dict(a=[1], b=pd.to_datetime(["2001"])))
expected = pd.Series(pd.to_datetime("2001"), index=[0], name="b")
for method in ["cummax", "cummin"]:
result = getattr(df.groupby("a")["b"], method)()
tm.assert_series_equal(expected, result)

result = df.groupby("a")["b"].cummax()
tm.assert_series_equal(expected, result)

# GH 15635
df = pd.DataFrame(dict(a=[1, 2, 1], b=[2, 1, 1]))
result = df.groupby("a").b.cummax()
expected = pd.Series([2, 1, 2], name="b")
tm.assert_series_equal(result, expected)

df = pd.DataFrame(dict(a=[1, 2, 1], b=[1, 2, 2]))
result = df.groupby("a").b.cummin()
expected = pd.Series([1, 2, 1], name="b")
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize(
"in_vals, out_vals",
Expand Down