Skip to content

Fix: Reanme duplicate function names in unittests #48906

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 3 commits into from
Oct 3, 2022
Merged

Fix: Reanme duplicate function names in unittests #48906

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
03224e4
Fix: Reanme duplicate function names in unittests
FloHofstetter Oct 1, 2022
92e952a
Fix: Reanme duplicate function names in unittests
FloHofstetter Oct 1, 2022
6011b11
Fix: Reanme duplicate function names in unittests
FloHofstetter Oct 2, 2022
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
8 changes: 4 additions & 4 deletions pandas/tests/groupby/aggregate/test_aggregate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,8 +281,8 @@ def test_groupby_mixed_cols_axis1(func, expected_data, result_dtype_dict):
def test_aggregate_item_by_item(df):
grouped = df.groupby("A")

aggfun = lambda ser: ser.size
result = grouped.agg(aggfun)
aggfun_0 = lambda ser: ser.size
result = grouped.agg(aggfun_0)
foo = (df.A == "foo").sum()
bar = (df.A == "bar").sum()
K = len(result.columns)
Expand All @@ -294,10 +294,10 @@ def test_aggregate_item_by_item(df):
exp = Series(np.array([bar] * K), index=list("BCD"), name="bar")
tm.assert_almost_equal(result.xs("bar"), exp)

def aggfun(ser):
def aggfun_1(ser):
return ser.size

result = DataFrame().groupby(df.A).agg(aggfun)
result = DataFrame().groupby(df.A).agg(aggfun_1)
assert isinstance(result, DataFrame)
assert len(result) == 0

Expand Down
30 changes: 14 additions & 16 deletions pandas/tests/groupby/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,10 @@ def max_value(group):
def test_groupby_return_type():

# GH2893, return a reduced type

def func(dataf):
return dataf["val2"] - dataf["val2"].mean()

df1 = DataFrame(
[
{"val1": 1, "val2": 20},
Expand All @@ -121,9 +125,6 @@ def test_groupby_return_type():
]
)

def func(dataf):
return dataf["val2"] - dataf["val2"].mean()

with tm.assert_produces_warning(FutureWarning):
result = df1.groupby("val1", squeeze=True).apply(func)
assert isinstance(result, Series)
Expand All @@ -137,9 +138,6 @@ def func(dataf):
]
)

def func(dataf):
return dataf["val2"] - dataf["val2"].mean()

with tm.assert_produces_warning(FutureWarning):
result = df2.groupby("val1", squeeze=True).apply(func)
assert isinstance(result, Series)
Expand All @@ -162,51 +160,51 @@ def test_inconsistent_return_type():
}
)

def f(grp):
def f_0(grp):
return grp.iloc[0]

expected = df.groupby("A").first()[["B"]]
result = df.groupby("A").apply(f)[["B"]]
result = df.groupby("A").apply(f_0)[["B"]]
tm.assert_frame_equal(result, expected)

def f(grp):
def f_1(grp):
if grp.name == "Tiger":
return None
return grp.iloc[0]

result = df.groupby("A").apply(f)[["B"]]
result = df.groupby("A").apply(f_1)[["B"]]
e = expected.copy()
e.loc["Tiger"] = np.nan
tm.assert_frame_equal(result, e)

def f(grp):
def f_2(grp):
if grp.name == "Pony":
return None
return grp.iloc[0]

result = df.groupby("A").apply(f)[["B"]]
result = df.groupby("A").apply(f_2)[["B"]]
e = expected.copy()
e.loc["Pony"] = np.nan
tm.assert_frame_equal(result, e)

# 5592 revisited, with datetimes
def f(grp):
def f_3(grp):
if grp.name == "Pony":
return None
return grp.iloc[0]

result = df.groupby("A").apply(f)[["C"]]
result = df.groupby("A").apply(f_3)[["C"]]
e = df.groupby("A").first()[["C"]]
e.loc["Pony"] = pd.NaT
tm.assert_frame_equal(result, e)

# scalar outputs
def f(grp):
def f_4(grp):
if grp.name == "Pony":
return None
return grp.iloc[0].loc["C"]

result = df.groupby("A").apply(f)
result = df.groupby("A").apply(f_4)
e = df.groupby("A").first()["C"].copy()
e.loc["Pony"] = np.nan
e.name = None
Expand Down
18 changes: 9 additions & 9 deletions pandas/tests/io/pytables/test_append.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -361,7 +361,7 @@ def test_append_with_strings(setup_path):
with ensure_clean_store(setup_path) as store:
with catch_warnings(record=True):

def check_col(key, name, size):
def check_col_0(key, name, size):
assert (
getattr(store.get_storer(key).table.description, name).itemsize
== size
Expand All @@ -371,20 +371,20 @@ def check_col(key, name, size):
df = DataFrame([[123, "asdqwerty"], [345, "dggnhebbsdfbdfb"]])
store.append("df_big", df)
tm.assert_frame_equal(store.select("df_big"), df)
check_col("df_big", "values_block_1", 15)
check_col_0("df_big", "values_block_1", 15)

# appending smaller string ok
df2 = DataFrame([[124, "asdqy"], [346, "dggnhefbdfb"]])
store.append("df_big", df2)
expected = concat([df, df2])
tm.assert_frame_equal(store.select("df_big"), expected)
check_col("df_big", "values_block_1", 15)
check_col_0("df_big", "values_block_1", 15)

# avoid truncation on elements
df = DataFrame([[123, "asdqwerty"], [345, "dggnhebbsdfbdfb"]])
store.append("df_big2", df, min_itemsize={"values": 50})
tm.assert_frame_equal(store.select("df_big2"), df)
check_col("df_big2", "values_block_1", 50)
check_col_0("df_big2", "values_block_1", 50)

# bigger string on next append
store.append("df_new", df)
Expand Down Expand Up @@ -437,28 +437,28 @@ def check_col(key, name, size):

with ensure_clean_store(setup_path) as store:

def check_col(key, name, size):
def check_col_1(key, name, size):
assert getattr(store.get_storer(key).table.description, name).itemsize, size
Copy link
Member

Choose a reason for hiding this comment

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

Thanks for doing this @FloHofstetter !

🤔 what an odd function...I wonder if it was meant to be

            assert getattr(store.get_storer(key).table.description, name).itemsize == size

I'll look through the history to see if there's any clues

Copy link
Member

Choose a reason for hiding this comment

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

Indeed 😄

https://github.com/pandas-dev/pandas/pull/16169/files

             def check_col(key, name, size):
-                self.assertEqual(getattr(store.get_storer(
-                    key).table.description, name).itemsize, size)
+                assert getattr(store.get_storer(key)
+                               .table.description, name).itemsize, size

cc @gfyoung this is typo right? Just double-checking, in case you remember

Looks like this should be the same as check_col_0 above, can we just keep that one as check_col and remove this one @FloHofstetter ?

Copy link
Member

Choose a reason for hiding this comment

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

Yep, that indeed looks like a typo @MarcoGorelli


df = DataFrame({"A": "foo", "B": "bar"}, index=range(10))

# a min_itemsize that creates a data_column
_maybe_remove(store, "df")
store.append("df", df, min_itemsize={"A": 200})
check_col("df", "A", 200)
check_col_1("df", "A", 200)
assert store.get_storer("df").data_columns == ["A"]

# a min_itemsize that creates a data_column2
_maybe_remove(store, "df")
store.append("df", df, data_columns=["B"], min_itemsize={"A": 200})
check_col("df", "A", 200)
check_col_1("df", "A", 200)
assert store.get_storer("df").data_columns == ["B", "A"]

# a min_itemsize that creates a data_column2
_maybe_remove(store, "df")
store.append("df", df, data_columns=["B"], min_itemsize={"values": 200})
check_col("df", "B", 200)
check_col("df", "values_block_0", 200)
check_col_1("df", "B", 200)
check_col_1("df", "values_block_0", 200)
assert store.get_storer("df").data_columns == ["B"]

# infer the .typ on subsequent appends
Expand Down
16 changes: 8 additions & 8 deletions pandas/tests/resample/test_resampler_grouper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,10 +65,10 @@ def test_deferred_with_groupby():
df = DataFrame(data, columns=["date", "id", "score"])
df.date = pd.to_datetime(df.date)

def f(x):
def f_0(x):
return x.set_index("date").resample("D").asfreq()

expected = df.groupby("id").apply(f)
expected = df.groupby("id").apply(f_0)
result = df.set_index("date").groupby("id").resample("D").asfreq()
tm.assert_frame_equal(result, expected)

Expand All @@ -80,10 +80,10 @@ def f(x):
}
).set_index("date")

def f(x):
def f_1(x):
return x.resample("1D").ffill()

expected = df.groupby("group").apply(f)
expected = df.groupby("group").apply(f_1)
result = df.groupby("group").resample("1D").ffill()
tm.assert_frame_equal(result, expected)

Expand Down Expand Up @@ -257,16 +257,16 @@ def test_apply():
# reduction
expected = g.resample("2s").sum()

def f(x):
def f_0(x):
return x.resample("2s").sum()

result = r.apply(f)
result = r.apply(f_0)
tm.assert_frame_equal(result, expected)

def f(x):
def f_1(x):
return x.resample("2s").apply(lambda y: y.sum())

result = g.apply(f)
result = g.apply(f_1)
# y.sum() results in int64 instead of int32 on 32-bit architectures
expected = expected.astype("int64")
tm.assert_frame_equal(result, expected)
Expand Down
8 changes: 4 additions & 4 deletions pandas/tests/window/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1064,10 +1064,10 @@ def test_expanding_corr_cov(self, f):

result = getattr(r, f)(self.frame)

def func(x):
def func_0(x):
return getattr(x.expanding(), f)(self.frame)

expected = g.apply(func)
expected = g.apply(func_0)
# GH 39591: groupby.apply returns 1 instead of nan for windows
# with all nan values
null_idx = list(range(20, 61)) + list(range(72, 113))
Expand All @@ -1079,10 +1079,10 @@ def func(x):

result = getattr(r.B, f)(pairwise=True)

def func(x):
def func_1(x):
return getattr(x.B.expanding(), f)(pairwise=True)

expected = g.apply(func)
expected = g.apply(func_1)
tm.assert_series_equal(result, expected)

def test_expanding_apply(self, raw):
Expand Down
1 change: 0 additions & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@ disable = [
"access-member-before-definition",
"bad-super-call",
"c-extension-no-member",
"function-redefined",
"import-error",
"inherit-non-class",
"invalid-repr-returned",
Expand Down