Skip to content

Rewrite dict literal for files in tests/groupby & ./pandas/tests/dtypes #38205

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
Dec 2, 2020
Merged

Rewrite dict literal for files in tests/groupby & ./pandas/tests/dtypes #38205

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2d2ca13
change dict to literal
Qbiwan Dec 1, 2020
ed4b574
pep8 line 1031 test_transform
Qbiwan Dec 1, 2020
201e46e
change dict to literal
Qbiwan Dec 1, 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
4 changes: 2 additions & 2 deletions pandas/tests/dtypes/test_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ def coerce(request):
((1,), True, "tuple"),
(tuple(), True, "tuple-empty"),
({"a": 1}, True, "dict"),
(dict(), True, "dict-empty"),
({}, True, "dict-empty"),
({"a", 1}, "set", "set"),
(set(), "set", "set-empty"),
(frozenset({"a", 1}), "set", "frozenset"),
Expand Down Expand Up @@ -1489,7 +1489,7 @@ def test_datetimeindex_from_empty_datetime64_array():
def test_nan_to_nat_conversions():

df = DataFrame(
dict({"A": np.asarray(range(10), dtype="float64"), "B": Timestamp("20010101")})
{"A": np.asarray(range(10), dtype="float64"), "B": Timestamp("20010101")}
)
df.iloc[3:6, :] = np.nan
result = df.loc[4, "B"]
Expand Down
8 changes: 4 additions & 4 deletions pandas/tests/groupby/test_function.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -692,14 +692,14 @@ def test_cummin(numpy_dtypes_for_minmax):
tm.assert_frame_equal(result, expected)

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

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

# GH 15635
df = DataFrame(dict(a=[1, 2, 1], b=[1, 2, 2]))
df = DataFrame({"a": [1, 2, 1], "b": [1, 2, 2]})
result = df.groupby("a").b.cummin()
expected = Series([1, 2, 1], name="b")
tm.assert_series_equal(result, expected)
Expand Down Expand Up @@ -748,14 +748,14 @@ def test_cummax(numpy_dtypes_for_minmax):
tm.assert_frame_equal(result, expected)

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

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

# GH 15635
df = DataFrame(dict(a=[1, 2, 1], b=[2, 1, 1]))
df = DataFrame({"a": [1, 2, 1], "b": [2, 1, 1]})
result = df.groupby("a").b.cummax()
expected = Series([2, 1, 2], name="b")
tm.assert_series_equal(result, expected)
Expand Down
54 changes: 31 additions & 23 deletions pandas/tests/groupby/transform/test_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,7 @@ def test_transform_dtype():
def test_transform_bug():
# GH 5712
# transforming on a datetime column
df = DataFrame(dict(A=Timestamp("20130101"), B=np.arange(5)))
df = DataFrame({"A": Timestamp("20130101"), "B": np.arange(5)})
result = df.groupby("A")["B"].transform(lambda x: x.rank(ascending=False))
expected = Series(np.arange(5, 0, step=-1), name="B")
tm.assert_series_equal(result, expected)
Expand All @@ -251,7 +251,7 @@ def test_transform_numeric_to_boolean():
def test_transform_datetime_to_timedelta():
# GH 15429
# transforming a datetime to timedelta
df = DataFrame(dict(A=Timestamp("20130101"), B=np.arange(5)))
df = DataFrame({"A": Timestamp("20130101"), "B": np.arange(5)})
expected = Series([Timestamp("20130101") - Timestamp("20130101")] * 5, name="A")

# this does date math without changing result type in transform
Expand Down Expand Up @@ -442,7 +442,7 @@ def test_transform_coercion():
# 14457
# when we are transforming be sure to not coerce
# via assignment
df = DataFrame(dict(A=["a", "a"], B=[0, 1]))
df = DataFrame({"A": ["a", "a"], "B": [0, 1]})
g = df.groupby("A")

expected = g.transform(np.mean)
Expand All @@ -456,43 +456,50 @@ def test_groupby_transform_with_int():

# floats
df = DataFrame(
dict(
A=[1, 1, 1, 2, 2, 2],
B=Series(1, dtype="float64"),
C=Series([1, 2, 3, 1, 2, 3], dtype="float64"),
D="foo",
)
{
"A": [1, 1, 1, 2, 2, 2],
"B": Series(1, dtype="float64"),
"C": Series([1, 2, 3, 1, 2, 3], dtype="float64"),
"D": "foo",
}
)
with np.errstate(all="ignore"):
result = df.groupby("A").transform(lambda x: (x - x.mean()) / x.std())
expected = DataFrame(
dict(B=np.nan, C=Series([-1, 0, 1, -1, 0, 1], dtype="float64"))
{"B": np.nan, "C": Series([-1, 0, 1, -1, 0, 1], dtype="float64")}
)
tm.assert_frame_equal(result, expected)

# int case
df = DataFrame(dict(A=[1, 1, 1, 2, 2, 2], B=1, C=[1, 2, 3, 1, 2, 3], D="foo"))
df = DataFrame(
{
"A": [1, 1, 1, 2, 2, 2],
"B": 1,
"C": [1, 2, 3, 1, 2, 3],
"D": "foo",
}
)
with np.errstate(all="ignore"):
result = df.groupby("A").transform(lambda x: (x - x.mean()) / x.std())
expected = DataFrame(dict(B=np.nan, C=[-1, 0, 1, -1, 0, 1]))
expected = DataFrame({"B": np.nan, "C": [-1, 0, 1, -1, 0, 1]})
tm.assert_frame_equal(result, expected)

# int that needs float conversion
s = Series([2, 3, 4, 10, 5, -1])
df = DataFrame(dict(A=[1, 1, 1, 2, 2, 2], B=1, C=s, D="foo"))
df = DataFrame({"A": [1, 1, 1, 2, 2, 2], "B": 1, "C": s, "D": "foo"})
with np.errstate(all="ignore"):
result = df.groupby("A").transform(lambda x: (x - x.mean()) / x.std())

s1 = s.iloc[0:3]
s1 = (s1 - s1.mean()) / s1.std()
s2 = s.iloc[3:6]
s2 = (s2 - s2.mean()) / s2.std()
expected = DataFrame(dict(B=np.nan, C=concat([s1, s2])))
expected = DataFrame({"B": np.nan, "C": concat([s1, s2])})
tm.assert_frame_equal(result, expected)

# int downcasting
result = df.groupby("A").transform(lambda x: x * 2 / 2)
expected = DataFrame(dict(B=1, C=[2, 3, 4, 10, 5, -1]))
expected = DataFrame({"B": 1, "C": [2, 3, 4, 10, 5, -1]})
tm.assert_frame_equal(result, expected)


Expand Down Expand Up @@ -659,11 +666,11 @@ def test_cython_transform_frame(op, args, targop):
# group by values, index level, columns
for df in [df, df2]:
for gb_target in [
dict(by=labels),
dict(level=0),
dict(by="string"),
]: # dict(by='string_missing')]:
# dict(by=['int','string'])]:
{"by": labels},
{"level": 0},
{"by": "string"},
]: # {"by": 'string_missing'}]:
# {"by": ['int','string']}]:

gb = df.groupby(**gb_target)
# allowlisted methods set the selection before applying
Expand Down Expand Up @@ -986,7 +993,7 @@ def test_transform_absent_categories(func):
x_vals = [1]
x_cats = range(2)
y = [1]
df = DataFrame(dict(x=Categorical(x_vals, x_cats), y=y))
df = DataFrame({"x": Categorical(x_vals, x_cats), "y": y})
result = getattr(df.y.groupby(df.x), func)()
expected = df.y
tm.assert_series_equal(result, expected)
Expand All @@ -1005,7 +1012,7 @@ def test_ffill_not_in_axis(func, key, val):

def test_transform_invalid_name_raises():
# GH#27486
df = DataFrame(dict(a=[0, 1, 1, 2]))
df = DataFrame({"a": [0, 1, 1, 2]})
g = df.groupby(["a", "b", "b", "c"])
with pytest.raises(ValueError, match="not a valid function name"):
g.transform("some_arbitrary_name")
Expand All @@ -1025,7 +1032,8 @@ def test_transform_invalid_name_raises():
"obj",
[
DataFrame(
dict(a=[0, 0, 0, 1, 1, 1], b=range(6)), index=["A", "B", "C", "D", "E", "F"]
{"a": [0, 0, 0, 1, 1, 1], "b": range(6)},
index=["A", "B", "C", "D", "E", "F"],
),
Series([0, 0, 0, 1, 1, 1], index=["A", "B", "C", "D", "E", "F"]),
],
Expand Down