Skip to content

Commit

Permalink
STYLE: Inconsistent namespace - reshape (#39992) (#40058)
Browse files Browse the repository at this point in the history 
Co-authored-by: Marco Gorelli <marcogorelli@protonmail.com>
  • Loading branch information
@alexprincel @MarcoGorelli
alexprincel and MarcoGorelli authored Feb 28, 2021
1 parent 4c5e6fa commit f4b67b5
Show file tree
Hide file tree
Showing 13 changed files with 245 additions and 260 deletions.
32 changes: 16 additions & 16 deletions pandas/tests/reshape/concat/test_concat.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -437,42 +437,42 @@ def __getitem__(self, index):
except KeyError as err:
raise IndexError from err

tm.assert_frame_equal(pd.concat(CustomIterator1(), ignore_index=True), expected)
tm.assert_frame_equal(concat(CustomIterator1(), ignore_index=True), expected)

class CustomIterator2(abc.Iterable):
def __iter__(self):
yield df1
yield df2

tm.assert_frame_equal(pd.concat(CustomIterator2(), ignore_index=True), expected)
tm.assert_frame_equal(concat(CustomIterator2(), ignore_index=True), expected)

def test_concat_order(self):
# GH 17344
dfs = [DataFrame(index=range(3), columns=["a", 1, None])]
dfs += [DataFrame(index=range(3), columns=[None, 1, "a"]) for i in range(100)]

result = pd.concat(dfs, sort=True).columns
result = concat(dfs, sort=True).columns
expected = dfs[0].columns
tm.assert_index_equal(result, expected)

def test_concat_different_extension_dtypes_upcasts(self):
a = Series(pd.array([1, 2], dtype="Int64"))
b = Series(to_decimal([1, 2]))

result = pd.concat([a, b], ignore_index=True)
result = concat([a, b], ignore_index=True)
expected = Series([1, 2, Decimal(1), Decimal(2)], dtype=object)
tm.assert_series_equal(result, expected)

def test_concat_ordered_dict(self):
# GH 21510
expected = pd.concat(
expected = concat(
[Series(range(3)), Series(range(4))], keys=["First", "Another"]
)
result = pd.concat({"First": Series(range(3)), "Another": Series(range(4))})
result = concat({"First": Series(range(3)), "Another": Series(range(4))})
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize("pdt", [Series, pd.DataFrame])
@pytest.mark.parametrize("pdt", [Series, DataFrame])
@pytest.mark.parametrize("dt", np.sctypes["float"])
def test_concat_no_unnecessary_upcast(dt, pdt):
# GH 13247
Expand All @@ -483,11 +483,11 @@ def test_concat_no_unnecessary_upcast(dt, pdt):
pdt(np.array([np.nan], dtype=dt, ndmin=dims)),
pdt(np.array([5], dtype=dt, ndmin=dims)),
]
x = pd.concat(dfs)
x = concat(dfs)
assert x.values.dtype == dt


@pytest.mark.parametrize("pdt", [create_series_with_explicit_dtype, pd.DataFrame])
@pytest.mark.parametrize("pdt", [create_series_with_explicit_dtype, DataFrame])
@pytest.mark.parametrize("dt", np.sctypes["int"])
def test_concat_will_upcast(dt, pdt):
with catch_warnings(record=True):
Expand All @@ -497,7 +497,7 @@ def test_concat_will_upcast(dt, pdt):
pdt(np.array([np.nan], ndmin=dims)),
pdt(np.array([5], dtype=dt, ndmin=dims)),
]
x = pd.concat(dfs)
x = concat(dfs)
assert x.values.dtype == "float64"


Expand All @@ -506,7 +506,7 @@ def test_concat_empty_and_non_empty_frame_regression():
df1 = DataFrame({"foo": [1]})
df2 = DataFrame({"foo": []})
expected = DataFrame({"foo": [1.0]})
result = pd.concat([df1, df2])
result = concat([df1, df2])
tm.assert_frame_equal(result, expected)


Expand All @@ -516,7 +516,7 @@ def test_concat_sparse():
expected = DataFrame(data=[[0, 0], [1, 1], [2, 2]]).astype(
pd.SparseDtype(np.int64, 0)
)
result = pd.concat([a, a], axis=1)
result = concat([a, a], axis=1)
tm.assert_frame_equal(result, expected)


Expand All @@ -527,7 +527,7 @@ def test_concat_dense_sparse():
expected = Series(data=[1, None, 1], index=[0, 1, 0]).astype(
pd.SparseDtype(np.float64, None)
)
result = pd.concat([a, b], axis=0)
result = concat([a, b], axis=0)
tm.assert_series_equal(result, expected)


Expand Down Expand Up @@ -565,11 +565,11 @@ def test_concat_frame_axis0_extension_dtypes():
df1 = DataFrame({"a": pd.array([1, 2, 3], dtype="Int64")})
df2 = DataFrame({"a": np.array([4, 5, 6])})

result = pd.concat([df1, df2], ignore_index=True)
result = concat([df1, df2], ignore_index=True)
expected = DataFrame({"a": [1, 2, 3, 4, 5, 6]}, dtype="Int64")
tm.assert_frame_equal(result, expected)

result = pd.concat([df2, df1], ignore_index=True)
result = concat([df2, df1], ignore_index=True)
expected = DataFrame({"a": [4, 5, 6, 1, 2, 3]}, dtype="Int64")
tm.assert_frame_equal(result, expected)

Expand All @@ -578,7 +578,7 @@ def test_concat_preserves_extension_int64_dtype():
# GH 24768
df_a = DataFrame({"a": [-1]}, dtype="Int64")
df_b = DataFrame({"b": [1]}, dtype="Int64")
result = pd.concat([df_a, df_b], ignore_index=True)
result = concat([df_a, df_b], ignore_index=True)
expected = DataFrame({"a": [-1, None], "b": [None, 1]}, dtype="Int64")
tm.assert_frame_equal(result, expected)

Expand Down
38 changes: 18 additions & 20 deletions pandas/tests/reshape/concat/test_dataframe.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ def test_concat_multiple_frames_dtypes(self):
# GH#2759
A = DataFrame(data=np.ones((10, 2)), columns=["foo", "bar"], dtype=np.float64)
B = DataFrame(data=np.ones((10, 2)), dtype=np.float32)
results = pd.concat((A, B), axis=1).dtypes
results = concat((A, B), axis=1).dtypes
expected = Series(
[np.dtype("float64")] * 2 + [np.dtype("float32")] * 2,
index=["foo", "bar", 0, 1],
Expand All @@ -28,7 +28,7 @@ def test_concat_tuple_keys(self):
# GH#14438
df1 = DataFrame(np.ones((2, 2)), columns=list("AB"))
df2 = DataFrame(np.ones((3, 2)) * 2, columns=list("AB"))
results = pd.concat((df1, df2), keys=[("bee", "bah"), ("bee", "boo")])
results = concat((df1, df2), keys=[("bee", "bah"), ("bee", "boo")])
expected = DataFrame(
{
"A": {
Expand All @@ -53,20 +53,18 @@ def test_concat_named_keys(self):
# GH#14252
df = DataFrame({"foo": [1, 2], "bar": [0.1, 0.2]})
index = Index(["a", "b"], name="baz")
concatted_named_from_keys = pd.concat([df, df], keys=index)
concatted_named_from_keys = concat([df, df], keys=index)
expected_named = DataFrame(
{"foo": [1, 2, 1, 2], "bar": [0.1, 0.2, 0.1, 0.2]},
index=pd.MultiIndex.from_product((["a", "b"], [0, 1]), names=["baz", None]),
)
tm.assert_frame_equal(concatted_named_from_keys, expected_named)

index_no_name = Index(["a", "b"], name=None)
concatted_named_from_names = pd.concat(
[df, df], keys=index_no_name, names=["baz"]
)
concatted_named_from_names = concat([df, df], keys=index_no_name, names=["baz"])
tm.assert_frame_equal(concatted_named_from_names, expected_named)

concatted_unnamed = pd.concat([df, df], keys=index_no_name)
concatted_unnamed = concat([df, df], keys=index_no_name)
expected_unnamed = DataFrame(
{"foo": [1, 2, 1, 2], "bar": [0.1, 0.2, 0.1, 0.2]},
index=pd.MultiIndex.from_product((["a", "b"], [0, 1]), names=[None, None]),
Expand All @@ -81,24 +79,24 @@ def test_concat_axis_parameter(self):
# Index/row/0 DataFrame
expected_index = DataFrame({"A": [0.1, 0.2, 0.3, 0.4]}, index=[0, 1, 0, 1])

concatted_index = pd.concat([df1, df2], axis="index")
concatted_index = concat([df1, df2], axis="index")
tm.assert_frame_equal(concatted_index, expected_index)

concatted_row = pd.concat([df1, df2], axis="rows")
concatted_row = concat([df1, df2], axis="rows")
tm.assert_frame_equal(concatted_row, expected_index)

concatted_0 = pd.concat([df1, df2], axis=0)
concatted_0 = concat([df1, df2], axis=0)
tm.assert_frame_equal(concatted_0, expected_index)

# Columns/1 DataFrame
expected_columns = DataFrame(
[[0.1, 0.3], [0.2, 0.4]], index=[0, 1], columns=["A", "A"]
)

concatted_columns = pd.concat([df1, df2], axis="columns")
concatted_columns = concat([df1, df2], axis="columns")
tm.assert_frame_equal(concatted_columns, expected_columns)

concatted_1 = pd.concat([df1, df2], axis=1)
concatted_1 = concat([df1, df2], axis=1)
tm.assert_frame_equal(concatted_1, expected_columns)

series1 = Series([0.1, 0.2])
Expand All @@ -107,29 +105,29 @@ def test_concat_axis_parameter(self):
# Index/row/0 Series
expected_index_series = Series([0.1, 0.2, 0.3, 0.4], index=[0, 1, 0, 1])

concatted_index_series = pd.concat([series1, series2], axis="index")
concatted_index_series = concat([series1, series2], axis="index")
tm.assert_series_equal(concatted_index_series, expected_index_series)

concatted_row_series = pd.concat([series1, series2], axis="rows")
concatted_row_series = concat([series1, series2], axis="rows")
tm.assert_series_equal(concatted_row_series, expected_index_series)

concatted_0_series = pd.concat([series1, series2], axis=0)
concatted_0_series = concat([series1, series2], axis=0)
tm.assert_series_equal(concatted_0_series, expected_index_series)

# Columns/1 Series
expected_columns_series = DataFrame(
[[0.1, 0.3], [0.2, 0.4]], index=[0, 1], columns=[0, 1]
)

concatted_columns_series = pd.concat([series1, series2], axis="columns")
concatted_columns_series = concat([series1, series2], axis="columns")
tm.assert_frame_equal(concatted_columns_series, expected_columns_series)

concatted_1_series = pd.concat([series1, series2], axis=1)
concatted_1_series = concat([series1, series2], axis=1)
tm.assert_frame_equal(concatted_1_series, expected_columns_series)

# Testing ValueError
with pytest.raises(ValueError, match="No axis named"):
pd.concat([series1, series2], axis="something")
concat([series1, series2], axis="something")

def test_concat_numerical_names(self):
# GH#15262, GH#12223
Expand All @@ -142,7 +140,7 @@ def test_concat_numerical_names(self):
)
),
)
result = pd.concat((df.iloc[:2, :], df.iloc[-2:, :]))
result = concat((df.iloc[:2, :], df.iloc[-2:, :]))
expected = DataFrame(
{"col": [0, 1, 7, 8]},
dtype="int32",
Expand All @@ -155,7 +153,7 @@ def test_concat_numerical_names(self):
def test_concat_astype_dup_col(self):
# GH#23049
df = DataFrame([{"a": "b"}])
df = pd.concat([df, df], axis=1)
df = concat([df, df], axis=1)

result = df.astype("category")
expected = DataFrame(
Expand Down
Loading

0 comments on commit f4b67b5

Please sign in to comment.