Skip to content

Pivot nans fix #28540

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

Closed
wants to merge 7 commits into from
Closed

Pivot nans fix #28540

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
79a08d7
Merge pull request #1 from pandas-dev/master
endremborza Sep 19, 2019
114e2d0
keep nan cols test
endremborza Sep 19, 2019
b9c237a
add keep nan cols functionality
endremborza Sep 19, 2019
07b3df7
black formatting
endremborza Sep 19, 2019
39a6427
extend pivot nancol test
endremborza Sep 20, 2019
8c5fd32
restructure keep nan cols in tests
endremborza Sep 20, 2019
2bfdf2b
restructure keep nan cols implementation
endremborza Sep 20, 2019
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
2 changes: 1 addition & 1 deletion pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5980,7 +5980,7 @@ def pivot_table(
margins=False,
dropna=True,
margins_name="All",
observed=False,
observed=True,
):
from pandas.core.reshape.pivot import pivot_table

Expand Down
13 changes: 5 additions & 8 deletions pandas/core/reshape/pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ def pivot_table(
margins=False,
dropna=True,
margins_name="All",
observed=False,
observed=True,
):
index = _convert_by(index)
columns = _convert_by(columns)
Expand Down Expand Up @@ -92,11 +92,12 @@ def pivot_table(
pass
values = list(values)

grouped = data.groupby(keys, observed=observed)
if dropna:
grouped = data.groupby(keys, observed=observed)
else:
grouped = data.groupby(keys, observed=False)
agged = grouped.agg(aggfunc)
if dropna and isinstance(agged, ABCDataFrame) and len(agged.columns):
agged = agged.dropna(how="all")

# gh-21133
# we want to down cast if
# the original values are ints
Expand Down Expand Up @@ -172,10 +173,6 @@ def pivot_table(
if len(index) == 0 and len(columns) > 0:
table = table.T

# GH 15193 Make sure empty columns are removed if dropna=True
if isinstance(table, ABCDataFrame) and dropna:
table = table.dropna(how="all", axis=1)

return table


Expand Down
53 changes: 53 additions & 0 deletions pandas/tests/reshape/test_pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,6 +185,59 @@ def test_pivot_table_dropna(self):
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)

def test_pivot_table_keep_nancols(self): # GH18030
df = pd.DataFrame(
{
"metric_value": [10, 11, 0, 3, np.nan, np.nan, 100, 20],
"metric_name": ["m", "n", "m", "x", "n", "x", "m", "n"],
"product": ["A", "A", "B", "B", "C", "C", "D", "D"],
"measurer": ["Tom", "Tom", "Bill", "Tom", "Bill", "Tom", "Bill", "Tom"],
}
)
pv_col = df.pivot_table(
"metric_value",
"metric_name",
["measurer", "product"],
dropna=True,
)
pv_ind = df.pivot_table(
"metric_value",
["measurer", "product"],
"metric_name",
dropna=True,
)

m = MultiIndex.from_tuples(
[
("Bill", "B"),
("Bill", "C"),
("Bill", "D"),
("Tom", "A"),
("Tom", "B"),
("Tom", "C"),
("Tom", "D"),
],
names=["measurer", "product"],
)
tm.assert_index_equal(pv_col.columns, m)
Copy link
Member

Choose a reason for hiding this comment

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

Can you construct the expected output and use tm.assert_frame_equal(result, expected instead? You should see that in a lot of other tests

Copy link
Contributor Author

Choose a reason for hiding this comment

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

did one way

tm.assert_index_equal(pv_ind.index, m)

expected_pv_col = pd.DataFrame(
{
("Bill", "B"): {"m": 0.0, "n": np.nan, "x": np.nan},
("Bill", "C"): {"m": np.nan, "n": np.nan, "x": np.nan},
("Bill", "D"): {"m": 100.0, "n": np.nan, "x": np.nan},
("Tom", "A"): {"m": 10.0, "n": 11.0, "x": np.nan},
("Tom", "B"): {"m": np.nan, "n": np.nan, "x": 3.0},
("Tom", "C"): {"m": np.nan, "n": np.nan, "x": np.nan},
("Tom", "D"): {"m": np.nan, "n": 20.0, "x": np.nan},
}
)
expected_pv_col.index.name = "metric_name"
expected_pv_col.columns.names = ["measurer", "product"]

tm.assert_frame_equal(pv_col, expected_pv_col)

def test_pivot_table_categorical(self):

cat1 = Categorical(
Expand Down