Skip to content
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

BUG: No error raised in to_stata() for -np.inf #45350 #45360

Merged
merged 3 commits into from
Jan 16, 2022
Merged

BUG: No error raised in to_stata() for -np.inf #45350 #45360

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
c52c237
BUG: No error raised in to_stata() for -np.inf #45350
flcong Jan 14, 2022
ada0664
BUG: Update #45350
flcong Jan 14, 2022
3f195ea
BUG: Update #45350
flcong Jan 14, 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
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v1.5.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ MultiIndex

I/O
^^^
-
- Bug in :meth:`DataFrame.to_stata` where no error is raised if the :class:`DataFrame` contains ``-np.inf`` (:issue:`45350`)
-

Period
Expand Down
8 changes: 4 additions & 4 deletions pandas/io/stata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -625,12 +625,12 @@ def _cast_to_stata_types(data: DataFrame) -> DataFrame:
if data[col].max() >= 2 ** 53 or data[col].min() <= -(2 ** 53):
ws = precision_loss_doc.format("int64", "float64")
elif dtype in (np.float32, np.float64):
value = data[col].max()
if np.isinf(value):
if np.isinf(data[col]).any():
raise ValueError(
f"Column {col} has a maximum value of infinity which is outside "
"the range supported by Stata."
f"Column {col} contains infinity or -infinity"
"which is outside the range supported by Stata."
)
value = data[col].max()
if dtype == np.float32 and value > float32_max:
data[col] = data[col].astype(np.float64)
elif dtype == np.float64:
Expand Down
20 changes: 7 additions & 13 deletions pandas/tests/io/test_stata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1473,15 +1473,6 @@ def test_out_of_range_double(self):
with tm.ensure_clean() as path:
df.to_stata(path)

df.loc[2, "ColumnTooBig"] = np.inf
msg = (
"Column ColumnTooBig has a maximum value of infinity which is outside "
"the range supported by Stata"
)
with pytest.raises(ValueError, match=msg):
with tm.ensure_clean() as path:
df.to_stata(path)

def test_out_of_range_float(self):
original = DataFrame(
{
Expand All @@ -1507,14 +1498,17 @@ def test_out_of_range_float(self):
original["ColumnTooBig"] = original["ColumnTooBig"].astype(np.float64)
tm.assert_frame_equal(original, reread.set_index("index"))

original.loc[2, "ColumnTooBig"] = np.inf
@pytest.mark.parametrize("infval", [np.inf, -np.inf])
def test_inf(self, infval):
# GH 45350
df = DataFrame({"WithoutInf": [0.0, 1.0], "WithInf": [2.0, infval]})
msg = (
"Column ColumnTooBig has a maximum value of infinity which "
"is outside the range supported by Stata"
"Column WithInf contains infinity or -infinity"
"which is outside the range supported by Stata."
)
with pytest.raises(ValueError, match=msg):
with tm.ensure_clean() as path:
original.to_stata(path)
df.to_stata(path)

def test_path_pathlib(self):
df = tm.makeDataFrame()
Expand Down