Skip to content

Bug: Made it so that 0 was included in uint8 #14412

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

Bug: Made it so that 0 was included in uint8 #14412

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
3d2ce5b
Made it so that 0 was included in uint8
Oct 12, 2016
81b4965
Added a test to check uint8 with 0
Oct 12, 2016
b6331a5
Added release note to issue 14401 resolve.
Oct 13, 2016
8a836b2
Edited mistakes in whatsnew
Oct 13, 2016
3427e4f
Added tests for the max and min values of all dtypes to to_numeric
Oct 14, 2016
0da1918
Changed the tests so that it iterated through a dictionary.
Oct 15, 2016
c6be0eb
Changed the test to work with python 3.x
Oct 17, 2016
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
3 changes: 3 additions & 0 deletions doc/source/whatsnew/v0.19.1.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,3 +48,6 @@ Bug Fixes
- Bug in ``MultiIndex.set_levels`` where illegal level values were still set after raising an error (:issue:`13754`)
- Bug in ``DataFrame.to_json`` where ``lines=True`` and a value contained a ``}`` character (:issue:`14391`)
- Bug in ``df.groupby`` causing an ``AttributeError`` when grouping a single index frame by a column and the index level (:issue`14327`)
- Bug in ``pd.to_numeric`` where it would not downcast a 0 to a uint8 (:issue:`14404`)
Copy link
Contributor

Choose a reason for hiding this comment

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

just make a single entry

- Bug in ``pd.to_numeric`` where it would not downcast a 0 properly. (:issue:`14401`)
- Bug in ``pd.to_numeric`` where a 0 was not unsigned on a downcast = 'unsigned' argument (:issue:`14401`)
56 changes: 56 additions & 0 deletions pandas/tools/tests/test_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -401,6 +401,62 @@ def test_downcast(self):
res = pd.to_numeric(data, downcast=downcast)
tm.assert_numpy_array_equal(res, expected)

# check that the smallest and largest values in each integer type pass to each type.
Copy link
Contributor

Choose a reason for hiding this comment

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

this is still overly verbose. do something like.

checks = [('int8', 'integer', [np.iinfo(np.int8).min, np.iinfo(np.int8).max]), 
                  .....
               ]

for dtype, downcast, min_max in checks:
     ....

integer_dtype_min_max = {
'int8': [np.iinfo(np.int8).min, np.iinfo(np.int8).max],
'int16': [np.iinfo(np.int16).min, np.iinfo(np.int16).max],
'int32': [np.iinfo(np.int32).min, np.iinfo(np.int32).max],
'int64': [np.iinfo(np.int64).min, np.iinfo(np.int64).max]
}

for dtype, min_max in integer_dtype_min_max.items():
series = pd.to_numeric(pd.Series(min_max), downcast = 'integer')
tm.assert_equal(series.dtype, dtype)


unsigned_dtype_min_max = {
'uint8': [np.iinfo(np.uint8).min, np.iinfo(np.uint8).max],
'uint16': [np.iinfo(np.uint16).min, np.iinfo(np.uint16).max],
'uint32': [np.iinfo(np.uint32).min, np.iinfo(np.uint32).max],
# 'uint64': [np.iinfo(np.uint64).min, np.iinfo(np.uint64).max]
}

for dtype, min_max in unsigned_dtype_min_max.items():
series = pd.to_numeric(pd.Series(min_max), downcast = 'unsigned')
tm.assert_equal(series.dtype, dtype)

#check to see if the minimum number to shift integer types actually shifts

integer_dtype_min_max_plus = {
'int16': [np.iinfo(np.int8).min, np.iinfo(np.int8).max + 1],
'int32': [np.iinfo(np.int16).min, np.iinfo(np.int16).max + 1],
'int64': [np.iinfo(np.int32).min, np.iinfo(np.int32).max + 1],
}

for dtype, min_max in integer_dtype_min_max_plus.items():
series = pd.to_numeric(pd.Series(min_max), downcast = 'integer')
tm.assert_equal(series.dtype, dtype)

integer_dtype_min_max_minus = {
'int16': [np.iinfo(np.int8).min - 1, np.iinfo(np.int16).max],
'int32': [np.iinfo(np.int16).min - 1, np.iinfo(np.int32).max],
'int64': [np.iinfo(np.int32).min - 1, np.iinfo(np.int64).max]
}

for dtype, min_max in integer_dtype_min_max_minus.items():
series = pd.to_numeric(pd.Series(min_max), downcast = 'integer')
tm.assert_equal(series.dtype, dtype)

unsigned_dtype_min_max_plus = {
'uint16': [np.iinfo(np.uint8).min, np.iinfo(np.uint8).max + 1],
'uint32': [np.iinfo(np.uint16).min, np.iinfo(np.uint16).max + 1],
# 'uint64': [np.iinfo(np.uint32).min, np.iinfo(np.uint32).max + 1],
}

for dtype, min_max in unsigned_dtype_min_max_plus.items():
series = pd.to_numeric(pd.Series(min_max), downcast = 'unsigned')
tm.assert_equal(series.dtype, dtype)

if __name__ == '__main__':
nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
exit=False)
2 changes: 1 addition & 1 deletion pandas/tools/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,7 +205,7 @@ def to_numeric(arg, errors='raise', downcast=None):

if downcast in ('integer', 'signed'):
typecodes = np.typecodes['Integer']
elif downcast == 'unsigned' and np.min(values) > 0:
elif downcast == 'unsigned' and np.min(values) >= 0:
typecodes = np.typecodes['UnsignedInteger']
elif downcast == 'float':
typecodes = np.typecodes['Float']
Expand Down