Skip to content

BUG: add names parameter to read_excel #12895

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 3 commits into from
Closed

BUG: add names parameter to read_excel #12895

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
273c42f
add names parameter to read_excel
OXPHOS Apr 13, 2016
95e5272
update test cases
OXPHOS Apr 14, 2016
7e60733
remove tests
OXPHOS Apr 14, 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
1 change: 1 addition & 0 deletions doc/source/whatsnew/v0.18.1.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,3 +319,4 @@ Bug Fixes
- Bug in ``.describe()`` resets categorical columns information (:issue:`11558`)
- Bug where ``loffset`` argument was not applied when calling ``resample().count()`` on a timeseries (:issue:`12725`)
- ``pd.read_excel()`` now accepts path objects (e.g. ``pathlib.Path``, ``py.path.local``) for the file path, in line with other ``read_*`` functions (:issue:`12655`)
- ``pd.read_excel()`` now accepts column names associated with keyword argument ``names``(:issue `12870`)
16 changes: 9 additions & 7 deletions pandas/io/excel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,7 @@ def read_excel(io, sheetname=0, header=0, skiprows=None, skip_footer=0,
io = ExcelFile(io, engine=engine)

return io._parse_excel(
sheetname=sheetname, header=header, skiprows=skiprows,
sheetname=sheetname, header=header, skiprows=skiprows, names=names,
index_col=index_col, parse_cols=parse_cols, parse_dates=parse_dates,
date_parser=date_parser, na_values=na_values, thousands=thousands,
convert_float=convert_float, has_index_names=has_index_names,
Expand Down Expand Up @@ -230,7 +230,7 @@ def __init__(self, io, **kwds):
' buffer or path for io.')

def parse(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
index_col=None, parse_cols=None, parse_dates=False,
names=None, index_col=None, parse_cols=None, parse_dates=False,
date_parser=None, na_values=None, thousands=None,
convert_float=True, has_index_names=None,
converters=None, squeeze=False, **kwds):
Expand All @@ -242,7 +242,7 @@ def parse(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
"""

return self._parse_excel(sheetname=sheetname, header=header,
skiprows=skiprows,
skiprows=skiprows, names=names,
index_col=index_col,
has_index_names=has_index_names,
parse_cols=parse_cols,
Expand Down Expand Up @@ -288,10 +288,10 @@ def _excel2num(x):
else:
return i in parse_cols

def _parse_excel(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
index_col=None, has_index_names=None, parse_cols=None,
parse_dates=False, date_parser=None, na_values=None,
thousands=None, convert_float=True,
def _parse_excel(self, sheetname=0, header=0, skiprows=None, names=None,
skip_footer=0, index_col=None, has_index_names=None,
parse_cols=None, parse_dates=False, date_parser=None,
na_values=None, thousands=None, convert_float=True,
verbose=False, squeeze=False, **kwds):

skipfooter = kwds.pop('skipfooter', None)
Expand Down Expand Up @@ -465,6 +465,8 @@ def _parse_cell(cell_contents, cell_typ):
**kwds)

output[asheetname] = parser.read()
if names is not None:
output[asheetname].columns = names
if not squeeze or isinstance(output[asheetname], DataFrame):
output[asheetname].columns = output[
asheetname].columns.set_names(header_names)
Expand Down
22 changes: 22 additions & 0 deletions pandas/io/tests/test_excel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,6 +455,28 @@ def test_read_one_empty_col_with_header(self):
expected_header_zero = DataFrame(columns=[0], dtype='int64')
tm.assert_frame_equal(actual_header_zero, expected_header_zero)

# GH 12870 : pass down column names associated with keyword argument names
def test_set_column_names_in_parameter(self):
refdf = pd.DataFrame([[1, 'foo'], [2, 'bar'],
[3, 'baz']], columns=['a', 'b'])

Copy link
Contributor

Choose a reason for hiding this comment

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

I don't think its necessary to include the files, instead I'd like to test with a dataframe that you write out, these cases:

  • write with no header, read back with the specified names (like you are testing here)
  • write with a header, and use names (I think we replace with the names at this point)

with ensure_clean(self.ext) as pth:
with ExcelWriter(pth) as writer:
refdf.to_excel(writer, 'Data_no_head',
header=False, index=False)
refdf.to_excel(writer, 'Data_with_head', index=False)

refdf.columns = ['A', 'B']

with ExcelFile(pth) as reader:
xlsdf_no_head = read_excel(reader, 'Data_no_head',
header=None, names=['A', 'B'])
xlsdf_with_head = read_excel(reader, 'Data_with_head',
index_col=None, names=['A', 'B'])

tm.assert_frame_equal(xlsdf_no_head, refdf)
tm.assert_frame_equal(xlsdf_with_head, refdf)


class XlrdTests(ReadingTestsBase):
"""
Expand Down