Skip to content

Test Decorators and Better Pytest Integration in 'test_excel' #19829

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

Merged
merged 19 commits into from
Feb 26, 2018
Merged

Test Decorators and Better Pytest Integration in 'test_excel' #19829

Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
377edd8
Added decorator to XlrdTests
WillAyd Feb 21, 2018
c8b7f28
Replaced subclasses with parametrization
WillAyd Feb 21, 2018
44fa2f9
Moved xlrd skip to SharedItems
WillAyd Feb 21, 2018
069d700
Parametrized ExcelWriter subclasses
WillAyd Feb 21, 2018
0f64f3a
Finished up decorator cleanup for reads, linted
WillAyd Feb 21, 2018
ed761ef
Fixed issue with xlwt install
WillAyd Feb 21, 2018
2dff85d
Cleaned up all Test{} writer tests
WillAyd Feb 21, 2018
1976804
Converted Writer setup/teardown to pytest fixture
WillAyd Feb 21, 2018
d6bb4aa
Final refactor to remove _skip_if_no module funcs
WillAyd Feb 21, 2018
d885b93
LINTing
WillAyd Feb 21, 2018
a681e5e
Added wraps to compat for Py27 testing
WillAyd Feb 22, 2018
8035620
Comments for compat.wraps requirement
WillAyd Feb 23, 2018
0cfdaf7
Removed hard-coded ensure_clean
WillAyd Feb 25, 2018
96708be
Futher parametrization
WillAyd Feb 25, 2018
9b16035
Moved ensure_clean to class fixture
WillAyd Feb 25, 2018
164ee9c
Changed pytest.skip to pytest.xfail for visibility
WillAyd Feb 25, 2018
849933d
Updated docstring and name of class test fixture
WillAyd Feb 25, 2018
112dae4
Parametrized .xlsm writing tests
WillAyd Feb 26, 2018
872e7d6
Added xfail for Py2, Linux, xlsxwriter combo
WillAyd Feb 26, 2018
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
Prev Previous commit
Next Next commit
Finished up decorator cleanup for reads, linted
  • Loading branch information
@WillAyd
WillAyd committed Feb 25, 2018
commit 0f64f3a8975e4c53765e9f3c748fd121677fb880
60 changes: 29 additions & 31 deletions pandas/tests/io/test_excel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,8 +134,8 @@ def test_usecols_int(self, ext):
dfref = self.get_csv_refdf('test1')
dfref = dfref.reindex(columns=['A', 'B', 'C'])
df1 = self.get_exceldf('test1', ext, 'Sheet1', index_col=0, usecols=3)
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1], index_col=0,
usecols=3)
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
index_col=0, usecols=3)

with tm.assert_produces_warning(FutureWarning):
df3 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
Expand All @@ -152,8 +152,8 @@ def test_usecols_list(self, ext):
dfref = dfref.reindex(columns=['B', 'C'])
df1 = self.get_exceldf('test1', ext, 'Sheet1', index_col=0,
usecols=[0, 2, 3])
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1], index_col=0,
usecols=[0, 2, 3])
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
index_col=0, usecols=[0, 2, 3])

with tm.assert_produces_warning(FutureWarning):
df3 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
Expand All @@ -171,8 +171,8 @@ def test_usecols_str(self, ext):
df1 = dfref.reindex(columns=['A', 'B', 'C'])
df2 = self.get_exceldf('test1', ext, 'Sheet1', index_col=0,
usecols='A:D')
df3 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1], index_col=0,
usecols='A:D')
df3 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
index_col=0, usecols='A:D')

with tm.assert_produces_warning(FutureWarning):
df4 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
Expand Down Expand Up @@ -277,7 +277,8 @@ def test_excel_table(self, ext):
dfref = self.get_csv_refdf('test1')

df1 = self.get_exceldf('test1', ext, 'Sheet1', index_col=0)
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1], index_col=0)
df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
index_col=0)
# TODO add index to file
tm.assert_frame_equal(df1, dfref, check_names=False)
tm.assert_frame_equal(df2, dfref, check_names=False)
Expand Down Expand Up @@ -350,7 +351,8 @@ def test_reader_converters(self, ext):

# should read in correctly and set types of single cells (not array
# dtypes)
actual = self.get_exceldf(basename, ext, 'Sheet1', converters=converters)
actual = self.get_exceldf(basename, ext, 'Sheet1',
converters=converters)
tm.assert_frame_equal(actual, expected)

def test_reader_dtype(self, ext):
Expand Down Expand Up @@ -426,11 +428,10 @@ def test_read_excel_blank_with_header(self, ext):
actual = self.get_exceldf('blank_with_header', ext, 'Sheet1')
tm.assert_frame_equal(actual, expected)

@td.skip_if_no('openpyxl')
@td.skip_if_no('xlwt')
# GH 12292 : error when read one empty column from excel file
def test_read_one_empty_col_no_header(self, ext):
_skip_if_no_xlwt()
_skip_if_no_openpyxl()

df = pd.DataFrame(
[["", 1, 100],
["", 2, 200],
Expand All @@ -456,10 +457,9 @@ def test_read_one_empty_col_no_header(self, ext):
tm.assert_frame_equal(actual_header_none, expected)
tm.assert_frame_equal(actual_header_zero, expected)

@td.skip_if_no('openpyxl')
@td.skip_if_no('xlwt')
def test_read_one_empty_col_with_header(self, ext):
_skip_if_no_xlwt()
_skip_if_no_openpyxl()

df = pd.DataFrame(
[["", 1, 100],
["", 2, 200],
Expand All @@ -486,10 +486,9 @@ def test_read_one_empty_col_with_header(self, ext):
expected_header_zero = DataFrame(columns=[0], dtype='int64')
tm.assert_frame_equal(actual_header_zero, expected_header_zero)

@td.skip_if_no('openpyxl')
@td.skip_if_no('xlwt')
def test_set_column_names_in_parameter(self, ext):
_skip_if_no_xlwt()
_skip_if_no_openpyxl()

# GH 12870 : pass down column names associated with
# keyword argument names
refdf = pd.DataFrame([[1, 'foo'], [2, 'bar'],
Expand Down Expand Up @@ -529,14 +528,16 @@ def test_sheet_name_and_sheetname(self, ext):
dfref = self.get_csv_refdf('test1')
df1 = self.get_exceldf('test1', ext, sheet_name='Sheet1') # doc
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
df2 = self.get_exceldf('test1', ext, sheetname='Sheet1') # bkwrd compat
df2 = self.get_exceldf('test1', ext,
sheetname='Sheet1') # bkwrd compat

tm.assert_frame_equal(df1, dfref, check_names=False)
tm.assert_frame_equal(df2, dfref, check_names=False)

def test_sheet_name_both_raises(self, ext):
with tm.assert_raises_regex(TypeError, "Cannot specify both"):
self.get_exceldf('test1', ext, sheetname='Sheet1', sheet_name='Sheet1')
self.get_exceldf('test1', ext, sheetname='Sheet1',
sheet_name='Sheet1')


@pytest.mark.parametrize("ext", ['.xls', '.xlsx', '.xlsm'])
Expand All @@ -559,9 +560,8 @@ def test_excel_read_buffer(self, ext):
actual = read_excel(xls, 'Sheet1', index_col=0)
tm.assert_frame_equal(expected, actual)

@td.skip_if_no('xlwt')
def test_read_xlrd_Book(self, ext):
_skip_if_no_xlwt()

df = self.frame
with ensure_clean('.xls') as pth:
df.to_excel(pth, "SheetA")
Expand Down Expand Up @@ -659,14 +659,12 @@ def test_reader_closes_file(self, ext):

assert f.closed

@td.skip_if_no('openpyxl')
@td.skip_if_no('xlwt')
def test_creating_and_reading_multiple_sheets(self, ext):
# Test reading multiple sheets, from a runtime created excel file
# with multiple sheets.
# See PR #9450

_skip_if_no_xlwt()
_skip_if_no_openpyxl()

def tdf(sheetname):
d, i = [11, 22, 33], [1, 2, 3]
return DataFrame(d, i, columns=[sheetname])
Expand Down Expand Up @@ -778,9 +776,9 @@ def test_read_excel_multiindex(self, ext):
header=[0, 1], skiprows=2)
tm.assert_frame_equal(actual, expected)

@td.skip_if_no('xlsxwriter')
def test_read_excel_multiindex_empty_level(self, ext):
# GH 12453
_skip_if_no_xlsxwriter()
with ensure_clean('.xlsx') as path:
df = DataFrame({
('Zero', ''): {0: 0},
Expand Down Expand Up @@ -818,9 +816,9 @@ def test_read_excel_multiindex_empty_level(self, ext):
actual = pd.read_excel(path, header=[0, 1])
tm.assert_frame_equal(actual, expected)

@td.skip_if_no('xlsxwriter')
def test_excel_multindex_roundtrip(self, ext):
# GH 4679
_skip_if_no_xlsxwriter()
with ensure_clean('.xlsx') as pth:
for c_idx_names in [True, False]:
for r_idx_names in [True, False]:
Expand Down Expand Up @@ -937,11 +935,10 @@ def test_read_excel_chunksize(self, ext):
pd.read_excel(os.path.join(self.dirpath, 'test1' + ext),
chunksize=100)

@td.skip_if_no('openpyxl')
@td.skip_if_no('xlwt')
def test_read_excel_parse_dates(self, ext):
# GH 11544, 12051
_skip_if_no_openpyxl()
_skip_if_no_xlwt() # for df2.to_excel

df = DataFrame(
{'col': [1, 2, 3],
'date_strings': pd.date_range('2012-01-01', periods=3)})
Expand Down Expand Up @@ -1707,7 +1704,8 @@ def roundtrip(df, header=True, parser_hdr=0, index=True):
assert res.shape == (1, 2)
assert res.iloc[0, 0] is not np.nan

def test_excel_010_hemstring_raises_NotImplementedError(self, merge_cells, engine, ext):
def test_excel_010_hemstring_raises_NotImplementedError(self, merge_cells,
engine,ext):
# This test was failing only for j>1 and header=False,
# So I reproduced a simple test.
if merge_cells:
Expand Down