def _check_excel_multiindex_dates(self, ext):
path = '__tmp_to_excel_multiindex_dates__' + ext + '__.' + ext
# try multiindex with dates
tsframe = self.tsframe
old_index = tsframe.index
new_index = [old_index, np.arange(len(old_index))]
tsframe.index = MultiIndex.from_arrays(new_index)
tsframe.to_excel(path, 'test1', index_label=['time', 'foo'])
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=[0, 1])
tm.assert_frame_equal(tsframe, recons, check_names=False)
self.assertEquals(recons.index.names, ['time', 'foo'])
# infer index
tsframe.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(tsframe, recons)
self.tsframe.index = old_index # needed if setUP becomes classmethod
os.remove(path)
def test_excel_stop_iterator(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, 'test2.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([['aaaa', 'bbbbb']], columns=['Test', 'Test1'])
tm.assert_frame_equal(parsed, expected)
def _check_extension_sheets(self, ext):
path = '__tmp_to_excel_from_excel_sheets__.' + ext
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# Test writing to separate sheets
writer = ExcelWriter(path)
self.frame.to_excel(writer, 'test1')
self.tsframe.to_excel(writer, 'test2')
writer.save()
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
recons = reader.parse('test2', index_col=0)
tm.assert_frame_equal(self.tsframe, recons)
np.testing.assert_equal(2, len(reader.sheet_names))
np.testing.assert_equal('test1', reader.sheet_names[0])
np.testing.assert_equal('test2', reader.sheet_names[1])
os.remove(path)
def test_excel_stop_iterator(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, "test2.xls"))
parsed = excel_data.parse("Sheet1")
expected = DataFrame([["aaaa", "bbbbb"]], columns=["Test", "Test1"])
tm.assert_frame_equal(parsed, expected)
def _check_extension_sheets(self, ext):
path = '__tmp_to_excel_from_excel_sheets__.' + ext
self.frame['A'][:5] = nan
self.frame.to_excel(path,'test1')
self.frame.to_excel(path,'test1', cols=['A', 'B'])
self.frame.to_excel(path,'test1', header=False)
self.frame.to_excel(path,'test1', index=False)
# Test writing to separate sheets
writer = ExcelWriter(path)
self.frame.to_excel(writer,'test1')
self.tsframe.to_excel(writer,'test2')
writer.save()
reader = ExcelFile(path)
recons = reader.parse('test1',index_col=0)
tm.assert_frame_equal(self.frame, recons)
recons = reader.parse('test2',index_col=0)
tm.assert_frame_equal(self.tsframe, recons)
np.testing.assert_equal(2, len(reader.sheet_names))
np.testing.assert_equal('test1', reader.sheet_names[0])
np.testing.assert_equal('test2', reader.sheet_names[1])
os.remove(path)
def test_excel_cell_error_na(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, "test3.xls"))
parsed = excel_data.parse("Sheet1")
expected = DataFrame([[np.nan]], columns=["Test"])
tm.assert_frame_equal(parsed, expected)
def test_excel_cell_error_na(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, 'test3.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([[np.nan]], columns=['Test'])
tm.assert_frame_equal(parsed, expected)
def test_to_excel_unicode_filename(self):
_skip_if_no_excelsuite()
for ext in ["xls", "xlsx"]:
filename = u"\u0192u." + ext
try:
f = open(filename, "wb")
except UnicodeEncodeError:
raise nose.SkipTest("no unicode file names on this system")
else:
f.close()
df = DataFrame(
[[0.123456, 0.234567, 0.567567], [12.32112, 123123.2, 321321.2]],
index=["A", "B"],
columns=["X", "Y", "Z"],
)
df.to_excel(filename, "test1", float_format="%.2f")
reader = ExcelFile(filename)
rs = reader.parse("test1", index_col=None)
xp = DataFrame(
[[0.12, 0.23, 0.57], [12.32, 123123.20, 321321.20]], index=["A", "B"], columns=["X", "Y", "Z"]
)
tm.assert_frame_equal(rs, xp)
os.remove(filename)
def test_to_excel_unicode_filename(self):
_skip_if_no_excelsuite()
for ext in ['xls', 'xlsx']:
filename = '\u0192u.' + ext
try:
f = open(filename, 'wb')
except UnicodeEncodeError:
raise nose.SkipTest('no unicode file names on this system')
else:
f.close()
df = DataFrame([[0.123456, 0.234567, 0.567567],
[12.32112, 123123.2, 321321.2]],
index=['A', 'B'], columns=['X', 'Y', 'Z'])
with ensure_clean(filename) as filename:
df.to_excel(filename, 'test1', float_format='%.2f')
reader = ExcelFile(filename)
rs = reader.parse('test1', index_col=None)
xp = DataFrame([[0.12, 0.23, 0.57],
[12.32, 123123.20, 321321.20]],
index=['A', 'B'], columns=['X', 'Y', 'Z'])
tm.assert_frame_equal(rs, xp)
def _check_extension_sheets(self, ext):
path = "__tmp_to_excel_from_excel_sheets__." + ext
self.frame["A"][:5] = nan
self.frame.to_excel(path, "test1")
self.frame.to_excel(path, "test1", cols=["A", "B"])
self.frame.to_excel(path, "test1", header=False)
self.frame.to_excel(path, "test1", index=False)
# Test writing to separate sheets
writer = ExcelWriter(path)
self.frame.to_excel(writer, "test1")
self.tsframe.to_excel(writer, "test2")
writer.save()
reader = ExcelFile(path)
recons = reader.parse("test1", index_col=0)
tm.assert_frame_equal(self.frame, recons)
recons = reader.parse("test2", index_col=0)
tm.assert_frame_equal(self.tsframe, recons)
np.testing.assert_equal(2, len(reader.sheet_names))
np.testing.assert_equal("test1", reader.sheet_names[0])
np.testing.assert_equal("test2", reader.sheet_names[1])
os.remove(path)
def test_excel_stop_iterator(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, 'test2.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([['aaaa','bbbbb']], columns=['Test', 'Test1'])
assert_frame_equal(parsed, expected)
def test_excel_cell_error_na(self):
_skip_if_no_xlrd()
excel_data = ExcelFile(os.path.join(self.dirpath, 'test3.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([[np.nan]], columns=['Test'])
assert_frame_equal(parsed, expected)
def getExcelChunck(file, ws, drange, rid=-1, cid=-1):
xls = ExcelFile(file)
df = xls.parse(ws)
# get the range from expression
# B4H4
m = re.search('([A-Z]+)([0-9]+)([A-Z]+)([0-9]+)', drange)
c1 = sord(m.group(1))
c2 = sord(m.group(3)) + 1
r1 = int(m.group(2)) - 2
r2 = int(m.group(4)) - 2
df2 = df.ix[r1:r2, c1:c2]
if (rid >= 0):
rh = int(rid) - 2
df2.columns = df.ix[rh, c1:c2]
df2.columns = df2.columns.map(
lambda x: str(x).strip().replace('.0', ''))
if (cid >= 0):
ch = sord(cid)
df2.index = df.ix[r1:r2, ch]
df2.index = df2.index.map(lambda x: str(x).strip().replace('.0', ''))
return (df2)
def test_to_excel_unicode_filename(self):
_skip_if_no_excelsuite()
for ext in ['xls', 'xlsx']:
filename = u'\u0192u.' + ext
try:
f = open(filename, 'wb')
except UnicodeEncodeError:
raise nose.SkipTest('no unicode file names on this system')
else:
f.close()
df = DataFrame([[0.123456, 0.234567, 0.567567],
[12.32112, 123123.2, 321321.2]],
index=['A', 'B'],
columns=['X', 'Y', 'Z'])
df.to_excel(filename, 'test1', float_format='%.2f')
reader = ExcelFile(filename)
rs = reader.parse('test1', index_col=None)
xp = DataFrame([[0.12, 0.23, 0.57], [12.32, 123123.20, 321321.20]],
index=['A', 'B'],
columns=['X', 'Y', 'Z'])
tm.assert_frame_equal(rs, xp)
os.remove(filename)
def _check_extension_mixed(self, ext):
path = '__tmp_to_excel_from_excel_mixed__.' + ext
with ensure_clean(path) as path:
self.mixed_frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0)
tm.assert_frame_equal(self.mixed_frame, recons)
def test_excel_table(self):
pth = os.path.join(self.dirpath, 'test.xls')
xls = ExcelFile(pth)
df = xls.parse('Sheet1')
df2 = read_csv(self.csv1)
df3 = xls.parse('Sheet2', skiprows=[1])
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def _check_extension_mixed(self, ext):
path = '__tmp_to_excel_from_excel_mixed__.' + ext
self.mixed_frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0, has_index_names=True)
tm.assert_frame_equal(self.mixed_frame, recons)
os.remove(path)
def _check_extension_mixed(self, ext):
path = '__tmp_to_excel_from_excel_mixed__.' + ext
self.mixed_frame.to_excel(path,'test1')
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0, has_index_names=True)
tm.assert_frame_equal(self.mixed_frame, recons)
os.remove(path)
def _check_extension_mixed(self, ext):
path = "__tmp_to_excel_from_excel_mixed__." + ext
self.mixed_frame.to_excel(path, "test1")
reader = ExcelFile(path)
recons = reader.parse("test1", index_col=0)
tm.assert_frame_equal(self.mixed_frame, recons)
os.remove(path)
def test_excel_cell_error_na(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest('xlrd not installed, skipping')
excel_data = ExcelFile(os.path.join(self.dirpath, 'test3.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([[np.nan]], columns=['Test'])
assert_frame_equal(parsed, expected)
def _check_extension_tsframe(self, ext):
path = '__tmp_to_excel_from_excel_tsframe__.' + ext
df = tm.makeTimeDataFrame()[:5]
with ensure_clean(path) as path:
df.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(df, recons)
def test_xlsx_table(self):
_skip_if_no_openpyxl()
pth = os.path.join(self.dirpath, 'test.xlsx')
xlsx = ExcelFile(pth)
df = xlsx.parse('Sheet1', index_col=0, parse_dates=True)
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df3 = xlsx.parse('Sheet2', skiprows=[1], index_col=0, parse_dates=True)
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def test_excel_stop_iterator(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest('xlrd not installed, skipping')
excel_data = ExcelFile(os.path.join(self.dirpath, 'test2.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([['aaaa', 'bbbbb']], columns=['Test', 'Test1'])
assert_frame_equal(parsed, expected)
def test_xlsx_table(self):
_skip_if_no_openpyxl()
pth = os.path.join(self.dirpath, 'test.xlsx')
xlsx = ExcelFile(pth)
df = xlsx.parse('Sheet1', index_col=0, parse_dates=True)
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df3 = xlsx.parse('Sheet2', skiprows=[1], index_col=0, parse_dates=True)
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def test_excel_stop_iterator(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest('xlrd not installed, skipping')
excel_data = ExcelFile(os.path.join(self.dirpath, 'test2.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([['aaaa','bbbbb']], columns=['Test', 'Test1'])
assert_frame_equal(parsed, expected)
def test_excel_stop_iterator(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest("xlrd not installed, skipping")
excel_data = ExcelFile(os.path.join(self.dirpath, "test2.xls"))
parsed = excel_data.parse("Sheet1")
expected = DataFrame([["aaaa", "bbbbb"]], columns=["Test", "Test1"])
assert_frame_equal(parsed, expected)
def test_excel_cell_error_na(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest('xlrd not installed, skipping')
excel_data = ExcelFile(os.path.join(self.dirpath, 'test3.xls'))
parsed = excel_data.parse('Sheet1')
expected = DataFrame([[np.nan]], columns=['Test'])
assert_frame_equal(parsed, expected)
def _check_extension(self, ext):
path = '__tmp_to_excel_from_excel__.' + ext
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# test roundtrip
self.frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', index=False)
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='NA')
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=0, na_values=['NA'])
tm.assert_frame_equal(self.frame, recons)
os.remove(path)
def _check_extension_tsframe(self, ext):
path = "__tmp_to_excel_from_excel_tsframe__." + ext
df = tm.makeTimeDataFrame()[:5]
df.to_excel(path, "test1")
reader = ExcelFile(path)
recons = reader.parse("test1")
tm.assert_frame_equal(df, recons)
os.remove(path)
def test_excel_roundtrip_bool(self):
_skip_if_no_openpyxl()
# Test roundtrip np.bool8, does not seem to work for xls
path = '__tmp_excel_roundtrip_bool__.xlsx'
frame = (DataFrame(np.random.randn(10, 2)) >= 0)
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(frame, recons)
os.remove(path)
def test_excel_roundtrip_bool(self):
_skip_if_no_openpyxl()
# Test roundtrip np.bool8, does not seem to work for xls
path = "__tmp_excel_roundtrip_bool__.xlsx"
frame = DataFrame(np.random.randn(10, 2)) >= 0
frame.to_excel(path, "test1")
reader = ExcelFile(path)
recons = reader.parse("test1")
tm.assert_frame_equal(frame, recons)
os.remove(path)
def test_to_excel_periodindex(self):
_skip_if_no_excelsuite()
for ext in ['xls', 'xlsx']:
path = '__tmp_to_excel_periodindex__.' + ext
frame = self.tsframe
xp = frame.resample('M', kind='period')
xp.to_excel(path, 'sht1')
reader = ExcelFile(path)
rs = reader.parse('sht1', index_col=0, parse_dates=True)
tm.assert_frame_equal(xp, rs.to_period('M'))
os.remove(path)
def test_excel_roundtrip_datetime(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
# datetime.date, not sure what to test here exactly
path = '__tmp_excel_roundtrip_datetime__.xls'
tsf = self.tsframe.copy()
tsf.index = [x.date() for x in self.tsframe.index]
tsf.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(self.tsframe, recons)
os.remove(path)
def test_excel_roundtrip_datetime(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
# datetime.date, not sure what to test here exactly
path = "__tmp_excel_roundtrip_datetime__.xls"
tsf = self.tsframe.copy()
tsf.index = [x.date() for x in self.tsframe.index]
tsf.to_excel(path, "test1")
reader = ExcelFile(path)
recons = reader.parse("test1")
tm.assert_frame_equal(self.tsframe, recons)
os.remove(path)
def test_excel_roundtrip_bool(self):
_skip_if_no_openpyxl()
# Test roundtrip np.bool8, does not seem to work for xls
path = '__tmp_excel_roundtrip_bool__.xlsx'
frame = (DataFrame(np.random.randn(10, 2)) >= 0)
with ensure_clean(path) as path:
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(frame, recons)
def test_to_excel_periodindex(self):
_skip_if_no_excelsuite()
for ext in ['xls', 'xlsx']:
path = '__tmp_to_excel_periodindex__.' + ext
frame = self.tsframe
xp = frame.resample('M', kind='period')
xp.to_excel(path, 'sht1')
reader = ExcelFile(path)
rs = reader.parse('sht1', index_col=0, parse_dates=True)
tm.assert_frame_equal(xp, rs.to_period('M'))
os.remove(path)
def test_to_excel_periodindex(self):
_skip_if_no_excelsuite()
for ext in ["xls", "xlsx"]:
path = "__tmp_to_excel_periodindex__." + ext
frame = self.tsframe
xp = frame.resample("M", kind="period")
xp.to_excel(path, "sht1")
reader = ExcelFile(path)
rs = reader.parse("sht1", index_col=0, parse_dates=True)
tm.assert_frame_equal(xp, rs.to_period("M"))
os.remove(path)
def test_excel_table(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest("xlrd not installed, skipping")
pth = os.path.join(self.dirpath, "test.xls")
xls = ExcelFile(pth)
df = xls.parse("Sheet1", index_col=0, parse_dates=True)
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df3 = xls.parse("Sheet2", skiprows=[1], index_col=0, parse_dates=True)
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def test_excel_table(self):
try:
import xlrd
except ImportError:
raise nose.SkipTest('xlrd not installed, skipping')
pth = os.path.join(self.dirpath, 'test.xls')
xls = ExcelFile(pth)
df = xls.parse('Sheet1', index_col=0, parse_dates=True)
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df3 = xls.parse('Sheet2', skiprows=[1], index_col=0, parse_dates=True)
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def test_xlsx_table(self):
try:
import openpyxl
except ImportError:
raise nose.SkipTest('openpyxl not installed, skipping')
pth = os.path.join(self.dirpath, 'test.xlsx')
xlsx = ExcelFile(pth)
df = xlsx.parse('Sheet1', index_col=0, parse_dates=True)
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df3 = xlsx.parse('Sheet2', skiprows=[1], index_col=0, parse_dates=True)
assert_frame_equal(df, df2)
assert_frame_equal(df3, df2)
def test_to_excel(self):
try:
import xlwt
import xlrd
import openpyxl
except ImportError:
raise nose.SkipTest
path = "__tmp__.xlsx"
self.panel.to_excel(path)
reader = ExcelFile(path)
for item, df in self.panel.iteritems():
recdf = reader.parse(str(item), index_col=0)
assert_frame_equal(df, recdf)
def test_excel_roundtrip_datetime(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
# datetime.date, not sure what to test here exactly
path = '__tmp_excel_roundtrip_datetime__.xls'
tsf = self.tsframe.copy()
with ensure_clean(path) as path:
tsf.index = [x.date() for x in self.tsframe.index]
tsf.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(self.tsframe, recons)
def test_to_excel(self):
try:
import xlwt
import xlrd
import openpyxl
except ImportError:
raise nose.SkipTest
path = '__tmp__.xlsx'
self.panel.to_excel(path)
reader = ExcelFile(path)
for item, df in self.panel.iteritems():
recdf = reader.parse(str(item),index_col=0)
assert_frame_equal(df, recdf)
def test_excel_read_buffer(self):
_skip_if_no_xlrd()
_skip_if_no_openpyxl()
pth = os.path.join(self.dirpath, 'test.xls')
f = open(pth, 'rb')
xls = ExcelFile(f)
# it works
xls.parse('Sheet1', index_col=0, parse_dates=True)
pth = os.path.join(self.dirpath, 'test.xlsx')
f = open(pth, 'rb')
xl = ExcelFile(f)
df = xl.parse('Sheet1', index_col=0, parse_dates=True)
def test_parse_cols_int(self):
_skip_if_no_openpyxl()
_skip_if_no_xlrd()
suffix = ["", "x"]
for s in suffix:
pth = os.path.join(self.dirpath, "test.xls%s" % s)
xls = ExcelFile(pth)
df = xls.parse("Sheet1", index_col=0, parse_dates=True, parse_cols=3)
df2 = self.read_csv(self.csv1, index_col=0, parse_dates=True)
df2 = df2.reindex(columns=["A", "B", "C"])
df3 = xls.parse("Sheet2", skiprows=[1], index_col=0, parse_dates=True, parse_cols=3)
tm.assert_frame_equal(df, df2)
tm.assert_frame_equal(df3, df2)
def test_parse_cols_str(self):
_skip_if_no_openpyxl()
_skip_if_no_xlrd()
suffix = ['', 'x']
for s in suffix:
pth = os.path.join(self.dirpath, 'test.xls%s' % s)
xls = ExcelFile(pth)
df = xls.parse('Sheet1',
index_col=0,
parse_dates=True,
parse_cols='A:D')
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df2 = df2.reindex(columns=['A', 'B', 'C'])
df3 = xls.parse('Sheet2',
skiprows=[1],
index_col=0,
parse_dates=True,
parse_cols='A:D')
tm.assert_frame_equal(
df, df2, check_names=False
) # TODO add index to xls, read xls ignores index name ?
tm.assert_frame_equal(df3, df2, check_names=False)
del df, df2, df3
df = xls.parse('Sheet1',
index_col=0,
parse_dates=True,
parse_cols='A,C,D')
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df2 = df2.reindex(columns=['B', 'C'])
df3 = xls.parse('Sheet2',
skiprows=[1],
index_col=0,
parse_dates=True,
parse_cols='A,C,D')
tm.assert_frame_equal(
df, df2, check_names=False) # TODO add index to xls file
tm.assert_frame_equal(df3, df2, check_names=False)
del df, df2, df3
df = xls.parse('Sheet1',
index_col=0,
parse_dates=True,
parse_cols='A,C:D')
df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
df2 = df2.reindex(columns=['B', 'C'])
df3 = xls.parse('Sheet2',
skiprows=[1],
index_col=0,
parse_dates=True,
parse_cols='A,C:D')
tm.assert_frame_equal(df, df2, check_names=False)
tm.assert_frame_equal(df3, df2, check_names=False)
def _check_extension_int64(self, ext):
path = '__tmp_to_excel_from_excel_int64__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# Test np.int64, values read come back as float
frame = DataFrame(np.random.randint(-10, 10, size=(10, 2)), dtype=np.int64)
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1').astype(np.int64)
tm.assert_frame_equal(frame, recons, check_dtype=False)
def _check_extension_bool(self, ext):
path = '__tmp_to_excel_from_excel_bool__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# Test reading/writing np.bool8, roundtrip only works for xlsx
frame = (DataFrame(np.random.randn(10, 2)) >= 0)
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1').astype(np.bool8)
tm.assert_frame_equal(frame, recons)
def test_to_excel_float_format(self):
_skip_if_no_excelsuite()
for ext in ['xls', 'xlsx']:
filename = '__tmp_to_excel_float_format__.' + ext
df = DataFrame([[0.123456, 0.234567, 0.567567],
[12.32112, 123123.2, 321321.2]],
index=['A', 'B'],
columns=['X', 'Y', 'Z'])
df.to_excel(filename, 'test1', float_format='%.2f')
reader = ExcelFile(filename)
rs = reader.parse('test1', index_col=None)
xp = DataFrame([[0.12, 0.23, 0.57], [12.32, 123123.20, 321321.20]],
index=['A', 'B'],
columns=['X', 'Y', 'Z'])
tm.assert_frame_equal(rs, xp)
os.remove(filename)
def test_excel_roundtrip_indexname(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
path = '%s.xls' % tm.rands(10)
df = DataFrame(np.random.randn(10, 4))
df.index.name = 'foo'
with ensure_clean(path) as path:
df.to_excel(path)
xf = ExcelFile(path)
result = xf.parse(xf.sheet_names[0], index_col=0)
tm.assert_frame_equal(result, df)
self.assertEqual(result.index.name, 'foo')
def test_to_excel(self):
try:
import os
import xlwt
import xlrd
import openpyxl
from pandas.io.parsers import ExcelFile
except ImportError:
raise nose.SkipTest
for ext in ['xls', 'xlsx']:
path = '__tmp__.' + ext
self.panel.to_excel(path)
reader = ExcelFile(path)
for item, df in self.panel.iteritems():
recdf = reader.parse(str(item), index_col=0)
assert_frame_equal(df, recdf)
os.remove(path)
def _check_extension_colaliases(self, ext):
path = '__tmp_to_excel_from_excel_aliases__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# column aliases
col_aliases = Index(['AA', 'X', 'Y', 'Z'])
self.frame2.to_excel(path, 'test1', header=col_aliases)
reader = ExcelFile(path)
rs = reader.parse('test1', index_col=0)
xp = self.frame2.copy()
xp.columns = col_aliases
tm.assert_frame_equal(xp, rs)
def test_specify_kind_xlsx(self):
_skip_if_no_openpyxl()
xlsx_file = os.path.join(self.dirpath, 'test.xlsx')
xls_file = os.path.join(self.dirpath, 'test.xls')
self.assertRaises(Exception, ExcelFile, xls_file, kind='xlsx')
ExcelFile(open(xlsx_file, 'rb'), kind='xlsx')
self.assertRaises(Exception, ExcelFile, open(xls_file, 'rb'),
kind='xlsx')
def _check_excel_multiindex(self, ext):
path = '__tmp_to_excel_multiindex__' + ext + '__.' + ext
frame = self.frame
old_index = frame.index
arrays = np.arange(len(old_index) * 2).reshape(2, -1)
new_index = MultiIndex.from_arrays(arrays, names=['first', 'second'])
frame.index = new_index
frame.to_excel(path, 'test1', header=False)
frame.to_excel(path, 'test1', cols=['A', 'B'])
# round trip
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
df = reader.parse('test1', index_col=[0, 1], parse_dates=False)
tm.assert_frame_equal(frame, df)
self.assertEqual(frame.index.names, df.index.names)
self.frame.index = old_index # needed if setUP becomes a classmethod
os.remove(path)
def test_excel_roundtrip_indexname(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
path = '%s.xls' % tm.rands(10)
df = DataFrame(np.random.randn(10, 4))
df.index.name = 'foo'
df.to_excel(path)
xf = ExcelFile(path)
result = xf.parse(xf.sheet_names[0], index_col=0)
tm.assert_frame_equal(result, df)
self.assertEqual(result.index.name, 'foo')
try:
os.remove(path)
except os.error:
pass
def _check_excel_multiindex_dates(self, ext):
path = '__tmp_to_excel_multiindex_dates__' + ext + '__.' + ext
# try multiindex with dates
tsframe = self.tsframe
old_index = tsframe.index
new_index = [old_index, np.arange(len(old_index))]
tsframe.index = MultiIndex.from_arrays(new_index)
tsframe.to_excel(path, 'test1', index_label=['time', 'foo'])
reader = ExcelFile(path)
recons = reader.parse('test1', index_col=[0, 1])
tm.assert_frame_equal(tsframe, recons, check_names=False)
self.assertEquals(recons.index.names, ['time', 'foo'])
# infer index
tsframe.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
tm.assert_frame_equal(tsframe, recons)
self.tsframe.index = old_index # needed if setUP becomes classmethod
os.remove(path)
def test_parse_cols_int(self):
_skip_if_no_openpyxl()
_skip_if_no_xlrd()
suffix = ['', 'x']
for s in suffix:
pth = os.path.join(self.dirpath, 'test.xls%s' % s)
xls = ExcelFile(pth)
df = xls.parse('Sheet1',
index_col=0,
parse_dates=True,
parse_cols=3)
df2 = self.read_csv(self.csv1, index_col=0, parse_dates=True)
df2 = df2.reindex(columns=['A', 'B', 'C'])
df3 = xls.parse('Sheet2',
skiprows=[1],
index_col=0,
parse_dates=True,
parse_cols=3)
tm.assert_frame_equal(df, df2)
tm.assert_frame_equal(df3, df2)
def saving_simulation(self, file_path=None):
"""
CANNOT BE COMPLETED FOR NOW BECAUSE OF A BUG OF PANDAS
"""
if file_path is None:
raise Exception(
'A complete path to the file should be provided. DO not hesitate to use os.path.join'
)
writer = ExcelFile(file_path)
print writer
cohorts_list_base = [
self.cohorts, self.cohorts_alt, self.percapita_pv,
self.percapita_pv_alt, self.aggregate_pv, self.aggregate_pv_alt
]
cohorts_list = []
for df in cohorts_list_base:
try:
name = df.name
cohorts_list.append(df)
print 'good to go'
except:
print 'no such cohort in this simulation'
print len(cohorts_list)
df_dict = dict(
(dataframe.name, dataframe) for dataframe in cohorts_list)
print df_dict
for name, attribute in df_dict.iteritems():
print 'new dataframe'
#try:
attribute.to_excel(writer, sheet_name=name)
#except:
# print 'BUG ENCOUNTERED'
writer.save()