Skip to content

Commit a050a33

Browse files
jrebackjreback
committed
Merge pull request #11870 from grahamjeffries/bugfix-11544
raise NotImplemented for date parsing args in read_excel #11544
2 parents b56b1e4 + 2a066c0 commit a050a33

File tree

3 files changed

+52
-31
lines changed

3 files changed

+52
-31
lines changed

‎doc/source/whatsnew/v0.18.0.txt‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -340,4 +340,8 @@ Bug Fixes
340340
- Bug in ``Index`` prevents copying name of passed ``Index``, when a new name is not provided (:issue:`11193`)
341341

342342
- Bug in ``read_excel`` failing to read any non-empty sheets when empty sheets exist and ``sheetname=None`` (:issue:`11711`)
343+
344+
- Bug in ``read_excel`` failing to raise ``NotImplemented`` error when keywords `parse_dates` and `date_parser` are provided (:issue:`11544`)
345+
343346
- Bug in ``read_sql`` with pymysql connections failing to return chunked data (:issue:`11522`)
347+

‎pandas/io/excel.py‎

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -293,7 +293,14 @@ def _parse_excel(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
293293
stacklevel=3)
294294

295295
if 'chunksize' in kwds:
296-
raise NotImplementedError("Reading an Excel file in chunks "
296+
raise NotImplementedError("chunksize keyword of read_excel "
297+
"is not implemented")
298+
if parse_dates:
299+
raise NotImplementedError("parse_dates keyword of read_excel "
300+
"is not implemented")
301+
302+
if date_parser is not None:
303+
raise NotImplementedError("date_parser keyword of read_excel "
297304
"is not implemented")
298305

299306
import xlrd

‎pandas/io/tests/test_excel.py‎

Lines changed: 40 additions & 30 deletions
Original file line numberDiff line numberDiff line change
@@ -167,10 +167,9 @@ def test_parse_cols_int(self):
167167

168168
dfref = self.get_csv_refdf('test1')
169169
dfref = dfref.reindex(columns=['A', 'B', 'C'])
170-
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
171-
parse_cols=3)
170+
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_cols=3)
172171
df2 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
173-
parse_dates=True, parse_cols=3)
172+
parse_cols=3)
174173
# TODO add index to xls file)
175174
tm.assert_frame_equal(df1, dfref, check_names=False)
176175
tm.assert_frame_equal(df2, dfref, check_names=False)
@@ -179,10 +178,9 @@ def test_parse_cols_list(self):
179178

180179
dfref = self.get_csv_refdf('test1')
181180
dfref = dfref.reindex(columns=['B', 'C'])
182-
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
181+
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0,
183182
parse_cols=[0, 2, 3])
184183
df2 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
185-
parse_dates=True,
186184
parse_cols=[0, 2, 3])
187185
# TODO add index to xls file)
188186
tm.assert_frame_equal(df1, dfref, check_names=False)
@@ -193,28 +191,28 @@ def test_parse_cols_str(self):
193191
dfref = self.get_csv_refdf('test1')
194192

195193
df1 = dfref.reindex(columns=['A', 'B', 'C'])
196-
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
194+
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0,
197195
parse_cols='A:D')
198196
df3 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
199-
parse_dates=True, parse_cols='A:D')
197+
parse_cols='A:D')
200198
# TODO add index to xls, read xls ignores index name ?
201199
tm.assert_frame_equal(df2, df1, check_names=False)
202200
tm.assert_frame_equal(df3, df1, check_names=False)
203201

204202
df1 = dfref.reindex(columns=['B', 'C'])
205-
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
203+
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0,
206204
parse_cols='A,C,D')
207205
df3 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
208-
parse_dates=True, parse_cols='A,C,D')
206+
parse_cols='A,C,D')
209207
# TODO add index to xls file
210208
tm.assert_frame_equal(df2, df1, check_names=False)
211209
tm.assert_frame_equal(df3, df1, check_names=False)
212210

213211
df1 = dfref.reindex(columns=['B', 'C'])
214-
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
212+
df2 = self.get_exceldf('test1', 'Sheet1', index_col=0,
215213
parse_cols='A,C:D')
216214
df3 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
217-
parse_dates=True, parse_cols='A,C:D')
215+
parse_cols='A,C:D')
218216
tm.assert_frame_equal(df2, df1, check_names=False)
219217
tm.assert_frame_equal(df3, df1, check_names=False)
220218

@@ -251,23 +249,23 @@ def test_excel_table_sheet_by_index(self):
251249
excel = self.get_excelfile('test1')
252250
dfref = self.get_csv_refdf('test1')
253251

254-
df1 = read_excel(excel, 0, index_col=0, parse_dates=True)
255-
df2 = read_excel(excel, 1, skiprows=[1], index_col=0, parse_dates=True)
252+
df1 = read_excel(excel, 0, index_col=0)
253+
df2 = read_excel(excel, 1, skiprows=[1], index_col=0)
256254
tm.assert_frame_equal(df1, dfref, check_names=False)
257255
tm.assert_frame_equal(df2, dfref, check_names=False)
258256

259-
df1 = excel.parse(0, index_col=0, parse_dates=True)
260-
df2 = excel.parse(1, skiprows=[1], index_col=0, parse_dates=True)
257+
df1 = excel.parse(0, index_col=0)
258+
df2 = excel.parse(1, skiprows=[1], index_col=0)
261259
tm.assert_frame_equal(df1, dfref, check_names=False)
262260
tm.assert_frame_equal(df2, dfref, check_names=False)
263261

264-
df3 = read_excel(excel, 0, index_col=0, parse_dates=True, skipfooter=1)
265-
df4 = read_excel(excel, 0, index_col=0, parse_dates=True, skip_footer=1)
262+
df3 = read_excel(excel, 0, index_col=0, skipfooter=1)
263+
df4 = read_excel(excel, 0, index_col=0, skip_footer=1)
266264
tm.assert_frame_equal(df3, df1.ix[:-1])
267265
tm.assert_frame_equal(df3, df4)
268266

269-
df3 = excel.parse(0, index_col=0, parse_dates=True, skipfooter=1)
270-
df4 = excel.parse(0, index_col=0, parse_dates=True, skip_footer=1)
267+
df3 = excel.parse(0, index_col=0, skipfooter=1)
268+
df4 = excel.parse(0, index_col=0, skip_footer=1)
271269
tm.assert_frame_equal(df3, df1.ix[:-1])
272270
tm.assert_frame_equal(df3, df4)
273271

@@ -279,16 +277,15 @@ def test_excel_table(self):
279277

280278
dfref = self.get_csv_refdf('test1')
281279

282-
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True)
283-
df2 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0,
284-
parse_dates=True)
280+
df1 = self.get_exceldf('test1', 'Sheet1', index_col=0)
281+
df2 = self.get_exceldf('test1', 'Sheet2', skiprows=[1], index_col=0)
285282
# TODO add index to file
286283
tm.assert_frame_equal(df1, dfref, check_names=False)
287284
tm.assert_frame_equal(df2, dfref, check_names=False)
288285

289-
df3 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
286+
df3 = self.get_exceldf('test1', 'Sheet1', index_col=0,
290287
skipfooter=1)
291-
df4 = self.get_exceldf('test1', 'Sheet1', index_col=0, parse_dates=True,
288+
df4 = self.get_exceldf('test1', 'Sheet1', index_col=0,
292289
skip_footer=1)
293290
tm.assert_frame_equal(df3, df1.ix[:-1])
294291
tm.assert_frame_equal(df3, df4)
@@ -389,7 +386,7 @@ def test_reading_all_sheets_with_blank(self):
389386
basename = 'blank_with_header'
390387
dfs = self.get_exceldf(basename, sheetname=None)
391388
expected_keys = ['Sheet1', 'Sheet2', 'Sheet3']
392-
tm.assert_contains_all(expected_keys, dfs.keys())
389+
tm.assert_contains_all(expected_keys, dfs.keys())
393390

394391
# GH6403
395392
def test_read_excel_blank(self):
@@ -411,14 +408,14 @@ class XlrdTests(ReadingTestsBase):
411408
def test_excel_read_buffer(self):
412409

413410
pth = os.path.join(self.dirpath, 'test1' + self.ext)
414-
expected = read_excel(pth, 'Sheet1', index_col=0, parse_dates=True)
411+
expected = read_excel(pth, 'Sheet1', index_col=0)
415412
with open(pth, 'rb') as f:
416-
actual = read_excel(f, 'Sheet1', index_col=0, parse_dates=True)
413+
actual = read_excel(f, 'Sheet1', index_col=0)
417414
tm.assert_frame_equal(expected, actual)
418415

419416
with open(pth, 'rb') as f:
420417
xls = ExcelFile(f)
421-
actual = read_excel(xls, 'Sheet1', index_col=0, parse_dates=True)
418+
actual = read_excel(xls, 'Sheet1', index_col=0)
422419
tm.assert_frame_equal(expected, actual)
423420

424421
def test_read_xlrd_Book(self):
@@ -680,7 +677,7 @@ def test_excel_oldindex_format(self):
680677
tm.assert_frame_equal(actual, expected, check_names=False)
681678

682679
def test_read_excel_bool_header_arg(self):
683-
#GH 6114
680+
# GH 6114
684681
for arg in [True, False]:
685682
with tm.assertRaises(TypeError):
686683
pd.read_excel(os.path.join(self.dirpath, 'test1' + self.ext),
@@ -692,6 +689,19 @@ def test_read_excel_chunksize(self):
692689
pd.read_excel(os.path.join(self.dirpath, 'test1' + self.ext),
693690
chunksize=100)
694691

692+
def test_read_excel_parse_dates(self):
693+
# GH 11544
694+
with tm.assertRaises(NotImplementedError):
695+
pd.read_excel(os.path.join(self.dirpath, 'test1' + self.ext),
696+
parse_dates=True)
697+
698+
def test_read_excel_date_parser(self):
699+
# GH 11544
700+
with tm.assertRaises(NotImplementedError):
701+
dateparse = lambda x: pd.datetime.strptime(x, '%Y-%m-%d %H:%M:%S')
702+
pd.read_excel(os.path.join(self.dirpath, 'test1' + self.ext),
703+
date_parser=dateparse)
704+
695705
def test_read_excel_skiprows_list(self):
696706
#GH 4903
697707
actual = pd.read_excel(os.path.join(self.dirpath, 'testskiprows' + self.ext),
@@ -1093,7 +1103,7 @@ def test_to_excel_periodindex(self):
10931103
xp.to_excel(path, 'sht1')
10941104

10951105
reader = ExcelFile(path)
1096-
rs = read_excel(reader, 'sht1', index_col=0, parse_dates=True)
1106+
rs = read_excel(reader, 'sht1', index_col=0)
10971107
tm.assert_frame_equal(xp, rs.to_period('M'))
10981108

10991109
def test_to_excel_multiindex(self):

0 commit comments

Comments
 (0)