forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathexcel.py
1810 lines (1526 loc) · 59.9 KB
/
excel.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""
Module parse to/from Excel
"""
# ---------------------------------------------------------------------
# ExcelFile class
from datetime import datetime, date, time, MINYEAR, timedelta
import os
import abc
import warnings
from textwrap import fill
from io import UnsupportedOperation
from distutils.version import LooseVersion
import numpy as np
import pandas._libs.json as json
from pandas.util._decorators import Appender, deprecate_kwarg
from pandas.errors import EmptyDataError
import pandas.compat as compat
from pandas.compat import (map, zip, reduce, range, lrange, u, add_metaclass,
string_types, OrderedDict)
from pandas.core.dtypes.common import (
is_integer, is_float,
is_bool, is_list_like)
from pandas.core import config
from pandas.core.frame import DataFrame
from pandas.io.parsers import TextParser
from pandas.io.common import (_is_url, _urlopen, _validate_header_arg,
get_filepath_or_buffer, _NA_VALUES,
_stringify_path)
from pandas.io.formats.printing import pprint_thing
__all__ = ["read_excel", "ExcelWriter", "ExcelFile"]
_writer_extensions = ["xlsx", "xls", "xlsm"]
_writers = {}
_read_excel_doc = """
Read an Excel table into a pandas DataFrame
Parameters
----------
io : string, path object (pathlib.Path or py._path.local.LocalPath),
file-like object, pandas ExcelFile, or xlrd workbook.
The string could be a URL. Valid URL schemes include http, ftp, s3,
gcs, and file. For file URLs, a host is expected. For instance, a local
file could be file://localhost/path/to/workbook.xlsx
sheet_name : string, int, mixed list of strings/ints, or None, default 0
Strings are used for sheet names, Integers are used in zero-indexed
sheet positions.
Lists of strings/integers are used to request multiple sheets.
Specify None to get all sheets.
str|int -> DataFrame is returned.
list|None -> Dict of DataFrames is returned, with keys representing
sheets.
Available Cases
* Defaults to 0 -> 1st sheet as a DataFrame
* 1 -> 2nd sheet as a DataFrame
* "Sheet1" -> 1st sheet as a DataFrame
* [0,1,"Sheet5"] -> 1st, 2nd & 5th sheet as a dictionary of DataFrames
* None -> All sheets as a dictionary of DataFrames
sheetname : string, int, mixed list of strings/ints, or None, default 0
.. deprecated:: 0.21.0
Use `sheet_name` instead
header : int, list of ints, default 0
Row (0-indexed) to use for the column labels of the parsed
DataFrame. If a list of integers is passed those row positions will
be combined into a ``MultiIndex``. Use None if there is no header.
names : array-like, default None
List of column names to use. If file contains no header row,
then you should explicitly pass header=None
index_col : int, list of ints, default None
Column (0-indexed) to use as the row labels of the DataFrame.
Pass None if there is no such column. If a list is passed,
those columns will be combined into a ``MultiIndex``. If a
subset of data is selected with ``usecols``, index_col
is based on the subset.
parse_cols : int or list, default None
.. deprecated:: 0.21.0
Pass in `usecols` instead.
usecols : int or list, default None
* If None then parse all columns,
* If int then indicates last column to be parsed
* If list of ints then indicates list of column numbers to be parsed
* If string then indicates comma separated list of Excel column letters and
column ranges (e.g. "A:E" or "A,C,E:F"). Ranges are inclusive of
both sides.
squeeze : boolean, default False
If the parsed data only contains one column then return a Series
dtype : Type name or dict of column -> type, default None
Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32}
Use `object` to preserve data as stored in Excel and not interpret dtype.
If converters are specified, they will be applied INSTEAD
of dtype conversion.
.. versionadded:: 0.20.0
engine: string, default None
If io is not a buffer or path, this must be set to identify io.
Acceptable values are None or xlrd
converters : dict, default None
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels, values are functions that take one
input argument, the Excel cell content, and return the transformed
content.
true_values : list, default None
Values to consider as True
.. versionadded:: 0.19.0
false_values : list, default None
Values to consider as False
.. versionadded:: 0.19.0
skiprows : list-like
Rows to skip at the beginning (0-indexed)
nrows : int, default None
Number of rows to parse
.. versionadded:: 0.23.0
na_values : scalar, str, list-like, or dict, default None
Additional strings to recognize as NA/NaN. If dict passed, specific
per-column NA values. By default the following values are interpreted
as NaN: '""" + fill("', '".join(sorted(_NA_VALUES)), 70, subsequent_indent=" ") + """'.
keep_default_na : bool, default True
If na_values are specified and keep_default_na is False the default NaN
values are overridden, otherwise they're appended to.
verbose : boolean, default False
Indicate number of NA values placed in non-numeric columns
thousands : str, default None
Thousands separator for parsing string columns to numeric. Note that
this parameter is only necessary for columns stored as TEXT in Excel,
any numeric columns will automatically be parsed, regardless of display
format.
comment : str, default None
Comments out remainder of line. Pass a character or characters to this
argument to indicate comments in the input file. Any data between the
comment string and the end of the current line is ignored.
skip_footer : int, default 0
.. deprecated:: 0.23.0
Pass in `skipfooter` instead.
skipfooter : int, default 0
Rows at the end to skip (0-indexed)
convert_float : boolean, default True
convert integral floats to int (i.e., 1.0 --> 1). If False, all numeric
data will be read in as floats: Excel stores all numbers as floats
internally
Returns
-------
parsed : DataFrame or Dict of DataFrames
DataFrame from the passed in Excel file. See notes in sheet_name
argument for more information on when a Dict of Dataframes is returned.
Examples
--------
An example DataFrame written to a local file
>>> df_out = pd.DataFrame([('string1', 1),
... ('string2', 2),
... ('string3', 3)],
... columns=['Name', 'Value'])
>>> df_out
Name Value
0 string1 1
1 string2 2
2 string3 3
>>> df_out.to_excel('tmp.xlsx')
The file can be read using the file name as string or an open file object:
>>> pd.read_excel('tmp.xlsx')
Name Value
0 string1 1
1 string2 2
2 string3 3
>>> pd.read_excel(open('tmp.xlsx','rb'))
Name Value
0 string1 1
1 string2 2
2 string3 3
Index and header can be specified via the `index_col` and `header` arguments
>>> pd.read_excel('tmp.xlsx', index_col=None, header=None)
0 1 2
0 NaN Name Value
1 0.0 string1 1
2 1.0 string2 2
3 2.0 string3 3
Column types are inferred but can be explicitly specified
>>> pd.read_excel('tmp.xlsx', dtype={'Name':str, 'Value':float})
Name Value
0 string1 1.0
1 string2 2.0
2 string3 3.0
True, False, and NA values, and thousands separators have defaults,
but can be explicitly specified, too. Supply the values you would like
as strings or lists of strings!
>>> pd.read_excel('tmp.xlsx',
... na_values=['string1', 'string2'])
Name Value
0 NaN 1
1 NaN 2
2 string3 3
Comment lines in the excel input file can be skipped using the `comment` kwarg
>>> df = pd.DataFrame({'a': ['1', '#2'], 'b': ['2', '3']})
>>> df.to_excel('tmp.xlsx', index=False)
>>> pd.read_excel('tmp.xlsx')
a b
0 1 2
1 #2 3
>>> pd.read_excel('tmp.xlsx', comment='#')
a b
0 1 2
"""
def register_writer(klass):
"""Adds engine to the excel writer registry. You must use this method to
integrate with ``to_excel``. Also adds config options for any new
``supported_extensions`` defined on the writer."""
if not compat.callable(klass):
raise ValueError("Can only register callables as engines")
engine_name = klass.engine
_writers[engine_name] = klass
for ext in klass.supported_extensions:
if ext.startswith('.'):
ext = ext[1:]
if ext not in _writer_extensions:
config.register_option("io.excel.{ext}.writer".format(ext=ext),
engine_name, validator=str)
_writer_extensions.append(ext)
def _get_default_writer(ext):
_default_writers = {'xlsx': 'openpyxl', 'xlsm': 'openpyxl', 'xls': 'xlwt'}
try:
import xlsxwriter # noqa
_default_writers['xlsx'] = 'xlsxwriter'
except ImportError:
pass
return _default_writers[ext]
def get_writer(engine_name):
try:
return _writers[engine_name]
except KeyError:
raise ValueError("No Excel writer '{engine}'"
.format(engine=engine_name))
@Appender(_read_excel_doc)
@deprecate_kwarg("parse_cols", "usecols")
@deprecate_kwarg("skip_footer", "skipfooter")
def read_excel(io,
sheet_name=0,
header=0,
names=None,
index_col=None,
usecols=None,
squeeze=False,
dtype=None,
engine=None,
converters=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skipfooter=0,
convert_float=True,
**kwds):
# Can't use _deprecate_kwarg since sheetname=None has a special meaning
if is_integer(sheet_name) and sheet_name == 0 and 'sheetname' in kwds:
warnings.warn("The `sheetname` keyword is deprecated, use "
"`sheet_name` instead", FutureWarning, stacklevel=2)
sheet_name = kwds.pop("sheetname")
if 'sheet' in kwds:
raise TypeError("read_excel() got an unexpected keyword argument "
"`sheet`")
if not isinstance(io, ExcelFile):
io = ExcelFile(io, engine=engine)
return io.parse(
sheet_name=sheet_name,
header=header,
names=names,
index_col=index_col,
usecols=usecols,
squeeze=squeeze,
dtype=dtype,
converters=converters,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
convert_float=convert_float,
**kwds)
class ExcelFile(object):
"""
Class for parsing tabular excel sheets into DataFrame objects.
Uses xlrd. See read_excel for more documentation
Parameters
----------
io : string, path object (pathlib.Path or py._path.local.LocalPath),
file-like object or xlrd workbook
If a string or path object, expected to be a path to xls or xlsx file
engine: string, default None
If io is not a buffer or path, this must be set to identify io.
Acceptable values are None or xlrd
"""
def __init__(self, io, **kwds):
err_msg = "Install xlrd >= 0.9.0 for Excel support"
try:
import xlrd
except ImportError:
raise ImportError(err_msg)
else:
ver = tuple(map(int, xlrd.__VERSION__.split(".")[:2]))
if ver < (0, 9): # pragma: no cover
raise ImportError(err_msg +
". Current version " + xlrd.__VERSION__)
# could be a str, ExcelFile, Book, etc.
self.io = io
# Always a string
self._io = _stringify_path(io)
engine = kwds.pop('engine', None)
if engine is not None and engine != 'xlrd':
raise ValueError("Unknown engine: {engine}".format(engine=engine))
# If io is a url, want to keep the data as bytes so can't pass
# to get_filepath_or_buffer()
if _is_url(self._io):
io = _urlopen(self._io)
elif not isinstance(self.io, (ExcelFile, xlrd.Book)):
io, _, _, _ = get_filepath_or_buffer(self._io)
if engine == 'xlrd' and isinstance(io, xlrd.Book):
self.book = io
elif not isinstance(io, xlrd.Book) and hasattr(io, "read"):
# N.B. xlrd.Book has a read attribute too
if hasattr(io, 'seek'):
try:
# GH 19779
io.seek(0)
except UnsupportedOperation:
# HTTPResponse does not support seek()
# GH 20434
pass
data = io.read()
self.book = xlrd.open_workbook(file_contents=data)
elif isinstance(self._io, compat.string_types):
self.book = xlrd.open_workbook(self._io)
else:
raise ValueError('Must explicitly set engine if not passing in'
' buffer or path for io.')
def __fspath__(self):
return self._io
def parse(self,
sheet_name=0,
header=0,
names=None,
index_col=None,
usecols=None,
squeeze=False,
converters=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skipfooter=0,
convert_float=True,
**kwds):
"""
Parse specified sheet(s) into a DataFrame
Equivalent to read_excel(ExcelFile, ...) See the read_excel
docstring for more info on accepted parameters
"""
# Can't use _deprecate_kwarg since sheetname=None has a special meaning
if is_integer(sheet_name) and sheet_name == 0 and 'sheetname' in kwds:
warnings.warn("The `sheetname` keyword is deprecated, use "
"`sheet_name` instead", FutureWarning, stacklevel=2)
sheet_name = kwds.pop("sheetname")
elif 'sheetname' in kwds:
raise TypeError("Cannot specify both `sheet_name` "
"and `sheetname`. Use just `sheet_name`")
return self._parse_excel(sheet_name=sheet_name,
header=header,
names=names,
index_col=index_col,
usecols=usecols,
squeeze=squeeze,
converters=converters,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
convert_float=convert_float,
**kwds)
def _should_parse(self, i, usecols):
def _range2cols(areas):
"""
Convert comma separated list of column names and column ranges to a
list of 0-based column indexes.
>>> _range2cols('A:E')
[0, 1, 2, 3, 4]
>>> _range2cols('A,C,Z:AB')
[0, 2, 25, 26, 27]
"""
def _excel2num(x):
"Convert Excel column name like 'AB' to 0-based column index"
return reduce(lambda s, a: s * 26 + ord(a) - ord('A') + 1,
x.upper().strip(), 0) - 1
cols = []
for rng in areas.split(','):
if ':' in rng:
rng = rng.split(':')
cols += lrange(_excel2num(rng[0]), _excel2num(rng[1]) + 1)
else:
cols.append(_excel2num(rng))
return cols
if isinstance(usecols, int):
return i <= usecols
elif isinstance(usecols, compat.string_types):
return i in _range2cols(usecols)
else:
return i in usecols
def _parse_excel(self,
sheet_name=0,
header=0,
names=None,
index_col=None,
usecols=None,
squeeze=False,
dtype=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
verbose=False,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skipfooter=0,
convert_float=True,
**kwds):
_validate_header_arg(header)
if 'chunksize' in kwds:
raise NotImplementedError("chunksize keyword of read_excel "
"is not implemented")
if parse_dates is True and index_col is None:
warnings.warn("The 'parse_dates=True' keyword of read_excel was "
"provided without an 'index_col' keyword value.")
import xlrd
from xlrd import (xldate, XL_CELL_DATE,
XL_CELL_ERROR, XL_CELL_BOOLEAN,
XL_CELL_NUMBER)
epoch1904 = self.book.datemode
def _parse_cell(cell_contents, cell_typ):
"""converts the contents of the cell into a pandas
appropriate object"""
if cell_typ == XL_CELL_DATE:
if xlrd_0_9_3:
# Use the newer xlrd datetime handling.
try:
cell_contents = \
xldate.xldate_as_datetime(cell_contents,
epoch1904)
except OverflowError:
return cell_contents
# Excel doesn't distinguish between dates and time,
# so we treat dates on the epoch as times only.
# Also, Excel supports 1900 and 1904 epochs.
year = (cell_contents.timetuple())[0:3]
if ((not epoch1904 and year == (1899, 12, 31)) or
(epoch1904 and year == (1904, 1, 1))):
cell_contents = time(cell_contents.hour,
cell_contents.minute,
cell_contents.second,
cell_contents.microsecond)
else:
# Use the xlrd <= 0.9.2 date handling.
try:
dt = xldate.xldate_as_tuple(cell_contents, epoch1904)
except xldate.XLDateTooLarge:
return cell_contents
if dt[0] < MINYEAR:
cell_contents = time(*dt[3:])
else:
cell_contents = datetime(*dt)
elif cell_typ == XL_CELL_ERROR:
cell_contents = np.nan
elif cell_typ == XL_CELL_BOOLEAN:
cell_contents = bool(cell_contents)
elif convert_float and cell_typ == XL_CELL_NUMBER:
# GH5394 - Excel 'numbers' are always floats
# it's a minimal perf hit and less surprising
val = int(cell_contents)
if val == cell_contents:
cell_contents = val
return cell_contents
# xlrd >= 0.9.3 can return datetime objects directly.
if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
xlrd_0_9_3 = True
else:
xlrd_0_9_3 = False
ret_dict = False
# Keep sheetname to maintain backwards compatibility.
if isinstance(sheet_name, list):
sheets = sheet_name
ret_dict = True
elif sheet_name is None:
sheets = self.sheet_names
ret_dict = True
else:
sheets = [sheet_name]
# handle same-type duplicates.
sheets = list(OrderedDict.fromkeys(sheets).keys())
output = OrderedDict()
for asheetname in sheets:
if verbose:
print("Reading sheet {sheet}".format(sheet=asheetname))
if isinstance(asheetname, compat.string_types):
sheet = self.book.sheet_by_name(asheetname)
else: # assume an integer if not a string
sheet = self.book.sheet_by_index(asheetname)
data = []
should_parse = {}
for i in range(sheet.nrows):
row = []
for j, (value, typ) in enumerate(zip(sheet.row_values(i),
sheet.row_types(i))):
if usecols is not None and j not in should_parse:
should_parse[j] = self._should_parse(j, usecols)
if usecols is None or should_parse[j]:
row.append(_parse_cell(value, typ))
data.append(row)
if sheet.nrows == 0:
output[asheetname] = DataFrame()
continue
if is_list_like(header) and len(header) == 1:
header = header[0]
# forward fill and pull out names for MultiIndex column
header_names = None
if header is not None:
if is_list_like(header):
header_names = []
control_row = [True for x in data[0]]
for row in header:
if is_integer(skiprows):
row += skiprows
data[row], control_row = _fill_mi_header(
data[row], control_row)
header_name, data[row] = _pop_header_name(
data[row], index_col)
header_names.append(header_name)
else:
data[header] = _trim_excel_header(data[header])
if is_list_like(index_col):
# forward fill values for MultiIndex index
if not is_list_like(header):
offset = 1 + header
else:
offset = 1 + max(header)
for col in index_col:
last = data[offset][col]
for row in range(offset + 1, len(data)):
if data[row][col] == '' or data[row][col] is None:
data[row][col] = last
else:
last = data[row][col]
has_index_names = is_list_like(header) and len(header) > 1
# GH 12292 : error when read one empty column from excel file
try:
parser = TextParser(data,
header=header,
index_col=index_col,
has_index_names=has_index_names,
squeeze=squeeze,
dtype=dtype,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
**kwds)
output[asheetname] = parser.read(nrows=nrows)
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)
except EmptyDataError:
# No Data, return an empty DataFrame
output[asheetname] = DataFrame()
if ret_dict:
return output
else:
return output[asheetname]
@property
def sheet_names(self):
return self.book.sheet_names()
def close(self):
"""close io if necessary"""
if hasattr(self.io, 'close'):
self.io.close()
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
def _validate_freeze_panes(freeze_panes):
if freeze_panes is not None:
if (
len(freeze_panes) == 2 and
all(isinstance(item, int) for item in freeze_panes)
):
return True
raise ValueError("freeze_panes must be of form (row, column)"
" where row and column are integers")
# freeze_panes wasn't specified, return False so it won't be applied
# to output sheet
return False
def _trim_excel_header(row):
# trim header row so auto-index inference works
# xlrd uses '' , openpyxl None
while len(row) > 0 and (row[0] == '' or row[0] is None):
row = row[1:]
return row
def _fill_mi_header(row, control_row):
"""Forward fills blank entries in row, but only inside the same parent index
Used for creating headers in Multiindex.
Parameters
----------
row : list
List of items in a single row.
control_row : list of boolean
Helps to determine if particular column is in same parent index as the
previous value. Used to stop propagation of empty cells between
different indexes.
Returns
----------
Returns changed row and control_row
"""
last = row[0]
for i in range(1, len(row)):
if not control_row[i]:
last = row[i]
if row[i] == '' or row[i] is None:
row[i] = last
else:
control_row[i] = False
last = row[i]
return row, control_row
# fill blank if index_col not None
def _pop_header_name(row, index_col):
""" (header, new_data) for header rows in MultiIndex parsing"""
none_fill = lambda x: None if x == '' else x
if index_col is None:
# no index col specified, trim data for inference path
return none_fill(row[0]), row[1:]
else:
# pop out header name and fill w/ blank
i = index_col if not is_list_like(index_col) else max(index_col)
return none_fill(row[i]), row[:i] + [''] + row[i + 1:]
@add_metaclass(abc.ABCMeta)
class ExcelWriter(object):
"""
Class for writing DataFrame objects into excel sheets, default is to use
xlwt for xls, openpyxl for xlsx. See DataFrame.to_excel for typical usage.
Parameters
----------
path : string
Path to xls or xlsx file.
engine : string (optional)
Engine to use for writing. If None, defaults to
``io.excel.<extension>.writer``. NOTE: can only be passed as a keyword
argument.
date_format : string, default None
Format string for dates written into Excel files (e.g. 'YYYY-MM-DD')
datetime_format : string, default None
Format string for datetime objects written into Excel files
(e.g. 'YYYY-MM-DD HH:MM:SS')
mode : {'w' or 'a'}, default 'w'
File mode to use (write or append).
.. versionadded:: 0.24.0
Notes
-----
For compatibility with CSV writers, ExcelWriter serializes lists
and dicts to strings before writing.
"""
# Defining an ExcelWriter implementation (see abstract methods for more...)
# - Mandatory
# - ``write_cells(self, cells, sheet_name=None, startrow=0, startcol=0)``
# --> called to write additional DataFrames to disk
# - ``supported_extensions`` (tuple of supported extensions), used to
# check that engine supports the given extension.
# - ``engine`` - string that gives the engine name. Necessary to
# instantiate class directly and bypass ``ExcelWriterMeta`` engine
# lookup.
# - ``save(self)`` --> called to save file to disk
# - Mostly mandatory (i.e. should at least exist)
# - book, cur_sheet, path
# - Optional:
# - ``__init__(self, path, engine=None, **kwargs)`` --> always called
# with path as first argument.
# You also need to register the class with ``register_writer()``.
# Technically, ExcelWriter implementations don't need to subclass
# ExcelWriter.
def __new__(cls, path, engine=None, **kwargs):
# only switch class if generic(ExcelWriter)
if issubclass(cls, ExcelWriter):
if engine is None or (isinstance(engine, string_types) and
engine == 'auto'):
if isinstance(path, string_types):
ext = os.path.splitext(path)[-1][1:]
else:
ext = 'xlsx'
try:
engine = config.get_option('io.excel.{ext}.writer'
.format(ext=ext))
if engine == 'auto':
engine = _get_default_writer(ext)
except KeyError:
error = ValueError("No engine for filetype: '{ext}'"
.format(ext=ext))
raise error
cls = get_writer(engine)
return object.__new__(cls)
# declare external properties you can count on
book = None
curr_sheet = None
path = None
@abc.abstractproperty
def supported_extensions(self):
"extensions that writer engine supports"
pass
@abc.abstractproperty
def engine(self):
"name of engine"
pass
@abc.abstractmethod
def write_cells(self, cells, sheet_name=None, startrow=0, startcol=0,
freeze_panes=None):
"""
Write given formatted cells into Excel an excel sheet
Parameters
----------
cells : generator
cell of formatted data to save to Excel sheet
sheet_name : string, default None
Name of Excel sheet, if None, then use self.cur_sheet
startrow: upper left cell row to dump data frame
startcol: upper left cell column to dump data frame
freeze_panes: integer tuple of length 2
contains the bottom-most row and right-most column to freeze
"""
pass
@abc.abstractmethod
def save(self):
"""
Save workbook to disk.
"""
pass
def __init__(self, path, engine=None,
date_format=None, datetime_format=None, mode='w',
**engine_kwargs):
# validate that this engine can handle the extension
if isinstance(path, string_types):
ext = os.path.splitext(path)[-1]
else:
ext = 'xls' if engine == 'xlwt' else 'xlsx'
self.check_extension(ext)
self.path = path
self.sheets = {}
self.cur_sheet = None
if date_format is None:
self.date_format = 'YYYY-MM-DD'
else:
self.date_format = date_format
if datetime_format is None:
self.datetime_format = 'YYYY-MM-DD HH:MM:SS'
else:
self.datetime_format = datetime_format
self.mode = mode
def __fspath__(self):
return _stringify_path(self.path)
def _get_sheet_name(self, sheet_name):
if sheet_name is None:
sheet_name = self.cur_sheet
if sheet_name is None: # pragma: no cover
raise ValueError('Must pass explicit sheet_name or set '
'cur_sheet property')
return sheet_name
def _value_with_fmt(self, val):
"""Convert numpy types to Python types for the Excel writers.
Parameters
----------
val : object
Value to be written into cells
Returns
-------
Tuple with the first element being the converted value and the second
being an optional format
"""
fmt = None
if is_integer(val):
val = int(val)
elif is_float(val):
val = float(val)
elif is_bool(val):
val = bool(val)
elif isinstance(val, datetime):
fmt = self.datetime_format
elif isinstance(val, date):
fmt = self.date_format
elif isinstance(val, timedelta):
val = val.total_seconds() / float(86400)
fmt = '0'
else:
val = compat.to_str(val)
return val, fmt
@classmethod
def check_extension(cls, ext):
"""checks that path's extension against the Writer's supported
extensions. If it isn't supported, raises UnsupportedFiletypeError."""
if ext.startswith('.'):
ext = ext[1:]
if not any(ext in extension for extension in cls.supported_extensions):
msg = (u("Invalid extension for engine '{engine}': '{ext}'")
.format(engine=pprint_thing(cls.engine),
ext=pprint_thing(ext)))
raise ValueError(msg)
else:
return True
# Allow use as a contextmanager