У меня возникли проблемы при чтении данных из файла Excel.Файл Excel содержит имена столбцов с символами Юникода.
Из-за некоторых причин автоматизации мне нужно передать аргумент usecols в функцию pandas.read_excel.
Дело в том, что когда я не использую аргумент usecols , данные загружаются без ошибок.
Вот код:
import pandas as pd
df = pd.read_excel(file)
df.colums
Index([u'col1', u'col2', u'col3', u'col with unicode à', u'col4'], dtype='object')
Если я использую usecols:
COLUMNS = ['col1', 'col2', 'col with unicode à']
df = pd.read_excel(file, usecols = COLUMNS)
Я получаю следующую ошибку:
ValueError: Usecols do not match columns, columns expected but not found: ['col with unicode \xc3\xa0']
Использование encoding = 'utf-8' в качестве аргумента read_excel не решает проблему, а также кодирование элементов COLUMNS.
РЕДАКТИРОВАТЬ: Здесь полное окно ошибки.
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-22-541ccb88da6a> in <module>()
2 df = pd.read_excel(file)
3 cols = df.columns
----> 4 df = pd.read_excel(file, usecols = ['col1', 'col2', 'col with unicode à'])
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\util\_decorators.pyc in wrapper(*args, **kwargs)
186 else:
187 kwargs[new_arg_name] = new_arg_value
--> 188 return func(*args, **kwargs)
189 return wrapper
190 return _deprecate_kwarg
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\util\_decorators.pyc in wrapper(*args, **kwargs)
186 else:
187 kwargs[new_arg_name] = new_arg_value
--> 188 return func(*args, **kwargs)
189 return wrapper
190 return _deprecate_kwarg
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\excel.pyc in read_excel(io, sheet_name, header, names, index_col, parse_cols, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, verbose, parse_dates, date_parser, thousands, comment, skip_footer, skipfooter, convert_float, mangle_dupe_cols, **kwds)
373 convert_float=convert_float,
374 mangle_dupe_cols=mangle_dupe_cols,
--> 375 **kwds)
376
377
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\excel.pyc in parse(self, sheet_name, header, names, index_col, usecols, squeeze, converters, true_values, false_values, skiprows, nrows, na_values, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
716 convert_float=convert_float,
717 mangle_dupe_cols=mangle_dupe_cols,
--> 718 **kwds)
719
720 @property
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\excel.pyc in parse(self, sheet_name, header, names, index_col, usecols, squeeze, dtype, true_values, false_values, skiprows, nrows, na_values, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
599 usecols=usecols,
600 mangle_dupe_cols=mangle_dupe_cols,
--> 601 **kwds)
602
603 output[asheetname] = parser.read(nrows=nrows)
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in TextParser(*args, **kwds)
2154 """
2155 kwds['engine'] = 'python'
-> 2156 return TextFileReader(*args, **kwds)
2157
2158
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in __init__(self, f, engine, **kwds)
893 self.options['has_index_names'] = kwds['has_index_names']
894
--> 895 self._make_engine(self.engine)
896
897 def close(self):
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in _make_engine(self, engine)
1130 ' "c", "python", or' ' "python-fwf")'.format(
1131 engine=engine))
-> 1132 self._engine = klass(self.f, **self.options)
1133
1134 def _failover_to_python(self):
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in __init__(self, f, **kwds)
2236 self._col_indices = None
2237 (self.columns, self.num_original_columns,
-> 2238 self.unnamed_cols) = self._infer_columns()
2239
2240 # Now self.columns has the set of columns that we will process.
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in _infer_columns(self)
2609 columns = [names]
2610 else:
-> 2611 columns = self._handle_usecols(columns, columns[0])
2612 else:
2613 try:
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in _handle_usecols(self, columns, usecols_key)
2669 col_indices.append(usecols_key.index(col))
2670 except ValueError:
-> 2671 _validate_usecols_names(self.usecols, usecols_key)
2672 else:
2673 col_indices.append(col)
C:\Users\GiacomoSachs\Anaconda2\lib\site-packages\pandas\io\parsers.pyc in _validate_usecols_names(usecols, names)
1235 raise ValueError(
1236 "Usecols do not match columns, "
-> 1237 "columns expected but not found: {missing}".format(missing=missing)
1238 )
1239
ValueError: Usecols do not match columns, columns expected but not found: ['col with unicode \xc3\xa0']