Description
See PR: #13233 and pandas/io/tests/parser/usecols.py test_usecols_with_multibyte_unicode_characters
Code Sample, a copy-pastable example if possible
import pandas as pd
from pandas.compat import StringIO
s = '''あああ,いい,ううう,ええええ
0.056674973,8,True,a
2.613230982,2,False,b
3.568935038,7,False,a
'''
data = {
'あああ': {
0: 0.056674972999999997,
1: 2.6132309819999997,
2: 3.5689350380000002
},
'いい': {0: 8, 1: 2, 2: 7}
}
expected = pd.DataFrame(data)
df = pd.read_csv(StringIO(s), usecols=[u'あああ', u'いい'])>>> df = pd.read_csv(StringIO(s), usecols=[u'あああ', u'いい'])
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "pandas/io/parsers.py", line 562, in parser_f
return _read(filepath_or_buffer, kwds)
File "pandas/io/parsers.py", line 315, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
File "pandas/io/parsers.py", line 645, in __init__
self._make_engine(self.engine)
File "pandas/io/parsers.py", line 799, in _make_engine
self._engine = CParserWrapper(self.f, **self.options)
File "pandas/io/parsers.py", line 1263, in __init__
raise ValueError("Usecols do not match names.")
ValueError: Usecols do not match names.
>>> df = pd.read_csv(StringIO(s), usecols=[u'あああ', u'いい'], engine='python')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "pandas/io/parsers.py", line 562, in parser_f
return _read(filepath_or_buffer, kwds)
File "pandas/io/parsers.py", line 315, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
File "pandas/io/parsers.py", line 645, in __init__
self._make_engine(self.engine)
File "pandas/io/parsers.py", line 805, in _make_engine
self._engine = klass(self.f, **self.options)
File "pandas/io/parsers.py", line 1609, in __init__
self.columns, self.num_original_columns = self._infer_columns()
File "pandas/io/parsers.py", line 1905, in _infer_columns
columns = self._handle_usecols(columns, columns[0])
File "pandas/io/parsers.py", line 1958, in _handle_usecols
col_indices.append(usecols_key.index(u))
ValueError: u'\u3042\u3042\u3042' is not in list
Expected Output
あああ いい
0 0.056675 8
1 2.613231 2
2 3.568935 7
output of pd.show_versions()
INSTALLED VERSIONS
commit: 71f5139f14b38a1a3c1d9fd7d9219947399faec0
python: 2.7.11.final.0
python-bits: 64
OS: Darwin
OS-release: 15.3.0
machine: x86_64
processor: i386
byteorder: little
LC_ALL: None
LANG: en_US.UTF-8
pandas: 0.18.1+54.g71f5139.dirty
nose: 1.3.7
pip: 8.1.2
setuptools: 20.7.0
Cython: 0.24
numpy: 1.11.0
scipy: None
statsmodels: None
xarray: None
IPython: None
sphinx: None
patsy: None
dateutil: 2.5.3
pytz: 2016.4
blosc: None
bottleneck: None
tables: None
numexpr: None
matplotlib: None
openpyxl: None
xlrd: None
xlwt: None
xlsxwriter: None
lxml: None
bs4: None
html5lib: None
httplib2: None
apiclient: None
sqlalchemy: None
pymysql: None
psycopg2: None
jinja2: None
boto: None
pandas_datareader: None