pandas.read_csv()报错OSError:Initializing from file failed

 运行代码如下:

import os 
import pandas as pd
import requests
PATH='F:/Machine Learning/Python-Machine-Learning-Blueprints(python机器学习实践指南)/Chapter 01/iris/'
r=requests.get('https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data')
with open(PATH+'iris.data','w') as f:
    f.write(r.text)
df=pd.read_csv(PATH+'iris.data', names=["sepal length", "sepal width", "petal length", "petal width", "class"])

结果报错: 

---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
 in ()
----> 1 df=pd.read_csv(PATH+'iris.data', names=["sepal length", "sepal width", "petal length", "petal width", "class"])

c:\users\administrator\appdata\local\programs\python\python36\lib\site-packages\pandas\io\parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)
    707                     skip_blank_lines=skip_blank_lines)
    708 
--> 709         return _read(filepath_or_buffer, kwds)
    710 
    711     parser_f.__name__ = name

c:\users\administrator\appdata\local\programs\python\python36\lib\site-packages\pandas\io\parsers.py in _read(filepath_or_buffer, kwds)
    447 
    448     # Create the parser.
--> 449     parser = TextFileReader(filepath_or_buffer, **kwds)
    450 
    451     if chunksize or iterator:

c:\users\administrator\appdata\local\programs\python\python36\lib\site-packages\pandas\io\parsers.py in __init__(self, f, engine, **kwds)
    816             self.options['has_index_names'] = kwds['has_index_names']
    817 
--> 818         self._make_engine(self.engine)
    819 
    820     def close(self):

c:\users\administrator\appdata\local\programs\python\python36\lib\site-packages\pandas\io\parsers.py in _make_engine(self, engine)
   1047     def _make_engine(self, engine='c'):
   1048         if engine == 'c':
-> 1049             self._engine = CParserWrapper(self.f, **self.options)
   1050         else:
   1051             if engine == 'python':

c:\users\administrator\appdata\local\programs\python\python36\lib\site-packages\pandas\io\parsers.py in __init__(self, src, **kwds)
   1693         kwds['allow_leading_cols'] = self.index_col is not False
   1694 
-> 1695         self._reader = parsers.TextReader(src, **kwds)
   1696 
   1697         # XXX

pandas\_libs\parsers.pyx in pandas._libs.parsers.TextReader.__cinit__()

pandas\_libs\parsers.pyx in pandas._libs.parsers.TextReader._setup_parser_source()

OSError: Initializing from file failed

路径、文件名都完整。错误提示1048,发现调用pandas的read_csv()方法时,默认使用C engine,当文件路径中包含中文名时,使用C engine会报错。将engine改为python,即可解决此问题。

解决方法:指明engine为python

df=pd.read_csv(path, names=["sepal length", "sepal width", "petal length", "petal width", "class"],\
               engine = 'python')# 指明engine为Python

 

 

你可能感兴趣的:(python,pandas)