UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte, while reading csv file in pandas
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte, while reading csv file in pandas
我知道已经有人问过类似的问题我已经看过所有这些问题并尝试过但帮助不大。我正在使用 OSX 10.11 El Capitan，python3.6.，虚拟环境，也没有尝试过。我正在使用 jupyter notebook 和 spyder3。
我是 python 的新手，但了解基本的 ML 并遵循 post 学习如何解决 Kaggle 挑战：Link to Blog, Link to Data Set
.我卡在了前几行代码
`
import pandas as pd
destinations = pd.read_csv("destinations.csv")
test = pd.read_csv("test.csv")
train = pd.read_csv("train.csv")
它给我错误
UnicodeDecodeError Traceback (most recent call last)
<ipython-input-19-a928a98eb1ff> in <module>()
1 import pandas as pd
----> 2 df = pd.read_csv('destinations.csv', compression='infer',date_parser=True, usecols=([0,1,3]))
3 df.head()
/usr/local/lib/python3.6/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)
653 skip_blank_lines=skip_blank_lines)
654
--> 655 return _read(filepath_or_buffer, kwds)
656
657 parser_f.__name__ = name
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
403
404 # Create the parser.
--> 405 parser = TextFileReader(filepath_or_buffer, **kwds)
406
407 if chunksize or iterator:
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
762 self.options['has_index_names'] = kwds['has_index_names']
763
--> 764 self._make_engine(self.engine)
765
766 def close(self):
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _make_engine(self, engine)
983 def _make_engine(self, engine='c'):
984 if engine == 'c':
--> 985 self._engine = CParserWrapper(self.f, **self.options)
986 else:
987 if engine == 'python':
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
1603 kwds['allow_leading_cols'] = self.index_col is not False
1604
-> 1605 self._reader = parsers.TextReader(src, **kwds)
1606
1607 # XXX
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__ (pandas/_libs/parsers.c:6175)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._get_header (pandas/_libs/parsers.c:9691)()
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte
stakoverflow 上的一些答案表明这是因为它是 gzip 压缩的，但是 Chrome 下载了 .csv 文件并且 .csv.gz 无处可见并返回文件未找到错误。
然后我在某处阅读以使用 encoding='latin1'，但在这样做之后我收到解析器错误：
---------------------------------------------------------------------------
ParserError Traceback (most recent call last)
<ipython-input-21-f9c451f864a2> in <module>()
1 import pandas as pd
2
----> 3 destinations = pd.read_csv("destinations.csv",encoding='latin1')
4 test = pd.read_csv("test.csv")
5 train = pd.read_csv("train.csv")
/usr/local/lib/python3.6/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)
653 skip_blank_lines=skip_blank_lines)
654
--> 655 return _read(filepath_or_buffer, kwds)
656
657 parser_f.__name__ = name
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
409
410 try:
--> 411 data = parser.read(nrows)
412 finally:
413 parser.close()
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
1003 raise ValueError('skipfooter not supported for iteration')
1004
-> 1005 ret = self._engine.read(nrows)
1006
1007 if self.options.get('as_recarray'):
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
1746 def read(self, nrows=None):
1747 try:
-> 1748 data = self._reader.read(nrows)
1749 except StopIteration:
1750 if self._first_chunk:
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.read (pandas/_libs/parsers.c:10862)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_low_memory (pandas/_libs/parsers.c:11138)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_rows (pandas/_libs/parsers.c:11884)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._tokenize_rows (pandas/_libs/parsers.c:11755)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.raise_parser_error (pandas/_libs/parsers.c:28765)()
ParserError: Error tokenizing data. C error: Expected 2 fields in line 11, saw 3
我花了几个小时调试它，尝试在 Atom 上打开 csv 文件（没有其他应用程序可以打开它），在线网络应用程序（有些崩溃）但没有人 help.I 尝试过使用其他人的内核已经解决了问题，但没有帮助。
你可以尝试使用编解码器吗
import codecs
with codecs.open("destinations.csv", "r",encoding='utf-8', errors='ignore') as file_dat:
destinations = pd.read_csv(file_data))
它仍然很可能是压缩数据。 gzip的幻数是0x1f 0x8b，和你得到的UnicodeDecodeError一致。
您可以尝试即时解压缩数据：
with open('destinations.csv', 'rb') as fd:
gzip_fd = gzip.GzipFile(fileobj=fd)
destinations = pd.read_csv(gzip_fd)
或使用 pandas' 内置 gzip 支持：
destinations = pd.read_csv('destinations.csv', compression='gzip')
尝试在读取 csv 文件时包含此编码
pd.read_csv('csv_file', encoding='ISO-8859–1')
我知道已经有人问过类似的问题我已经看过所有这些问题并尝试过但帮助不大。我正在使用 OSX 10.11 El Capitan，python3.6.，虚拟环境，也没有尝试过。我正在使用 jupyter notebook 和 spyder3。
我是 python 的新手，但了解基本的 ML 并遵循 post 学习如何解决 Kaggle 挑战：Link to Blog, Link to Data Set
.我卡在了前几行代码 `
import pandas as pd
destinations = pd.read_csv("destinations.csv")
test = pd.read_csv("test.csv")
train = pd.read_csv("train.csv")
它给我错误
UnicodeDecodeError Traceback (most recent call last)
<ipython-input-19-a928a98eb1ff> in <module>()
1 import pandas as pd
----> 2 df = pd.read_csv('destinations.csv', compression='infer',date_parser=True, usecols=([0,1,3]))
3 df.head()
/usr/local/lib/python3.6/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)
653 skip_blank_lines=skip_blank_lines)
654
--> 655 return _read(filepath_or_buffer, kwds)
656
657 parser_f.__name__ = name
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
403
404 # Create the parser.
--> 405 parser = TextFileReader(filepath_or_buffer, **kwds)
406
407 if chunksize or iterator:
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
762 self.options['has_index_names'] = kwds['has_index_names']
763
--> 764 self._make_engine(self.engine)
765
766 def close(self):
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _make_engine(self, engine)
983 def _make_engine(self, engine='c'):
984 if engine == 'c':
--> 985 self._engine = CParserWrapper(self.f, **self.options)
986 else:
987 if engine == 'python':
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
1603 kwds['allow_leading_cols'] = self.index_col is not False
1604
-> 1605 self._reader = parsers.TextReader(src, **kwds)
1606
1607 # XXX
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__ (pandas/_libs/parsers.c:6175)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._get_header (pandas/_libs/parsers.c:9691)()
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte
stakoverflow 上的一些答案表明这是因为它是 gzip 压缩的，但是 Chrome 下载了 .csv 文件并且 .csv.gz 无处可见并返回文件未找到错误。
然后我在某处阅读以使用 encoding='latin1'，但在这样做之后我收到解析器错误：
---------------------------------------------------------------------------
ParserError Traceback (most recent call last)
<ipython-input-21-f9c451f864a2> in <module>()
1 import pandas as pd
2
----> 3 destinations = pd.read_csv("destinations.csv",encoding='latin1')
4 test = pd.read_csv("test.csv")
5 train = pd.read_csv("train.csv")
/usr/local/lib/python3.6/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)
653 skip_blank_lines=skip_blank_lines)
654
--> 655 return _read(filepath_or_buffer, kwds)
656
657 parser_f.__name__ = name
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
409
410 try:
--> 411 data = parser.read(nrows)
412 finally:
413 parser.close()
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
1003 raise ValueError('skipfooter not supported for iteration')
1004
-> 1005 ret = self._engine.read(nrows)
1006
1007 if self.options.get('as_recarray'):
/usr/local/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
1746 def read(self, nrows=None):
1747 try:
-> 1748 data = self._reader.read(nrows)
1749 except StopIteration:
1750 if self._first_chunk:
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.read (pandas/_libs/parsers.c:10862)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_low_memory (pandas/_libs/parsers.c:11138)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_rows (pandas/_libs/parsers.c:11884)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._tokenize_rows (pandas/_libs/parsers.c:11755)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.raise_parser_error (pandas/_libs/parsers.c:28765)()
ParserError: Error tokenizing data. C error: Expected 2 fields in line 11, saw 3
我花了几个小时调试它，尝试在 Atom 上打开 csv 文件（没有其他应用程序可以打开它），在线网络应用程序（有些崩溃）但没有人 help.I 尝试过使用其他人的内核已经解决了问题，但没有帮助。
你可以尝试使用编解码器吗
import codecs
with codecs.open("destinations.csv", "r",encoding='utf-8', errors='ignore') as file_dat:
destinations = pd.read_csv(file_data))
它仍然很可能是压缩数据。 gzip的幻数是0x1f 0x8b，和你得到的UnicodeDecodeError一致。
您可以尝试即时解压缩数据：
with open('destinations.csv', 'rb') as fd:
gzip_fd = gzip.GzipFile(fileobj=fd)
destinations = pd.read_csv(gzip_fd)
或使用 pandas' 内置 gzip 支持：
destinations = pd.read_csv('destinations.csv', compression='gzip')
尝试在读取 csv 文件时包含此编码
pd.read_csv('csv_file', encoding='ISO-8859–1')