Ch. 7 cell 57 data does not read

[vista888]

When I run movies = pd.read_table('datasets/movielens/movies.dat', sep='::', header=None, names=mnames)
I get the following error:

UnicodeDecodeError                        Traceback (most recent call last)
/var/folders/31/mhwrpttd4_n27dn_wmgr4vqh0000gn/T/ipykernel_12218/3495340260.py in <module>
      1 mnames = ['movie_id', 'title', 'genres']
----> 2 movies = pd.read_table('datasets/movielens/movies.dat', sep='::',
      3                        header=None, names=mnames)
      4 movies[:10]

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
    309                     stacklevel=stacklevel,
    310                 )
--> 311             return func(*args, **kwargs)
    312 
    313         return wrapper

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/readers.py in read_table(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, encoding_errors, delim_whitespace, low_memory, memory_map, float_precision)
    681     kwds.update(kwds_defaults)
    682 
--> 683     return _read(filepath_or_buffer, kwds)
    684 
    685 

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/readers.py in _read(filepath_or_buffer, kwds)
    480 
    481     # Create the parser.
--> 482     parser = TextFileReader(filepath_or_buffer, **kwds)
    483 
    484     if chunksize or iterator:

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/readers.py in __init__(self, f, engine, **kwds)
    809             self.options["has_index_names"] = kwds["has_index_names"]
    810 
--> 811         self._engine = self._make_engine(self.engine)
    812 
    813     def close(self):

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/readers.py in _make_engine(self, engine)
   1038             )
   1039         # error: Too many arguments for "ParserBase"
-> 1040         return mapping[engine](self.f, **self.options)  # type: ignore[call-arg]
   1041 
   1042     def _failover_to_python(self):

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in __init__(self, f, **kwds)
    110                 self.num_original_columns,
    111                 self.unnamed_cols,
--> 112             ) = self._infer_columns()
    113         except (TypeError, ValueError):
    114             self.close()

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in _infer_columns(self)
    490         else:
    491             try:
--> 492                 line = self._buffered_line()
    493 
    494             except StopIteration as err:

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in _buffered_line(self)
    582             return self.buf[0]
    583         else:
--> 584             return self._next_line()
    585 
    586     def _check_for_bom(self, first_row):

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in _next_line(self)
    679 
    680             while True:
--> 681                 orig_line = self._next_iter_line(row_num=self.pos + 1)
    682                 self.pos += 1
    683 

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in _next_iter_line(self, row_num)
    740             # assert for mypy, data is Iterator[str] or None, would error in next
    741             assert self.data is not None
--> 742             return next(self.data)
    743         except csv.Error as e:
    744             if (

~/.pyenv/versions/3.8.1/envs/tutorials/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py in _read()
    226 
    227             def _read():
--> 228                 line = f.readline()
    229                 pat = re.compile(sep)
    230 

~/.pyenv/versions/3.8.1/lib/python3.8/codecs.py in decode(self, input, final)
    320         # decode input (taking the buffer into account)
    321         data = self.buffer + input
--> 322         (result, consumed) = self._buffer_decode(data, self.errors, final)
    323         # keep undecoded input until the next call
    324         self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 3114: invalid continuation byte```

[Wes McKinney]

Try adding encoding='latin-1'. I will update the file in this repository with a utf-8-encoded version of the data

[vista888]

Thanks! That worked for me.

[Wes McKinney]

Fixed in e9f3eab