In [1]:
import pandas as pd
In [7]:
filename = "../data/auto-mpg.data"
column_names = ['mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'year', 'origin', 'name']
df = pd.read_csv(filename, delim_whitespace=True, names=column_names)
In [9]:
df.to_csv("../data/auto-mpg.csv")
In [20]:
filename = "../data/iris.data"
df = pd.read_csv(filename, header=False)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-20-0f4d9e66e72c> in <module>()
1 filename = "../data/iris.data"
----> 2 df = pd.read_csv(filename, header=False)
/opt/conda/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, doublequote, delim_whitespace, low_memory, memory_map, float_precision)
676 skip_blank_lines=skip_blank_lines)
677
--> 678 return _read(filepath_or_buffer, kwds)
679
680 parser_f.__name__ = name
/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
438
439 # Create the parser.
--> 440 parser = TextFileReader(filepath_or_buffer, **kwds)
441
442 if chunksize or iterator:
/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
780 # might mutate self.engine
781 self.engine = self._check_file_or_buffer(f, engine)
--> 782 self.options, self.engine = self._clean_options(options, engine)
783
784 if 'has_index_names' in kwds:
/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py in _clean_options(self, options, engine)
937 skiprows = options['skiprows']
938
--> 939 _validate_header_arg(options['header'])
940
941 depr_warning = ''
/opt/conda/lib/python3.6/site-packages/pandas/io/common.py in _validate_header_arg(header)
113 def _validate_header_arg(header):
114 if isinstance(header, bool):
--> 115 raise TypeError("Passing a bool to header is invalid. "
116 "Use header=None for no header or "
117 "header=int or list-like of ints to specify "
TypeError: Passing a bool to header is invalid. Use header=None for no header or header=int or list-like of ints to specify the row(s) making up the column names
In [19]:
df
Out[19]:
5.1
3.5
1.4
0.2
Iris-setosa
0
4.9
3.0
1.4
0.2
Iris-setosa
1
4.7
3.2
1.3
0.2
Iris-setosa
2
4.6
3.1
1.5
0.2
Iris-setosa
3
5.0
3.6
1.4
0.2
Iris-setosa
4
5.4
3.9
1.7
0.4
Iris-setosa
5
4.6
3.4
1.4
0.3
Iris-setosa
6
5.0
3.4
1.5
0.2
Iris-setosa
7
4.4
2.9
1.4
0.2
Iris-setosa
8
4.9
3.1
1.5
0.1
Iris-setosa
9
5.4
3.7
1.5
0.2
Iris-setosa
10
4.8
3.4
1.6
0.2
Iris-setosa
11
4.8
3.0
1.4
0.1
Iris-setosa
12
4.3
3.0
1.1
0.1
Iris-setosa
13
5.8
4.0
1.2
0.2
Iris-setosa
14
5.7
4.4
1.5
0.4
Iris-setosa
15
5.4
3.9
1.3
0.4
Iris-setosa
16
5.1
3.5
1.4
0.3
Iris-setosa
17
5.7
3.8
1.7
0.3
Iris-setosa
18
5.1
3.8
1.5
0.3
Iris-setosa
19
5.4
3.4
1.7
0.2
Iris-setosa
20
5.1
3.7
1.5
0.4
Iris-setosa
21
4.6
3.6
1.0
0.2
Iris-setosa
22
5.1
3.3
1.7
0.5
Iris-setosa
23
4.8
3.4
1.9
0.2
Iris-setosa
24
5.0
3.0
1.6
0.2
Iris-setosa
25
5.0
3.4
1.6
0.4
Iris-setosa
26
5.2
3.5
1.5
0.2
Iris-setosa
27
5.2
3.4
1.4
0.2
Iris-setosa
28
4.7
3.2
1.6
0.2
Iris-setosa
29
4.8
3.1
1.6
0.2
Iris-setosa
...
...
...
...
...
...
119
6.9
3.2
5.7
2.3
Iris-virginica
120
5.6
2.8
4.9
2.0
Iris-virginica
121
7.7
2.8
6.7
2.0
Iris-virginica
122
6.3
2.7
4.9
1.8
Iris-virginica
123
6.7
3.3
5.7
2.1
Iris-virginica
124
7.2
3.2
6.0
1.8
Iris-virginica
125
6.2
2.8
4.8
1.8
Iris-virginica
126
6.1
3.0
4.9
1.8
Iris-virginica
127
6.4
2.8
5.6
2.1
Iris-virginica
128
7.2
3.0
5.8
1.6
Iris-virginica
129
7.4
2.8
6.1
1.9
Iris-virginica
130
7.9
3.8
6.4
2.0
Iris-virginica
131
6.4
2.8
5.6
2.2
Iris-virginica
132
6.3
2.8
5.1
1.5
Iris-virginica
133
6.1
2.6
5.6
1.4
Iris-virginica
134
7.7
3.0
6.1
2.3
Iris-virginica
135
6.3
3.4
5.6
2.4
Iris-virginica
136
6.4
3.1
5.5
1.8
Iris-virginica
137
6.0
3.0
4.8
1.8
Iris-virginica
138
6.9
3.1
5.4
2.1
Iris-virginica
139
6.7
3.1
5.6
2.4
Iris-virginica
140
6.9
3.1
5.1
2.3
Iris-virginica
141
5.8
2.7
5.1
1.9
Iris-virginica
142
6.8
3.2
5.9
2.3
Iris-virginica
143
6.7
3.3
5.7
2.5
Iris-virginica
144
6.7
3.0
5.2
2.3
Iris-virginica
145
6.3
2.5
5.0
1.9
Iris-virginica
146
6.5
3.0
5.2
2.0
Iris-virginica
147
6.2
3.4
5.4
2.3
Iris-virginica
148
5.9
3.0
5.1
1.8
Iris-virginica
149 rows × 5 columns
Content source: f-guitart/data_mining
Similar notebooks: