blob: be38032e6d1360dadea82c0bcdf269c02f20c88e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
# Copyright (c) 2017 Weitian LI <weitian@aaronly.me>
# MIT license
"""
Input/output utilities.
"""
import os
import logging
from datetime import datetime
import pandas as pd
logger = logging.getLogger(__name__)
def dataframe_to_csv(df, outfile, comment=None, clobber=False):
"""
Save the given Pandas DataFrame into a CSV text file.
Parameters
----------
df : `~pandas.DataFrame`
The DataFrame to be saved to the CSV text file.
outfile : string
The path to the output CSV file.
comment : list[str], optional
A list of comments to be prepended to the output CSV file header.
The prefix ``#`` is not required and will be automatically added.
clobber : bool, optional
Whether overwrite the existing output file?
Default: False
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("Not a Pandas DataFrame!")
# Create directory if necessary
dirname = os.path.dirname(outfile)
if not os.path.exists(dirname):
os.makedirs(dirname)
logger.info("Created output directory: {0}".format(dirname))
if os.path.exists(outfile):
if clobber:
logger.warning("Removed existing file: {0}".format(outfile))
os.remove(outfile)
else:
raise OSError("Output file exists: {0}".format(outfile))
# Add a default header comment
if comment is None:
comment = ["by %s" % __name__,
"at %s" % datetime.now().isoformat()]
with open(outfile, "w") as fh:
# Write header comments with ``#`` prefixed.
fh.write("".join(["# "+line.strip()+"\n" for line in comment]))
df.to_csv(fh, header=True, index=False)
logger.info("Wrote DataFrame to CSV file: {0}".format(outfile))
|
