Last active
September 26, 2016 20:15
-
-
Save jcausey-astate/10f579694dd3470c4c6b3a4dad1fdee1 to your computer and use it in GitHub Desktop.
Given a CSV or tab-delimited input file (ASCII-encoding), replace all missing values or all occurances of a specified value with a new marker. Useful for large scientific data where some values are missing (i.e. gene microarrays, etc).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! /usr/bin/env python | |
################################################################################################### | |
# Given a CSV or tab-delimited input file (ASCII-encoding), replace all | |
# missing values or all occurances of a specified value with a new marker. | |
# Useful for large scientific data where some values are missing (i.e. gene | |
# microarrays, etc) | |
# | |
# The MIT License (MIT) | |
# | |
# Copyright (c) 2016 Jason L Causey, Arkansas State University | |
# | |
# Permission is hereby granted, free of charge, to any person obtaining a copy | |
# of this software and associated documentation files (the "Software"), to deal | |
# in the Software without restriction, including without limitation the rights | |
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |
# copies of the Software, and to permit persons to whom the Software is | |
# furnished to do so, subject to the following conditions: | |
# | |
# The above copyright notice and this permission notice shall be included in all | |
# copies or substantial portions of the Software. | |
# | |
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | |
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | |
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | |
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | |
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | |
# SOFTWARE. | |
################################################################################################### | |
usage = """ | |
Usage: | |
{0} ascii_matrix_file [--help] [--missing=MISSING-MARKER] [--fill=FILL-MARKER] [--output=OUTPUT-FILE] | |
Fill all instances of MISSING-MARKER in an ASCII-format (CSV or tab-delimited) | |
matrix or table with the value specified by MISSING-FILL | |
ascii_matrix_file - a CSV or tab-delimited file in ASCII encoding | |
--help - show this help message and exit | |
--missing=MISSING-MARKER - MISSING-MARKER is the value in input file that currently | |
marks "missing value" locations. | |
Default is '' (no value at all) - literally missing. | |
--fill=FILL-MARKER - FILL-MARKER is the value to place in output file for | |
all missing locations. | |
Default is 0. | |
--output=OUTPUT-FILE - direct output to OUTPUT-FILE instead of stdout | |
Default output is to stdout | |
""" | |
import sys, csv, os | |
def usage(code=0): | |
print(usage.format(os.path.basename(sys.argv[0]))) | |
if code != None: | |
sys.exit(code) | |
if len(sys.argv) < 2: | |
usage(1) | |
inname = sys.argv[1] | |
outname = None | |
missing_ch = '' | |
fill_value = '0' | |
ids_file = None | |
ids = None | |
if len(sys.argv) > 2: | |
for i in range(2, 6): | |
if len(sys.argv) > i and sys.argv[i][0:3] == '--h': | |
usage(0) | |
if len(sys.argv) > i and sys.argv[i].split('=')[0] == '--missing': | |
missing_ch = sys.argv[i].split('=')[1] | |
if len(sys.argv) > i and sys.argv[i].split('=')[0] == '--fill': | |
fill_value = sys.argv[i].split('=')[1] | |
if len(sys.argv) > i and sys.argv[i].split('=')[0] == '--output': | |
outname = sys.argv[i].split('=')[1] | |
of = sys.stdout | |
with open(inname, 'rb') as csvfile: | |
dialect = csv.Sniffer().sniff(csvfile.read(8*1024)) | |
csvfile.seek(0) | |
reader = csv.reader(csvfile, dialect) | |
if outname != None: | |
of = open(outname, 'wb') | |
writer = csv.writer(of, dialect) | |
for line in reader: | |
line = [fill_value if v == missing_ch else v for v in line] | |
writer.writerow(line) | |
if outname != None: | |
of.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment