Mercurial > repos > yufei-luo > s_mart

comparison smart_toolShed/SMART/Java/Python/GetRandomSubset.py @ 0:e0f8dcca02ed

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded S-MART tool. A toolbox manages RNA-Seq and ChIP-Seq data.
author yufei-luo
date Thu, 17 Jan 2013 10:52:14 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e0f8dcca02ed
1 #! /usr/bin/env python
2 #
3 # Copyright INRA-URGI 2009-2011
4 #
5 # This software is governed by the CeCILL license under French law and
6 # abiding by the rules of distribution of free software. You can use,
7 # modify and/ or redistribute the software under the terms of the CeCILL
8 # license as circulated by CEA, CNRS and INRIA at the following URL
9 # "http://www.cecill.info".
10 #
11 # As a counterpart to the access to the source code and rights to copy,
12 # modify and redistribute granted by the license, users are provided only
13 # with a limited warranty and the software's author, the holder of the
14 # economic rights, and the successive licensors have only limited
15 # liability.
16 #
17 # In this respect, the user's attention is drawn to the risks associated
18 # with loading, using, modifying and/or developing or reproducing the
19 # software by the user in light of its specific status of free software,
20 # that may mean that it is complicated to manipulate, and that also
21 # therefore means that it is reserved for developers and experienced
22 # professionals having in-depth computer knowledge. Users are therefore
23 # encouraged to load and test the software's suitability as regards their
24 # requirements in conditions enabling the security of their systems and/or
25 # data to be ensured and, more generally, to use and operate it in the
26 # same conditions as regards security.
27 #
28 # The fact that you are presently reading this means that you have had
29 # knowledge of the CeCILL license and that you accept its terms.
30 #
31 import random
32 from optparse import OptionParser
33 from commons.core.parsing.ParserChooser import ParserChooser
34 from commons.core.writer.TranscriptWriter import TranscriptWriter
35 from SMART.Java.Python.structure.Transcript import Transcript
36 from SMART.Java.Python.misc.Progress import Progress
37
38 class GetRandomSubset(object):
39
40 def __init__(self, verbosity):
41 self.verbosity = verbosity
42
43 def setInputFile(self, fileName, format):
44 chooser = ParserChooser(self.verbosity)
45 chooser.findFormat(format)
46 self.parser = chooser.getParser(fileName)
47
48 def setNumber(self, number, percent):
49 if number != None:
50 self.number = number
51 elif percent != None:
52 self.number = int(float(percent) / 100 * self.parser.getNbTranscripts())
53 else:
54 raise Exception("Error! Number of elements to output is not given!")
55
56 def setOutputFile(self, fileName):
57 self.writer = TranscriptWriter(fileName, "gff3", self.verbosity)
58
59 def chooseElements(self):
60 self.randomIndices = random.sample(range(self.parser.getNbTranscripts()), self.number)
61
62 def run(self):
63 self.chooseElements()
64 progress = Progress(self.parser.getNbTranscripts(), "Reading input file", self.verbosity)
65 nbWritten = 0
66 for cpt1, transcript in enumerate(self.parser.getIterator()):
67 if cpt1 in self.randomIndices:
68 self.writer.addTranscript(transcript)
69 nbWritten += 1
70 progress.inc()
71 self.writer.write()
72 self.writer.close()
73 progress.done()
74 if self.verbosity > 1:
75 print "%d transcripts read" % (self.parser.getNbTranscripts())
76 print "%d transcripts written" % (nbWritten)
77
78
79 if __name__ == "__main__":
80
81 description = "Get Random Subset v1.0.1: Get a random sub-set of a list of genomic coordinates. [Category: Personal]"
82
83 parser = OptionParser(description = description)
84 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="input file [compulsory] [format: file in transcript format given by -f]")
85 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of file [compulsory] [format: transcript file format]")
86 parser.add_option("-n", "--number", dest="number", action="store", default=None, type="string", help="number of elements to output [format: int]")
87 parser.add_option("-p", "--percent", dest="percent", action="store", default=None, type="string", help="percentage of elements to output (between 0 and 100) [format: int]")
88 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="output file [format: output file in GFF3 format]")
89 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
90 (options, args) = parser.parse_args()
91
92 grs = GetRandomSubset(options.verbosity)
93 grs.setInputFile(options.inputFileName, options.format)
94 grs.setNumber(options.number, options.percent)
95 grs.setOutputFile(options.outputFileName)
96 grs.run()