Mercurial > repos > sblanck > mpagenomics_normalize
comparison preprocess.py @ 0:a89bae08bf2d
Uploaded
| author | sblanck |
|---|---|
| date | Mon, 27 Apr 2015 05:48:52 -0400 |
| parents | |
| children | 4d25dec9707e |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:a89bae08bf2d |
|---|---|
| 1 import os | |
| 2 import re | |
| 3 import shutil | |
| 4 import sys | |
| 5 import subprocess | |
| 6 import zipfile | |
| 7 import optparse | |
| 8 | |
| 9 def main(): | |
| 10 | |
| 11 parser = optparse.OptionParser() | |
| 12 parser.add_option('-s', action="store", dest='summary') | |
| 13 parser.add_option('-p', action="store", dest='new_file_path') | |
| 14 parser.add_option('-c', action="store", dest='inputcdffull_name') | |
| 15 parser.add_option('-f', action="store", dest='inputufl_name') | |
| 16 parser.add_option('-g', action="store", dest='inputugp_name') | |
| 17 parser.add_option('-a', action="store", dest='inputacs_name') | |
| 18 parser.add_option('-d', action="store", dest='inputcdffull') | |
| 19 parser.add_option('-v', action="store", dest='inputufl') | |
| 20 parser.add_option('-h', action="store", dest='inputugp') | |
| 21 parser.add_option('-b', action="store", dest='inputacs') | |
| 22 parser.add_option('-t', action="store", dest='tumorcsv') | |
| 23 parser.add_option('-y', action="store", dest='settingsType') | |
| 24 parser.add_option('-o', action="store", dest='outputgraph') | |
| 25 parser.add_option('-z', action="store", dest='zipfigures') | |
| 26 parser.add_option('-k', action="store", dest='outputlog') | |
| 27 parser.add_option('-l', action="store", dest='log') | |
| 28 parser.add_option('-u', action="store", dest='user_id') | |
| 29 | |
| 30 parser.add_option('-i', action="append", dest='inputFile', default=[]) | |
| 31 parser.add_option('-n', action='append', dest='inputFileName', default=[]) | |
| 32 | |
| 33 options, args = parser.parse_args() | |
| 34 outputFileName=options.outputFile | |
| 35 | |
| 36 print options.inputFile | |
| 37 print options.inputFileName | |
| 38 | |
| 39 dataSetName="dataset" | |
| 40 destinationPath=os.path.join(options.new_file_path, user, dataset) | |
| 41 | |
| 42 mpagenomics_dir = os.path.join(destinationPath,"mpagenomics",user) | |
| 43 data_dir = os.path.join(options.new_file_path, user) | |
| 44 | |
| 45 try: | |
| 46 os.makedirs(data_dir) | |
| 47 except: | |
| 48 shutil.rmtree(data_dir) | |
| 49 os.makedirs(data_dir) | |
| 50 | |
| 51 if (not os.path.isdir(mpagenomics_dir)): | |
| 52 os.makedirs(mpagenomics_dir) | |
| 53 | |
| 54 for inputFile, inputFileName in zip(options.inputFile,options.inputFileName): | |
| 55 source = inputFile | |
| 56 destination=os.path.join(data_dir,inputFileName) | |
| 57 os.symlink(source,destination) | |
| 58 | |
| 59 if (cdffull_name.count(",") != 0): | |
| 60 chipType=cdffull_name.split(",",1)[0] | |
| 61 tagExt=cdffull_name.split(",",1)[1] | |
| 62 tag=tagExt.split(".",1)[0] | |
| 63 else: | |
| 64 chipType=cdffull_name.split(".",1)[0] | |
| 65 tag="" | |
| 66 | |
| 67 _copy(cdffull,os.path.join(data_dir, cdffull_name)) | |
| 68 _copy(ugp,os.path.join(data_dir, ugp_name)) | |
| 69 _copy(ufl,os.path.join(data_dir, ufl_name)) | |
| 70 _copy(acs,os.path.join(data_dir, acs_name)) | |
| 71 | |
| 72 | |
| 73 fig_dir = os.path.join("mpagenomics", user, "figures", dataset, "signal") | |
| 74 abs_fig_dir = os.path.join(new_files_directory, fig_dir) | |
| 75 | |
| 76 | |
| 77 retcode = _preprocess(chipType, dataSetName, mpagenomics_dir, data_dir, options.new_file_path, options.tumorcsv, options.settingType, options.outputgraph, options.outputlog, options.log, tag) | |
| 78 | |
| 79 if (retcode == 0): | |
| 80 if (os.path.isdir(abs_fig_dir)) and (outputgraph == "TRUE"): | |
| 81 | |
| 82 new_files = os.listdir(abs_fig_dir) | |
| 83 zipbuf = zipfile.ZipFile(os.path.join(abs_fig_dir, zipfigures), 'w', zipfile.ZIP_DEFLATED) | |
| 84 for current_file in new_files: | |
| 85 fn = os.path.join(abs_fig_dir, current_file) | |
| 86 relfn = fn[len(abs_fig_dir) + len(os.sep):] | |
| 87 zipbuf.write(fn, relfn) | |
| 88 | |
| 89 f = open(report, "w") | |
| 90 # Create report | |
| 91 try: | |
| 92 for name in extra_file_names: | |
| 93 f.write("%s\t%s\t%s\n" %(re.match(r"^\d+_task_(.*).dat$", name).group(1),dataset,chipType)) | |
| 94 finally: | |
| 95 shutil.rmtree(data_dir) | |
| 96 f.close() | |
| 97 | |
| 98 sys.exit(retcode) | |
| 99 | |
| 100 sys.exit(retcode) | |
| 101 | |
| 102 | |
| 103 def _copy(source, destination): | |
| 104 try: | |
| 105 os.link(source, destination) | |
| 106 except: | |
| 107 shutil.copy(source, destination) | |
| 108 | |
| 109 def _preprocess (chipType,dataset,mpagenomics_dir,data_dir,tmp_dir,tumor,settingType,outputgraph,outputlog,log,tag): | |
| 110 script_dir=os.path.dirname(os.path.abspath(__file__)) | |
| 111 | |
| 112 if (outputlog=="TRUE"): | |
| 113 errfile=open(log,'w') | |
| 114 else: | |
| 115 errfile=open(os.path.join(tmp_dir,"errfile.log"),'w') | |
| 116 | |
| 117 retcode = subprocess.call(["Rscript", os.path.join(script_dir,"preprocess.R"), chipType, dataset, mpagenomics_dir, data_dir, tumor, settingType, outputgraph, tag], stdout = errfile, stderr = errfile) | |
| 118 return(retcode) | |
| 119 | |
| 120 | |
| 121 if __name__ == "__main__": | |
| 122 main() |
