Separate filelist and roi_summary file into separate txt files.

scatter_roi_files.py

import argparse
import os
import sys
from itertools import izip
import collections
import errno

"""
This script takes two files: a list of form 'filename,slice#', and another
tab-delimited list of mean values for each ROI.  Every line should line up.

"""

#---------------------------------------------------------------------------
class ROIParser(argparse.ArgumentParser):
    def error(self, message):
        sys.stderr.write('error: %s\n' % message)
        self.print_help()
        sys.exit(2)

#---------------------------------------------------------------------------
def mkdir_p(path):
    """Recursive directory creation function.
    See http://stackoverflow.com/questions/600268/mkdir-p-functionality-in-python
    """
    try:
        os.makedirs(path)
    except OSError as exc: # Python >2.5
        if exc.errno == errno.EEXIST and os.path.isdir(path):
            pass
        else: raise

#---------------------------------------------------------------------------
def getFileNumber(filename):
    import re
    pos = filename.find("RestingState")
    start = pos + len("RestingState")
    ss = filename[start:]
    # find first digit after RestingState in file
    m = re.search("\d", ss)
    return ss[m.start():m.start()+3]

#---------------------------------------------------------------------------
def file_len(fname):
    with open(fname) as f:
        for i, l in enumerate(f):
            pass
    return i + 1

#---------------------------------------------------------------------------
def ReadData(filenamesFile=None, roiSummaryFile=None, roiNamesList=None):

    if file_len(roiSummaryFile.name) != file_len(filenamesFile.name):
        print("File line mismatch! ")
        sys.exit(2)

    fileList = []
    fileNameROIListDict = collections.defaultdict(list)
    with open(filenamesFile.name) as fidList, open(roiSummaryFile.name) as fidSummary: 
        for fnItem, sumItem in izip(fidList, fidSummary):
            roiList = [float(roi.lstrip().rstrip()) for roi in sumItem.split('\t')]
            fileNameROIListDict[fnItem.lstrip().rstrip().split(',')[0]].append(roiList)
    fileNameROINameDict = collections.defaultdict(dict)
    for fname, timepointList in fileNameROIListDict.iteritems():
        for index, roiName in enumerate(roiNamesList):
            fileNameROINameDict[fname][roiName] = [roiValueList[index] for roiValueList in timepointList]

    mkdir_p("output")
    for fname, roiDict in fileNameROINameDict.iteritems():
        for roiName, valList in roiDict.iteritems():
            with open("output/"+roiName+"_"+getFileNumber(os.path.basename(os.path.splitext(fname)[0]))+".txt", 'a') as outFile:
                outFile.write("\n".join(map(str,valList)))

#---------------------------------------------------------------------------
if __name__ == '__main__':

    parser = ROIParser()

    parser.add_argument("-f", "--fileList", dest="filenames",
        required=True, type=argparse.FileType('r'))

    parser.add_argument("-s", "--summary", dest="summary",
        required=True, type=argparse.FileType('r'))

    parser.add_argument('--roiNames',
        type=str, default=None,
        help='Comma separated list of ROI names. Example: --roiNames "insula,mpfc,striatum,precuneus"')

    arguments = parser.parse_args(sys.argv[1:])

    roiNamesList = arguments.roiNames.split(',')

    ReadData(filenamesFile=arguments.filenames,
            roiSummaryFile=arguments.summary,
            roiNamesList=roiNamesList)