comparison combine_output.py @ 1:071a185c2ced

new tools

0:4b94bb2d381c

    '''
    Writes tab-separated data to file
    @param data: dictionary containing merged dataset
    @param out_csv: output csv file
    '''
    header = ['Centrotype',
              'cent.Factor',
              'scan nr.',
              'R.T. (umin)',
              'nr. Peaks',
              'R.T.',
              'Name',
              'FORMULA',
              'Library',
              'CAS',
              'Forward',

    outfile_multi_handle = open(out_csv_multi, 'wb')
    output_single_handle = csv.writer(outfile_single_handle, delimiter="\t")
    output_multi_handle = csv.writer(outfile_multi_handle, delimiter="\t")

    # Write headers
    output_single_handle.writerow(header)
    output_multi_handle.writerow(header * nhits)
    # Combine all hits for each centrotype into one line
    line = []
    for centrotype_idx in xrange(len(data)):
        for hit in data[centrotype_idx]:
            line.extend(hit)
        output_multi_handle.writerow(line)
        line = []

    # Write one line for each centrotype
    for centrotype_idx in xrange(len(data)):
        for hit in data[centrotype_idx]:
            output_single_handle.writerow(hit)


def main():
    '''
    Combine Output main function
    It will merge the result files from "RankFilter"  and "Lookup RI for CAS numbers" 

1:071a185c2ced

    '''
    Writes tab-separated data to file
    @param data: dictionary containing merged dataset
    @param out_csv: output csv file
    '''
    # Columns we don't repeat:
    header_part1 = ['Centrotype',
              'cent.Factor',
              'scan nr.',
              'R.T. (umin)',
              'nr. Peaks',
              'R.T.']
    # These are the headers/columns we repeat in case of 
    # combining hits in one line (see alternative_headers method below):
    header_part2 = [
              'Name',
              'FORMULA',
              'Library',
              'CAS',
              'Forward',

    outfile_multi_handle = open(out_csv_multi, 'wb')
    output_single_handle = csv.writer(outfile_single_handle, delimiter="\t")
    output_multi_handle = csv.writer(outfile_multi_handle, delimiter="\t")

    # Write headers
    output_single_handle.writerow(header_part1 + header_part2)
    output_multi_handle.writerow(header_part1 + header_part2 + alternative_headers(header_part2, nhits-1))
    # Combine all hits for each centrotype into one line
    line = []
    for centrotype_idx in xrange(len(data)):
        i = 0
        for hit in data[centrotype_idx]:
            if i==0:
                line.extend(hit)
            else:
                line.extend(hit[6:])
            i = i+1
        # small validation (if error, it is a programming error):
        if i > nhits:
            raise Exception('Error: more hits that expected for  centrotype_idx ' + centrotype_idx)
        output_multi_handle.writerow(line)
        line = []

    # Write one line for each centrotype
    for centrotype_idx in xrange(len(data)):
        for hit in data[centrotype_idx]:
            output_single_handle.writerow(hit)

def alternative_headers(header_part2, nr_alternative_hits):
    ''' 
    This method will iterate over the header names and add the string 'ALT#_' before each, 
    where # is the number of the alternative, according to number of alternative hits we want to add
    to final csv/tsv
    '''
    result = []
    for i in xrange(nr_alternative_hits): 
        for header_name in header_part2:
            result.append("ALT" + str(i+1) + "_" + header_name) 
    return result

def main():
    '''
    Combine Output main function
    It will merge the result files from "RankFilter"  and "Lookup RI for CAS numbers"