Mercurial > repos > mheinzl > hd

comparison hd.py @ 5:445442a6aeb0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit dda3de3fc961976844f5f44b756fe03e39d3b0db
author mheinzl
date Tue, 15 May 2018 10:56:52 -0400
parents ceb3a9b4bef5
children e76e404c1719
comparison
equal deleted inserted replaced
4:ceb3a9b4bef5 5:445442a6aeb0
455 #ham2 = [] 455 #ham2 = []
456 #min_valueList = [] 456 #min_valueList = []
457 #min_tagsList = [] 457 #min_tagsList = []
458 #diff11_zeros = [] 458 #diff11_zeros = []
459 #min_tagsList_zeros = [] 459 #min_tagsList_zeros = []
460 i = 0 # counter, only used to see how many HDs of tags were already calculated 460 c = 0 # counter, only used to see how many HDs of tags were already calculated
461 if mate_b is False: # HD calculation for all a's 461 if mate_b is False: # HD calculation for all a's
462 half1_mate1 = array1_half 462 half1_mate1 = array1_half
463 half2_mate1 = array1_half2 463 half2_mate1 = array1_half2
464 half1_mate2 = array2_half 464 half1_mate2 = array2_half
465 half2_mate2 = array2_half2 465 half2_mate2 = array2_half2
494 d = d_2 494 d = d_2
495 d2 = d_1 495 d2 = d_1
496 else: # half1, corrects the variable of the HD from both halfs if it is a or b 496 else: # half1, corrects the variable of the HD from both halfs if it is a or b
497 d = d_1 497 d = d_1
498 d2 = d_2 498 d2 = d_2
499 min_valueList[i] = d + d2 499 min_valueList[c] = d + d2
500 min_tagsList[i] = tag 500 min_tagsList[c] = tag
501 ham1.append[i] = d 501 ham1.append[c] = d
502 ham2.append[i] = d2 502 ham2.append[c] = d2
503 difference1 = abs(d - d2) 503 difference1 = abs(d - d2)
504 diff11[i] = difference1 504 diff11[c] = difference1
505 rel_difference = round(float(difference1) / (d + d2), 1) 505 rel_difference = round(float(difference1) / (d + d2), 1)
506 relativeDiffList[i] = rel_difference 506 relativeDiffList[c] = rel_difference
507 507
508 #### tags which have identical parts: 508 #### tags which have identical parts:
509 if d == 0 or d2 == 0: 509 if d == 0 or d2 == 0:
510 min_tagsList_zeros[i] = tag 510 min_tagsList_zeros[c] = tag
511 difference1_zeros = abs(d - d2) 511 difference1_zeros = abs(d - d2)
512 diff11_zeros[i] = difference1_zeros 512 diff11_zeros[c] = difference1_zeros
513 i += 1 513 c += 1
514 514
515 #print(i) 515 #print(i)
516 diff11 = [st for st in diff11 if st != 999] 516 diff11 = [st for st in diff11 if st != 999]
517 ham1 = [st for st in ham1 if st != 999] 517 ham1 = [st for st in ham1 if st != 999]
518 ham2 = [st for st in ham2 if st != 999] 518 ham2 = [st for st in ham2 if st != 999]
709 files = [file1] 709 files = [file1]
710 name1 = name1.split(".tabular")[0] 710 name1 = name1.split(".tabular")[0]
711 names = [name1] 711 names = [name1]
712 pdf_files = [title_savedFile_pdf] 712 pdf_files = [title_savedFile_pdf]
713 csv_files = [title_savedFile_csv] 713 csv_files = [title_savedFile_csv]
714
715 print(type(onlyDuplicates))
716 print(onlyDuplicates)
717 714
718 for f, name_file, pdf_f, csv_f in zip(files, names, pdf_files, csv_files): 715 for f, name_file, pdf_f, csv_f in zip(files, names, pdf_files, csv_files):
719 with open(csv_f, "w") as output_file, PdfPages(pdf_f) as pdf: 716 with open(csv_f, "w") as output_file, PdfPages(pdf_f) as pdf:
720 print("dataset: ", name_file) 717 print("dataset: ", name_file)
721 integers, data_array = readFileReferenceFree(f) 718 integers, data_array = readFileReferenceFree(f)