# HG changeset patch # User mheinzl # Date 1526397322 14400 # Node ID e2596a4e1c56ed1d0bab44866eae95d4212e078f # Parent 6f124cc95838543eccc123272a0a18368e74da3c planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a diff -r 6f124cc95838 -r e2596a4e1c56 hd.py --- a/hd.py Tue May 15 11:08:42 2018 -0400 +++ b/hd.py Tue May 15 11:15:22 2018 -0400 @@ -439,25 +439,25 @@ array2_half = numpy.array([i[0:(len(i)) / 2] for i in array2]) # mate2 part1 array2_half2 = numpy.array([i[len(i) / 2:len(i)] for i in array2]) # mate2 part2 - diff11 = 999 * numpy.ones(len(array2)) - relativeDiffList = 999 * numpy.ones(len(array2)) - ham1 = 999 * numpy.ones(len(array2)) - ham2 = 999 * numpy.ones(len(array2)) - min_valueList = 999 * numpy.ones(len(array2)) - min_tagsList = 999 * numpy.ones(len(array2)) - diff11_zeros = 999 * numpy.ones(len(array2)) - min_tagsList_zeros = 999 * numpy.ones(len(array2)) + #diff11 = 999 * numpy.ones(len(array2)) + #relativeDiffList = 999 * numpy.ones(len(array2)) + #ham1 = 999 * numpy.ones(len(array2)) + #ham2 = 999 * numpy.ones(len(array2)) + #min_valueList = 999 * numpy.ones(len(array2)) + #min_tagsList = 999 * numpy.ones(len(array2)) + #diff11_zeros = 999 * numpy.ones(len(array2)) + #min_tagsList_zeros = 999 * numpy.ones(len(array2)) - #diff11 = [] - #relativeDiffList = [] - #ham1 = [] - #ham2 = [] - #min_valueList = [] - #min_tagsList = [] - #diff11_zeros = [] - #min_tagsList_zeros = [] - counter = 0 # counter, only used to see how many HDs of tags were already calculated + diff11 = [] + relativeDiffList = [] + ham1 = [] + ham2 = [] + min_valueList = [] + min_tagsList = [] + diff11_zeros = [] + min_tagsList_zeros = [] + i = 0 # counter, only used to see how many HDs of tags were already calculated if mate_b is False: # HD calculation for all a's half1_mate1 = array1_half half2_mate1 = array1_half2 @@ -496,22 +496,21 @@ else: # half1, corrects the variable of the HD from both halfs if it is a or b d = d_1 d2 = d_2 - min_valueList[counter] = d + d2 - min_tagsList[counter] = tag - ham1[counter] = d - ham2[counter] = d2 + min_valueList.append(d + d2) + min_tagsList.append(tag) + ham1.append.append(d) + ham2.append.append(d2) difference1 = abs(d - d2) - diff11[counter] = difference1 + diff11.append(difference1) rel_difference = round(float(difference1) / (d + d2), 1) - relativeDiffList[counter] = rel_difference + relativeDiffList.append(rel_difference) #### tags which have identical parts: if d == 0 or d2 == 0: - min_tagsList_zeros[counter] = tag + min_tagsList_zeros.append(tag) difference1_zeros = abs(d - d2) - diff11_zeros[counter] = difference1_zeros - - counter += 1 + diff11_zeros.append(difference1_zeros) + i += 1 #print(i) diff11 = [st for st in diff11 if st != 999] @@ -713,6 +712,9 @@ pdf_files = [title_savedFile_pdf] csv_files = [title_savedFile_csv] + print(type(onlyDuplicates)) + print(onlyDuplicates) + for f, name_file, pdf_f, csv_f in zip(files, names, pdf_files, csv_files): with open(csv_f, "w") as output_file, PdfPages(pdf_f) as pdf: print("dataset: ", name_file) diff -r 6f124cc95838 -r e2596a4e1c56 hd.xml --- a/hd.xml Tue May 15 11:08:42 2018 -0400 +++ b/hd.xml Tue May 15 11:15:22 2018 -0400 @@ -1,5 +1,5 @@ - + python matplotlib