fsd: fsd.py annotate

annotate fsd.py @ 16:6bd9ef49d013 draft

planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a

author	mheinzl
date	Mon, 08 Oct 2018 05:50:18 -0400
parents
children	2e517a54eedc

rev	line source
16 6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	1 #!/usr/bin/env python
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	2
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	3 # Family size distribution of SSCSs
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	4 #
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	5 # Author: Monika Heinzl, Johannes-Kepler University Linz (Austria)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	6 # Contact: monika.heinzl@edumail.at
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	7 #
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	8 # Takes at least one TABULAR file with tags before the alignment to the SSCS, but up to 4 files can be provided, as input.
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	9 # The program produces a plot which shows the distribution of family sizes of the all SSCSs from the input files and
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	10 # a tabular file with the data of the plot, as well as a TXT file with all tags of the DCS and their family sizes.
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	11 # If only one file is provided, then a family size distribution, which is separated after SSCSs without a partner and DCSs, is produced.
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	12 # Whereas a family size distribution with multiple data in one plot is produced, when more than one file (up to 4) is given.
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	13
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	14 # USAGE: python FSD_Galaxy_1.4_commandLine_FINAL.py --inputFile1 filename --inputName1 filename --inputFile2 filename2 --inputName2 filename2 --inputFile3 filename3 --inputName3 filename3 --inputFile4 filename4 --inputName4 filename4 --output_tabular outptufile_name_tabular --output_pdf outptufile_name_pdf
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	15
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	16 import argparse
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	17 import sys
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	18
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	19 import matplotlib.pyplot as plt
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	20 import numpy
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	21 from matplotlib.backends.backend_pdf import PdfPages
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	23 plt.switch_backend('agg')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	24
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	25
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	26 def readFileReferenceFree(file):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	27 with open(file, 'r') as dest_f:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	28 data_array = numpy.genfromtxt(dest_f, skip_header=0, delimiter='\t', comments='#', dtype='string')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	29 return(data_array)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	30
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	31
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	32 def make_argparser():
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	33 parser = argparse.ArgumentParser(description='Family Size Distribution of duplex sequencing data')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	34 parser.add_argument('--inputFile1', help='Tabular File with three columns: ab or ba, tag and family size.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	35 parser.add_argument('--inputName1')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	36 parser.add_argument('--inputFile2', default=None, help='Tabular File with three columns: ab or ba, tag and family size.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	37 parser.add_argument('--inputName2')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	38 parser.add_argument('--inputFile3', default=None, help='Tabular File with three columns: ab or ba, tag and family size.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	39 parser.add_argument('--inputName3')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	40 parser.add_argument('--inputFile4', default=None, help='Tabular File with three columns: ab or ba, tag and family size.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	41 parser.add_argument('--inputName4')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	42 parser.add_argument('--output_pdf', default="data.pdf", type=str, help='Name of the pdf file.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	43 parser.add_argument('--output_tabular', default="data.tabular", type=str, help='Name of the tabular file.')
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	44 return parser
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	45
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	46
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	47 def compare_read_families(argv):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	48 parser = make_argparser()
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	49 args = parser.parse_args(argv[1:])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	50
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	51 firstFile = args.inputFile1
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	52 name1 = args.inputName1
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	53
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	54 secondFile = args.inputFile2
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	55 name2 = args.inputName2
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	56 thirdFile = args.inputFile3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	57 name3 = args.inputName3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	58 fourthFile = args.inputFile4
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	59 name4 = args.inputName4
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	60
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	61 title_file = args.output_tabular
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	62 title_file2 = args.output_pdf
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	63
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	64 sep = "\t"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	65
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	66 plt.rc('figure', figsize=(11.69, 8.27)) # A4 format
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	67 plt.rcParams['patch.edgecolor'] = "black"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	68 plt.rcParams['axes.facecolor'] = "E0E0E0" # grey background color
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	69 plt.rcParams['xtick.labelsize'] = 14
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	70 plt.rcParams['ytick.labelsize'] = 14
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	71
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	72 list_to_plot = []
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	73 label = []
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	74 data_array_list = []
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	75 with open(title_file, "w") as output_file, PdfPages(title_file2) as pdf:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	76 fig = plt.figure()
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	77 plt.subplots_adjust(bottom=0.25)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	78 if firstFile != str(None):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	79 file1 = readFileReferenceFree(firstFile)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	80 integers = numpy.array(file1[:, 0]).astype(int) # keep original family sizes
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	81
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	82 # for plot: replace all big family sizes by 22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	83 data1 = numpy.array(file1[:, 0]).astype(int)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	84 bigFamilies = numpy.where(data1 > 20)[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	85 data1[bigFamilies] = 22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	86
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	87 name1 = name1.split(".tabular")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	88 list_to_plot.append(data1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	89 label.append(name1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	90 data_array_list.append(file1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	91
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	92 legend = "\n\n\n{}".format(name1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	93 plt.text(0.1, 0.11, legend, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	94 legend1 = "singletons:\nabsolute nr.\n{:,}".format(numpy.bincount(data1)[1])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	95 plt.text(0.4, 0.11, legend1, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	96
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	97 legend3 = "rel. freq\n{:.3f}".format(float(numpy.bincount(data1)[1]) / len(data1))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	98 plt.text(0.5, 0.11, legend3, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	99
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	100 legend4 = "family size > 20:\nabsolute nr.\n{:,}".format(numpy.bincount(data1)[len(numpy.bincount(data1)) - 1].astype(int))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	101 plt.text(0.6, 0.11, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	102
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	103 legend5 = "rel. freq\n{:.3f}".format(float(numpy.bincount(data1)[len(numpy.bincount(data1)) - 1]) / len(data1))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	104 plt.text(0.7, 0.11, legend5, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	105
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	106 legend6 = "total length\n{:,}".format(len(data1))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	107 plt.text(0.8, 0.11, legend6, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	108
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	109 if secondFile != str(None):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	110 file2 = readFileReferenceFree(secondFile)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	111 data2 = numpy.asarray(file2[:, 0]).astype(int)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	112 bigFamilies2 = numpy.where(data2 > 20)[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	113 data2[bigFamilies2] = 22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	114
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	115 list_to_plot.append(data2)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	116 name2 = name2.split(".tabular")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	117 label.append(name2)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	118 data_array_list.append(file2)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	119
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	120 plt.text(0.1, 0.09, name2, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	121
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	122 legend1 = "{:,}".format(numpy.bincount(data2)[1])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	123 plt.text(0.4, 0.09, legend1, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	124
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	125 legend3 = "{:.3f}".format(float(numpy.bincount(data2)[1]) / len(data2))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	126 plt.text(0.5, 0.09, legend3, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	127
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	128 legend4 = "{:,}".format(numpy.bincount(data2)[len(numpy.bincount(data2)) - 1].astype(int))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	129 plt.text(0.6, 0.09, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	130
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	131 legend5 = "{:.3f}".format(float(numpy.bincount(data2)[len(numpy.bincount(data2)) - 1]) / len(data2))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	132 plt.text(0.7, 0.09, legend5, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	133
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	134 legend6 = "{:,}".format(len(data2))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	135 plt.text(0.8, 0.09, legend6, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	136
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	137 if thirdFile != str(None):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	138 file3 = readFileReferenceFree(thirdFile)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	139
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	140 data3 = numpy.asarray(file3[:, 0]).astype(int)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	141 bigFamilies3 = numpy.where(data3 > 20)[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	142 data3[bigFamilies3] = 22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	143
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	144 list_to_plot.append(data3)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	145 name3 = name3.split(".tabular")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	146 label.append(name3)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	147 data_array_list.append(file3)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	148
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	149 plt.text(0.1, 0.07, name3, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	150
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	151 legend1 = "{:,}".format(numpy.bincount(data3)[1])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	152 plt.text(0.4, 0.07, legend1, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	153
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	154 legend3 = "{:.3f}".format(float(numpy.bincount(data3)[1]) / len(data3))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	155 plt.text(0.5, 0.07, legend3, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	156
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	157 legend4 = "{:,}".format(numpy.bincount(data3)[len(numpy.bincount(data3)) - 1].astype(int))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	158 plt.text(0.6, 0.07, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	159
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	160 legend5 = "{:.3f}".format(float(numpy.bincount(data3)[len(numpy.bincount(data3)) - 1]) / len(data3))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	161 plt.text(0.7, 0.07, legend5, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	162
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	163 legend6 = "{:,}".format(len(data3))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	164 plt.text(0.8, 0.07, legend6, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	165
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	166 if fourthFile != str(None):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	167 file4 = readFileReferenceFree(fourthFile)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	168
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	169 data4 = numpy.asarray(file4[:, 0]).astype(int)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	170
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	171 bigFamilies4 = numpy.where(data4 > 20)[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	172 data4[bigFamilies4] = 22
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	173
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	174 list_to_plot.append(data4)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	175 name4 = name4.split(".tabular")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	176 label.append(name4)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	177 data_array_list.append(file4)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	178
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	179 plt.text(0.1, 0.05, name4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	180
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	181 legend1 = "{:,}".format(numpy.bincount(data4)[1])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	182 plt.text(0.4, 0.05, legend1, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	183
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	184 legend4 = "{:.3f}".format(float(numpy.bincount(data4)[1]) / len(data4))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	185 plt.text(0.5, 0.05, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	186
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	187 legend4 = "{:,}".format(numpy.bincount(data4)[len(numpy.bincount(data4)) - 1].astype(int))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	188 plt.text(0.6, 0.05, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	189
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	190 legend5 = "{:.3f}".format(float(numpy.bincount(data4)[len(numpy.bincount(data4)) - 1]) / len(data4))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	191 plt.text(0.7, 0.05, legend5, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	192
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	193 legend6 = "{:,}".format(len(data4))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	194 plt.text(0.8, 0.05, legend6, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	195
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	196 maximumX = numpy.amax(numpy.concatenate(list_to_plot))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	197 minimumX = numpy.amin(numpy.concatenate(list_to_plot))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	198
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	199 counts = plt.hist(list_to_plot, bins=range(minimumX, maximumX + 1), stacked=False, edgecolor="black",
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	200 linewidth=1, label=label, align="left", alpha=0.7, rwidth=0.8)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	201
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	202 ticks = numpy.arange(minimumX - 1, maximumX, 1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	203 ticks1 = map(str, ticks)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	204 ticks1[len(ticks1) - 1] = ">20"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	205 plt.xticks(numpy.array(ticks), ticks1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	206
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	207 plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(0.9, 1))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	208 # plt.title("Family Size Distribution", fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	209 plt.xlabel("Family size", fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	210 plt.ylabel("Absolute Frequency", fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	211 plt.margins(0.01, None)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	212 plt.grid(b=True, which="major", color="#424242", linestyle=":")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	213 pdf.savefig(fig)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	214 plt.close()
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	215
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	216 # write data to CSV file
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	217 output_file.write("Values from family size distribution with all datasets\n")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	218 output_file.write("\nFamily size")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	219 for i in label:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	220 output_file.write("{}{}".format(sep, i))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	221 # output_file.write("{}sum".format(sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	222 output_file.write("\n")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	223 j = 0
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	224 for fs in counts[1][0:len(counts[1]) - 1]:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	225 if fs == 21:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	226 fs = ">20"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	227 else:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	228 fs = "={}".format(fs)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	229 output_file.write("FS{}{}".format(fs, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	230 if len(label) == 1:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	231 output_file.write("{}{}".format(int(counts[0][j]), sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	232 else:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	233 for n in range(len(label)):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	234 output_file.write("{}{}".format(int(counts[0][n][j]), sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	235 output_file.write("\n")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	236 j += 1
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	237 output_file.write("sum{}".format(sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	238 if len(label) == 1:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	239 output_file.write("{}{}".format(int(sum(counts[0])), sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	240 else:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	241 for i in counts[0]:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	242 output_file.write("{}{}".format(int(sum(i)), sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	243
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	244 # Family size distribution after DCS and SSCS
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	245 for dataset, data, name_file in zip(list_to_plot, data_array_list, label):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	246 maximumX = numpy.amax(dataset)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	247 minimumX = numpy.amin(dataset)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	248
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	249 tags = numpy.array(data[:, 2])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	250 seq = numpy.array(data[:, 1])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	251 data = numpy.array(dataset)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	252
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	253 # find all unique tags and get the indices for ALL tags, but only once
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	254 u, index_unique, c = numpy.unique(numpy.array(seq), return_counts=True, return_index=True)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	255 d = u[c > 1]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	256
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	257 # get family sizes, tag for duplicates
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	258 duplTags_double = data[numpy.in1d(seq, d)]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	259 duplTags = duplTags_double[0::2] # ab of DCS
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	260 duplTagsBA = duplTags_double[1::2] # ba of DCS
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	261
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	262 # duplTags_double_tag = tags[numpy.in1d(seq, d)]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	263 # duplTags_double_seq = seq[numpy.in1d(seq, d)]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	264
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	265 # get family sizes for SSCS with no partner
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	266 ab = numpy.where(tags == "ab")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	267 abSeq = seq[ab]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	268 ab = data[ab]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	269 ba = numpy.where(tags == "ba")[0]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	270 baSeq = seq[ba]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	271 ba = data[ba]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	272
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	273 dataAB = ab[numpy.in1d(abSeq, d, invert=True)]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	274 dataBA = ba[numpy.in1d(baSeq, d, invert=True)]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	275
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	276 list1 = [duplTags_double, dataAB, dataBA] # list for plotting
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	277
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	278 # information for family size >= 3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	279 dataAB_FS3 = dataAB[dataAB >= 3]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	280 dataBA_FS3 = dataBA[dataBA >= 3]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	281 ab_FS3 = ab[ab >= 3]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	282 ba_FS3 = ba[ba >= 3]
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	283
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	284 duplTags_FS3 = duplTags[(duplTags >= 3) & (duplTagsBA >= 3)] # ab+ba with FS>=3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	285 duplTags_FS3_BA = duplTagsBA[(duplTags >= 3) & (duplTagsBA >= 3)] # ba+ab with FS>=3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	286 duplTags_double_FS3 = len(duplTags_FS3) + len(duplTags_FS3_BA) # both ab and ba strands with FS>=3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	287
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	288 fig = plt.figure()
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	289
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	290 plt.subplots_adjust(bottom=0.3)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	291 counts = plt.hist(list1, bins=range(minimumX, maximumX + 1), stacked=True, label=["duplex", "ab", "ba"], edgecolor="black", linewidth=1, align="left", color=["#FF0000", "#5FB404", "#FFBF00"])
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	292 # tick labels of x axis
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	293 ticks = numpy.arange(minimumX - 1, maximumX, 1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	294 ticks1 = map(str, ticks)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	295 ticks1[len(ticks1) - 1] = ">20"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	296 plt.xticks(numpy.array(ticks), ticks1)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	297 singl = counts[0][2][0] # singletons
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	298 last = counts[0][2][len(counts[0][0]) - 1] # large families
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	299
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	300 plt.legend(loc='upper right', fontsize=14, bbox_to_anchor=(0.9, 1), frameon=True)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	301 # plt.title(name1, fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	302 plt.xlabel("Family size", fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	303 plt.ylabel("Absolute Frequency", fontsize=14)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	304 plt.margins(0.01, None)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	305 plt.grid(b=True, which="major", color="#424242", linestyle=":")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	306
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	307 # extra information beneath the plot
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	308 legend = "SSCS ab= \nSSCS ba= \nDCS (total)= \nlength of dataset="
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	309 plt.text(0.1, 0.09, legend, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	310
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	311 legend = "absolute numbers\n\n{:,}\n{:,}\n{:,} ({:,})\n{:,}".format(len(dataAB), len(dataBA), len(duplTags), len(duplTags_double), (len(dataAB) + len(dataBA) + len(duplTags)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	312 plt.text(0.35, 0.09, legend, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	313
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	314 legend = "relative frequencies\nunique\n{:.3f}\n{:.3f}\n{:.3f}\n{:,}".format(float(len(dataAB)) / (len(dataAB) + len(dataBA) + len(duplTags)), float(len(dataBA)) / (len(dataAB) + len(dataBA) + len(duplTags)), float(len(duplTags)) / (len(dataAB) + len(dataBA) + len(duplTags)), (len(dataAB) + len(dataBA) + len(duplTags)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	315 plt.text(0.54, 0.09, legend, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	316
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	317 legend = "total\n{:.3f}\n{:.3f}\n{:.3f} ({:.3f})\n{:,}".format(float(len(dataAB)) / (len(ab) + len(ba)), float(len(dataBA)) / (len(ab) + len(ba)), float(len(duplTags)) / (len(ab) + len(ba)), float(len(duplTags_double)) / (len(ab) + len(ba)), (len(ab) + len(ba)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	318 plt.text(0.64, 0.09, legend, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	319
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	320 legend1 = "\nsingletons:\nfamily size > 20:"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	321 plt.text(0.1, 0.03, legend1, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	322
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	323 legend4 = "{:,}\n{:,}".format(singl.astype(int), last.astype(int))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	324 plt.text(0.35, 0.03, legend4, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	325
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	326 legend3 = "{:.3f}\n{:.3f}".format(singl / len(data), last / len(data))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	327 plt.text(0.54, 0.03, legend3, size=12, transform=plt.gcf().transFigure)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	328
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	329 pdf.savefig(fig)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	330 plt.close()
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	331
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	332 # write same information to a csv file
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	333 count = numpy.bincount(integers) # original counts of family sizes
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	334 output_file.write("\nDataset:{}{}\n".format(sep, name_file))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	335 output_file.write("max. family size:{}{}\n".format(sep, max(integers)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	336 output_file.write("absolute frequency:{}{}\n".format(sep, count[len(count) - 1]))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	337 output_file.write("relative frequency:{}{:.3f}\n\n".format(sep, float(count[len(count) - 1]) / sum(count)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	338
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	339 output_file.write("{}singletons:{}{}family size > 20:\n".format(sep, sep, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	340 output_file.write("{}absolute nr.{}rel. freq{}absolute nr.{}rel. freq{}total length\n".format(sep, sep, sep, sep, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	341 output_file.write("{}{}{}{}{:.3f}{}{}{}{:.3f}{}{}\n\n".format(name_file, sep, singl.astype(int), sep, singl / len(data), sep, last.astype(int), sep, last / len(data), sep, len(data)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	342
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	343 # information for FS >= 1
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	344 output_file.write("The unique frequencies were calculated from the dataset where the tags occured only once (=ab without DCS, ba without DCS)\nWhereas the total frequencies were calculated from the whole dataset (=including the DCS).\n\n")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	345 output_file.write("FS >= 1{}{}unique:{}total:\n".format(sep, sep, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	346 output_file.write("nr./rel. freq of ab={}{}{}{:.3f}{}{:.3f}\n".format(sep, len(dataAB), sep, float(len(dataAB)) / (len(dataAB) + len(dataBA) + len( duplTags)), sep, float(len(dataAB)) / (len(ab) + len(ba))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	347 output_file.write("nr./rel. freq of ba={}{}{}{:.3f}{}{:.3f}\n".format(sep, len(dataBA), sep, float(len(dataBA)) / (len(dataBA) + len(dataBA) + len(duplTags)), sep, float(len(dataBA)) / (len(ba) + len(ba))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	348 output_file.write("nr./rel. freq of DCS (total)={}{} ({}){}{:.3f}{}{:.3f} ({:.3f})\n".format(sep, len(duplTags), len(duplTags_double), sep, float(len(duplTags)) / (len(dataAB) + len(dataBA) + len(duplTags)), sep, float(len(duplTags)) / ( len(ab) + len(ba)), float(len(duplTags_double)) / (len(ab) + len(ba))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	349 output_file.write("length of dataset={}{}{}{}{}{}\n".format(sep, (len(dataAB) + len(dataBA) + len(duplTags)), sep, (len(dataAB) + len(dataBA) + len(duplTags)), sep, (len(ab) + len(ba))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	350 # information for FS >= 3
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	351 output_file.write("FS >= 3{}{}unique:{}total:\n".format(sep, sep, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	352 output_file.write("nr./rel. freq of ab={}{}{}{:.3f}{}{:.3f}\n".format(sep, len(dataAB_FS3), sep, float(len(dataAB_FS3)) / (len(dataAB_FS3) + len(dataBA_FS3) + len(duplTags_FS3)), sep, float(len(dataAB_FS3)) / (len(ab_FS3) + len(ba_FS3))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	353 output_file.write("nr./rel. freq of ba={}{}{}{:.3f}{}{:.3f}\n".format(sep, len(dataBA_FS3), sep, float(len(dataBA_FS3)) / (len(dataBA_FS3) + len(dataBA_FS3) + len(duplTags_FS3)), sep, float(len(dataBA_FS3)) / (len(ba_FS3) + len(ba_FS3))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	354 output_file.write("nr./rel. freq of DCS (total)={}{} ({}){}{:.3f}{}{:.3f} ({:.3f})\n".format(sep, len(duplTags_FS3), duplTags_double_FS3, sep, float(len( duplTags_FS3)) / (len(dataBA_FS3) + len(duplTags_FS3)), sep, float(len(duplTags_FS3)) / (len(ab_FS3) + len(ba_FS3)), float(duplTags_double_FS3) / (len(ab_FS3) + len(ba_FS3))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	355 output_file.write("length of dataset={}{}{}{}{}{}\n".format(sep, (len(dataAB_FS3) + len(dataBA_FS3) + len(duplTags_FS3)), sep, (len(dataAB_FS3) + len(dataBA_FS3) + len(duplTags_FS3)), sep, (len(ab_FS3) + len(ba_FS3))))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	356
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	357 output_file.write("\nValues from family size distribution\n")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	358 output_file.write("{}duplex{}ab{}ba{}sum\n".format(sep, sep, sep, sep))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	359 for dx, ab, ba, fs in zip(counts[0][0], counts[0][1], counts[0][2], counts[1]):
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	360 if fs == 21:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	361 fs = ">20"
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	362 else:
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	363 fs = "={}".format(fs)
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	364 ab1 = ab - dx
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	365 ba1 = ba - ab
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	366 output_file.write("FS{}{}{}{}{}{}{}{}{}\n".format(fs, sep, int(dx), sep, int(ab1), sep, int(ba1), sep, int(ba)))
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	367
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	368 print("Files successfully created!")
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	369
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	370
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	371 if __name__ == '__main__':
6bd9ef49d013 planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a mheinzl parents: diff changeset	372 sys.exit(compare_read_families(sys.argv))

Mercurial > repos > mheinzl > fsd

annotate fsd.py @ 16:6bd9ef49d013 draft