comparison fsd.py @ 10:f7136e93604b draft

planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/fsd commit b9403b3ce2b7a41fa8ee1aa47909152de78cf641

9:2c5fc522ded4

# The program produces a plot which shows the distribution of family sizes of the all SSCSs from the input files and
# a CSV file with the data of the plot, as well as a TXT file with all tags of the DCS and their family sizes.
# If only one file is provided, then a family size distribution, which is separated after SSCSs without a partner and DCSs, is produced.
# Whereas a family size distribution with multiple data in one plot is produced, when more than one file (up to 4) is given.

# USAGE: python FSD_Galaxy_1.4_commandLine_FINAL.py filename --inputFile2 filename2 --inputFile3 filename3 --inputFile4 filename4 /
#        --title_file outputFileName --sep "characterWhichSeparatesCSVFile"

import numpy
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
import argparse

    parser = make_argparser()
    args=parser.parse_args(argv[1:])

    firstFile = args.inputFile1
    name1 = args.inputName1
    #firstFile = args.inputName1
    
    secondFile = args.inputFile2
    name2 = args.inputName2
    thirdFile = args.inputFile3
    name3 = args.inputName3

        exit(4)

    plt.rc('figure', figsize=(11.69, 8.27))  # A4 format
    plt.rcParams['patch.edgecolor'] = "black"
    plt.rcParams['axes.facecolor'] = "E0E0E0"  # grey background color
    plt.rcParams['xtick.labelsize'] = 12
    plt.rcParams['ytick.labelsize'] = 12

    list_to_plot = []
    label = []
    data_array_list = []

    with open(title_file, "w") as output_file, PdfPages(title_file2) as pdf:
       fig = plt.figure()
       plt.subplots_adjust(bottom=0.25)
       if firstFile != str(None):
           print(firstFile)
           
           file1 = readFileReferenceFree(firstFile)
           integers = numpy.array(file1[:, 0]).astype(int)  ## keep original family sizes

           # for plot: replace all big family sizes by 22
           data1 = numpy.array(file1[:, 0]).astype(int)

       ticks1 = map(str, ticks)
       ticks1[len(ticks1) - 1] = ">20"
       plt.xticks(numpy.array(ticks), ticks1)

       plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(0.9, 1))
       plt.title("Family Size Distribution", fontsize=14)
       plt.xlabel("No. of Family Members", fontsize=14)
       plt.ylabel("Absolute Frequency", fontsize=14)
       plt.margins(0.01, None)
       plt.grid(b=True, which="major", color="#424242", linestyle=":")
       pdf.savefig(fig)
       plt.close()

            plt.xticks(numpy.array(ticks), ticks1)
            singl = counts[0][2][0]  # singletons
            last = counts[0][2][len(counts[0][0]) - 1]  # large families

            plt.legend(loc='upper right', fontsize=14, bbox_to_anchor=(0.9, 1), frameon=True)
            plt.title(name1, fontsize=14)
            plt.xlabel("No. of Family Members", fontsize=14)
            plt.ylabel("Absolute Frequency", fontsize=14)
            plt.margins(0.01, None)
            plt.grid(b=True, which="major", color="#424242", linestyle=":")

            ## extra information beneath the plot

10:f7136e93604b

# The program produces a plot which shows the distribution of family sizes of the all SSCSs from the input files and
# a CSV file with the data of the plot, as well as a TXT file with all tags of the DCS and their family sizes.
# If only one file is provided, then a family size distribution, which is separated after SSCSs without a partner and DCSs, is produced.
# Whereas a family size distribution with multiple data in one plot is produced, when more than one file (up to 4) is given.

# 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 --sep "characterWhichSeparatesCSVFile" --output_csv outptufile_name_csv --output_pdf outptufile_name_pdf

import numpy
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
import argparse

    parser = make_argparser()
    args=parser.parse_args(argv[1:])

    firstFile = args.inputFile1
    name1 = args.inputName1
    
    secondFile = args.inputFile2
    name2 = args.inputName2
    thirdFile = args.inputFile3
    name3 = args.inputName3

        exit(4)

    plt.rc('figure', figsize=(11.69, 8.27))  # A4 format
    plt.rcParams['patch.edgecolor'] = "black"
    plt.rcParams['axes.facecolor'] = "E0E0E0"  # grey background color
    plt.rcParams['xtick.labelsize'] = 14
    plt.rcParams['ytick.labelsize'] = 14

    list_to_plot = []
    label = []
    data_array_list = []

    with open(title_file, "w") as output_file, PdfPages(title_file2) as pdf:
       fig = plt.figure()
       plt.subplots_adjust(bottom=0.25)
       if firstFile != str(None):
           file1 = readFileReferenceFree(firstFile)
           integers = numpy.array(file1[:, 0]).astype(int)  ## keep original family sizes

           # for plot: replace all big family sizes by 22
           data1 = numpy.array(file1[:, 0]).astype(int)

       ticks1 = map(str, ticks)
       ticks1[len(ticks1) - 1] = ">20"
       plt.xticks(numpy.array(ticks), ticks1)

       plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(0.9, 1))
     #  plt.title("Family Size Distribution", fontsize=14)
       plt.xlabel("Family size", fontsize=14)
       plt.ylabel("Absolute Frequency", fontsize=14)
       plt.margins(0.01, None)
       plt.grid(b=True, which="major", color="#424242", linestyle=":")
       pdf.savefig(fig)
       plt.close()

            plt.xticks(numpy.array(ticks), ticks1)
            singl = counts[0][2][0]  # singletons
            last = counts[0][2][len(counts[0][0]) - 1]  # large families

            plt.legend(loc='upper right', fontsize=14, bbox_to_anchor=(0.9, 1), frameon=True)
         #   plt.title(name1, fontsize=14)
            plt.xlabel("Family size", fontsize=14)
            plt.ylabel("Absolute Frequency", fontsize=14)
            plt.margins(0.01, None)
            plt.grid(b=True, which="major", color="#424242", linestyle=":")

            ## extra information beneath the plot