removing the old format converter

src/PHYLIP_format_converter.py

-#!/usr/bin/env python3
-
-'''
-Script to convert the PHYLIP format into the 
-for neighborjoining needed format. 
-
-The input has to be a lower left triangular or full matrix.
-Names will be cut after 10 characters and are not allowed 
-to contain blanks or other seperators.
-
-author: Birgitta Päuker
-'''
-
-import sys, re, argparse
-import numpy as np
-import openFile
-
-'''
-Function to convert the PHYLIP Format into the for neighborjoining needed format.
-'''
-def convert_format(progname, progoutfilepath, convoutfilepath):
-  # Read in the lines
-  infile= openFile.open_file(progoutfilepath)
-  lines = infile.readlines()
-  infile.close()
-
-  # Open the outputfile
-  outfile = openFile.open_file(convoutfilepath, 'w')
-
-  # Writing the headline
-  num_genomesre = re.search(r'\w+', lines[0])
-  num_genomes = num_genomesre[0]
-  
-  # Check if first line is a digit
-  if not (num_genomes.isdigit()):
-    sys.stderr.write("{}: The first line of the distmatrix from {} needs to "
-                     "be the number of sequences".format(sys.argv[0],progname))
-    exit(1)
-  outfile.write("# pairwise dist values for {} sequences\n"
-                .format(num_genomes))
-  
-  distmatrix = np.zeros((int(num_genomes), int(num_genomes)))
-  linegenomeidx = 0
-  testfullmatrix = False
-  
-  # Convert distances into needed format
-  for line in lines[1:]:
-    '''
-    for normal PHYLIP Format the used seperator is \t. 
-    But some are using " " as seperator
-    Replacing sep \t with " "
-    '''
-    line = line.replace("\t", " ")
-    values = line.strip().split(' ')
-    
-    # Remove all empty string elements
-    values = list(filter(None, values))
-  
-    # Replace a nan in the distancematrix with distance 1.0
-    for value in values[1:]:
-      if(value.isalpha()):
-        if value == "nan":
-          values[values.index(value)] = 1.0
-          sys.stdout.write("# Replaced the value nan in {} with distance 1.0\n"
-                           .format(progoutfilepath))
-        else:
-          sys.stderr.write("There are characters in the distancematrix in file "
-                           "{}\n".format(progoutfilepath))
-          exit(1)
-      
-    # Testing if there are enough distances per sequence in a line
-    if(len(values) < linegenomeidx + 1):
-      sys.stderr.write("{}: In the distmatrix of {} are not enough distances "
-                       "per sequence.\n".format(sys.argv[0], progname))
-      exit(1)
-      
-    # Writing the name of the genom (10 characters) with its index
-    name = values[0]
-    outfile.write("{}\t{}\n".format(linegenomeidx, name[:10]))
-    
-    # Filling the distmatrix:
-    if not (linegenomeidx == 0):
-      # working with the lower left triangular matrix
-      # for each processed rowgenom read in the dist to the current linegenome
-      for row in range(linegenomeidx):
-        distmatrix[linegenomeidx][row] = values[row + 1]
-        
-    # if full matrix, fill full distmatrix for later test
-    if(len(values) > linegenomeidx + 2):
-      testfullmatrix = True
-      for row in range(linegenomeidx + 1, len(values)-1):
-        distmatrix[linegenomeidx][row] = values[row + 1]
-        
-    linegenomeidx = linegenomeidx + 1
-    
-  # Testing for a full matrix if it is semetric, to find cases like fswm and 
-  # kmacs where there are no seperators between the name and the first distance.
-  if(testfullmatrix):
-    for i in range(distmatrix.shape[0]):
-      for j in range(i+1,distmatrix.shape[1]):
-        if(distmatrix[i][j] != distmatrix[j][i]):
-          sys.stderr.write("{}: The distancmatrix of {} can not be converted "
-                           "into needed format.\nPlease search for the cause in"
-                           " file {}.\nA possible reason might be a missing "
-                           "blank between genomename and first distance.\n"
-                           .format(sys.argv[0], progname, progoutfilepath))
-          exit(1)
-          
-  # Print into outputfile:
-  for lineidx in range(linegenomeidx):
-    for rowidx in range(lineidx + 1, linegenomeidx):
-      # write dist from linegenome to rowgenome
-      dist = distmatrix[rowidx][lineidx]
-      outfile.write("dist {} {} {:.10f}\n".format(lineidx, rowidx, dist))
-      
-  outfile.close()

src/phybema.py

@@ -6,7 +6,6 @@ author: Birgitta Päuker
 '''
 
 import sys, os, shutil
-import PHYLIP_format_converter as fc
 import ete
 import callTreeCmp as treecmp
 import callProg