Merge pull request #464 from cclauss/print-function

Use print() function in both Python 2 and Python 3

bin/metawrap-scripts/add_bins_to_blobplot.py

@@ -2,6 +2,7 @@
 # THis script takes in a blobplot text file and and number of bins as input, and annotates
 # each line in the blob file with its bin name (if that contig exists in one of the bins)
 
+from __future__ import print_function
 import sys, os
 
 # load the binned contigs:
@@ -19,11 +20,11 @@
 	if line.split("\t")[0]=="seqid":
 		for i, field in enumerate(line.strip().split("\t")):
 			if field=="taxlevel_phylum": phylum_column=i
-		print line.strip() + "\tbin\tbinned_yes_no\tbinned_phylum"
+		print(line.strip() + "\tbin\tbinned_yes_no\tbinned_phylum")
 	elif line.split("\t")[0] in contig_bins:
 		phylum=line.split("\t")[phylum_column]
-		print "\t".join([line.strip(), contig_bins[line.split("\t")[0]], "Binned", phylum])
+		print("\t".join([line.strip(), contig_bins[line.split("\t")[0]], "Binned", phylum]))
 
 	else:
-		print "\t".join([line.strip(), "Unbinned", "Unbinned", "Unbinned"])
+		print("\t".join([line.strip(), "Unbinned", "Unbinned", "Unbinned"]))
 

bin/metawrap-scripts/binning_refiner.py

@@ -28,6 +28,7 @@
 # And the publication: https://www.ncbi.nlm.nih.gov/pubmed/28186226
 
 
+from __future__ import print_function
 import os
 import glob
 import shutil

bin/metawrap-scripts/blobology/rm_short_contigs.py

@@ -1,12 +1,13 @@
 #! /usr/bin/env python
 
+from __future__ import print_function
 import sys
 
 f=open(sys.argv[1])
 for line in f:
 	if line.startswith(">"):
 		cut=line.split("_")
 		if int(cut[3])>999:
-			print line.strip()
+			print(line.strip())
 		else: quit
-	else: print line.strip()
+	else: print(line.strip())

bin/metawrap-scripts/choose_best_bin.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys
 
 # This script takes in the reassembled_bins.stats file of the binning module and choses the best possible
@@ -34,7 +35,7 @@
 
 
 for i in best_bins:
-	print i+'.'+best_bins[i][0]
+	print(i+'.'+best_bins[i][0])
 
 
 

bin/metawrap-scripts/classify_bins.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys,os
 
 def add_to_tree( tree, tax_list, length ):
@@ -60,5 +61,5 @@ def traverse(tree, taxonomy, weight):
 
 	#print tax_tree
 	consensus=traverse(tax_tree, [], 0)
-	print filename + "\t" + ";".join(consensus)
+	print(filename + "\t" + ";".join(consensus))
 

bin/metawrap-scripts/consolidate_two_sets_of_bins.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys, os
 
 '''
@@ -18,7 +19,7 @@
 x=float(sys.argv[7])
 
 # load a list of good bins (>70% complete, <10% contaminated) to save time (wont look at bad bins later on).
-print "Loading list of good bins (comp>" + str(c)+ "%, cont<" + str(x) + "%)"
+print("Loading list of good bins (comp>" + str(c)+ "%, cont<" + str(x) + "%)")
 good_bins_1={}
 good_bins_2={}
 for line in open(sys.argv[3]):
@@ -50,7 +51,7 @@
 '''
 
 
-print  "load in the info about the contigs in each bin..."
+print("load in the info about the contigs in each bin...")
 for bin_file in good_bins_1:
         bins_1[bin_file]={}
 	contig_len=0
@@ -82,7 +83,7 @@
 
 
 
-print "make all bossible comparisons between the two bin sets, and record total % idential length"
+print("make all bossible comparisons between the two bin sets, and record total % idential length")
 all_bin_pairs={}
 for bin_1 in good_bins_1:
 	all_bin_pairs[bin_1]={}
@@ -107,7 +108,7 @@
 		all_bin_pairs[bin_1][bin_2]=max([ratio_1, ratio_2])
 
 
-print "load in completion and contamination scores of all the bins"
+print("load in completion and contamination scores of all the bins")
 bins_1_stats={}
 bins_2_stats={}
 bins_1_summary={}
@@ -131,7 +132,7 @@
 
 
 # go through all good bins and chose best ones
-print "go through first group, pull out identical bins from second group, and choose best"
+print("go through first group, pull out identical bins from second group, and choose best")
 os.system("mkdir "+sys.argv[5])
 new_summary_file=bins_1_summary["header"]
 bins_2_matches={}
@@ -154,7 +155,7 @@
 	os.system(cmd)
 	bin_ct+=1
 
-print "retrieve bins from second group that were not found in first group"
+print("retrieve bins from second group that were not found in first group")
 for bin_2 in bins_2_stats:
 	if bins_2_stats[bin_2][0]<c or bins_2_stats[bin_2][1]>x: continue
 	if bin_2 in bins_2_matches: continue
@@ -167,6 +168,6 @@
 f = open(sys.argv[5]+".stats", 'w') 
 f.write(new_summary_file) 
 
-print "There were " + str(bin_ct) + " bins cherry-picked from the original sets!"
+print("There were " + str(bin_ct) + " bins cherry-picked from the original sets!")
 
 

bin/metawrap-scripts/dereplicate_contigs_in_bins.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys, os
 
 # Usage: ./script.py bins.stats binsFolder outFolder
 
 # load in bin completion and contamination scores
-print "Loading in bin completion and contamination scores..."
+print("Loading in bin completion and contamination scores...")
 bin_scores={}
 for line in open(sys.argv[1]):
 	if "completeness" in line: continue
@@ -13,7 +14,7 @@
 	bin_scores[cut[0]]=score
 
 # load in contigs in each bin
-print "Loading in contigs in each bin..."
+print("Loading in contigs in each bin...")
 contig_mapping={}
 for bin_file in os.listdir(sys.argv[2]):
 	bin_name=".".join(bin_file.split("/")[-1].split(".")[:-1])
@@ -29,7 +30,7 @@
 
 
 # go over the bin files again and make a new dereplicated version of each bin file	
-print "Making a new dereplicated version of each bin file"
+print("Making a new dereplicated version of each bin file")
 os.system("mkdir "+sys.argv[3])
 for bin_file in os.listdir(sys.argv[2]):
         bin_name=".".join(bin_file.split("/")[-1].split(".")[:-1])

bin/metawrap-scripts/filter_nanopore_reads_for_bin_reassembly.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys, os
 
 complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'a':'t', 't':'a', 'c':'g', 'g':'c', 'N':'N', 'n':'n', '*':'*'} 
@@ -9,7 +10,7 @@ def rev_comp(seq):
 	return rev_comp[::-1]
 
 # load bin contigs
-print "loading contig to bin mappings..."
+print("loading contig to bin mappings...")
 contig_bins={}
 for bin_file in os.listdir(sys.argv[1]):
 	if bin_file.endswith(".fa") or bin_file.endswith(".fasta"): 
@@ -21,7 +22,7 @@ def rev_comp(seq):
 # store the read names and what bins they belong in in these dictionaries
 # strict stores only perfectly aligning reads and permissive stores any aligned reads
 
-print "Parsing sam file and writing reads to appropriate files depending what bin they alligned to..."
+print("Parsing sam file and writing reads to appropriate files depending what bin they alligned to...")
 files={}
 opened_bins={}
 for line in sys.stdin:
@@ -60,9 +61,9 @@ def rev_comp(seq):
 	files[sys.argv[2]+"/"+bin_name+".nanopore.fastq"].write('@' + cut[0] + "/1" + "\n" + cut[9] + "\n+\n" + cut[10] + "\n")
 
 
-print "closing files"
+print("closing files")
 for f in files:
 	files[f].close()
 
 
-print "Finished splitting reads!"
+print("Finished splitting reads!")

bin/metawrap-scripts/filter_out_fastq_reads.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys
 
 # this script takes in a list of fastq read names and picks them out of a .fastq file.
@@ -20,7 +21,7 @@
 		#	if soi in line: found=True
 
 	if found==True: 
-		print line
+		print(line)
 		sys.stdout.flush()
 
 

bin/metawrap-scripts/filter_reads_for_bin_reassembly.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python2.7
 #usage: 
 # bwa mem -a assembly.fa reads_1.fastq reads_2.fastq | ./filter_reads_for_bin_reassembly.py original_bin_folder reads_1.fastq reads_2.fastq output_dir
+from __future__ import print_function
 import sys, os
 strict_snp_cutoff = int(sys.argv[3])
 permissive_snp_cutoff = int(sys.argv[4])
@@ -13,7 +14,7 @@ def rev_comp(seq):
 	return rev_comp[::-1]
 
 # load bin contigs
-print "loading contig to bin mappings..."
+print("loading contig to bin mappings...")
 contig_bins={}
 for bin_file in os.listdir(sys.argv[1]):
 	if bin_file.endswith(".fa") or bin_file.endswith(".fasta"): 
@@ -25,7 +26,7 @@ def rev_comp(seq):
 # store the read names and what bins they belong in in these dictionaries
 # strict stores only perfectly aligning reads and permissive stores any aligned reads
 
-print "Parsing sam file and writing reads to appropriate files depending what bin they alligned to..."
+print("Parsing sam file and writing reads to appropriate files depending what bin they alligned to...")
 files={}
 opened_bins={}
 for line in sys.stdin:
@@ -106,11 +107,11 @@ def rev_comp(seq):
 		files[sys.argv[2]+"/"+bin_name+".permissive_2.fastq"].write('@' + R_cut[0] + "/2" + "\n" + R_cut[9] + "\n+\n" + R_cut[10] + "\n")
 
 
-print "closing files"
+print("closing files")
 for f in files:
 	files[f].close()
 
 
-print "Finished splitting reads!"
+print("Finished splitting reads!")
 
 

bin/metawrap-scripts/fix_config_naming.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys
 
 for line in open(sys.argv[1]):
@@ -7,4 +8,4 @@
 			if c=="=": c="_"
 			sys.stdout.write(c)
 	else:
-		print line.rstrip()
+		print(line.rstrip())

bin/metawrap-scripts/fix_megahit_contig_naming.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys
 import textwrap
 
@@ -25,5 +26,5 @@
 
 
 for k in sorted(dic, key=lambda k: len(dic[k]), reverse=True):
-        print k
-        print textwrap.fill(dic[k], 100, break_on_hyphens = False)
+        print(k)
+        print(textwrap.fill(dic[k], 100, break_on_hyphens = False))

bin/metawrap-scripts/gather-counts.py

@@ -11,6 +11,7 @@
 
 C. Titus Brown, 11/2015
 """
+from __future__ import print_function
 import os, os.path
 import sys
 import csv
@@ -19,9 +20,9 @@ def process_quant_file(root, filename, outname):
     """
     Convert individual quant.sf files into .counts files (transcripts\tcount).
     """
-    print >>sys.stderr, 'Loading counts from:', root, filename
+    print('Loading counts from:', root, filename, file=sys.stderr)
     outfp = open(outname, 'w')
-    print >>outfp, "transcript\tcount"
+    print("transcript\tcount", file=outfp)
 
     d = {}
     full_file = os.path.join(root, filename)
@@ -30,7 +31,7 @@ def process_quant_file(root, filename, outname):
             continue
         name, length, eff_length, tpm, count = line.strip().split('\t')
 
-        print >>outfp, "%s\t%s" % (name, float(tpm))
+        print("%s\t%s" % (name, float(tpm)), file=outfp)
 
 
 def main():
@@ -43,7 +44,7 @@ def main():
     quantlist = []
 
     start_dir = '.'
-    print >>sys.stderr, 'Starting in:', os.path.abspath(start_dir)
+    print('Starting in:', os.path.abspath(start_dir), file=sys.stderr)
     for root, dirs, files in os.walk('.'):
         for filename in files:
             if filename.endswith('quant.sf'):
@@ -54,7 +55,7 @@ def main():
 
                 break
 
-    print ",\n".join([ "\"%s\"" % i for i in sorted(quantlist)])
+    print(",\n".join([ "\"%s\"" % i for i in sorted(quantlist)]))
 
 if __name__ == '__main__':
     main()

bin/metawrap-scripts/interleave_fastq.py

@@ -5,6 +5,7 @@
 Usage:
     interleave-fasta fasta_file1 fasta_file2
 """
+from __future__ import print_function
 
 import sys
 
@@ -15,20 +16,20 @@ def interleave(f1, f2):
         line = f1.readline()
         if line.strip() == "":
             break
-        print line.strip()
+        print(line.strip())
 
         for i in xrange(3):
-            print f1.readline().strip()
+            print(f1.readline().strip())
 
         for i in xrange(4):
-            print f2.readline().strip()
+            print(f2.readline().strip())
 
 if __name__ == '__main__':
     try:
         file1 = sys.argv[1]
         file2 = sys.argv[2]
     except:
-        print __doc__
+        print(__doc__)
         sys.exit(1)
 
     if file1[-2:] == "gz":

bin/metawrap-scripts/kraken2_translate.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+from __future__ import print_function
 import sys
 import os
 

bin/metawrap-scripts/kraken_to_krona.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python2.7
+from __future__ import print_function
 import sys
 # This script takes in a translated kraken file of either contigs (from SPAdes) or reads, and parses it into a format for ktImportText to produce a kronachart.
 data={}
@@ -24,5 +25,5 @@
 
 
 for tax in data:
-	print str(data[tax]) + "\t" + tax
+	print(str(data[tax]) + "\t" + tax)