Added Ecoli dataset with tree, add clean goal, improve logs

Makefile

@@ -5,7 +5,12 @@ test:testsuite/test_rep.sh
 	@echo "all tests passed"
 
 test_y:
-	src/phybema.py --tools mash andi dnadiff -- testdata/Yersinia/
+	src/phybema.py --tools mash andi -- testdata/Yersinia/
+
+test_e:
+	src/phybema.py --tools mash andi -- testdata/E_coli/ 
 
 clean:
 	@${RM} -r temp out
+	@${RM} -f testdata/E_coli/sequence.fasta
+	@${RM} -f testdata/Yersinia/sequence.fasta

src/callProg.py

@@ -25,7 +25,7 @@ def run_prog(progname,call_list,fixed_out_file_name,progoutfilepath):
   sys.stderr.write("# starting program {}\n".format(progname))
   start_time = datetime.now()
   
-  sys.stderr.write(' '.join(call_list))
+  sys.stderr.write('# {}\n'.format(' '.join(call_list)))
   try:
     output = subprocess.run(call_list,stdout=subprocess.PIPE,
                             stderr=subprocess.PIPE, universal_newlines=True)

src/parser.py

@@ -122,7 +122,6 @@ def create_datatuplelist(datasetpaths):
         uncompressed_file = "{}".format(mo.group(1))
         if not os.path.isfile(uncompressed_file):
           call_list = ['gzip','-k','-d',datafile]
-          sys.stderr.write('{}\n'.format(' '.join(call_list)))
           try:
             output = subprocess.run(call_list,stdout=subprocess.PIPE,
                                     stderr=subprocess.PIPE, 

testdata/E_coli/.gitignore

+sequence.fasta

testdata/E_coli/tree.nh

+(((CP000970,CU928164),(FM180568,((CP000247,AE014075),(CU928162,(CP000243,(CU928161,CP000468)))))),(CU928163,((CP000034, (BA000007, AE005174)),(((AP009048, U00096.3),(CP000802,CP000946)),((CP000266,(AE005674, AE014073)), ((CP000038,(CP000036,CP001063)),(CP000800,(CU928145,(AP009240,CU928160)))))))));