remove extra comments and prints

Author: David Pellow

classify_fasta.py

@@ -43,7 +43,6 @@ def main(args):
     seqs = []
     print "Reading {} in batches of 100k sequences".format(infile)
     i = 0
-    # TODO: buffer this and run classification on batches (say ~10k sequences at a time)
     fp = open(infile)
     with open(outfile,'w') as o:
         for name, seq, _ in utils.readfq(fp):
@@ -70,7 +69,6 @@ def main(args):
     print "Finished classifying"
     print "Class scores written in: {}".format(outfile)
 
-
 if __name__=='__main__':
     args = parse_user_input()
     main(args)

plasclass/plasclass.py

@@ -1,5 +1,5 @@
 ###
-# Define the classifier class and provide a set of functions to enable classification
+# Define the plasclass class and provide a set of functions to enable classification
 ###
 
 import numpy as np
@@ -48,12 +48,11 @@ def classify(self,seq):
             while seq_ind < len(seq):
                 print "Starting new batch"
                 seq_batch = seq[seq_ind:seq_ind + 100000]
-                print "Partitioning by length"
                 scales = [self._get_scale(len(s)) for s in seq_batch]
                 scale_partitions = {s: [seq_batch[i] for i,v in enumerate(scales) if v == s] for s in self._scales}
 
                 partitioned_classifications = {}
-                for scale in self._scales: #scale_partitions:
+                for scale in self._scales:
                     part_seqs = scale_partitions[scale]
                     if len(part_seqs) <= 0: continue
                     print "Getting kmer frequencies for partition length {}".format(scale)
@@ -74,7 +73,7 @@ def classify(self,seq):
 
                 seq_ind += 100000
 
-            # pool.close() TODO: is this needed?
+            # pool.close()
             return np.array(results)
 
         else:

plasclass/plasclass_utils.py

@@ -1,4 +1,4 @@
-# Utility functions for the classifier module
+# Utility functions for the plasclass module
 
 complements = {'A':'T', 'C':'G', 'G':'C', 'T':'A'}
 nt_bits = {'A':0,'C':1,'G':2,'T':3}