Merge branch 'master' of gitlab.pasteur.fr:hub-courses/python_one_week_4_biologists_solutions

source/Collection_Data_Types.rst

@@ -391,7 +391,7 @@ Compute the 6 mers occurences of the sequence above, and print each 6mer and it'
    >>> s = s.replace('\n', '')
    >>> kmers = get_kmer_occurences(s, 6)
    >>> for kmer in kmers:
-   >>>   print kmer[0], '..', kmer[1]
+   >>>   print(kmer[0], '..', kmer[1])
    gcagag .. 2
    aacttc .. 1
    gcaact .. 1

source/_static/code/kmer.py

 
 def get_kmer_occurences(seq, kmer_len):
     """
-    return a list of tuple 
+    return a list of tuple
     each tuple contains a kmers present in seq and its occurence
     """
+    # Counter dictionary (keys will be kmers, values will be counts)
     kmers = {}
     stop = len(seq) - kmer_len
     for i in range(stop + 1):
+        # Extract kmer starting at position i
         kmer = seq[i: i + kmer_len]
+        # Increment the count for kmer
+        # or create the entry the first time this kmer is seen
+        # using default value 0, plus 1
         kmers[kmer] = kmers.get(kmer, 0) + 1
-    return kmers.items()
+    # pairs (kmer, count)
\ No newline at end of file
+    return kmers.items()