#!/usr/bin/python

seq_filename = "Ecoli_genome.txt"
total_length = 0
dinucleotide = {} # create an empty dictionary
genome = ""

seq_file = open(seq_filename, "r")
for raw_line in seq_file:
    line = raw_line.rstrip("\r\n")
    length = len(line)
    genome += line
    total_length += length

seq_file.close()

print "This genome was {0} nucleotides long".format(total_length)
print "The first 1000 nucleotides are {0}".format(genome[0:1000])

for position in range(total_length-1):
   dinuc = genome[position:position+2]
   if dinucleotide.has_key(dinuc):
       dinucleotide[dinuc] += 1
   else:
       dinucleotide[dinuc] = 1


for n in dinucleotide.keys():
    fraction = 100.0 * dinucleotide[n] / total_length
    print "The dinucleotide {0} occurs {1} times, or {2} %".format(n, dinucleotide[n], fraction)