#!/usr/bin/env python

import random
import sys

#function that simulates the DNA sequence
def simulate_sequence(length):
    dna = ['A', 'C', 'G', 'T']
    sequence = ''
    for i in range(length):
        sequence += random.choice(dna)
    return sequence

#function that determines the nucleotide frequencies
def nucleotide_percentage(sequence):
    print str(sequence.count('A')) + ' As ',
    print str(sequence.count('C')) + ' Cs ',
    print str(sequence.count('G')) + ' Gs ',
    print str(sequence.count('T')) + ' Ts'

#function that determines the sequence identities
def sequence_identity(set):
    iden = []
    count = 0.0
    for x in range(len(set)-1):
        print str(x), str(x+1)
        for n in range(len(set[x])):
            if set[x][n] == set[x+1][n]:
                count += 1
        iden.append(count/len(set[x]))
        count = 0.0
    return iden


#get three values from the parameters
setsize = int(sys.argv[1])      #number of sequences to simulate
minlength = int(sys.argv[2])    #minimum sequence length
maxlength = int(sys.argv[3])    #maximum sequence length

sequenceset = []
for i in range(setsize):
    rlength = random.randint(minlength, maxlength)
    sequenceset.append(simulate_sequence(rlength))

identity = sequence_identity(sequenceset)

#print the results
for i in range(len(sequenceset)):
    print sequenceset[i]
    if i < len(sequenceset)-1:
        print 'sequence identity to next sequence : ' + str(identity[i])
    nucleotide_percentage(sequenceset[i])
    print