#from human import dna
from guinea_pig import dna


# Question 0: How often is a base followed immediately by the same base?
# (if completely random, we'd expect this to be 0.25)

count = 0
for j in range(len(dna)-1):              # len(dna)-1 possible starting locations
    if dna[j] == dna[j+1]:
        count += 1

percent = count/float(len(dna)-1)

print("percent of repeat bases:")
print(percent)
print('')


# Question 1: What percentage of consecutive bases are pattern 'AT'?
# (if completely random, we'd expect 1/16 pairs)

count = 0
for j in range(len(dna)-1):              # len(dna)-1 possible starting locations
    if dna[j:j+2] == 'AT':
        count += 1

percent = count/float(len(dna)-1)

print("percent of AT pairs:")
print(percent)
print('')


# Question 2: What are the relative percentage of bases that immediately follow an 'A'?

countA = countC = countG = countT = 0
for j in range(len(dna)-1):              # len(dna)-1 possible starting locations
    if dna[j] == 'A':
        if dna[j+1] == 'A':
            countA += 1
        elif dna[j+1] == 'C':
            countC += 1
        elif dna[j+1] == 'G':
            countG += 1
        else:
            countT += 1

total = float(countA + countC + countG + countT)
print("percent of bases following an A:")
print('A', countA/total)
print('C', countC/total)
print('G', countG/total)
print('T', countT/total)
print('')


# Question 3: What percentage of the time is a base the same as the base that was TWO earlier?

count = 0
for j in range(len(dna)-3):        # only len(dna)-3 possible locations for first of the two
    if dna[j] == dna[j+2]:
        count += 1

print("percent of base matches two apart:")
print(count/float(len(dna)-2))
print('')


# Question 4: How many times does the pattern CCAAT occur?
# (We want you to determine this WITHOUT using the built-in count method)
# (Hint: Keep track of a sliding window of the most recent five characters)

count = 0
for j in range(len(dna)-4):
    if dna[j:j+5] == 'CCAAT':
        count += 1

print("number of CCAAT occurrences:")
print(count)
print('')