fin = open("ecoli_uti89.txt")
dna = ""
for line in fin.readlines():
    dna += line.strip()

print dna[-10:]

len(dna)

funcs = []

def count_for(dna, letter):
    c = 0
    for x in dna:
        if x == letter:
            c += 1
    return c

funcs.append(count_for)

def count_builtin(dna, letter):
    return dna.count(letter)

funcs.append(count_builtin)

def count_rec(dna, letter):
    if len(dna) == 0:
        return 0
    if dna[0] == letter:
        return 1 + count_rec(dna[1:], letter)
    else:
        return count_rec(dna[1:], letter)
#funcs.append(count_rec)

# Mitchell Sharp:

def count_diff(dna, letter):
    start = len(dna)
    dna2 = dna.replace(letter, "")
    end = len(dna2)
    return start - end

funcs.append(count_diff)

# Bryan Urban:

def count_while(dna, letter):
    c = 0
    num = 0
    while(c<len(dna)):
        if(dna[c]==letter):
            num+=1
        c+=1
    return num

funcs.append(count_while)

# Elizabeth Dye and Deonna Thornton

def count_dict(dna,letter):
    d={}
    for i in range(len(dna)):
        try:
            d[dna[i]]+=1
        except:
            d[dna[i]]=1
    
    if letter in d:
        return d[letter]
    else:
        return 0
  
funcs.append(count_dict)

# Hunter Lewis

def count_split(dna,letter):
    count = 0
    half1 = dna[0:len(dna)/2]
    half2 = dna[len(dna)/2:-1]
    for ele in half1:
        if ele == letter:
            count += 1
    for ele2 in half2:
        if ele2 == letter:
            count += 1
    return count

funcs.append(count_split)

# Mark Woodard

def count_skip(dna, letter):
    num = 0
    for i in range(0, len(dna), 2):
        if dna[i] == letter:
            num += 1
    for i in range(1, len(dna), 2):
        if dna[i] == letter:
            num += 1
    return num

funcs.append(count_skip)

#Deonna Thornton and Elizabeth Dye

def count_idx(dna, letter):
    a = []
    b = []
    for elt in dna:
        a.append(elt)
    a.sort()
    for i in range(len(a)):
        if a[i] == letter:
            b.append(a[i])
            g = len(b)
    if letter not in a:
        g = 0
    return g

funcs.append(count_idx)

# Mitch Lowry

def count_range(dna, letter):
    count = 0
    for x in range(len(dna)):
        if dna[x] == letter:
            count += 1
    return count

funcs.append(count_range)

# Luke Lasley

def count_reverse(dna, letter):
    count = len(dna)
    for ele in dna:
        if ele != letter:
            count -=1
    return count

funcs.append(count_reverse)

# Luke Evans, from the Filters link above

def count_filter(dna, letter):
    count = 0
    letters = [elem for elem in dna if elem == letter]
    count += len(letters)
    return count

funcs.append(count_filter)

# Chris Woodward

def count_sort(dna, letter):
    num = 0
    data = sorted(dna)
    for a in data:
        if a == letter:
            num += 1
        if num > 0 and a != letter:
            break
    return num

funcs.append(count_sort)

dir(count_for)

names = []
timings = []
results = []
import time

for f in funcs:
    t0 = time.clock()
    results.append(f(dna, "C"))
    t1 = time.clock()
    cpu_time = t1 - t0
    timings.append(cpu_time)
    names.append(f.func_name[6:])

timings

names

results

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

fig, ax = plt.subplots()

ind = np.arange(len(funcs))
width = 0.75

rects1 = ax.bar(ind, timings, width, color="r")

ax.set_xticks(ind + width / 2)
ax.set_xticklabels(names, rotation="vertical")

letters = ["A", "T", "G", "C"]
counts = []
for let in letters:
    counts.append(count_builtin(dna, let))

counts

plt.pie(counts, labels=letters)