Harvard:Biophysics 101/2007/Notebook:Keller Rinaudo/2007-2-8

The Script

#!/usr/bin/env python

# Create an empty list to store the strings
import random
List = []
s = []
All_Strings = []

# Generate 10,000 strings using a for loop and add those to the list
print "Generating Strings..."
for i in range(10000):
   s = ''.join([random.choice('HT') for n in range(10)])
   List.append(s)
print '='*70

# Iterate through the list and count up the stretches of H's and T's
tally = [0 for i in range(10)]

variables = ['H','T']
print "Counting repeat stretches of H and T..."
for j in variables:
    for i in range (10):
        substr = ''.join([j for n in range(i+1)])
        for k in range (10000):
            All_Strings = List[k]
            count = 0
            pos = All_Strings.find(substr,0)
            while not pos == -1:
                count = count + 1
                pos = All_Strings.find(substr,pos+1)
            tally[i] = tally[i] + count

 #We must then print i and the number of times that i occurs (tally[i])
for i in range(len(tally)):
    print "%2d: %6d" % (i+1, tally[i])
print '='*70
print "Calculation Complete"

Output

>>> 
Generating Strings...
======================================================================
Counting repeat stretches of H and T...
 1: 100000
 2:  44902
 3:  19947
 4:   8716
 5:   3745
 6:   1554
 7:    604
 8:    212
 9:     61
10:     15
======================================================================
Calculation Complete
>>>