2.5 Problem 3

path="/Users/rocke/Desktop/wonderland.txt"
datafile=open(path,"r")
outfile=open("/Users/rocke/Desktop/wonderland.txt","w")
for line in datafile:
    outfile.write(line)
outfile.close()

datafile=open("/Users/rocke/Desktop/wonderland.txt","r")

letterFreqDic={}
alphabet="ABCDEFGHIJKLMNOPQRSTUVWXYZ"
for letter in alphabet:
    letterFreqDic[letter]=0
#print(letterFreqDic)
n = 0
for i, line in enumerate(datafile):
    if i< 60000:
        line=line.strip()
        if i <20:print(line)
        for letter in line:
            if letter.isalpha():
                letter = letter.upper()
                #print(letter)
                letterFreqDic[letter] = letterFreqDic[letter]+1
                n+=1

print(letterFreqDic)
letterfrequency=[]
for letter in alphabet:
    c=letterFreqDic[letter]
    letterfrequency.append((c/n,letter))

letterfrequency.sort()
letterfrequency.reverse()
for i in letterfrequency:
    print(i)

#Project Gutenberg's Alice's Adventures in Wonderland, by Lewis Carroll

#This eBook is for the use of anyone anywhere at no cost and with
#almost no restrictions whatsoever.  You may copy it, give it away or
#re-use it under the terms of the Project Gutenberg License included
#with this eBook or online at www.gutenberg.org


#Title: Alice's Adventures in Wonderland

#Author: Lewis Carroll

#Posting Date: June 25, 2008 [EBook #11]
#Release Date: March, 1994
#[Last updated: December 20, 2011]

#Language: English


#*** START OF THIS PROJECT GUTENBERG EBOOK ALICE'S ADVENTURES IN WONDERLAND ***
#{'P': 1968, 'Z': 80, 'S': 7268, 'M': 2467, 'N': 8051, 'Q': 220, 'F': 2382, 'V': 963, 'W': 2952, 'C': 3000, 'T': 12200, 'B': 1746, 'K': #1290, 'E': 15395, 'A': 9802, 'Y': 2584, 'G': 2943, 'J': 235, 'L': 5211, 'I': 8633, 'R': 6610, 'X': 176, 'D': 5469, 'O': 9477, 'H': #7889, 'U': 3978}
#(0.12517379603053932, 'E')
#(0.09919586304466253, 'T')
#(0.07969818439047395, 'A')
#(0.0770556716454317, 'O')
#(0.07019326931676817, 'I')
#(0.06546113880103098, 'N')
#(0.06414394783273301, 'H')
#(0.05909471578759076, 'S')
#(0.05374464382993601, 'R')
#(0.04446739139272618, 'D')
#(0.042369642813584955, 'L')
#(0.03234435599931701, 'U')
#(0.024392425338851442, 'C')
#(0.02400214653342982, 'W')
#(0.023928969257413266, 'G')
#(0.021010009025197375, 'Y')
#(0.02005870443698217, 'M')
#(0.019367585719048046, 'F')
#(0.016001431022286548, 'P')
#(0.01419639154721154, 'B')
#(0.01048874289570612, 'K')
#(0.007829968533771313, 'V')
#(0.0019107399848766963, 'J')
#(0.001788777858182439, 'Q')
#(0.0014310222865459514, 'X')
#(0.0006504646757027052, 'Z')

#https://drive.google.com/file/d/0By4QogT9U6sTbm5pamhQdFRDcDQ/view?usp=sharing