How to compare word frequencies from two text files?

Question

How to compare word frequencies from two text files in python? For example, if a word contains in file1 and file2 both then it should be written only once but not adding their frequencies while comparing, it should be {'The': 3,5}. Here 3 is the frequency in file1 and 5 is frequency in file2. And if some words only exist in one file but not both then for that file there should be 0. Please Help Here is what I have done so far:

import operator
f1=open('file1.txt','r') #file 1
f2=open('file2.txt','r') #file 2

wordlist=[]
wordlist2=[]
for line in f1:
    for word in line.split():
        wordlist.append(word)

for line in f2:
    for word in line.split():
        wordlist2.append(word)

worddictionary = {}
for word in wordlist:
    if word in worddictionary:
        worddictionary[word] += 1
    else:
        worddictionary[word] = 1

worddictionary2 = {}
for word in wordlist2:
    if word in worddictionary2:
        worddictionary2[word] += 1
    else:
        worddictionary2[word] = 1

print(worddictionary)
print(worddictionary2)

Answer 1

Edit: Here's the more general way you would do this for any list of files (explanation in comments):

f1=open('file1.txt','r') #file 1
f2=open('file2.txt','r') #file 2

file_list = [f1, f2] # This would hold all your open files
num_files = len(file_list)

frequencies = {} # We'll just make one dictionary to hold the frequencies

for i, f in enumerate(file_list): # Loop over the files, keeping an index i
    for line in f: # Get the lines of that file
        for word in line.split(): # Get the words of that file
            if not word in frequencies:
                frequencies[word] = [0 for _ in range(num_files)] # make a list of 0's for any word you haven't seen yet -- one 0 for each file

            frequencies[word][i] += 1 # Increment the frequency count for that word and file

print frequencies

Keeping with the code you wrote, here's how you could create a combined dictionary:

import operator
f1=open('file1.txt','r') #file 1
f2=open('file2.txt','r') #file 2

wordlist=[]
wordlist2=[]
for line in f1:
    for word in line.split():
        wordlist.append(word)

for line in f2:
    for word in line.split():
        wordlist2.append(word)

worddictionary = {}
for word in wordlist:
    if word in worddictionary:
        worddictionary[word] += 1
    else:
        worddictionary[word] = 1

worddictionary2 = {}
for word in wordlist2:
    if word in worddictionary2:
        worddictionary2[word] += 1
    else:
        worddictionary2[word] = 1

# Create a combined dictionary
combined_dictionary = {}
all_word_set = set(worddictionary.keys()) | set(worddictionary2.keys())
for word in all_word_set:
    combined_dictionary[word] = [0,0]
    if word in worddictionary:
        combined_dictionary[word][0] = worddictionary[word]
    if word in worddictionary2:
        combined_dictionary[word][1] = worddictionary2[word]


print(worddictionary)
print(worddictionary2)
print(combined_dictionary)