Question

I cant get this python program to read all the unique words in a file. It can only read the number of the unique words in a line.

import re
import string
from collections import Counter
# opens user inputted filename ".txt" and (w+) makes new and writes
def main():
textname = input("Enter the file to search: ")
fh = open(textname, 'r', encoding='utf-8' )
linecount = 0
wordcount = 0
count = {}
print("Sumary of the", fh)
for line in fh.readlines():
linecount = linecount+1
word = re.findall('[a-zA-Z0-9\-\']+', line)
wordcount = len(word) + wordcount
unique_words_line = len(set(word))
#print(length)
length = len(word)

print("Line",linecount, ":", length, "words", unique_words_line, "unique words")

# if line in count:
# count[line] += 1
# else:
# count[line] = 1

print("Total number of world found in the file is:", wordcount)
print("Total number of unique words found in the file are:", )
# for word, times in count.items():
# print ("%s was found %d times" %(word, times))

if __name__ == "__main__": main()

Answer 1

Please Refer to the following code below:

import re


# opens user inputted filename ".txt" and (w+) makes new and writes
def main():
    textname = input("Enter the file to search: ")
    fh = open(textname, 'r', encoding='utf-8')
    linecount = 0
    wordcount = 0
    count = {}
    print("Sumary of the", fh.name)
    # set to store unique words of file
    unique_words = set()
    for line in fh.readlines():
        linecount = linecount + 1
        word = re.findall('[a-zA-Z0-9\-\']+', line)
        # loop for iteration in unique words in line
        for i in set(word):
            # adding unique words of file to file unique words
            unique_words.add(i)
        wordcount = len(word) + wordcount
    unique_words_line = len(set(unique_words))

    print("Line", linecount, ":", wordcount, " words:", unique_words_line, "unique words")

    print("Total number of word found in the file is:", wordcount)
    print("Total number of unique words found in the file are:", unique_words_line)


if __name__ == "__main__":
    main()

Output:-

Enter the file to search: textname.txt
Sumary of the textname.txt
Line 3 : 8 words: 4 unique words
Total number of word found in the file is: 8
Total number of unique words found in the file are: 4

Input file textname.txt:-

print print print anoop
sharma print
print abc

============================================================================

Please refer to the images below:-

Code:-

OUTPUT:-

INput file:-

=============================================================================

Please upvote

=============================================================================