-
Notifications
You must be signed in to change notification settings - Fork 73
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Added the script for word frequrncy counter issue
- Loading branch information
Showing
1 changed file
with
27 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
import re | ||
from collections import Counter | ||
|
||
def find_words_frequency(file_path): | ||
''' | ||
This script takes the path of the text file to be processed, as input (argument) | ||
and prints the top ten words and also prints their counts in given text file. | ||
''' | ||
with open(file_path, 'r', encoding='utf-8') as file: | ||
text = file.read().lower() | ||
|
||
all_words = re.findall(r'\b\w+\b', text) | ||
word_frequency = Counter(all_words) | ||
most_common_words = word_frequency.most_common(10) | ||
|
||
# Print in tabular format | ||
print(f"{'Word':<15} {'Count':<5}") | ||
print("-" * 20) | ||
for word, count in most_common_words: | ||
print(f"{word:<15} {count:<5}") | ||
|
||
def main(): | ||
file_path = input("Enter the path of file : ") | ||
find_words_frequency(file_path) | ||
|
||
if __name__ == "__main__": | ||
main() |