Untitled
from collections import Counter import re # Function to get word frequency matrix from a text file def get_word_frequency_matrix(file_path): with open(file_path, 'r') as file: text = file.read() # Clean the text (remove punctuation and convert to lowercase) words = re.findall(r'\b\w+\b', text.lower()) # Count word frequencies word_freq = Counter(words) # Create the word frequency matrix (list of tuples with word and frequency) word_freq_matrix = list(word_freq.items()) return word_freq_matrix # Example usage file_path = 'your_text_file.txt' word_freq_matrix = get_word_frequency_matrix(file_path) # Print the word frequency matrix for word, freq in word_freq_matrix: print(f'{word}: {freq}')
Leave a Comment