Binomial distribution in VMS - Printable Version

Code:

#!/bin/bash



# Check if the correct number of arguments has been passed

if [ "$#" -ne 2 ]; then

    echo "Usage: $0 <inputfile> <outputfile>"

    exit 1

fi



# Input file and output file from the arguments

inputfile="$1"

outputfile="$2"



# Perform character replacements and write to the output file, remove empty lines

sed -e 's/@[^;]*;/w/g' \

    -e '/^$/d' "$inputfile" > "$outputfile"



# Print success message

echo "The file has been successfully written to $outputfile."

Code:

import sys

from collections import Counter

import re



# Function to calculate digram (bigram) frequency within words

def calculate_digram_frequency(filepath):

    # Read file content

    with open(filepath, 'r', encoding='utf-8') as file:

        text = file.read().lower()



    # Replace non-letter characters with spaces, except within words

    text = re.sub(r'[^a-z\s]', ' ', text)



    # Split text into words based on spaces

    words = text.split()



    # List to store bigrams

    bigrams = []



    # Generate bigrams within each word

    for word in words:

        if len(word) >= 2:

            bigrams.extend(word[i:i+2] for i in range(len(word) - 1))



    # Count the occurrences of each bigram

    counter = Counter(bigrams)



    return counter, len(bigrams)



# Main program

if __name__ == "__main__":

    if len(sys.argv) != 3:

        print("Usage: python program.py <input_filepath> <output_filepath>")

        sys.exit(1)



    input_filepath = sys.argv[1]  # Input file as an argument

    output_filepath = sys.argv[2]  # Output file as an argument



    # Calculate frequencies

    counter, total_bigram_count = calculate_digram_frequency(input_filepath)



    # Sort bigrams by frequency and select the top 12

    top_bigrams = counter.most_common(12)



    # Write the top 12 bigrams to the output file

    with open(output_filepath, 'w', encoding='utf-8') as output_file:

        output_file.write("  No.  Bigram Frequency (in %) Frequency\n")

        for i, (bigram, frequency) in enumerate(top_bigrams, 1):

            bigram_upper = bigram.upper()  # Convert bigram to uppercase

            frequency_percentage = (frequency / total_bigram_count) * 100 if total_bigram_count > 0 else 0.0

            output_file.write(f"{i:>4} {bigram_upper:>8} {frequency_percentage:>13.4f} {frequency:>10}\n")