Binomial distribution in VMS - Printable Version

Code:
import sys
import numpy as np
from scipy.special import comb

def calculate_binomial_distribution(n, max_length):
    """Berechnet eine Binomialverteilung für Wortlängen."""
    k_values = np.arange(1, max_length + 1)
    # Berechne die Binomialverteilung für die Formel choose(9, k-1) / 2^9
    probabilities = [comb(n, k-1) / (2 ** n) for k in k_values]
  
    # Normiere die Verteilung
    probabilities /= np.sum(probabilities)
  
    return probabilities

def adjust_word_lengths(words, target_distribution):
    """Passt die Wortlängen an die Zielverteilung an, indem Wörter gekürzt oder verlängert werden."""
    adjusted_words = []
    max_word_length = len(target_distribution)
  
    length_bins = np.arange(1, max_word_length + 1)
    length_probs = np.array(target_distribution)
  
    for word in words:
        current_length = len(word)
        target_length = np.random.choice(length_bins, p=length_probs)
      
        # Falls die Zielwortlänge kleiner ist, kürze das Wort
        if target_length < current_length:
            adjusted_words.append(word[:target_length])
        # Falls die Zielwortlänge größer ist, verlängere das Wort mit 'X'
        elif target_length > current_length:
            adjusted_words.append(word + 'X' * (target_length - current_length))
        else:
            adjusted_words.append(word)  # Wenn die Länge passt, bleibt das Wort unverändert
  
    return adjusted_words

def process_text(file_path):
    """Liest den Text aus der Datei, passt die Wortlängen an und gibt den neuen Text zurück."""
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            lines = file.readlines()
    except FileNotFoundError:
        print(f"Error: The file {file_path} was not found.")
        sys.exit(1)
    except IOError as e:
        print(f"Error: An error occurred while reading the file: {e}")
        sys.exit(1)
  
    max_word_length = 15  # Maximale Wortlänge festlegen
    n = 9  # Anzahl der Würfe für die Binomialverteilung
  
    # Berechne die Binomialverteilung
    target_distribution = calculate_binomial_distribution(n, max_word_length)
  
    adjusted_lines = []
    for line in lines:
        words = line.split()
        adjusted_words = adjust_word_lengths(words, target_distribution)
        adjusted_lines.append(' '.join(adjusted_words))
  
    return '\n'.join(adjusted_lines)

def main():
    if len(sys.argv) != 2:
        print("Usage: python adjust_word_length.py <filename>")
        sys.exit(1)
  
    file_path = sys.argv[1]
    new_text = process_text(file_path)
    print("Modified text:")
    print(new_text)

if __name__ == "__main__":
    main()