Binomial distribution in VMS - Printable Version

Code:

import sys
import numpy as np
import matplotlib.pyplot as plt
from scipy.special import comb
def calculate_binomial_distribution(n, max_length):
    """Calculates a binomial distribution for word lengths."""
    k_values = np.arange(1, max_length + 1)
    # Calculate the binomial distribution for the formula comb(n, k) * (0.5 ** n)
    probabilities = [comb(n, k) * (0.5 ** n) for k in k_values]
    # Normalize the distribution
    probabilities /= np.sum(probabilities)
    return k_values, probabilities
def plot_binomial_distribution(n, max_length):
    """Visualizes the binomial distribution and overlays the theoretical curve."""
    k_values, probabilities = calculate_binomial_distribution(n, max_length)
   
    # Calculate the theoretical binomial curve
    theoretical_probabilities = [comb(n, k) * (0.5 ** n) for k in k_values]
    theoretical_probabilities /= np.sum(theoretical_probabilities)
   
    plt.figure(figsize=(10, 6))
   
    # Plot the calculated probabilities
    plt.bar(k_values, probabilities, width=0.6, edgecolor='black', alpha=0.6, label='Calculated Distribution')
   
    # Plot the theoretical binomial curve
    plt.plot(k_values, theoretical_probabilities, 'r--', marker='o', label='Theoretical Distribution')
   
    plt.xlabel('Word Length')
    plt.ylabel('Probability')
    plt.title(f'Binomial Distribution for n={n}')
    plt.legend()
    plt.grid(True)
    plt.show()
def adjust_word_lengths(words, target_distribution):
    """Adjusts word lengths to fit the target distribution by truncating or extending words."""
    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)
   
        # If the target word length is shorter, truncate the word
        if target_length < current_length:
            adjusted_words.append(word[:target_length])
        # If the target word length is longer, extend the word with 'X'
        elif target_length > current_length:
            adjusted_words.append(word + 'X' * (target_length - current_length))
        else:
            adjusted_words.append(word)  # If the length matches, keep the word as is
    return adjusted_words
def process_text(file_path, output_path):
    """Reads the text from the file, adjusts word lengths, and writes the modified text to an output file."""
    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  # Set maximum word length
    n = 9  # Number of trials for the binomial distribution
    # Calculate the binomial distribution
    _, 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))
    # Write the modified text to the output file
    try:
        with open(output_path, 'w', encoding='utf-8') as file:
            file.write('\n'.join(adjusted_lines))
        print(f"Modified text has been written to {output_path}.")
    except IOError as e:
        print(f"Error: An error occurred while writing the file: {e}")
        sys.exit(1)
def main():
    if len(sys.argv) != 3:
        print("Usage: python adjust_word_length.py <input_filename> <output_filename>")
        sys.exit(1)
    input_file_path = sys.argv[1]
    output_file_path = sys.argv[2]
   
    # Optional visualization of the distribution
    max_word_length = 15
    n = 9
    plot_binomial_distribution(n, max_word_length)
   
    # Process the text and write to the output file
    process_text(input_file_path, output_file_path)
if __name__ == "__main__":
    main()

Code:

import numpy as np
import matplotlib.pyplot as plt
from scipy.special import comb
import argparse
import os
def calculate_binomial_distribution(n, max_length):
    """Berechnet eine Binomialverteilung für Wortlängen."""
    k_values = np.arange(1, max_length + 1)
    probabilities = [comb(n, k) * (0.5 ** n) for k in k_values]
    probabilities /= np.sum(probabilities)  # Normiert die Verteilung
    return k_values, probabilities
def plot_binomial_distribution(word_lengths, max_length=15, n=10):
    """Visualisiert die Binomialverteilung basierend auf den Wortlängen in der Textdatei."""
    if len(word_lengths) == 0:
        print("Error: Keine Wörter in der Datei gefunden.")
        return
   
    # Berechnung der Binomialverteilung
    k_values, binomial_probabilities = calculate_binomial_distribution(n, max_length)
   
    # Berechnung der Häufigkeitsverteilung für das Histogramm
    counts, bins = np.histogram(word_lengths, bins=np.arange(0.5, max_length + 1.5))
    probabilities = counts / np.sum(counts)  # Normalisieren
   
    plt.figure(figsize=(10, 6))
   
    # Histogramm der Wortlängen
    bin_centers = (bins[:-1] + bins[1:]) / 2
    plt.bar(bin_centers, probabilities, width=0.6, edgecolor='black', alpha=0.6, label='Calculated Distribution')
   
    # Binomialverteilungskurve anpassen
    plt.plot(k_values, binomial_probabilities, 'r--', marker='o', label='Theoretical Distribution')
   
    # Achsenbegrenzungen setzen, um die Kurve korrekt darzustellen
    plt.xlim(0.5, max_length + 0.5)
    plt.xticks(np.arange(1, max_length + 1))
   
    plt.xlabel('Word Length')
    plt.ylabel('Probability')
    plt.title(f'Binomial Distribution for n={n}')
    plt.legend()
    plt.grid(True)
    plt.show()
def process_text_file(file_path):
    """Liests eine Textdatei ein und berechnet die Wortlängen."""
    if not os.path.isfile(file_path):
        print(f"Error: Die Datei {file_path} wurde nicht gefunden.")
        return None
   
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            text = file.read()
    except IOError as e:
        print(f"Error: Ein Fehler ist beim Lesen der Datei aufgetreten: {e}")
        return None
   
    words = text.split()
    word_lengths = [len(word) for word in words]
   
    return word_lengths
def main():
    parser = argparse.ArgumentParser(description="Visualisiert die Binomialverteilung basierend auf einer Textdatei.")
    parser.add_argument('file', type=str, help='Pfad zur Textdatei')
    args = parser.parse_args()
   
    # Textdatei verarbeiten
    word_lengths = process_text_file(args.file)
   
    if word_lengths is not None:
        plot_binomial_distribution(word_lengths, max_length=15, n=10)
if __name__ == "__main__":
    main()