| import matplotlib.pyplot as plt |
| import numpy as np |
| import pandas as pd |
| from preprocess import split_sentences, split_words |
|
|
| def graph_sentence_lengths(files, window=20): |
| plt.figure(figsize=(12, 6)) |
| |
| for file in files: |
| with open(file.name, 'r', encoding='utf-8') as f: |
| text = f.read() |
| |
| sentences = split_sentences(text) |
| lengths = [] |
| for sent in sentences: |
| words = split_words(sent) |
| lengths.append(len(words)) |
| |
| n = len(lengths) |
| if n > 1: |
| smoothed = [] |
| half = window // 2 |
| for i in range(n): |
| start = max(0, i - half) |
| end = min(n, i + half + 1) |
| smoothed.append(np.median(lengths[start:end])) |
| |
| x_normalized = np.linspace(0, 1, n) |
| plt.plot(x_normalized, smoothed, label=file.name.split('/')[-1], linewidth=1.5) |
| |
| plt.xlabel('Относительная позиция в тексте') |
| plt.ylabel('Длина предложения (сглажено)') |
| plt.title('Распределение длин предложений по тексту') |
| plt.legend(loc='upper right', fontsize=8) |
| plt.grid(True, alpha=0.3) |
| return plt.gcf() |
