ETL Pipeline Data Volume

import matplotlib.pyplot as plt
import squarify
import numpy as np

# Data volume (in TB/day)
labels = ['Kafka Streams', 'Batch Files', 'API Ingestion', 'CDC Events',
          'Log Aggregation', 'IoT Sensors', 'Web Scraping', 'Third-party APIs']
sizes = [45, 28, 18, 32, 22, 38, 8, 12]
total = sum(sizes)

# CLAUDE.md colors
colors = ['#27D3F5', '#F5276C', '#6CF527', '#5314E6', '#F5B027',
          '#276CF5', '#F54927', '#27F5B0']

fig, ax = plt.subplots(figsize=(12, 8), facecolor='#0a0a0f')
ax.set_facecolor('#0a0a0f')

pct = [s/total*100 for s in sizes]
squarify.plot(sizes=sizes, 
              label=[f'{l}\n{s}TB ({p:.1f}%)' for l, s, p in zip(labels, sizes, pct)],
              color=colors, alpha=0.85, ax=ax,
              text_kwargs={'fontsize': 10, 'color': 'white', 'fontweight': 'bold'})

ax.axis('off')
ax.set_title(f'Daily ETL Data Volume - {total}TB/day', 
             fontsize=18, color='#f8fafc', fontweight='bold', pad=20)

plt.tight_layout()
plt.show()