# Advanced visualization
fig, axes = plt.subplots(2, 3, figsize=(18, 12))
# Plot 1: Parameter evolution across iterations
ax = axes[0, 0]
colors = ['lightblue', 'orange', 'lightgreen', 'red']
for i, result in enumerate(all_results):
if i < len(colors):
ax.scatter(result.samples['beta'], result.samples['gamma'],
alpha=0.6, s=20, color=colors[i], label=f'Iteration {i+1}')
ax.axvline(beta_true, color='red', linestyle='--', linewidth=2, alpha=0.8)
ax.axhline(gamma_true, color='red', linestyle='--', linewidth=2, alpha=0.8)
ax.set_xlabel('β (transmission rate)')
ax.set_ylabel('γ (recovery rate)')
ax.set_title('Parameter Space Evolution')
ax.legend()
ax.grid(True, alpha=0.3)
# Plot 2: Final parameter distributions
ax = axes[0, 1]
ax.hist(final_samples['beta'], bins=25, alpha=0.7, color='blue', density=True, label='β')
ax.axvline(beta_true, color='red', linestyle='--', linewidth=2, label=f'True β = {beta_true}')
ax.axvline(final_samples['beta'].median(), color='blue', linestyle='-', linewidth=2,
label=f'Est. β = {final_samples["beta"].median():.2f}')
ax.set_xlabel('β')
ax.set_ylabel('Density')
ax.set_title('β Distribution')
ax.legend()
ax.grid(True, alpha=0.3)
ax = axes[0, 2]
ax.hist(final_samples['gamma'], bins=25, alpha=0.7, color='orange', density=True, label='γ')
ax.axvline(gamma_true, color='red', linestyle='--', linewidth=2, label=f'True γ = {gamma_true}')
ax.axvline(final_samples['gamma'].median(), color='orange', linestyle='-', linewidth=2,
label=f'Est. γ = {final_samples["gamma"].median():.2f}')
ax.set_xlabel('γ')
ax.set_ylabel('Density')
ax.set_title('γ Distribution')
ax.legend()
ax.grid(True, alpha=0.3)
# Plot 3: R0 distribution
ax = axes[1, 0]
ax.hist(R0_samples, bins=25, alpha=0.7, color='purple', density=True)
ax.axvline(R0_true, color='red', linestyle='--', linewidth=2, label=f'True R₀ = {R0_true:.2f}')
ax.axvline(R0_median, color='purple', linestyle='-', linewidth=2, label=f'Est. R₀ = {R0_median:.2f}')
ax.set_xlabel('R₀')
ax.set_ylabel('Density')
ax.set_title('R₀ Distribution')
ax.legend()
ax.grid(True, alpha=0.3)
# Plot 4: Acceptance rate evolution
ax = axes[1, 1]
iterations = range(1, len(all_results) + 1)
sample_counts = [len(result.samples) for result in all_results]
ax.bar(iterations, sample_counts, alpha=0.7, color='green')
ax.set_xlabel('Iteration')
ax.set_ylabel('Plausible Samples')
ax.set_title('Sample Count per Iteration')
ax.grid(True, alpha=0.3)
# Plot 5: Feature selection summary
ax = axes[1, 2]
all_features = []
for result in all_results:
all_features.extend(result.emulated_outputs)
feature_counts = pd.Series(all_features).value_counts()
feature_counts.plot(kind='bar', ax=ax, color='teal', alpha=0.7)
ax.set_xlabel('Features')
ax.set_ylabel('Times Selected')
ax.set_title('Feature Selection Frequency')
ax.tick_params(axis='x', rotation=45)
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()
print(f"\n Feature Selection Summary:")
for feature, count in feature_counts.head().items():
print(f" {feature}: used {count} time(s)")