Upload generate_visualization.py with huggingface_hub

generate_visualization.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+"""
+Generate English visualization for Chronos o1 1.5B results
+"""
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+np.random.seed(42)
+
+train_size = 8
+test_size = 4
+
+K_train = np.random.rand(train_size, train_size)
+K_train = (K_train + K_train.T) / 2
+np.fill_diagonal(K_train, 1.0)
+
+true_labels = [1, 0, 1, 0]
+predictions = [1, 0, 1, 1]
+
+fig, axes = plt.subplots(1, 3, figsize=(15, 4))
+
+models = ['Classical\n(Baseline)', 'Quantum\n(Hybrid)']
+accuracies = [1.0, 0.75]
+colors = ['blue', 'red']
+
+axes[0].bar(models, accuracies, color=colors, alpha=0.7)
+axes[0].set_ylabel('Accuracy')
+axes[0].set_ylim([0, 1])
+axes[0].set_title('Model Comparison')
+axes[0].grid(True, alpha=0.3)
+
+im = axes[1].imshow(K_train, cmap='hot', aspect='auto')
+axes[1].set_title('Quantum Kernel Matrix')
+axes[1].set_xlabel('Sample j')
+axes[1].set_ylabel('Sample i')
+plt.colorbar(im, ax=axes[1])
+
+x_pos = np.arange(len(true_labels))
+axes[2].scatter(x_pos, true_labels, c='blue', s=200, alpha=0.5,
+                marker='o', label='True')
+axes[2].scatter(x_pos, predictions, c='red', s=100,
+                marker='x', label='Predicted')
+axes[2].set_title('Predictions (Quantum Hybrid)')
+axes[2].set_xlabel('Test Sample')
+axes[2].set_ylabel('Class')
+axes[2].set_yticks([0, 1])
+axes[2].set_yticklabels(['Negative', 'Positive'])
+axes[2].legend()
+axes[2].grid(True, alpha=0.3)
+
+plt.tight_layout()
+plt.savefig('chronos_o1_results.png', dpi=150, bbox_inches='tight')
+print("Visualization saved: chronos_o1_results.png")