File size: 6,899 Bytes
cfb5e7f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | """Visualization utilities for Myanmar Ghost project."""
from pathlib import Path
from typing import Any, Dict, List, Optional
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
def plot_training_curves(
history: Dict[str, List[float]],
metrics: List[str] = None,
title: str = "Training Curves",
output_path: Optional[str] = None,
figsize: tuple = (12, 8),
) -> plt.Figure:
"""Plot training curves for multiple metrics.
Args:
history: Dictionary mapping metric names to lists of values
metrics: List of metrics to plot (default: all)
title: Plot title
output_path: Path to save figure
figsize: Figure size
Returns:
Matplotlib figure
"""
if metrics is None:
metrics = list(history.keys())
n_metrics = len(metrics)
n_cols = min(2, n_metrics)
n_rows = (n_metrics + n_cols - 1) // n_cols
fig, axes = plt.subplots(n_rows, n_cols, figsize=figsize)
fig.suptitle(title, fontsize=16)
if n_metrics == 1:
axes = [axes]
else:
axes = axes.flatten() if hasattr(axes, 'flatten') else axes
for i, metric in enumerate(metrics):
ax = axes[i] if i < len(axes) else axes[0]
if metric in history:
values = history[metric]
steps = list(range(len(values)))
ax.plot(steps, values, marker='o', markersize=3)
ax.set_xlabel('Step/Epoch')
ax.set_ylabel(metric.capitalize())
ax.set_title(metric.capitalize())
ax.grid(True, alpha=0.3)
# Hide unused subplots
for i in range(n_metrics, len(axes)):
axes[i].set_visible(False)
plt.tight_layout()
if output_path:
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=150, bbox_inches='tight')
return fig
def plot_confusion_matrix(
cm: np.ndarray,
class_names: List[str],
title: str = "Confusion Matrix",
output_path: Optional[str] = None,
figsize: tuple = (10, 8),
normalize: bool = False,
) -> plt.Figure:
"""Plot confusion matrix.
Args:
cm: Confusion matrix
class_names: Names of classes
title: Plot title
output_path: Path to save figure
figsize: Figure size
normalize: Whether to normalize
Returns:
Matplotlib figure
"""
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
fig, ax = plt.subplots(figsize=figsize)
sns.heatmap(
cm,
annot=True,
fmt='.2f' if normalize else 'd',
cmap='Blues',
xticklabels=class_names,
yticklabels=class_names,
ax=ax,
)
ax.set_xlabel('Predicted')
ax.set_ylabel('True')
ax.set_title(title)
plt.tight_layout()
if output_path:
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=150, bbox_inches='tight')
return fig
def plot_label_distribution(
labels: List[Any],
class_names: Optional[List[str]] = None,
title: str = "Label Distribution",
output_path: Optional[str] = None,
figsize: tuple = (10, 6),
) -> plt.Figure:
"""Plot distribution of labels.
Args:
labels: List of labels
class_names: Names of classes
title: Plot title
output_path: Path to save figure
figsize: Figure size
Returns:
Matplotlib figure
"""
from collections import Counter
counts = Counter(labels)
if class_names:
labels_order = class_names
values = [counts.get(l, 0) for l in labels_order]
else:
labels_order = list(counts.keys())
values = list(counts.values())
fig, ax = plt.subplots(figsize=figsize)
bars = ax.bar(labels_order, values, color='steelblue', alpha=0.7)
# Add count labels on bars
for bar, count in zip(bars, values):
height = bar.get_height()
ax.text(
bar.get_x() + bar.get_width() / 2.,
height,
f'{int(count)}',
ha='center',
va='bottom',
)
ax.set_xlabel('Class')
ax.set_ylabel('Count')
ax.set_title(title)
ax.grid(True, alpha=0.3, axis='y')
plt.tight_layout()
if output_path:
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=150, bbox_inches='tight')
return fig
def plot_attention_weights(
attention_weights: np.ndarray,
tokens: List[str],
title: str = "Attention Weights",
output_path: Optional[str] = None,
figsize: tuple = (12, 10),
) -> plt.Figure:
"""Plot attention weights heatmap.
Args:
attention_weights: Attention weight matrix
tokens: List of tokens
title: Plot title
output_path: Path to save figure
figsize: Figure size
Returns:
Matplotlib figure
"""
fig, ax = plt.subplots(figsize=figsize)
sns.heatmap(
attention_weights,
xticklabels=tokens,
yticklabels=tokens,
cmap='viridis',
ax=ax,
cbar_kw={'label': 'Attention Weight'},
)
ax.set_xlabel('Key Tokens')
ax.set_ylabel('Query Tokens')
ax.set_title(title)
plt.tight_layout()
if output_path:
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=150, bbox_inches='tight')
return fig
def plot_loss_landscape(
losses: np.ndarray,
xlabel: str = "x",
ylabel: str = "y",
title: str = "Loss Landscape",
output_path: Optional[str] = None,
figsize: tuple = (10, 6),
) -> plt.Figure:
"""Plot loss landscape.
Args:
losses: 2D array of loss values
xlabel: Label for x-axis
ylabel: Label for y-axis
title: Plot title
output_path: Path to save figure
figsize: Figure size
Returns:
Matplotlib figure
"""
fig, ax = plt.subplots(figsize=figsize)
if losses.ndim == 1:
ax.plot(losses)
else:
sns.heatmap(losses, ax=ax, cmap='viridis')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
ax.set_title(title)
plt.tight_layout()
if output_path:
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=150, bbox_inches='tight')
return fig
if __name__ == "__main__":
print("Visualization utilities loaded")
print("Available functions:")
print(" - plot_training_curves")
print(" - plot_confusion_matrix")
print(" - plot_label_distribution")
print(" - plot_attention_weights")
print(" - plot_loss_landscape")
|