refactor: reorganize project structure by moving core modules and update import paths in API server
This commit is contained in:
@@ -0,0 +1,14 @@
|
||||
import joblib, numpy as np
|
||||
data = joblib.load('dataset_cache/training_data_2d_temporal.joblib')
|
||||
X, y = data['X'], data['y']
|
||||
print(f'Shape: {X.shape}, dtype: {X.dtype}')
|
||||
print(f'Labels unique: {np.unique(y)}')
|
||||
print(f'Label counts:')
|
||||
for lbl in sorted(np.unique(y)):
|
||||
print(f' Label {lbl}: {(y==lbl).sum()}')
|
||||
print(f'Range: [{X.min():.4f}, {X.max():.4f}], Mean: {X.mean():.4f}')
|
||||
print(f'AllZero patches: {(X.reshape(X.shape[0],-1).sum(1)==0).sum()}')
|
||||
for t in range(4):
|
||||
block = X[:, t*6:(t+1)*6]
|
||||
nz = (block.reshape(block.shape[0],-1).sum(1)!=0).sum()
|
||||
print(f' Timestep {t}: non-zero={nz}/{len(X)}')
|
||||
@@ -0,0 +1,786 @@
|
||||
"""
|
||||
Auto Report Generator for Land Classification
|
||||
Tự động tạo báo cáo HTML chi tiết sau training/prediction
|
||||
"""
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
import base64
|
||||
import io
|
||||
|
||||
# Optional: for generating charts
|
||||
try:
|
||||
import matplotlib
|
||||
matplotlib.use('Agg') # Non-interactive backend
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
MATPLOTLIB_AVAILABLE = True
|
||||
except ImportError:
|
||||
MATPLOTLIB_AVAILABLE = False
|
||||
|
||||
|
||||
def generate_confusion_matrix_image(conf_matrix, class_names):
|
||||
"""Tạo hình ảnh confusion matrix dạng base64"""
|
||||
if not MATPLOTLIB_AVAILABLE:
|
||||
return None
|
||||
|
||||
try:
|
||||
fig, ax = plt.subplots(figsize=(10, 8))
|
||||
conf_matrix = np.array(conf_matrix)
|
||||
|
||||
im = ax.imshow(conf_matrix, interpolation='nearest', cmap=plt.cm.Blues)
|
||||
ax.figure.colorbar(im, ax=ax)
|
||||
|
||||
ax.set(xticks=np.arange(len(class_names)),
|
||||
yticks=np.arange(len(class_names)),
|
||||
xticklabels=class_names, yticklabels=class_names,
|
||||
title='Confusion Matrix',
|
||||
ylabel='Thực tế (True)',
|
||||
xlabel='Dự đoán (Predicted)')
|
||||
|
||||
plt.setp(ax.get_xticklabels(), rotation=45, ha="right", rotation_mode="anchor")
|
||||
|
||||
# Add text annotations
|
||||
thresh = conf_matrix.max() / 2.
|
||||
for i in range(len(class_names)):
|
||||
for j in range(len(class_names)):
|
||||
ax.text(j, i, format(conf_matrix[i, j], 'd'),
|
||||
ha="center", va="center",
|
||||
color="white" if conf_matrix[i, j] > thresh else "black")
|
||||
|
||||
fig.tight_layout()
|
||||
|
||||
# Convert to base64
|
||||
buf = io.BytesIO()
|
||||
plt.savefig(buf, format='png', dpi=100, bbox_inches='tight')
|
||||
buf.seek(0)
|
||||
img_base64 = base64.b64encode(buf.read()).decode('utf-8')
|
||||
plt.close(fig)
|
||||
|
||||
return img_base64
|
||||
except Exception as e:
|
||||
print(f"Error generating confusion matrix image: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def generate_class_distribution_chart(class_names, classification_report):
|
||||
"""Tạo biểu đồ phân bố các class dạng base64"""
|
||||
if not MATPLOTLIB_AVAILABLE:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Extract support (number of samples) for each class
|
||||
supports = []
|
||||
for cls in class_names:
|
||||
if cls in classification_report:
|
||||
supports.append(classification_report[cls].get('support', 0))
|
||||
else:
|
||||
supports.append(0)
|
||||
|
||||
fig, ax = plt.subplots(figsize=(10, 6))
|
||||
colors = plt.cm.Set3(np.linspace(0, 1, len(class_names)))
|
||||
|
||||
bars = ax.bar(class_names, supports, color=colors)
|
||||
ax.set_xlabel('Loại đất')
|
||||
ax.set_ylabel('Số mẫu')
|
||||
ax.set_title('Phân bố số mẫu theo loại đất')
|
||||
plt.xticks(rotation=45, ha='right')
|
||||
|
||||
# Add value labels on bars
|
||||
for bar, val in zip(bars, supports):
|
||||
ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 0.5,
|
||||
str(int(val)), ha='center', va='bottom', fontsize=9)
|
||||
|
||||
fig.tight_layout()
|
||||
|
||||
# Convert to base64
|
||||
buf = io.BytesIO()
|
||||
plt.savefig(buf, format='png', dpi=100, bbox_inches='tight')
|
||||
buf.seek(0)
|
||||
img_base64 = base64.b64encode(buf.read()).decode('utf-8')
|
||||
plt.close(fig)
|
||||
|
||||
return img_base64
|
||||
except Exception as e:
|
||||
print(f"Error generating class distribution chart: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def generate_metrics_chart(class_names, classification_report):
|
||||
"""Tạo biểu đồ precision/recall/f1 cho từng class"""
|
||||
if not MATPLOTLIB_AVAILABLE:
|
||||
return None
|
||||
|
||||
try:
|
||||
precisions = []
|
||||
recalls = []
|
||||
f1_scores = []
|
||||
|
||||
for cls in class_names:
|
||||
if cls in classification_report:
|
||||
precisions.append(classification_report[cls].get('precision', 0))
|
||||
recalls.append(classification_report[cls].get('recall', 0))
|
||||
f1_scores.append(classification_report[cls].get('f1-score', 0))
|
||||
else:
|
||||
precisions.append(0)
|
||||
recalls.append(0)
|
||||
f1_scores.append(0)
|
||||
|
||||
x = np.arange(len(class_names))
|
||||
width = 0.25
|
||||
|
||||
fig, ax = plt.subplots(figsize=(12, 6))
|
||||
|
||||
bars1 = ax.bar(x - width, precisions, width, label='Precision', color='#3498db')
|
||||
bars2 = ax.bar(x, recalls, width, label='Recall', color='#2ecc71')
|
||||
bars3 = ax.bar(x + width, f1_scores, width, label='F1-Score', color='#e74c3c')
|
||||
|
||||
ax.set_xlabel('Loại đất')
|
||||
ax.set_ylabel('Score')
|
||||
ax.set_title('Precision / Recall / F1-Score theo loại đất')
|
||||
ax.set_xticks(x)
|
||||
ax.set_xticklabels(class_names, rotation=45, ha='right')
|
||||
ax.legend()
|
||||
ax.set_ylim(0, 1.1)
|
||||
|
||||
# Add grid
|
||||
ax.yaxis.grid(True, linestyle='--', alpha=0.7)
|
||||
|
||||
fig.tight_layout()
|
||||
|
||||
# Convert to base64
|
||||
buf = io.BytesIO()
|
||||
plt.savefig(buf, format='png', dpi=100, bbox_inches='tight')
|
||||
buf.seek(0)
|
||||
img_base64 = base64.b64encode(buf.read()).decode('utf-8')
|
||||
plt.close(fig)
|
||||
|
||||
return img_base64
|
||||
except Exception as e:
|
||||
print(f"Error generating metrics chart: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def generate_training_report(training_result, config=None):
|
||||
"""
|
||||
Tạo báo cáo HTML cho kết quả training
|
||||
|
||||
Args:
|
||||
training_result: Dict chứa kết quả từ train_model()
|
||||
config: Dict chứa cấu hình training (optional)
|
||||
|
||||
Returns:
|
||||
Tuple (report_path, report_html)
|
||||
"""
|
||||
|
||||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
|
||||
# Extract data from result
|
||||
train_acc = training_result.get('train_accuracy', 0) * 100
|
||||
test_acc = training_result.get('test_accuracy', 0) * 100
|
||||
train_samples = training_result.get('training_samples', 0)
|
||||
test_samples = training_result.get('testing_samples', 0)
|
||||
test_size = training_result.get('test_size', 0.2)
|
||||
classes = training_result.get('classes', [])
|
||||
cls_report = training_result.get('classification_report', {})
|
||||
conf_matrix = training_result.get('confusion_matrix', [])
|
||||
model_type = training_result.get('model_type', 'unknown')
|
||||
model_path = training_result.get('model_path', '')
|
||||
bbox = training_result.get('bbox', [])
|
||||
time_range = training_result.get('time_range', '')
|
||||
resolution = training_result.get('resolution', 20)
|
||||
|
||||
# Generate charts
|
||||
conf_matrix_img = generate_confusion_matrix_image(conf_matrix, classes) if conf_matrix else None
|
||||
class_dist_img = generate_class_distribution_chart(classes, cls_report) if cls_report else None
|
||||
metrics_img = generate_metrics_chart(classes, cls_report) if cls_report else None
|
||||
|
||||
# Build classification report table
|
||||
cls_report_rows = ""
|
||||
for cls in classes:
|
||||
if cls in cls_report:
|
||||
metrics = cls_report[cls]
|
||||
cls_report_rows += f"""
|
||||
<tr>
|
||||
<td><strong>{cls}</strong></td>
|
||||
<td>{metrics.get('precision', 0):.3f}</td>
|
||||
<td>{metrics.get('recall', 0):.3f}</td>
|
||||
<td>{metrics.get('f1-score', 0):.3f}</td>
|
||||
<td>{int(metrics.get('support', 0))}</td>
|
||||
</tr>
|
||||
"""
|
||||
|
||||
# Add averages
|
||||
for avg_type in ['macro avg', 'weighted avg']:
|
||||
if avg_type in cls_report:
|
||||
metrics = cls_report[avg_type]
|
||||
cls_report_rows += f"""
|
||||
<tr style="background-color: #f0f0f0; font-weight: bold;">
|
||||
<td>{avg_type}</td>
|
||||
<td>{metrics.get('precision', 0):.3f}</td>
|
||||
<td>{metrics.get('recall', 0):.3f}</td>
|
||||
<td>{metrics.get('f1-score', 0):.3f}</td>
|
||||
<td>{int(metrics.get('support', 0))}</td>
|
||||
</tr>
|
||||
"""
|
||||
|
||||
# Build confusion matrix table (fallback if no image)
|
||||
conf_matrix_table = ""
|
||||
if conf_matrix:
|
||||
conf_matrix_table = "<table class='conf-matrix'><tr><th></th>"
|
||||
for cls in classes:
|
||||
conf_matrix_table += f"<th>{cls}</th>"
|
||||
conf_matrix_table += "</tr>"
|
||||
for i, row in enumerate(conf_matrix):
|
||||
conf_matrix_table += f"<tr><th>{classes[i]}</th>"
|
||||
for val in row:
|
||||
conf_matrix_table += f"<td>{val}</td>"
|
||||
conf_matrix_table += "</tr>"
|
||||
conf_matrix_table += "</table>"
|
||||
|
||||
# HTML Template
|
||||
html = f"""
|
||||
<!DOCTYPE html>
|
||||
<html lang="vi">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Training Report - {timestamp}</title>
|
||||
<style>
|
||||
* {{
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
box-sizing: border-box;
|
||||
}}
|
||||
body {{
|
||||
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
|
||||
background: #f5f5f5;
|
||||
padding: 20px;
|
||||
line-height: 1.6;
|
||||
}}
|
||||
.container {{
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
background: white;
|
||||
border-radius: 15px;
|
||||
box-shadow: 0 10px 40px rgba(0,0,0,0.1);
|
||||
overflow: hidden;
|
||||
}}
|
||||
.header {{
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
color: white;
|
||||
padding: 40px;
|
||||
text-align: center;
|
||||
}}
|
||||
.header h1 {{
|
||||
font-size: 2.5em;
|
||||
margin-bottom: 10px;
|
||||
}}
|
||||
.header .subtitle {{
|
||||
opacity: 0.9;
|
||||
font-size: 1.1em;
|
||||
}}
|
||||
.content {{
|
||||
padding: 40px;
|
||||
}}
|
||||
.section {{
|
||||
margin-bottom: 40px;
|
||||
}}
|
||||
.section h2 {{
|
||||
color: #667eea;
|
||||
border-bottom: 3px solid #667eea;
|
||||
padding-bottom: 10px;
|
||||
margin-bottom: 20px;
|
||||
font-size: 1.5em;
|
||||
}}
|
||||
.stats-grid {{
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
|
||||
gap: 20px;
|
||||
margin-bottom: 30px;
|
||||
}}
|
||||
.stat-card {{
|
||||
background: linear-gradient(135deg, #667eea15 0%, #764ba215 100%);
|
||||
padding: 25px;
|
||||
border-radius: 10px;
|
||||
text-align: center;
|
||||
border: 1px solid #667eea30;
|
||||
}}
|
||||
.stat-card .value {{
|
||||
font-size: 2.5em;
|
||||
font-weight: bold;
|
||||
color: #667eea;
|
||||
}}
|
||||
.stat-card .label {{
|
||||
color: #666;
|
||||
margin-top: 5px;
|
||||
}}
|
||||
.stat-card.success .value {{
|
||||
color: #28a745;
|
||||
}}
|
||||
.stat-card.warning .value {{
|
||||
color: #ffc107;
|
||||
}}
|
||||
table {{
|
||||
width: 100%;
|
||||
border-collapse: collapse;
|
||||
margin: 20px 0;
|
||||
}}
|
||||
th, td {{
|
||||
padding: 12px 15px;
|
||||
text-align: left;
|
||||
border-bottom: 1px solid #ddd;
|
||||
}}
|
||||
th {{
|
||||
background: #667eea;
|
||||
color: white;
|
||||
}}
|
||||
tr:hover {{
|
||||
background-color: #f5f5f5;
|
||||
}}
|
||||
.conf-matrix {{
|
||||
font-size: 14px;
|
||||
}}
|
||||
.conf-matrix th, .conf-matrix td {{
|
||||
text-align: center;
|
||||
padding: 8px;
|
||||
}}
|
||||
.chart-container {{
|
||||
text-align: center;
|
||||
margin: 20px 0;
|
||||
}}
|
||||
.chart-container img {{
|
||||
max-width: 100%;
|
||||
border-radius: 10px;
|
||||
box-shadow: 0 4px 15px rgba(0,0,0,0.1);
|
||||
}}
|
||||
.info-box {{
|
||||
background: #e3f2fd;
|
||||
padding: 20px;
|
||||
border-radius: 10px;
|
||||
border-left: 5px solid #2196f3;
|
||||
margin: 20px 0;
|
||||
}}
|
||||
.info-row {{
|
||||
display: flex;
|
||||
margin: 10px 0;
|
||||
}}
|
||||
.info-label {{
|
||||
font-weight: bold;
|
||||
width: 200px;
|
||||
color: #555;
|
||||
}}
|
||||
.info-value {{
|
||||
color: #333;
|
||||
}}
|
||||
.footer {{
|
||||
background: #f8f9fa;
|
||||
padding: 20px;
|
||||
text-align: center;
|
||||
color: #666;
|
||||
font-size: 14px;
|
||||
}}
|
||||
@media print {{
|
||||
body {{
|
||||
background: white;
|
||||
padding: 0;
|
||||
}}
|
||||
.container {{
|
||||
box-shadow: none;
|
||||
}}
|
||||
}}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<h1>📊 Báo Cáo Training Model</h1>
|
||||
<p class="subtitle">Land Classification - {datetime.now().strftime("%d/%m/%Y %H:%M:%S")}</p>
|
||||
</div>
|
||||
|
||||
<div class="content">
|
||||
<!-- Summary Stats -->
|
||||
<div class="section">
|
||||
<h2>📈 Tóm Tắt Kết Quả</h2>
|
||||
<div class="stats-grid">
|
||||
<div class="stat-card success">
|
||||
<div class="value">{train_acc:.1f}%</div>
|
||||
<div class="label">Train Accuracy</div>
|
||||
</div>
|
||||
<div class="stat-card {'success' if test_acc >= 80 else 'warning'}">
|
||||
<div class="value">{test_acc:.1f}%</div>
|
||||
<div class="label">Test Accuracy</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{train_samples}</div>
|
||||
<div class="label">Training Samples</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{test_samples}</div>
|
||||
<div class="label">Testing Samples</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{len(classes)}</div>
|
||||
<div class="label">Số Classes</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{test_size*100:.0f}%</div>
|
||||
<div class="label">Test Size</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Configuration Info -->
|
||||
<div class="section">
|
||||
<h2>⚙️ Cấu Hình Training</h2>
|
||||
<div class="info-box">
|
||||
<div class="info-row">
|
||||
<span class="info-label">🤖 Model Type:</span>
|
||||
<span class="info-value">{model_type.upper()}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">📍 Khu vực (bbox):</span>
|
||||
<span class="info-value">{bbox}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">📅 Thời gian:</span>
|
||||
<span class="info-value">{time_range}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">📐 Độ phân giải:</span>
|
||||
<span class="info-value">{resolution}m</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">💾 Model Path:</span>
|
||||
<span class="info-value">{model_path}</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Classification Report -->
|
||||
<div class="section">
|
||||
<h2>📋 Classification Report</h2>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Loại đất</th>
|
||||
<th>Precision</th>
|
||||
<th>Recall</th>
|
||||
<th>F1-Score</th>
|
||||
<th>Support</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
{cls_report_rows}
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
<!-- Metrics Chart -->
|
||||
{'<div class="section"><h2>📊 Biểu Đồ Metrics</h2><div class="chart-container"><img src="data:image/png;base64,' + metrics_img + '" alt="Metrics Chart"></div></div>' if metrics_img else ''}
|
||||
|
||||
<!-- Class Distribution -->
|
||||
{'<div class="section"><h2>📊 Phân Bố Số Mẫu</h2><div class="chart-container"><img src="data:image/png;base64,' + class_dist_img + '" alt="Class Distribution"></div></div>' if class_dist_img else ''}
|
||||
|
||||
<!-- Confusion Matrix -->
|
||||
<div class="section">
|
||||
<h2>🔢 Confusion Matrix</h2>
|
||||
{'<div class="chart-container"><img src="data:image/png;base64,' + conf_matrix_img + '" alt="Confusion Matrix"></div>' if conf_matrix_img else conf_matrix_table}
|
||||
</div>
|
||||
|
||||
<!-- Classes List -->
|
||||
<div class="section">
|
||||
<h2>🏷️ Danh Sách Các Loại Đất</h2>
|
||||
<div class="info-box">
|
||||
<ul style="list-style: none; display: flex; flex-wrap: wrap; gap: 10px;">
|
||||
{''.join([f'<li style="background: #667eea; color: white; padding: 8px 15px; border-radius: 20px;">{cls}</li>' for cls in classes])}
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="footer">
|
||||
<p>🌍 Land Classification Training System | Generated: {datetime.now().strftime("%d/%m/%Y %H:%M:%S")}</p>
|
||||
<p>Data Source: Microsoft Planetary Computer (Sentinel-2 L2A, Sentinel-1 RTC)</p>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
# Save report
|
||||
reports_dir = Path("reports")
|
||||
reports_dir.mkdir(exist_ok=True)
|
||||
|
||||
report_filename = f"training_report_{timestamp}.html"
|
||||
report_path = reports_dir / report_filename
|
||||
|
||||
with open(report_path, 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
|
||||
return str(report_path), html
|
||||
|
||||
|
||||
def generate_prediction_report(prediction_result, config=None):
|
||||
"""
|
||||
Tạo báo cáo HTML cho kết quả prediction
|
||||
|
||||
Args:
|
||||
prediction_result: Dict chứa kết quả prediction
|
||||
config: Dict chứa cấu hình prediction (optional)
|
||||
|
||||
Returns:
|
||||
Tuple (report_path, report_html)
|
||||
"""
|
||||
|
||||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
|
||||
# Extract data
|
||||
output_file = prediction_result.get('output_file', '')
|
||||
shape = prediction_result.get('shape', [0, 0])
|
||||
unique_classes = prediction_result.get('unique_classes', [])
|
||||
bbox = prediction_result.get('bbox', [])
|
||||
time_range = prediction_result.get('time_range', '')
|
||||
n_features = prediction_result.get('n_features', 0)
|
||||
used_radar = prediction_result.get('used_radar', False)
|
||||
model_used = prediction_result.get('model_used', '')
|
||||
|
||||
# Calculate area (approximate)
|
||||
if len(bbox) == 4:
|
||||
# Approximate calculation (1 degree ≈ 111km at equator)
|
||||
width_km = (bbox[2] - bbox[0]) * 111 * 0.85 # cos adjustment for Vietnam
|
||||
height_km = (bbox[3] - bbox[1]) * 111
|
||||
area_km2 = width_km * height_km
|
||||
else:
|
||||
area_km2 = 0
|
||||
|
||||
total_pixels = shape[0] * shape[1] if len(shape) == 2 else 0
|
||||
|
||||
# HTML Template
|
||||
html = f"""
|
||||
<!DOCTYPE html>
|
||||
<html lang="vi">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Prediction Report - {timestamp}</title>
|
||||
<style>
|
||||
* {{
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
box-sizing: border-box;
|
||||
}}
|
||||
body {{
|
||||
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
|
||||
background: #f5f5f5;
|
||||
padding: 20px;
|
||||
line-height: 1.6;
|
||||
}}
|
||||
.container {{
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
background: white;
|
||||
border-radius: 15px;
|
||||
box-shadow: 0 10px 40px rgba(0,0,0,0.1);
|
||||
overflow: hidden;
|
||||
}}
|
||||
.header {{
|
||||
background: linear-gradient(135deg, #ff6b6b 0%, #ee5a6f 100%);
|
||||
color: white;
|
||||
padding: 40px;
|
||||
text-align: center;
|
||||
}}
|
||||
.header h1 {{
|
||||
font-size: 2.5em;
|
||||
margin-bottom: 10px;
|
||||
}}
|
||||
.content {{
|
||||
padding: 40px;
|
||||
}}
|
||||
.section {{
|
||||
margin-bottom: 40px;
|
||||
}}
|
||||
.section h2 {{
|
||||
color: #ff6b6b;
|
||||
border-bottom: 3px solid #ff6b6b;
|
||||
padding-bottom: 10px;
|
||||
margin-bottom: 20px;
|
||||
}}
|
||||
.stats-grid {{
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
|
||||
gap: 20px;
|
||||
}}
|
||||
.stat-card {{
|
||||
background: linear-gradient(135deg, #ff6b6b15 0%, #ee5a6f15 100%);
|
||||
padding: 25px;
|
||||
border-radius: 10px;
|
||||
text-align: center;
|
||||
border: 1px solid #ff6b6b30;
|
||||
}}
|
||||
.stat-card .value {{
|
||||
font-size: 2em;
|
||||
font-weight: bold;
|
||||
color: #ff6b6b;
|
||||
}}
|
||||
.stat-card .label {{
|
||||
color: #666;
|
||||
margin-top: 5px;
|
||||
}}
|
||||
.info-box {{
|
||||
background: #fff3cd;
|
||||
padding: 20px;
|
||||
border-radius: 10px;
|
||||
border-left: 5px solid #ff6b6b;
|
||||
margin: 20px 0;
|
||||
}}
|
||||
.info-row {{
|
||||
display: flex;
|
||||
margin: 10px 0;
|
||||
}}
|
||||
.info-label {{
|
||||
font-weight: bold;
|
||||
width: 200px;
|
||||
color: #555;
|
||||
}}
|
||||
.class-badge {{
|
||||
display: inline-block;
|
||||
background: #ff6b6b;
|
||||
color: white;
|
||||
padding: 8px 15px;
|
||||
border-radius: 20px;
|
||||
margin: 5px;
|
||||
}}
|
||||
.footer {{
|
||||
background: #f8f9fa;
|
||||
padding: 20px;
|
||||
text-align: center;
|
||||
color: #666;
|
||||
}}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<h1>🗺️ Báo Cáo Dự Đoán</h1>
|
||||
<p>Land Classification Prediction - {datetime.now().strftime("%d/%m/%Y %H:%M:%S")}</p>
|
||||
</div>
|
||||
|
||||
<div class="content">
|
||||
<div class="section">
|
||||
<h2>📈 Tóm Tắt Kết Quả</h2>
|
||||
<div class="stats-grid">
|
||||
<div class="stat-card">
|
||||
<div class="value">{total_pixels:,}</div>
|
||||
<div class="label">Tổng số Pixels</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{shape[0]}x{shape[1]}</div>
|
||||
<div class="label">Kích thước (px)</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{area_km2:.1f}</div>
|
||||
<div class="label">Diện tích (km²)</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{len(unique_classes)}</div>
|
||||
<div class="label">Số Classes</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{n_features}</div>
|
||||
<div class="label">Số Features</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="value">{'✅' if used_radar else '❌'}</div>
|
||||
<div class="label">Sử dụng Radar</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2>⚙️ Thông Tin Chi Tiết</h2>
|
||||
<div class="info-box">
|
||||
<div class="info-row">
|
||||
<span class="info-label">🤖 Model sử dụng:</span>
|
||||
<span>{model_used}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">📍 Khu vực (bbox):</span>
|
||||
<span>{bbox}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">📅 Thời gian:</span>
|
||||
<span>{time_range}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">💾 Output file:</span>
|
||||
<span>{output_file}</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2>🏷️ Các Classes Phát Hiện</h2>
|
||||
<div>
|
||||
{''.join([f'<span class="class-badge">{cls}</span>' for cls in unique_classes])}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="footer">
|
||||
<p>🌍 Land Classification System | Generated: {datetime.now().strftime("%d/%m/%Y %H:%M:%S")}</p>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
# Save report
|
||||
reports_dir = Path("reports")
|
||||
reports_dir.mkdir(exist_ok=True)
|
||||
|
||||
report_filename = f"prediction_report_{timestamp}.html"
|
||||
report_path = reports_dir / report_filename
|
||||
|
||||
with open(report_path, 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
|
||||
return str(report_path), html
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Test report generation
|
||||
test_result = {
|
||||
"success": True,
|
||||
"train_accuracy": 0.95,
|
||||
"test_accuracy": 0.87,
|
||||
"training_samples": 800,
|
||||
"testing_samples": 200,
|
||||
"test_size": 0.2,
|
||||
"classes": ["Lua", "Rung", "Nuoc", "Dan_cu", "Cay_lau_nam"],
|
||||
"model_type": "xgboost",
|
||||
"model_path": "model_train/model_xgboost_20251221.joblib",
|
||||
"bbox": [105.6, 9.3, 106.2, 9.8],
|
||||
"time_range": "2023-03-01/2023-05-31",
|
||||
"resolution": 20,
|
||||
"classification_report": {
|
||||
"Lua": {"precision": 0.92, "recall": 0.89, "f1-score": 0.90, "support": 50},
|
||||
"Rung": {"precision": 0.88, "recall": 0.91, "f1-score": 0.89, "support": 45},
|
||||
"Nuoc": {"precision": 0.95, "recall": 0.93, "f1-score": 0.94, "support": 40},
|
||||
"Dan_cu": {"precision": 0.85, "recall": 0.82, "f1-score": 0.83, "support": 35},
|
||||
"Cay_lau_nam": {"precision": 0.80, "recall": 0.85, "f1-score": 0.82, "support": 30},
|
||||
"macro avg": {"precision": 0.88, "recall": 0.88, "f1-score": 0.88, "support": 200},
|
||||
"weighted avg": {"precision": 0.88, "recall": 0.87, "f1-score": 0.87, "support": 200}
|
||||
},
|
||||
"confusion_matrix": [
|
||||
[45, 2, 1, 1, 1],
|
||||
[3, 41, 0, 1, 0],
|
||||
[1, 0, 37, 1, 1],
|
||||
[2, 1, 1, 29, 2],
|
||||
[1, 1, 1, 2, 26]
|
||||
]
|
||||
}
|
||||
|
||||
path, html = generate_training_report(test_result)
|
||||
print(f"Report generated: {path}")
|
||||
@@ -0,0 +1,306 @@
|
||||
"""
|
||||
Updated run_prediction function for api_server.py
|
||||
Uses FeatureExtractor for consistent feature extraction
|
||||
"""
|
||||
|
||||
async def run_prediction(config: PredictionConfig):
|
||||
"""Chạy prediction process - Sử dụng FeatureExtractor để đồng bộ với training"""
|
||||
global prediction_status
|
||||
|
||||
try:
|
||||
prediction_status["progress"] = "Đang import thư viện..."
|
||||
|
||||
# Import required libraries
|
||||
import numpy as np
|
||||
import xarray as xr
|
||||
from datetime import datetime as dt
|
||||
import hashlib
|
||||
from feature_extractor import get_feature_extractor
|
||||
|
||||
# Validate bbox
|
||||
if (config.min_lon < -180 or config.max_lon > 180 or
|
||||
config.min_lat < -90 or config.max_lat > 90):
|
||||
raise ValueError(f"Bbox không hợp lệ: ({config.min_lon}, {config.min_lat}, {config.max_lon}, {config.max_lat}). "
|
||||
f"Phải trong phạm vi (-180, -90, 180, 90)")
|
||||
|
||||
prediction_status["progress"] = "Đang load model..."
|
||||
|
||||
# Load model using ModelManager
|
||||
model_manager = get_model_manager()
|
||||
model, label_encoder, model_metadata = model_manager.load_model(config.model_filename)
|
||||
|
||||
# Get feature_mode from metadata (default to 'simple' if not specified)
|
||||
feature_mode = model_metadata.get("feature_mode", "simple")
|
||||
required_features = model_metadata.get("features", [])
|
||||
n_features_expected = model_metadata.get("n_features", len(required_features))
|
||||
|
||||
prediction_status["progress"] = f"Model: {model_metadata.get('model_type', 'unknown')}, mode={feature_mode}, features={n_features_expected}"
|
||||
|
||||
# Initialize FeatureExtractor with same mode as training
|
||||
extractor = get_feature_extractor(mode=feature_mode)
|
||||
|
||||
# Check if it's a CNN model (PyTorch)
|
||||
is_cnn_model = hasattr(model, '__class__') and 'CNN' in model.__class__.__name__
|
||||
if is_cnn_model:
|
||||
prediction_status["progress"] = "Phát hiện PyTorch CNN model..."
|
||||
try:
|
||||
import torch
|
||||
except ImportError:
|
||||
raise ImportError("PyTorch required for CNN models. Install: pip install torch")
|
||||
|
||||
# Initialize common variables
|
||||
bbox = [config.min_lon, config.min_lat, config.max_lon, config.max_lat]
|
||||
time_range = f"{config.start_date}/{config.end_date}"
|
||||
|
||||
# ============ LOAD SENTINEL-2 DATA ============
|
||||
prediction_status["progress"] = "Đang kết nối Microsoft Planetary Computer..."
|
||||
import pystac_client
|
||||
import planetary_computer
|
||||
from odc.stac import load
|
||||
|
||||
catalog = pystac_client.Client.open(
|
||||
"https://planetarycomputer.microsoft.com/api/stac/v1",
|
||||
modifier=planetary_computer.sign_inplace,
|
||||
)
|
||||
|
||||
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-2..."
|
||||
s2_search = catalog.search(
|
||||
collections=["sentinel-2-l2a"],
|
||||
bbox=bbox,
|
||||
datetime=time_range,
|
||||
query={"eo:cloud_cover": {"lt": config.cloud_cover}}
|
||||
)
|
||||
s2_items = list(s2_search.items())
|
||||
|
||||
if not s2_items:
|
||||
raise ValueError("Không tìm thấy dữ liệu Sentinel-2 cho khu vực và thời gian này")
|
||||
|
||||
s2_items = s2_items[:config.max_scenes]
|
||||
prediction_status["progress"] = f"Đang xử lý {len(s2_items)} scenes Sentinel-2..."
|
||||
|
||||
# Load different bands based on feature mode
|
||||
if feature_mode == 'simple':
|
||||
bands_to_load = ["B04", "B08", "SCL"]
|
||||
else: # temporal or extended
|
||||
bands_to_load = ["B02", "B03", "B04", "B08", "B11", "SCL"]
|
||||
|
||||
s2_data = load(
|
||||
s2_items,
|
||||
bbox=bbox,
|
||||
bands=bands_to_load,
|
||||
chunks={"time": 1, "x": 2048, "y": 2048},
|
||||
groupby="solar_day",
|
||||
resolution=config.resolution
|
||||
).compute()
|
||||
|
||||
prediction_status["progress"] = "Đã load Sentinel-2 data"
|
||||
|
||||
# ============ LOAD SENTINEL-1 DATA (RADAR) ============
|
||||
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-1 (Radar)..."
|
||||
use_radar = False
|
||||
vh_data = None
|
||||
vv_data = None
|
||||
|
||||
try:
|
||||
s1_search = catalog.search(
|
||||
collections=["sentinel-1-rtc"],
|
||||
bbox=bbox,
|
||||
datetime=time_range,
|
||||
)
|
||||
s1_items = list(s1_search.items())
|
||||
|
||||
if s1_items:
|
||||
s1_items = s1_items[:config.max_scenes]
|
||||
s1_data = load(
|
||||
s1_items,
|
||||
bbox=bbox,
|
||||
bands=["vh", "vv"],
|
||||
chunks={"time": 1, "x": 2048, "y": 2048},
|
||||
groupby="solar_day",
|
||||
resolution=config.resolution
|
||||
).compute()
|
||||
|
||||
# Convert to dB
|
||||
vh_data = 10 * np.log10(s1_data['vh'].where(s1_data['vh'] > 0))
|
||||
vv_data = 10 * np.log10(s1_data['vv'].where(s1_data['vv'] > 0))
|
||||
use_radar = True
|
||||
prediction_status["progress"] = f"Đã load Sentinel-1 data ({len(s1_items)} scenes)"
|
||||
else:
|
||||
prediction_status["progress"] = "Không có dữ liệu Sentinel-1, bỏ qua radar features"
|
||||
except Exception as e:
|
||||
prediction_status["progress"] = f"Lỗi load Sentinel-1: {str(e)}, bỏ qua radar features"
|
||||
|
||||
# ============ APPLY CLOUD MASK ============
|
||||
prediction_status["progress"] = "Đang xử lý mây..."
|
||||
if "SCL" in s2_data:
|
||||
scl = s2_data["SCL"]
|
||||
# SCL values: 3=cloud shadow, 8=cloud medium, 9=cloud high, 10=cirrus
|
||||
cloud_mask = (scl == 3) | (scl == 8) | (scl == 9) | (scl == 10)
|
||||
for band in s2_data.data_vars:
|
||||
if band != "SCL":
|
||||
s2_data[band] = s2_data[band].where(~cloud_mask)
|
||||
|
||||
# ============ EXTRACT FEATURES ============
|
||||
prediction_status["progress"] = f"Đang trích xuất features (mode={feature_mode})..."
|
||||
|
||||
if feature_mode == 'simple':
|
||||
# Calculate NDVI for simple mode
|
||||
nir = s2_data["B08"].astype('float32')
|
||||
red = s2_data["B04"].astype('float32')
|
||||
ndvi = (nir - red) / (nir + red + 1e-8)
|
||||
|
||||
# Fill NaN
|
||||
ndvi_filled = ndvi.ffill(dim='time').bfill(dim='time')
|
||||
|
||||
# Extract features using FeatureExtractor
|
||||
features = extractor.extract(
|
||||
ndvi_data=ndvi_filled,
|
||||
vh_data=vh_data,
|
||||
vv_data=vv_data
|
||||
)
|
||||
else:
|
||||
# temporal or extended mode
|
||||
# Fill NaN values in spectral bands
|
||||
for band in ["B02", "B03", "B04", "B08", "B11"]:
|
||||
if band in s2_data:
|
||||
s2_data[band] = s2_data[band].ffill(dim='time').bfill(dim='time')
|
||||
|
||||
# Extract features using FeatureExtractor
|
||||
features = extractor.extract(
|
||||
s2_data=s2_data,
|
||||
vh_data=vh_data,
|
||||
vv_data=vv_data
|
||||
)
|
||||
|
||||
# Handle NaN values
|
||||
features = np.nan_to_num(features, nan=0.0)
|
||||
|
||||
prediction_status["progress"] = f"Đã extract {features.shape[1]} features cho {features.shape[0]} pixels"
|
||||
|
||||
# ============ PREDICT ============
|
||||
prediction_status["progress"] = "Đang dự đoán..."
|
||||
|
||||
# Make prediction
|
||||
if is_cnn_model:
|
||||
predictions = model.predict(features)
|
||||
else:
|
||||
predictions = model.predict(features)
|
||||
|
||||
# Decode labels if label_encoder exists
|
||||
if label_encoder is not None:
|
||||
try:
|
||||
predictions = label_encoder.inverse_transform(predictions.astype(int))
|
||||
except:
|
||||
pass
|
||||
|
||||
# Reshape to original shape
|
||||
if feature_mode == 'simple' and 'B08' in s2_data:
|
||||
# Use B08 to get shape
|
||||
y_size = len(s2_data.y)
|
||||
x_size = len(s2_data.x)
|
||||
else:
|
||||
y_size = len(s2_data.y)
|
||||
x_size = len(s2_data.x)
|
||||
|
||||
pred_shape = (y_size, x_size)
|
||||
predictions_2d = predictions.reshape(pred_shape)
|
||||
|
||||
# ============ CREATE OUTPUT ============
|
||||
prediction_status["progress"] = "Đang tạo bản đồ phân loại..."
|
||||
|
||||
# Create output xarray
|
||||
prediction_da = xr.DataArray(
|
||||
predictions_2d,
|
||||
coords={
|
||||
"y": s2_data.y,
|
||||
"x": s2_data.x
|
||||
},
|
||||
dims=["y", "x"],
|
||||
name="classification"
|
||||
)
|
||||
|
||||
# Save output
|
||||
output_dir = Path("predictions")
|
||||
output_dir.mkdir(exist_ok=True)
|
||||
|
||||
timestamp = dt.now().strftime("%Y%m%d_%H%M%S")
|
||||
output_file = output_dir / f"prediction_{timestamp}.tif"
|
||||
|
||||
prediction_status["progress"] = "Đang lưu kết quả GeoTIFF..."
|
||||
|
||||
# Set CRS and save as GeoTIFF
|
||||
if hasattr(s2_data, 'rio') and s2_data.rio.crs is not None:
|
||||
prediction_da.rio.write_crs(s2_data.rio.crs, inplace=True)
|
||||
else:
|
||||
prediction_da.rio.write_crs("EPSG:4326", inplace=True)
|
||||
|
||||
prediction_da.rio.to_raster(str(output_file), driver="GTiff")
|
||||
|
||||
# Generate PNG preview
|
||||
prediction_status["progress"] = "Đang tạo PNG preview..."
|
||||
png_file = output_dir / f"prediction_{timestamp}.png"
|
||||
try:
|
||||
import matplotlib
|
||||
matplotlib.use('Agg')
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
fig, ax = plt.subplots(figsize=(12, 10), dpi=150)
|
||||
im = ax.imshow(predictions_2d, cmap='tab20', interpolation='nearest')
|
||||
ax.set_title(f'Prediction Result - {timestamp}', fontsize=14, fontweight='bold')
|
||||
ax.set_xlabel('X (pixels)', fontsize=10)
|
||||
ax.set_ylabel('Y (pixels)', fontsize=10)
|
||||
|
||||
cbar = plt.colorbar(im, ax=ax, fraction=0.046, pad=0.04)
|
||||
cbar.set_label('Class', rotation=270, labelpad=15)
|
||||
ax.grid(True, alpha=0.3, linestyle='--', linewidth=0.5)
|
||||
|
||||
plt.tight_layout()
|
||||
plt.savefig(str(png_file), dpi=150, bbox_inches='tight')
|
||||
plt.close(fig)
|
||||
|
||||
print(f"[PNG PREVIEW] Created: {png_file}")
|
||||
except Exception as e:
|
||||
print(f"[PNG PREVIEW ERROR] Failed to create PNG: {e}")
|
||||
png_file = None
|
||||
|
||||
# Get unique classes
|
||||
unique_classes = np.unique(predictions_2d)
|
||||
unique_classes = unique_classes[~np.isnan(unique_classes)].tolist()
|
||||
|
||||
prediction_status["is_predicting"] = False
|
||||
prediction_status["progress"] = "Hoàn thành! Đang tạo báo cáo..."
|
||||
prediction_status["output_file"] = str(output_file)
|
||||
prediction_status["result"] = {
|
||||
"output_file": str(output_file),
|
||||
"png_file": str(png_file) if png_file else None,
|
||||
"shape": list(pred_shape),
|
||||
"unique_classes": unique_classes,
|
||||
"bbox": bbox,
|
||||
"time_range": time_range,
|
||||
"n_features": features.shape[1],
|
||||
"feature_mode": feature_mode,
|
||||
"used_radar": use_radar,
|
||||
"model_used": config.model_filename
|
||||
}
|
||||
|
||||
# Auto generate prediction report
|
||||
try:
|
||||
report_path, _ = generate_prediction_report(prediction_status["result"])
|
||||
prediction_status["result"]["report_path"] = report_path
|
||||
prediction_status["result"]["report_filename"] = Path(report_path).name
|
||||
prediction_status["progress"] = "Hoàn thành! Báo cáo đã được tạo."
|
||||
print(f"[PREDICTION REPORT] Generated: {report_path}")
|
||||
except Exception as e:
|
||||
print(f"[PREDICTION REPORT ERROR] Failed to generate report: {e}")
|
||||
prediction_status["progress"] = "Hoàn thành! (Không thể tạo báo cáo)"
|
||||
|
||||
prediction_status["end_time"] = dt.now().isoformat()
|
||||
|
||||
except Exception as e:
|
||||
prediction_status["is_predicting"] = False
|
||||
prediction_status["error"] = str(e)
|
||||
prediction_status["progress"] = f"Lỗi: {str(e)}"
|
||||
prediction_status["end_time"] = dt.now().isoformat()
|
||||
import traceback
|
||||
print(f"[PREDICTION ERROR] {str(e)}")
|
||||
print(traceback.format_exc())
|
||||
Reference in New Issue
Block a user