Victor Phan
2196 lines
81 KiB
Python
2196 lines
81 KiB
Python
"""
|
|
API Server for Land Classification Model Training
|
|
Cho phép chọn dữ liệu và cấu hình training qua giao diện web
|
|
"""
|
|
|
|
from fastapi import FastAPI, BackgroundTasks, HTTPException
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.staticfiles import StaticFiles
|
|
from fastapi.responses import HTMLResponse, FileResponse
|
|
from pydantic import BaseModel
|
|
from typing import Optional, List
|
|
import uvicorn
|
|
import joblib
|
|
import json
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
import sys
|
|
|
|
# Import report generator
|
|
from report_generator import generate_training_report, generate_prediction_report
|
|
|
|
app = FastAPI(title="Land Classification Training API", version="1.0.0")
|
|
|
|
# Enable CORS
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
# Global training status``
|
|
training_status = {
|
|
"is_training": False,
|
|
"progress": "",
|
|
"error": None,
|
|
"result": None,
|
|
"start_time": None,
|
|
"end_time": None,
|
|
"cancel_requested": False
|
|
}
|
|
|
|
# Global prediction status
|
|
prediction_status = {
|
|
"is_predicting": False,
|
|
"progress": "",
|
|
"error": None,
|
|
"result": None,
|
|
"output_file": None,
|
|
"start_time": None,
|
|
"end_time": None
|
|
}
|
|
|
|
# Batch prediction queue
|
|
batch_queue = []
|
|
batch_results = []
|
|
|
|
|
|
class TrainingConfig(BaseModel):
|
|
"""Cấu hình training"""
|
|
# Khu vực (bbox)
|
|
min_lon: float = 105.6
|
|
min_lat: float = 9.3
|
|
max_lon: float = 106.2
|
|
max_lat: float = 9.8
|
|
|
|
# Thời gian
|
|
start_date: str = "2023-03-01"
|
|
end_date: str = "2023-05-31"
|
|
|
|
# Dữ liệu
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20 # 10m hoặc 20m
|
|
|
|
# Model parameters
|
|
model_type: str = "xgboost" # xgboost, random_forest, decision_tree, svm, cnn
|
|
n_estimators: int = 100
|
|
max_depth: int = 20
|
|
learning_rate: float = 0.1
|
|
use_gpu: bool = True
|
|
|
|
# Train/test split
|
|
test_size: float = 0.2 # Tỷ lệ dữ liệu dùng làm test (0-1)
|
|
|
|
# Cache
|
|
use_cache: bool = True # Cache dataset để test nhanh hơn
|
|
|
|
# Training data
|
|
training_shapefile: str = "train/ST_training data_updated_1130points_new.shp"
|
|
|
|
|
|
class PredictionConfig(BaseModel):
|
|
"""Cấu hình dự đoán"""
|
|
# Model to use
|
|
model_filename: str
|
|
|
|
# Khu vực (bbox)
|
|
min_lon: float = 105.6
|
|
min_lat: float = 9.3
|
|
max_lon: float = 106.2
|
|
max_lat: float = 9.8
|
|
|
|
# Thời gian
|
|
start_date: str = "2023-03-01"
|
|
end_date: str = "2023-05-31"
|
|
|
|
# Dữ liệu
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20
|
|
|
|
|
|
class TrainingStatus(BaseModel):
|
|
"""Trạng thái training"""
|
|
is_training: bool
|
|
progress: str
|
|
error: Optional[str]
|
|
result: Optional[dict]
|
|
start_time: Optional[str]
|
|
end_time: Optional[str]
|
|
|
|
|
|
class NDVIConfig(BaseModel):
|
|
"""Cấu hình tính NDVI time series"""
|
|
bbox: List[float] # [min_lon, min_lat, max_lon, max_lat]
|
|
start_date: str
|
|
end_date: str
|
|
max_cloud_cover: int = 30
|
|
resolution: int = 20
|
|
|
|
|
|
class PredictionWithNDVIConfig(BaseModel):
|
|
"""Cấu hình predict kết hợp land classification và NDVI"""
|
|
model_filename: str
|
|
min_lon: float
|
|
min_lat: float
|
|
max_lon: float
|
|
max_lat: float
|
|
start_date: str
|
|
end_date: str
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20
|
|
export_ndvi: bool = True # Export NDVI raster
|
|
export_classification: bool = True # Export classification raster
|
|
|
|
|
|
@app.get("/", response_class=HTMLResponse)
|
|
async def root():
|
|
"""Serve main index page with tabs"""
|
|
html_file = Path(__file__).parent / "index.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
return HTMLResponse("""
|
|
<html>
|
|
<head><title>Land Classification System</title></head>
|
|
<body>
|
|
<h1>Land Classification System</h1>
|
|
<p>API Documentation: <a href="/docs">/docs</a></p>
|
|
<p>Training: <a href="/training">/training</a></p>
|
|
<p>Prediction: <a href="/prediction">/prediction</a></p>
|
|
<p>Dashboard: <a href="/dashboard">/dashboard</a></p>
|
|
</body>
|
|
</html>
|
|
""")
|
|
|
|
|
|
@app.get("/training", response_class=HTMLResponse)
|
|
async def training_page():
|
|
"""Serve training interface"""
|
|
html_file = Path(__file__).parent / "training_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Training interface không tồn tại")
|
|
|
|
|
|
@app.get("/prediction", response_class=HTMLResponse)
|
|
async def prediction_page():
|
|
"""Serve prediction interface"""
|
|
html_file = Path(__file__).parent / "prediction_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Prediction interface không tồn tại")
|
|
|
|
|
|
@app.get("/dashboard", response_class=HTMLResponse)
|
|
async def dashboard():
|
|
"""Serve dashboard visualization"""
|
|
html_file = Path(__file__).parent / "dashboard.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Dashboard không tồn tại")
|
|
|
|
|
|
@app.get("/batch", response_class=HTMLResponse)
|
|
async def batch_page():
|
|
"""Serve batch processing interface"""
|
|
html_file = Path(__file__).parent / "batch_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Batch interface không tồn tại")
|
|
|
|
|
|
@app.get("/ndvi", response_class=HTMLResponse)
|
|
async def ndvi_page():
|
|
"""Serve NDVI time series interface"""
|
|
html_file = Path(__file__).parent / "ndvi_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="NDVI interface không tồn tại")
|
|
|
|
|
|
@app.get("/reports", response_class=HTMLResponse)
|
|
async def reports_page():
|
|
"""Serve reports management interface"""
|
|
html_file = Path(__file__).parent / "reports_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Reports interface không tồn tại")
|
|
|
|
|
|
@app.get("/api/config/presets")
|
|
async def get_presets():
|
|
"""Lấy các preset cấu hình sẵn"""
|
|
return {
|
|
"presets": [
|
|
{
|
|
"name": "PC - Nhỏ (3 tháng, 20m, 12 scenes)",
|
|
"config": {
|
|
"min_lon": 105.6, "min_lat": 9.3, "max_lon": 106.2, "max_lat": 9.8,
|
|
"start_date": "2023-03-01", "end_date": "2023-05-31",
|
|
"max_scenes": 12, "cloud_cover": 30, "resolution": 20,
|
|
"test_size": 0.2
|
|
}
|
|
},
|
|
{
|
|
"name": "Server - Trung bình (6 tháng, 10m, 30 scenes)",
|
|
"config": {
|
|
"min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
|
|
"start_date": "2023-01-01", "end_date": "2023-06-30",
|
|
"max_scenes": 30, "cloud_cover": 30, "resolution": 10,
|
|
"test_size": 0.2
|
|
}
|
|
},
|
|
{
|
|
"name": "Full - Lớn (1 năm, 10m, 60 scenes)",
|
|
"config": {
|
|
"min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
|
|
"start_date": "2022-09-01", "end_date": "2023-10-01",
|
|
"max_scenes": 60, "cloud_cover": 50, "resolution": 10,
|
|
"test_size": 0.2
|
|
}
|
|
}
|
|
]
|
|
}
|
|
|
|
|
|
@app.get("/api/training/status", response_model=TrainingStatus)
|
|
async def get_training_status():
|
|
"""Kiểm tra trạng thái training"""
|
|
return training_status
|
|
|
|
|
|
@app.post("/api/training/start")
|
|
async def start_training(config: TrainingConfig, background_tasks: BackgroundTasks):
|
|
"""Bắt đầu training với config đã chọn"""
|
|
global training_status
|
|
|
|
if training_status["is_training"]:
|
|
raise HTTPException(status_code=400, detail="Training đang chạy, vui lòng đợi")
|
|
|
|
# Reset status
|
|
training_status = {
|
|
"is_training": True,
|
|
"progress": "Đang khởi tạo...",
|
|
"error": None,
|
|
"result": None,
|
|
"start_time": datetime.now().isoformat(),
|
|
"end_time": None
|
|
}
|
|
|
|
# Run training in background
|
|
background_tasks.add_task(run_training, config)
|
|
|
|
return {"message": "Training đã bắt đầu", "status": training_status}
|
|
|
|
|
|
@app.post("/api/training/stop")
|
|
async def stop_training():
|
|
"""Dừng training (nếu đang chạy)"""
|
|
global training_status
|
|
|
|
if not training_status["is_training"]:
|
|
return {"message": "Không có training nào đang chạy"}
|
|
|
|
# Set cancel flag - the training will check this and stop
|
|
training_status["cancel_requested"] = True
|
|
training_status["progress"] = "Đang hủy training..."
|
|
|
|
return {"message": "Đang dừng training..."}
|
|
|
|
|
|
@app.post("/api/cache/clear")
|
|
async def clear_cache():
|
|
"""Xóa cache dataset"""
|
|
import shutil
|
|
cache_dir = Path("dataset_cache")
|
|
|
|
if not cache_dir.exists():
|
|
return {"message": "Không có cache để xóa", "deleted": 0}
|
|
|
|
# Count files
|
|
cache_files = list(cache_dir.glob("*.joblib"))
|
|
count = len(cache_files)
|
|
|
|
# Delete all cache files
|
|
for cache_file in cache_files:
|
|
try:
|
|
cache_file.unlink()
|
|
except:
|
|
pass
|
|
|
|
return {"message": f"Đã xóa {count} file cache", "deleted": count}
|
|
|
|
|
|
@app.get("/api/cache/info")
|
|
async def get_cache_info():
|
|
"""Lấy thông tin về cache với metadata đầy đủ, tự động xóa cache cũ có lazy data"""
|
|
cache_dir = Path("dataset_cache")
|
|
|
|
if not cache_dir.exists():
|
|
return {"exists": False, "files": [], "total_size_mb": 0}
|
|
|
|
cache_files = []
|
|
total_size = 0
|
|
deleted_count = 0
|
|
|
|
for cache_file in cache_dir.glob("*.joblib"):
|
|
# Skip if file doesn't exist (race condition)
|
|
if not cache_file.exists():
|
|
continue
|
|
|
|
size = cache_file.stat().st_size
|
|
|
|
# Try to load metadata from cache and check if it's valid
|
|
metadata = {}
|
|
is_valid = True
|
|
try:
|
|
cached_data = joblib.load(cache_file)
|
|
|
|
# Check if cache contains lazy data (will cause 403 errors)
|
|
if isinstance(cached_data, dict) and "s2_data" in cached_data:
|
|
s2_data_temp = cached_data["s2_data"]
|
|
is_lazy = False
|
|
try:
|
|
is_lazy = any(hasattr(s2_data_temp[var].data, 'chunks') for var in s2_data_temp.data_vars)
|
|
except:
|
|
pass
|
|
|
|
if is_lazy:
|
|
print(f"[CLEANUP] Deleting cache with lazy data: {cache_file.name}")
|
|
cache_file.unlink()
|
|
deleted_count += 1
|
|
is_valid = False
|
|
|
|
if is_valid and isinstance(cached_data, dict):
|
|
metadata = {
|
|
"bbox": cached_data.get("bbox", []),
|
|
"time_range": cached_data.get("time_range", ""),
|
|
"resolution": cached_data.get("resolution", 20),
|
|
"n_samples": len(cached_data.get("features", [])),
|
|
"created": cached_data.get("timestamp", "")
|
|
}
|
|
# Parse time_range to get start/end dates
|
|
if metadata["time_range"]:
|
|
time_parts = metadata["time_range"].split("/")
|
|
if len(time_parts) == 2:
|
|
metadata["start_date"] = time_parts[0]
|
|
metadata["end_date"] = time_parts[1]
|
|
# Parse bbox to get min/max lon/lat
|
|
if metadata["bbox"] and len(metadata["bbox"]) == 4:
|
|
metadata["min_lon"] = metadata["bbox"][0]
|
|
metadata["min_lat"] = metadata["bbox"][1]
|
|
metadata["max_lon"] = metadata["bbox"][2]
|
|
metadata["max_lat"] = metadata["bbox"][3]
|
|
except Exception as e:
|
|
print(f"[CLEANUP] Error loading cache {cache_file.name}: {e}. Deleting...")
|
|
try:
|
|
cache_file.unlink()
|
|
deleted_count += 1
|
|
is_valid = False
|
|
except:
|
|
pass
|
|
|
|
# Only add valid cache files to the list
|
|
if is_valid:
|
|
total_size += size
|
|
cache_files.append({
|
|
"filename": cache_file.name,
|
|
"size_mb": round(size / 1024 / 1024, 2),
|
|
"modified": datetime.fromtimestamp(cache_file.stat().st_mtime).isoformat(),
|
|
"metadata": metadata
|
|
})
|
|
|
|
# Sort by modified time (newest first)
|
|
cache_files.sort(key=lambda x: x["modified"], reverse=True)
|
|
|
|
if deleted_count > 0:
|
|
print(f"[CLEANUP] Deleted {deleted_count} invalid cache files")
|
|
|
|
return {
|
|
"exists": True,
|
|
"files": cache_files,
|
|
"count": len(cache_files),
|
|
"total_size_mb": round(total_size / 1024 / 1024, 2),
|
|
"deleted_invalid": deleted_count
|
|
}
|
|
|
|
|
|
|
|
@app.get("/api/models/list")
|
|
async def list_models():
|
|
"""Liệt kê các model đã train"""
|
|
model_dir = Path("model_train")
|
|
if not model_dir.exists():
|
|
return {"models": []}
|
|
|
|
models = []
|
|
# List all .joblib model files (actual trained models)
|
|
for model_file in model_dir.glob("*.joblib"):
|
|
# Skip any file that contains '_info' in its name
|
|
if '_info' in model_file.stem:
|
|
continue
|
|
|
|
info = {}
|
|
# Try to find corresponding .json info file
|
|
# Remove .joblib and try with _info.json
|
|
base_name = model_file.stem # e.g., "model_cnn_20251221_163841"
|
|
info_file = model_dir / f"{base_name}_info.json"
|
|
|
|
if info_file.exists():
|
|
try:
|
|
with open(info_file) as f:
|
|
info = json.load(f)
|
|
except Exception as e:
|
|
info = {"error": str(e)}
|
|
|
|
size_mb = round(model_file.stat().st_size / 1024 / 1024, 2)
|
|
created = datetime.fromtimestamp(model_file.stat().st_mtime).isoformat()
|
|
|
|
models.append({
|
|
"filename": model_file.name,
|
|
"created": created,
|
|
"size_mb": size_mb,
|
|
"info": info
|
|
})
|
|
|
|
# Sort by creation time (newest first)
|
|
models.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"models": models}
|
|
|
|
|
|
# ============ REPORTS API ============
|
|
|
|
@app.get("/api/reports/list")
|
|
async def list_reports():
|
|
"""Liệt kê các báo cáo đã tạo"""
|
|
reports_dir = Path("reports")
|
|
reports_dir.mkdir(exist_ok=True)
|
|
|
|
reports = []
|
|
for report_file in reports_dir.glob("*.html"):
|
|
# Determine report type from filename
|
|
if "training" in report_file.name:
|
|
report_type = "training"
|
|
elif "prediction" in report_file.name:
|
|
report_type = "prediction"
|
|
else:
|
|
report_type = "unknown"
|
|
|
|
report_info = {
|
|
"filename": report_file.name,
|
|
"type": report_type,
|
|
"created": datetime.fromtimestamp(report_file.stat().st_mtime).isoformat(),
|
|
"size_kb": round(report_file.stat().st_size / 1024, 2),
|
|
"view_url": f"/api/reports/view/{report_file.name}",
|
|
"download_url": f"/api/reports/download/{report_file.name}",
|
|
"is_batch_job": False,
|
|
"batch_metadata": None
|
|
}
|
|
|
|
# Check if this is a batch job report
|
|
if report_type == "prediction":
|
|
predictions_dir = Path("predictions")
|
|
# Look for batch metadata JSON files that reference this report
|
|
for json_file in predictions_dir.glob("batch_*.json"):
|
|
try:
|
|
import json
|
|
with open(json_file, 'r') as f:
|
|
metadata = json.load(f)
|
|
if metadata.get("report_filename") == report_file.name or \
|
|
(metadata.get("batch_job_id") and report_file.name.endswith('.html')):
|
|
report_info["is_batch_job"] = True
|
|
report_info["batch_metadata"] = {
|
|
"batch_job_id": metadata.get("batch_job_id"),
|
|
"batch_name": metadata.get("batch_name"),
|
|
"batch_timestamp": metadata.get("batch_timestamp")
|
|
}
|
|
break
|
|
except Exception as e:
|
|
pass
|
|
|
|
reports.append(report_info)
|
|
|
|
# Sort by creation time (newest first)
|
|
reports.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"reports": reports, "count": len(reports)}
|
|
|
|
|
|
@app.get("/api/reports/view/{filename}", response_class=HTMLResponse)
|
|
async def view_report(filename: str):
|
|
"""Xem báo cáo HTML trực tiếp"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
html_content = f.read()
|
|
|
|
return HTMLResponse(content=html_content)
|
|
|
|
|
|
@app.get("/api/reports/download/{filename}")
|
|
async def download_report(filename: str):
|
|
"""Download báo cáo HTML"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
filename=filename,
|
|
media_type="text/html",
|
|
headers={
|
|
"Content-Disposition": f"attachment; filename={filename}"
|
|
}
|
|
)
|
|
|
|
|
|
@app.delete("/api/reports/delete/{filename}")
|
|
async def delete_report(filename: str):
|
|
"""Xóa một báo cáo"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
try:
|
|
file_path.unlink()
|
|
return {"message": f"Đã xóa báo cáo: {filename}", "success": True}
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail=f"Không thể xóa: {str(e)}")
|
|
|
|
|
|
@app.post("/api/prediction/start")
|
|
async def start_prediction(config: PredictionConfig, background_tasks: BackgroundTasks):
|
|
"""Bắt đầu dự đoán"""
|
|
global prediction_status
|
|
|
|
if prediction_status["is_predicting"]:
|
|
raise HTTPException(status_code=400, detail="Đang có dự đoán khác đang chạy")
|
|
|
|
# Reset status
|
|
prediction_status = {
|
|
"is_predicting": True,
|
|
"progress": "Đang khởi động...",
|
|
"error": None,
|
|
"result": None,
|
|
"output_file": None,
|
|
"start_time": datetime.now().isoformat(),
|
|
"end_time": None
|
|
}
|
|
|
|
# Run prediction in background
|
|
background_tasks.add_task(run_prediction, config)
|
|
|
|
return {"message": "Đã bắt đầu dự đoán", "status": prediction_status}
|
|
|
|
|
|
@app.get("/api/prediction/status")
|
|
async def get_prediction_status():
|
|
"""Kiểm tra trạng thái dự đoán"""
|
|
return prediction_status
|
|
|
|
|
|
async def run_training(config: TrainingConfig):
|
|
"""Chạy training process"""
|
|
global training_status
|
|
|
|
try:
|
|
training_status["cancel_requested"] = False
|
|
training_status["progress"] = "Đang import thư viện..."
|
|
|
|
# Import training module
|
|
from train_module import train_model
|
|
|
|
training_status["progress"] = "Đang load dữ liệu Sentinel-2..."
|
|
|
|
# Function to check if training should be cancelled
|
|
def should_cancel():
|
|
return training_status.get("cancel_requested", False)
|
|
|
|
# Run training
|
|
result = train_model(
|
|
bbox=[config.min_lon, config.min_lat, config.max_lon, config.max_lat],
|
|
time_range=f"{config.start_date}/{config.end_date}",
|
|
max_scenes=config.max_scenes,
|
|
cloud_cover=config.cloud_cover,
|
|
resolution=config.resolution,
|
|
training_shapefile=config.training_shapefile,
|
|
model_type=config.model_type,
|
|
n_estimators=config.n_estimators,
|
|
max_depth=config.max_depth,
|
|
learning_rate=config.learning_rate,
|
|
use_gpu=config.use_gpu,
|
|
use_cache=config.use_cache,
|
|
test_size=config.test_size,
|
|
status_callback=lambda msg: update_progress(msg),
|
|
cancel_check=should_cancel
|
|
)
|
|
|
|
if training_status.get("cancel_requested", False):
|
|
training_status["is_training"] = False
|
|
training_status["progress"] = "Đã hủy training"
|
|
training_status["error"] = "Training cancelled by user"
|
|
else:
|
|
training_status["is_training"] = False
|
|
training_status["progress"] = "Hoàn thành! Đang tạo báo cáo..."
|
|
training_status["result"] = result
|
|
|
|
# Auto generate report
|
|
if result.get("success", False):
|
|
try:
|
|
report_path, _ = generate_training_report(result)
|
|
training_status["result"]["report_path"] = report_path
|
|
training_status["result"]["report_filename"] = Path(report_path).name
|
|
training_status["progress"] = "Hoàn thành! Báo cáo đã được tạo."
|
|
print(f"[REPORT] Generated: {report_path}")
|
|
except Exception as e:
|
|
print(f"[REPORT ERROR] Failed to generate report: {e}")
|
|
training_status["progress"] = "Hoàn thành! (Không thể tạo báo cáo)"
|
|
|
|
training_status["end_time"] = datetime.now().isoformat()
|
|
|
|
except Exception as e:
|
|
training_status["is_training"] = False
|
|
training_status["error"] = str(e)
|
|
training_status["progress"] = f"Lỗi: {str(e)}"
|
|
training_status["end_time"] = datetime.now().isoformat()
|
|
import traceback
|
|
print(traceback.format_exc())
|
|
|
|
|
|
def update_progress(message: str):
|
|
"""Cập nhật progress message"""
|
|
global training_status
|
|
training_status["progress"] = message
|
|
print(f"[PROGRESS] {message}")
|
|
|
|
|
|
def update_prediction_progress(message: str):
|
|
"""Cập nhật prediction progress message"""
|
|
global prediction_status
|
|
prediction_status["progress"] = message
|
|
print(f"[PREDICTION PROGRESS] {message}")
|
|
|
|
|
|
async def run_prediction(config: PredictionConfig):
|
|
"""Chạy prediction process - Áp dụng phương pháp từ 02.predict_ODC.ipynb"""
|
|
global prediction_status
|
|
|
|
try:
|
|
prediction_status["progress"] = "Đang import thư viện..."
|
|
|
|
# Import required libraries
|
|
import xarray as xr
|
|
import numpy as np
|
|
from datetime import datetime as dt
|
|
import rioxarray
|
|
import dask.array as da
|
|
|
|
# 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
|
|
model_path = Path("model_train") / config.model_filename
|
|
if not model_path.exists():
|
|
raise FileNotFoundError(f"Model không tồn tại: {config.model_filename}")
|
|
|
|
model_data = joblib.load(model_path)
|
|
|
|
# Extract model from dict (models are saved as {'model': xgb_model, 'label_encoder': encoder})
|
|
if isinstance(model_data, dict):
|
|
model = model_data.get('model')
|
|
label_encoder = model_data.get('label_encoder')
|
|
else:
|
|
model = model_data
|
|
label_encoder = None
|
|
|
|
# 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..."
|
|
# Import PyTorch if needed
|
|
try:
|
|
import torch
|
|
except ImportError:
|
|
raise ImportError("PyTorch is required for CNN prediction. Install: pip install torch")
|
|
|
|
prediction_status["progress"] = "Đang kiểm tra cache dữ liệu đầu vào..."
|
|
import hashlib, os
|
|
cache_dir = Path("dataset_cache")
|
|
cache_dir.mkdir(exist_ok=True)
|
|
# Tạo cache key từ bbox, time_range, max_scenes, cloud_cover, resolution
|
|
cache_key = f"pred_{config.min_lon}_{config.min_lat}_{config.max_lon}_{config.max_lat}_{config.start_date}_{config.end_date}_{config.max_scenes}_{config.cloud_cover}_{config.resolution}"
|
|
cache_hash = hashlib.md5(cache_key.encode()).hexdigest()
|
|
cache_file = cache_dir / f"prediction_input_{cache_hash}.joblib"
|
|
|
|
# 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}"
|
|
|
|
# Try to load from cache first
|
|
s2_data = None
|
|
use_cache = False
|
|
|
|
if cache_file.exists():
|
|
prediction_status["progress"] = "Đang load dữ liệu từ cache..."
|
|
try:
|
|
cached = joblib.load(cache_file)
|
|
s2_data_temp = cached["s2_data"]
|
|
|
|
# Verify that cached data is not lazy (to avoid 403 errors from expired URLs)
|
|
# If s2_data has chunks attribute, it's a dask array (lazy)
|
|
is_lazy = False
|
|
try:
|
|
is_lazy = any(hasattr(s2_data_temp[var].data, 'chunks') for var in s2_data_temp.data_vars)
|
|
except:
|
|
pass
|
|
|
|
if is_lazy:
|
|
print(f"[WARNING] Cache contains lazy data with potentially expired URLs. Deleting cache...")
|
|
cache_file.unlink()
|
|
raise ValueError("Cache invalid - contains lazy data")
|
|
|
|
# Cache is valid, use it
|
|
s2_data = s2_data_temp
|
|
s2_items = cached.get("s2_items", [])
|
|
vh_monthly = cached.get("vh_monthly")
|
|
vv_monthly = cached.get("vv_monthly")
|
|
use_radar = cached.get("use_radar", False)
|
|
use_cache = True
|
|
print(f"[INFO] Loaded valid cache from {cache_file.name}")
|
|
|
|
except Exception as e:
|
|
print(f"[WARNING] Failed to load cache: {e}. Fetching fresh data...")
|
|
s2_data = None
|
|
|
|
# If cache not available or invalid, fetch from Microsoft
|
|
if s2_data is None:
|
|
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,
|
|
)
|
|
# ============ BƯỚC 1: TẢI DỮ LIỆU SENTINEL-2 ============
|
|
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..."
|
|
s2_data_lazy = load(
|
|
s2_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="solar_day",
|
|
resolution=config.resolution
|
|
)
|
|
# Compute s2_data to load into memory (avoid lazy loading from expired URLs)
|
|
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-2 vào bộ nhớ..."
|
|
s2_data = s2_data_lazy.compute()
|
|
|
|
# ============ BƯỚC 4: TẢI DỮ LIỆU SENTINEL-1 (Radar)... ============
|
|
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-1 (Radar)..."
|
|
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]
|
|
prediction_status["progress"] = f"Đang xử lý {len(s1_items)} scenes Sentinel-1..."
|
|
s1_data = load(
|
|
s1_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="sat:absolute_orbit",
|
|
resolution=config.resolution
|
|
)
|
|
if "vh" in s1_data and "vv" in s1_data:
|
|
vh = s1_data["vh"].astype('float32')
|
|
vv = s1_data["vv"].astype('float32')
|
|
vh_monthly = vh.resample(time="1ME").mean().compute()
|
|
vv_monthly = vv.resample(time="1ME").mean().compute()
|
|
use_radar = True
|
|
else:
|
|
vh_monthly = None
|
|
vv_monthly = None
|
|
use_radar = False
|
|
else:
|
|
vh_monthly = None
|
|
vv_monthly = None
|
|
use_radar = False
|
|
# Lưu cache
|
|
joblib.dump({
|
|
"s2_data": s2_data,
|
|
"s2_items": s2_items,
|
|
"vh_monthly": vh_monthly,
|
|
"vv_monthly": vv_monthly,
|
|
"use_radar": use_radar
|
|
}, cache_file)
|
|
|
|
# ============ BƯỚC 2: TÍNH NDVI VÀ XỬ LÝ MÂY ============
|
|
prediction_status["progress"] = "Đang tính toán NDVI và xử lý mây..."
|
|
|
|
# Calculate NDVI using Sentinel-2 band names (B08 = NIR, B04 = Red)
|
|
nir = s2_data["B08"].astype('float32')
|
|
red = s2_data["B04"].astype('float32')
|
|
ndvi = (nir - red) / (nir + red + 1e-8)
|
|
|
|
# Mask clouds using SCL band if available
|
|
if "SCL" in s2_data:
|
|
scl = s2_data["SCL"]
|
|
# SCL values: 4=vegetation, 5=bare soil, 6=water - these are clear
|
|
# 3=cloud shadow, 8=cloud medium, 9=cloud high, 10=cirrus - mask these
|
|
cloud_mask = (scl == 3) | (scl == 8) | (scl == 9) | (scl == 10)
|
|
ndvi = ndvi.where(~cloud_mask)
|
|
|
|
# ============ BƯỚC 3: ĐIỀN GIÁ TRỊ NAN (FILL NAN) ============
|
|
prediction_status["progress"] = "Đang điền giá trị bị che mây..."
|
|
|
|
# Fill NaN using forward fill and backward fill
|
|
ndvi_filled = ndvi.ffill(dim='time').bfill(dim='time')
|
|
|
|
# Resample to monthly average
|
|
prediction_status["progress"] = "Đang tính trung bình NDVI theo tháng..."
|
|
ndvi_monthly = ndvi_filled.resample(time="1ME").mean()
|
|
|
|
# Compute NDVI (convert from dask to numpy)
|
|
ndvi_monthly = ndvi_monthly.compute()
|
|
|
|
# ============ BƯỚC 4: TẢI DỮ LIỆU SENTINEL-1 (VH, VV) ============
|
|
# Only load radar if not already in cache
|
|
if not cache_file.exists() or (cache_file.exists() and not use_radar):
|
|
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-1 (Radar)..."
|
|
try:
|
|
# Initialize catalog if not already done
|
|
if not cache_file.exists():
|
|
pass
|
|
else:
|
|
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,
|
|
)
|
|
# Search Sentinel-1 data
|
|
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]
|
|
prediction_status["progress"] = f"Đang xử lý {len(s1_items)} scenes Sentinel-1..."
|
|
try:
|
|
s1_data = load(
|
|
s1_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="sat:absolute_orbit",
|
|
resolution=config.resolution
|
|
)
|
|
if "vh" in s1_data and "vv" in s1_data:
|
|
vh = s1_data["vh"].astype('float32')
|
|
vv = s1_data["vv"].astype('float32')
|
|
prediction_status["progress"] = "Đang tính trung bình VH/VV theo tháng..."
|
|
try:
|
|
vh_monthly = vh.resample(time="1ME").mean().compute()
|
|
vv_monthly = vv.resample(time="1ME").mean().compute()
|
|
use_radar = True
|
|
except Exception as radar_exc:
|
|
print(f"[RADAR WARNING] Không thể tính radar monthly: {radar_exc}")
|
|
vh_monthly = None
|
|
vv_monthly = None
|
|
use_radar = False
|
|
else:
|
|
prediction_status["progress"] = "Không tìm thấy bands VH/VV, tiếp tục với NDVI..."
|
|
use_radar = False
|
|
except Exception as radar_exc:
|
|
print(f"[RADAR WARNING] Không thể tải dữ liệu Sentinel-1: {radar_exc}")
|
|
vh_monthly = None
|
|
vv_monthly = None
|
|
use_radar = False
|
|
else:
|
|
prediction_status["progress"] = "Không có dữ liệu Sentinel-1, tiếp tục với NDVI..."
|
|
use_radar = False
|
|
except Exception as radar_exc:
|
|
print(f"[RADAR WARNING] Không thể truy cập Sentinel-1: {radar_exc}")
|
|
prediction_status["progress"] = "Không thể truy cập Sentinel-1, tiếp tục với NDVI..."
|
|
vh_monthly = None
|
|
vv_monthly = None
|
|
use_radar = False
|
|
|
|
# ============ BƯỚC 5: CHUẨN BỊ FEATURES CHO DỰ ĐOÁN ============
|
|
prediction_status["progress"] = "Đang chuẩn bị features cho dự đoán..."
|
|
|
|
# Get shape information
|
|
n_times_ndvi = len(ndvi_monthly.time)
|
|
y_size = len(ndvi_monthly.y)
|
|
x_size = len(ndvi_monthly.x)
|
|
n_pixels = y_size * x_size
|
|
|
|
# Prepare NDVI features (flatten each time step)
|
|
ndvi_features = []
|
|
for t in range(n_times_ndvi):
|
|
ndvi_t = ndvi_monthly.isel(time=t).values.flatten()
|
|
ndvi_features.append(ndvi_t)
|
|
|
|
# Stack NDVI features
|
|
features = np.column_stack(ndvi_features)
|
|
|
|
# Add radar features if available
|
|
if use_radar:
|
|
n_times_vh = len(vh_monthly.time)
|
|
n_times_vv = len(vv_monthly.time)
|
|
|
|
# Add VH features
|
|
for t in range(min(n_times_vh, n_times_ndvi)):
|
|
vh_t = vh_monthly.isel(time=t).values.flatten()
|
|
# Resize if needed
|
|
if len(vh_t) != n_pixels:
|
|
vh_t = np.resize(vh_t, n_pixels)
|
|
features = np.column_stack([features, vh_t])
|
|
|
|
# Add VV features
|
|
for t in range(min(n_times_vv, n_times_ndvi)):
|
|
vv_t = vv_monthly.isel(time=t).values.flatten()
|
|
# Resize if needed
|
|
if len(vv_t) != n_pixels:
|
|
vv_t = np.resize(vv_t, n_pixels)
|
|
features = np.column_stack([features, vv_t])
|
|
|
|
# Handle NaN values in features✓ CNN PyTorch: Mạnh nhất với ảnh vệ tinh, tự học features, tương thích GPU tốt, cần pip install torch
|
|
features = np.nan_to_num(features, nan=0.0)
|
|
|
|
# ============ BƯỚC 6: DỰ ĐOÁN ============
|
|
# Check model's expected feature count and adjust
|
|
try:
|
|
# Get expected number of features from model
|
|
if is_cnn_model:
|
|
# For PyTorch CNN, get n_features from model
|
|
expected_features = model.n_features
|
|
elif hasattr(model, 'n_features_in_'):
|
|
expected_features = model.n_features_in_
|
|
elif hasattr(model, 'feature_names_in_'):
|
|
expected_features = len(model.feature_names_in_)
|
|
else:
|
|
# Try to get from booster for XGBoost
|
|
try:
|
|
expected_features = model.get_booster().num_features()
|
|
except:
|
|
expected_features = features.shape[1]
|
|
|
|
prediction_status["progress"] = f"Model cần {expected_features} features, đang có {features.shape[1]} features..."
|
|
|
|
# Adjust features to match model
|
|
if features.shape[1] > expected_features:
|
|
# Trim to expected number (use only first N features - NDVI only)
|
|
prediction_status["progress"] = f"Cắt bớt features từ {features.shape[1]} xuống {expected_features}..."
|
|
features = features[:, :expected_features]
|
|
elif features.shape[1] < expected_features:
|
|
# Pad with zeros or repeat last features
|
|
prediction_status["progress"] = f"Thêm features từ {features.shape[1]} lên {expected_features}..."
|
|
n_missing = expected_features - features.shape[1]
|
|
# Repeat last feature column to fill
|
|
padding = np.tile(features[:, -1:], (1, n_missing))
|
|
features = np.column_stack([features, padding])
|
|
except Exception as e:
|
|
prediction_status["progress"] = f"Không thể xác định số features của model, tiếp tục với {features.shape[1]} features..."
|
|
|
|
prediction_status["progress"] = f"Đang dự đoán với {features.shape[1]} features..."
|
|
|
|
# Make prediction
|
|
if is_cnn_model:
|
|
# PyTorch CNN prediction
|
|
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)
|
|
except:
|
|
pass # Keep numeric predictions if inverse_transform fails
|
|
|
|
# Reshape to original shape
|
|
pred_shape = (y_size, x_size)
|
|
predictions_2d = predictions.reshape(pred_shape)
|
|
|
|
# ============ BƯỚC 7: TẠO OUTPUT VÀ LƯU KẾT QUẢ ============
|
|
prediction_status["progress"] = "Đang tạo bản đồ phân loại..."
|
|
|
|
# Create output xarray
|
|
prediction_da = xr.DataArray(
|
|
predictions_2d,
|
|
coords={
|
|
"y": ndvi_monthly.y,
|
|
"x": ndvi_monthly.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 for web display
|
|
prediction_status["progress"] = "Đang tạo PNG preview..."
|
|
png_file = output_dir / f"prediction_{timestamp}.png"
|
|
try:
|
|
import matplotlib
|
|
matplotlib.use('Agg') # Non-interactive backend
|
|
import matplotlib.pyplot as plt
|
|
|
|
# Create a figure with prediction result
|
|
fig, ax = plt.subplots(figsize=(12, 10), dpi=150)
|
|
|
|
# Plot prediction with colormap
|
|
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)
|
|
|
|
# Add colorbar
|
|
cbar = plt.colorbar(im, ax=ax, fraction=0.046, pad=0.04)
|
|
cbar.set_label('Class', rotation=270, labelpad=15)
|
|
|
|
# Add grid
|
|
ax.grid(True, alpha=0.3, linestyle='--', linewidth=0.5)
|
|
|
|
# Save PNG
|
|
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 for result
|
|
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],
|
|
"n_times_ndvi": n_times_ndvi,
|
|
"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(traceback.format_exc())
|
|
|
|
|
|
@app.get("/api/predictions/list")
|
|
async def list_predictions():
|
|
"""Lấy danh sách các file prediction đã tạo"""
|
|
predictions_dir = Path("predictions")
|
|
predictions_dir.mkdir(exist_ok=True)
|
|
|
|
predictions = []
|
|
for pred_file in predictions_dir.glob("*.tif"):
|
|
pred_info = {
|
|
"filename": pred_file.name,
|
|
"created": datetime.fromtimestamp(pred_file.stat().st_mtime).isoformat(),
|
|
"size_mb": round(pred_file.stat().st_size / 1024 / 1024, 2),
|
|
"download_url": f"/api/predictions/download/{pred_file.name}",
|
|
"is_batch_job": pred_file.name.startswith("batch_"),
|
|
"batch_metadata": None
|
|
}
|
|
|
|
# Try to load batch metadata from JSON sidecar if exists
|
|
json_file = pred_file.with_suffix('.json')
|
|
if json_file.exists():
|
|
try:
|
|
import json
|
|
with open(json_file, 'r') as f:
|
|
metadata = json.load(f)
|
|
pred_info["batch_metadata"] = {
|
|
"batch_job_id": metadata.get("batch_job_id"),
|
|
"batch_name": metadata.get("batch_name"),
|
|
"batch_timestamp": metadata.get("batch_timestamp")
|
|
}
|
|
except Exception as e:
|
|
print(f"[METADATA ERROR] Failed to load {json_file}: {e}")
|
|
|
|
# Check PNG preview
|
|
png_file = pred_file.with_suffix('.png')
|
|
pred_info["has_preview"] = png_file.exists()
|
|
if png_file.exists():
|
|
pred_info["preview_url"] = f"/api/predictions/preview/{png_file.name}"
|
|
|
|
predictions.append(pred_info)
|
|
|
|
# Sort by creation time (newest first)
|
|
predictions.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"predictions": predictions}
|
|
|
|
|
|
@app.get("/api/predictions/download/{filename}")
|
|
async def download_prediction(filename: str):
|
|
"""Download file prediction GeoTIFF"""
|
|
predictions_dir = Path("predictions")
|
|
file_path = predictions_dir / filename
|
|
|
|
# Security check: ensure filename doesn't contain path traversal
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"File không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
filename=filename,
|
|
media_type="image/tiff",
|
|
headers={
|
|
"Content-Disposition": f"attachment; filename={filename}"
|
|
}
|
|
)
|
|
|
|
|
|
@app.get("/api/predictions/preview/{filename}")
|
|
async def preview_prediction_png(filename: str):
|
|
"""Preview PNG image of prediction"""
|
|
predictions_dir = Path("predictions")
|
|
file_path = predictions_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"PNG preview không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
media_type="image/png"
|
|
)
|
|
|
|
|
|
@app.get("/api/predictions/preview/{filename}")
|
|
async def preview_prediction_png(filename: str):
|
|
"""Preview PNG image of prediction"""
|
|
predictions_dir = Path("predictions")
|
|
file_path = predictions_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"PNG preview không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
media_type="image/png"
|
|
)
|
|
|
|
|
|
# ============ DASHBOARD & VISUALIZATION API ============
|
|
|
|
@app.get("/api/dashboard/accuracy-trends")
|
|
async def get_accuracy_trends():
|
|
"""Lấy dữ liệu accuracy trends của các models theo thời gian"""
|
|
model_dir = Path("model_train")
|
|
if not model_dir.exists():
|
|
return {"trends": [], "models": []}
|
|
|
|
trends_data = []
|
|
for info_file in sorted(model_dir.glob("*.json")):
|
|
try:
|
|
with open(info_file) as f:
|
|
info = json.load(f)
|
|
|
|
# Extract relevant data
|
|
if "training_date" in info and "metrics" in info:
|
|
trends_data.append({
|
|
"date": info["training_date"],
|
|
"model_name": info.get("model_type", "unknown"),
|
|
"accuracy": info["metrics"].get("accuracy", 0),
|
|
"f1_score": info["metrics"].get("macro avg", {}).get("f1-score", 0),
|
|
"precision": info["metrics"].get("macro avg", {}).get("precision", 0),
|
|
"recall": info["metrics"].get("macro avg", {}).get("recall", 0),
|
|
"filename": info_file.stem + ".joblib"
|
|
})
|
|
except Exception as e:
|
|
print(f"Error loading {info_file}: {e}")
|
|
continue
|
|
|
|
# Sort by date
|
|
trends_data.sort(key=lambda x: x["date"])
|
|
|
|
return {
|
|
"trends": trends_data,
|
|
"models": list(set(d["model_name"] for d in trends_data))
|
|
}
|
|
|
|
|
|
@app.get("/api/dashboard/statistics")
|
|
async def get_statistics():
|
|
"""Lấy thống kê tổng quan: số models, predictions, reports"""
|
|
model_dir = Path("model_train")
|
|
predictions_dir = Path("predictions")
|
|
reports_dir = Path("reports")
|
|
|
|
# Count items
|
|
n_models = len(list(model_dir.glob("*.joblib"))) if model_dir.exists() else 0
|
|
n_predictions = len(list(predictions_dir.glob("*.tif"))) if predictions_dir.exists() else 0
|
|
n_reports = len(list(reports_dir.glob("*.html"))) if reports_dir.exists() else 0
|
|
|
|
# Get latest model info
|
|
latest_model = None
|
|
if model_dir.exists():
|
|
model_files = sorted(model_dir.glob("*.json"), key=lambda x: x.stat().st_mtime, reverse=True)
|
|
if model_files:
|
|
try:
|
|
with open(model_files[0]) as f:
|
|
latest_model = json.load(f)
|
|
except:
|
|
pass
|
|
|
|
# Get latest prediction
|
|
latest_prediction = None
|
|
if predictions_dir.exists():
|
|
pred_files = sorted(predictions_dir.glob("*.tif"), key=lambda x: x.stat().st_mtime, reverse=True)
|
|
if pred_files:
|
|
latest_prediction = {
|
|
"filename": pred_files[0].name,
|
|
"created": datetime.fromtimestamp(pred_files[0].stat().st_mtime).isoformat(),
|
|
"size_mb": round(pred_files[0].stat().st_size / 1024 / 1024, 2)
|
|
}
|
|
|
|
return {
|
|
"models": {
|
|
"total": n_models,
|
|
"latest": latest_model
|
|
},
|
|
"predictions": {
|
|
"total": n_predictions,
|
|
"latest": latest_prediction
|
|
},
|
|
"reports": {
|
|
"total": n_reports
|
|
},
|
|
"training_status": training_status,
|
|
"prediction_status": prediction_status
|
|
}
|
|
|
|
|
|
@app.get("/api/dashboard/class-distribution/{model_filename}")
|
|
async def get_class_distribution(model_filename: str):
|
|
"""Lấy phân bố các lớp từ model info"""
|
|
# Convert model filename to info filename
|
|
# e.g., model_cnn_20251221_163841.joblib -> model_cnn_20251221_163841_info.json
|
|
base_name = model_filename.replace(".joblib", "")
|
|
info_file = Path("model_train") / f"{base_name}_info.json"
|
|
|
|
if not info_file.exists():
|
|
raise HTTPException(status_code=404, detail="Model info không tồn tại")
|
|
|
|
with open(info_file) as f:
|
|
info = json.load(f)
|
|
|
|
# Extract class distribution from classification report
|
|
class_dist = {}
|
|
if "classification_report" in info:
|
|
for class_name, metrics in info["classification_report"].items():
|
|
if isinstance(metrics, dict) and "support" in metrics:
|
|
class_dist[class_name] = int(metrics["support"])
|
|
|
|
return {
|
|
"model": model_filename,
|
|
"class_distribution": class_dist,
|
|
"total_samples": sum(class_dist.values()) if class_dist else 0
|
|
}
|
|
|
|
|
|
# ============ BATCH PROCESSING API ============
|
|
|
|
class BatchPredictionItem(BaseModel):
|
|
"""Một item trong batch prediction"""
|
|
name: str
|
|
min_lon: float
|
|
min_lat: float
|
|
max_lon: float
|
|
max_lat: float
|
|
start_date: str = "2023-03-01"
|
|
end_date: str = "2023-05-31"
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20
|
|
|
|
|
|
class BatchPredictionConfig(BaseModel):
|
|
"""Cấu hình cho batch prediction"""
|
|
model_filename: str
|
|
items: List[BatchPredictionItem]
|
|
auto_retry: bool = True
|
|
max_retries: int = 3
|
|
|
|
|
|
@app.post("/api/batch/start")
|
|
async def start_batch_prediction(config: BatchPredictionConfig, background_tasks: BackgroundTasks):
|
|
"""Bắt đầu batch prediction"""
|
|
global batch_queue, batch_results
|
|
|
|
# Create batch jobs
|
|
batch_id = datetime.now().strftime("%Y%m%d_%H%M%S")
|
|
|
|
for idx, item in enumerate(config.items):
|
|
job = {
|
|
"batch_id": batch_id,
|
|
"job_id": f"{batch_id}_{idx}",
|
|
"name": item.name,
|
|
"status": "queued",
|
|
"progress": 0,
|
|
"error": None,
|
|
"result": None,
|
|
"retries": 0,
|
|
"max_retries": config.max_retries if config.auto_retry else 0,
|
|
"config": {
|
|
"model_filename": config.model_filename,
|
|
"min_lon": item.min_lon,
|
|
"min_lat": item.min_lat,
|
|
"max_lon": item.max_lon,
|
|
"max_lat": item.max_lat,
|
|
"start_date": item.start_date,
|
|
"end_date": item.end_date,
|
|
"max_scenes": item.max_scenes,
|
|
"cloud_cover": item.cloud_cover,
|
|
"resolution": item.resolution
|
|
},
|
|
"created_at": datetime.now().isoformat()
|
|
}
|
|
batch_queue.append(job)
|
|
|
|
# Start processing in background
|
|
background_tasks.add_task(process_batch_queue)
|
|
|
|
return {
|
|
"message": f"Đã tạo {len(config.items)} batch jobs",
|
|
"batch_id": batch_id,
|
|
"total_jobs": len(config.items)
|
|
}
|
|
|
|
|
|
@app.get("/api/batch/status")
|
|
async def get_batch_status():
|
|
"""Lấy trạng thái của batch queue"""
|
|
global batch_queue, batch_results
|
|
|
|
queued = [j for j in batch_queue if j["status"] == "queued"]
|
|
running = [j for j in batch_queue if j["status"] == "running"]
|
|
completed = [j for j in batch_results if j["status"] == "completed"]
|
|
failed = [j for j in batch_results if j["status"] == "failed"]
|
|
|
|
return {
|
|
"queue": {
|
|
"queued": len(queued),
|
|
"running": len(running),
|
|
"completed": len(completed),
|
|
"failed": len(failed),
|
|
"total": len(batch_queue) + len(batch_results)
|
|
},
|
|
"jobs": {
|
|
"queued": queued[:5], # Show first 5
|
|
"running": running,
|
|
"recent_completed": completed[:10], # Show last 10
|
|
"recent_failed": failed[:10]
|
|
}
|
|
}
|
|
|
|
|
|
@app.get("/api/batch/results/{batch_id}")
|
|
async def get_batch_results(batch_id: str):
|
|
"""Lấy kết quả của một batch"""
|
|
global batch_results
|
|
|
|
results = [j for j in batch_results if j["batch_id"] == batch_id]
|
|
|
|
if not results:
|
|
# Check if still in queue
|
|
queued = [j for j in batch_queue if j["batch_id"] == batch_id]
|
|
if queued:
|
|
return {
|
|
"batch_id": batch_id,
|
|
"status": "processing",
|
|
"jobs": queued
|
|
}
|
|
else:
|
|
raise HTTPException(status_code=404, detail="Batch không tồn tại")
|
|
|
|
return {
|
|
"batch_id": batch_id,
|
|
"status": "completed",
|
|
"jobs": results,
|
|
"summary": {
|
|
"total": len(results),
|
|
"successful": len([j for j in results if j["status"] == "completed"]),
|
|
"failed": len([j for j in results if j["status"] == "failed"])
|
|
}
|
|
}
|
|
|
|
|
|
@app.post("/api/batch/cancel/{batch_id}")
|
|
async def cancel_batch(batch_id: str):
|
|
"""Hủy một batch đang chạy"""
|
|
global batch_queue
|
|
|
|
# Remove from queue
|
|
removed = 0
|
|
batch_queue_copy = batch_queue.copy()
|
|
for job in batch_queue_copy:
|
|
if job["batch_id"] == batch_id and job["status"] == "queued":
|
|
batch_queue.remove(job)
|
|
removed += 1
|
|
|
|
return {
|
|
"message": f"Đã hủy {removed} jobs",
|
|
"batch_id": batch_id
|
|
}
|
|
|
|
|
|
async def process_batch_queue():
|
|
"""Process batch prediction queue"""
|
|
global batch_queue, batch_results
|
|
|
|
import asyncio
|
|
|
|
while batch_queue:
|
|
# Get next job
|
|
job = None
|
|
for j in batch_queue:
|
|
if j["status"] == "queued":
|
|
job = j
|
|
break
|
|
|
|
if not job:
|
|
break
|
|
|
|
# Mark as running
|
|
job["status"] = "running"
|
|
job["progress"] = 0
|
|
job["started_at"] = datetime.now().isoformat()
|
|
|
|
try:
|
|
# Create PredictionConfig from job config
|
|
pred_config = PredictionConfig(**job["config"])
|
|
|
|
print(f"[BATCH] Processing job {job['job_id']}: {job['name']}")
|
|
job["progress"] = 5
|
|
|
|
# Run prediction synchronously (in the same thread to avoid conflicts)
|
|
await asyncio.to_thread(run_batch_prediction, job, pred_config)
|
|
|
|
# Check if prediction was successful
|
|
if job.get("result") and not job.get("error"):
|
|
job["status"] = "completed"
|
|
job["progress"] = 100
|
|
job["completed_at"] = datetime.now().isoformat()
|
|
print(f"[BATCH] Job {job['job_id']} completed successfully")
|
|
else:
|
|
raise Exception(job.get("error", "Unknown error during prediction"))
|
|
|
|
except Exception as e:
|
|
job["error"] = str(e)
|
|
|
|
# Retry logic
|
|
if job["retries"] < job["max_retries"]:
|
|
job["retries"] += 1
|
|
job["status"] = "queued" # Retry
|
|
job["progress"] = 0
|
|
print(f"[BATCH] Job {job['job_id']} ({job['name']}) failed, retrying ({job['retries']}/{job['max_retries']}): {e}")
|
|
continue
|
|
else:
|
|
job["status"] = "failed"
|
|
job["progress"] = 0
|
|
job["completed_at"] = datetime.now().isoformat()
|
|
print(f"[BATCH] Job {job['job_id']} ({job['name']}) failed permanently: {e}")
|
|
|
|
# Move to results
|
|
batch_queue.remove(job)
|
|
batch_results.append(job)
|
|
|
|
# Keep only last 100 results
|
|
if len(batch_results) > 100:
|
|
batch_results = batch_results[-100:]
|
|
|
|
|
|
def run_batch_prediction(job: dict, config: PredictionConfig):
|
|
"""Run prediction for a single batch job"""
|
|
try:
|
|
job["progress"] = 10
|
|
|
|
# Import required libraries
|
|
import xarray as xr
|
|
import numpy as np
|
|
from datetime import datetime as dt
|
|
import rioxarray
|
|
import dask.array as da
|
|
|
|
job["progress"] = 15
|
|
|
|
# Load model
|
|
model_path = Path("model_train") / config.model_filename
|
|
if not model_path.exists():
|
|
raise FileNotFoundError(f"Model không tồn tại: {config.model_filename}")
|
|
|
|
model_data = joblib.load(model_path)
|
|
|
|
if isinstance(model_data, dict):
|
|
model = model_data.get('model')
|
|
label_encoder = model_data.get('label_encoder')
|
|
else:
|
|
model = model_data
|
|
label_encoder = None
|
|
|
|
job["progress"] = 20
|
|
|
|
# Check if CNN model
|
|
is_cnn_model = hasattr(model, '__class__') and 'CNN' in model.__class__.__name__
|
|
|
|
# Load data from 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,
|
|
)
|
|
|
|
bbox = [config.min_lon, config.min_lat, config.max_lon, config.max_lat]
|
|
time_range = f"{config.start_date}/{config.end_date}"
|
|
|
|
job["progress"] = 25
|
|
|
|
# Search 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")
|
|
|
|
s2_items = s2_items[:config.max_scenes]
|
|
|
|
job["progress"] = 35
|
|
|
|
# Load Sentinel-2 data
|
|
s2_data = load(
|
|
s2_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="solar_day",
|
|
resolution=config.resolution
|
|
)
|
|
|
|
job["progress"] = 50
|
|
|
|
# Calculate NDVI
|
|
nir = s2_data["B08"].astype('float32')
|
|
red = s2_data["B04"].astype('float32')
|
|
ndvi = (nir - red) / (nir + red + 1e-8)
|
|
|
|
# Mask clouds if SCL available
|
|
if "SCL" in s2_data:
|
|
scl = s2_data["SCL"]
|
|
cloud_mask = (scl == 3) | (scl == 8) | (scl == 9) | (scl == 10)
|
|
ndvi = ndvi.where(~cloud_mask)
|
|
|
|
# Fill NaN and resample
|
|
ndvi_filled = ndvi.ffill(dim='time').bfill(dim='time')
|
|
ndvi_monthly = ndvi_filled.resample(time="1ME").mean().compute()
|
|
|
|
job["progress"] = 70
|
|
|
|
# Prepare features
|
|
n_times_ndvi = len(ndvi_monthly.time)
|
|
y_size = len(ndvi_monthly.y)
|
|
x_size = len(ndvi_monthly.x)
|
|
n_pixels = y_size * x_size
|
|
|
|
ndvi_features = []
|
|
for t in range(n_times_ndvi):
|
|
ndvi_t = ndvi_monthly.isel(time=t).values.flatten()
|
|
ndvi_features.append(ndvi_t)
|
|
|
|
features = np.column_stack(ndvi_features)
|
|
features = np.nan_to_num(features, nan=0.0)
|
|
|
|
job["progress"] = 80
|
|
|
|
# Adjust features to match model expectations
|
|
try:
|
|
if is_cnn_model:
|
|
expected_features = model.n_features
|
|
elif hasattr(model, 'n_features_in_'):
|
|
expected_features = model.n_features_in_
|
|
else:
|
|
try:
|
|
expected_features = model.get_booster().num_features()
|
|
except:
|
|
expected_features = features.shape[1]
|
|
|
|
if features.shape[1] > expected_features:
|
|
features = features[:, :expected_features]
|
|
elif features.shape[1] < expected_features:
|
|
n_missing = expected_features - features.shape[1]
|
|
padding = np.tile(features[:, -1:], (1, n_missing))
|
|
features = np.column_stack([features, padding])
|
|
except:
|
|
pass
|
|
|
|
# Predict
|
|
if is_cnn_model:
|
|
predictions = model.predict(features)
|
|
else:
|
|
predictions = model.predict(features)
|
|
|
|
# Decode labels
|
|
if label_encoder is not None:
|
|
try:
|
|
predictions = label_encoder.inverse_transform(predictions)
|
|
except:
|
|
pass
|
|
|
|
job["progress"] = 90
|
|
|
|
# Reshape and create output
|
|
pred_shape = (y_size, x_size)
|
|
predictions_2d = predictions.reshape(pred_shape)
|
|
|
|
prediction_da = xr.DataArray(
|
|
predictions_2d,
|
|
coords={"y": ndvi_monthly.y, "x": ndvi_monthly.x},
|
|
dims=["y", "x"],
|
|
name="classification"
|
|
)
|
|
|
|
# Save output
|
|
output_dir = Path("predictions")
|
|
output_dir.mkdir(exist_ok=True)
|
|
|
|
output_file = output_dir / f"batch_{job['job_id']}_{job['name'].replace(' ', '_')}.tif"
|
|
|
|
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
|
|
png_file = output_dir / f"batch_{job['job_id']}_{job['name'].replace(' ', '_')}.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"{job['name']} - Batch {job['job_id']}", 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)
|
|
except Exception as e:
|
|
print(f"[BATCH PNG ERROR] {e}")
|
|
png_file = None
|
|
|
|
# Get unique classes
|
|
unique_classes = np.unique(predictions_2d)
|
|
unique_classes = unique_classes[~np.isnan(unique_classes)].tolist()
|
|
|
|
# Store result in job with batch metadata
|
|
job["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],
|
|
"n_times_ndvi": n_times_ndvi,
|
|
"model_used": config.model_filename,
|
|
"batch_job_id": job["job_id"],
|
|
"batch_name": job["name"],
|
|
"batch_timestamp": datetime.now().isoformat()
|
|
}
|
|
|
|
# Save batch metadata to JSON sidecar file for persistence
|
|
metadata_file = output_file.with_suffix('.json')
|
|
try:
|
|
import json
|
|
with open(metadata_file, 'w') as f:
|
|
json.dump(job["result"], f, indent=2, default=str)
|
|
print(f"[BATCH METADATA] Saved to {metadata_file}")
|
|
except Exception as e:
|
|
print(f"[BATCH METADATA ERROR] Failed to save metadata: {e}")
|
|
|
|
# Auto generate prediction report for batch job
|
|
try:
|
|
from report_generator import generate_prediction_report
|
|
report_path, _ = generate_prediction_report(job["result"])
|
|
job["result"]["report_path"] = report_path
|
|
job["result"]["report_filename"] = Path(report_path).name
|
|
print(f"[BATCH REPORT] Generated prediction report: {report_path}")
|
|
except Exception as e:
|
|
print(f"[BATCH REPORT ERROR] Failed to generate report: {e}")
|
|
|
|
job["progress"] = 100
|
|
|
|
except Exception as e:
|
|
job["error"] = str(e)
|
|
import traceback
|
|
print(f"[BATCH ERROR] Job {job['job_id']}: {traceback.format_exc()}")
|
|
|
|
|
|
# ============ PREDICTION WITH NDVI API ============
|
|
|
|
@app.post("/api/predict/with-ndvi")
|
|
async def predict_with_ndvi(config: PredictionWithNDVIConfig, background_tasks: BackgroundTasks):
|
|
"""Predict land classification và NDVI cho một khu vực"""
|
|
try:
|
|
import numpy as np
|
|
import xarray as xr
|
|
from pystac_client import Client
|
|
import planetary_computer
|
|
import odc.stac
|
|
import rasterio
|
|
from rasterio.transform import from_bounds
|
|
import hashlib, os
|
|
|
|
# Load model
|
|
model_path = Path(f"model_train/{config.model_filename}")
|
|
if not model_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Model {config.model_filename} không tồn tại")
|
|
|
|
model_data = joblib.load(model_path)
|
|
|
|
# Extract model from dict (models are saved as {'model': xgb_model, 'label_encoder': encoder})
|
|
if isinstance(model_data, dict):
|
|
model = model_data.get('model')
|
|
label_encoder = model_data.get('label_encoder')
|
|
else:
|
|
model = model_data
|
|
label_encoder = None
|
|
|
|
print(f"[PREDICT+NDVI] Loaded model: {config.model_filename}")
|
|
|
|
# Check cache first
|
|
cache_dir = Path("dataset_cache")
|
|
cache_dir.mkdir(exist_ok=True)
|
|
cache_key = f"pred_{config.min_lon}_{config.min_lat}_{config.max_lon}_{config.max_lat}_{config.start_date}_{config.end_date}_{config.max_scenes}_{config.cloud_cover}_{config.resolution}"
|
|
cache_hash = hashlib.md5(cache_key.encode()).hexdigest()
|
|
cache_file = cache_dir / f"prediction_input_{cache_hash}.joblib"
|
|
|
|
bbox = [config.min_lon, config.min_lat, config.max_lon, config.max_lat]
|
|
|
|
# Load from cache or fetch from Microsoft
|
|
if cache_file.exists():
|
|
print(f"[PREDICT+NDVI] Loading from cache: {cache_file.name}")
|
|
cached = joblib.load(cache_file)
|
|
# Extract s2_data from cache (already computed in cache)
|
|
s2_data = cached["s2_data"]
|
|
# Check if needed bands are available in cache
|
|
available_bands = list(s2_data.data_vars.keys())
|
|
needed_bands = ["B02", "B03", "B04", "B08"]
|
|
if all(band in available_bands for band in needed_bands):
|
|
# Use cached data directly (no need to compute again)
|
|
data = s2_data[needed_bands]
|
|
print(f"[PREDICT+NDVI] Using cached bands: {needed_bands}")
|
|
# Set items to match the number of time slices in the cached data
|
|
items = [None] * s2_data.sizes.get("time", 1)
|
|
else:
|
|
raise HTTPException(status_code=400,
|
|
detail=f"Cache thiếu bands cần thiết. Có: {available_bands}, Cần: {needed_bands}")
|
|
else:
|
|
print(f"[PREDICT+NDVI] No cache found, fetching from Microsoft Planetary Computer")
|
|
# Connect to Microsoft Planetary Computer
|
|
catalog = Client.open(
|
|
"https://planetarycomputer.microsoft.com/api/stac/v1",
|
|
modifier=planetary_computer.sign_inplace
|
|
)
|
|
|
|
time_range = f"{config.start_date}/{config.end_date}"
|
|
|
|
# Search for Sentinel-2 data
|
|
search = catalog.search(
|
|
collections=["sentinel-2-l2a"],
|
|
bbox=bbox,
|
|
datetime=time_range,
|
|
query={"eo:cloud_cover": {"lt": config.cloud_cover}}
|
|
)
|
|
|
|
items = list(search.items())[:config.max_scenes]
|
|
print(f"[PREDICT+NDVI] Found {len(items)} Sentinel-2 scenes")
|
|
|
|
if len(items) == 0:
|
|
raise HTTPException(status_code=404, detail="Không tìm thấy dữ liệu vệ tinh")
|
|
|
|
# Sign items to refresh SAS tokens (keep as pystac.Item, not dict)
|
|
signed_items = [planetary_computer.sign(item) for item in items]
|
|
|
|
# Load all bands needed for features
|
|
data = odc.stac.load(
|
|
signed_items,
|
|
bbox=bbox,
|
|
bands=["B02", "B03", "B04", "B08"], # Blue, Green, Red, NIR
|
|
resolution=config.resolution,
|
|
chunks={"x": 2048, "y": 2048}
|
|
).compute()
|
|
|
|
print(f"[PREDICT+NDVI] Loaded data shape: {data.dims}")
|
|
|
|
# Calculate NDVI and other indices
|
|
blue = data["B02"].values
|
|
green = data["B03"].values
|
|
red = data["B04"].values
|
|
nir = data["B08"].values
|
|
|
|
# Calculate indices
|
|
# NDVI = (NIR - Red) / (NIR + Red)
|
|
ndvi = (nir - red) / (nir + red + 1e-8)
|
|
|
|
# NDWI = (Green - NIR) / (Green + NIR)
|
|
ndwi = (green - nir) / (green + nir + 1e-8)
|
|
|
|
# NDBI = (SWIR - NIR) / (SWIR + NIR) - we use Red as proxy
|
|
ndbi = (red - nir) / (red + nir + 1e-8)
|
|
|
|
# Prepare features for prediction
|
|
# Assuming model was trained with [NDVI, NDWI, NDBI] features
|
|
height, width = ndvi.shape[1:3] # Skip time dimension
|
|
n_pixels = height * width
|
|
|
|
# Average over time dimension
|
|
ndvi_mean = np.nanmean(ndvi, axis=0)
|
|
ndwi_mean = np.nanmean(ndwi, axis=0)
|
|
ndbi_mean = np.nanmean(ndbi, axis=0)
|
|
|
|
# Reshape for prediction
|
|
features = np.stack([ndvi_mean.flatten(), ndwi_mean.flatten(), ndbi_mean.flatten()], axis=1)
|
|
|
|
# Handle NaN values
|
|
valid_mask = ~np.isnan(features).any(axis=1)
|
|
features_clean = features[valid_mask]
|
|
|
|
print(f"[PREDICT+NDVI] Predicting {features_clean.shape[0]} valid pixels...")
|
|
|
|
# Predict
|
|
predictions = model.predict(features_clean)
|
|
|
|
# Reshape back to raster
|
|
prediction_raster = np.full(n_pixels, -1, dtype=np.int16)
|
|
prediction_raster[valid_mask] = predictions
|
|
prediction_raster = prediction_raster.reshape(height, width)
|
|
|
|
# Prepare outputs
|
|
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
|
|
output_dir = Path("predictions")
|
|
output_dir.mkdir(exist_ok=True)
|
|
|
|
output_files = []
|
|
|
|
# Export NDVI if requested
|
|
if config.export_ndvi:
|
|
ndvi_file = output_dir / f"ndvi_{timestamp}.tif"
|
|
transform = from_bounds(bbox[0], bbox[1], bbox[2], bbox[3], width, height)
|
|
|
|
with rasterio.open(
|
|
ndvi_file, 'w',
|
|
driver='GTiff',
|
|
height=height,
|
|
width=width,
|
|
count=1,
|
|
dtype=ndvi_mean.dtype,
|
|
crs='EPSG:4326',
|
|
transform=transform
|
|
) as dst:
|
|
dst.write(ndvi_mean, 1)
|
|
|
|
output_files.append({"type": "ndvi", "path": str(ndvi_file)})
|
|
print(f"[PREDICT+NDVI] Saved NDVI to {ndvi_file}")
|
|
|
|
# Export classification if requested
|
|
if config.export_classification:
|
|
class_file = output_dir / f"classification_{timestamp}.tif"
|
|
transform = from_bounds(bbox[0], bbox[1], bbox[2], bbox[3], width, height)
|
|
|
|
with rasterio.open(
|
|
class_file, 'w',
|
|
driver='GTiff',
|
|
height=height,
|
|
width=width,
|
|
count=1,
|
|
dtype=prediction_raster.dtype,
|
|
crs='EPSG:4326',
|
|
transform=transform
|
|
) as dst:
|
|
dst.write(prediction_raster, 1)
|
|
|
|
output_files.append({"type": "classification", "path": str(class_file)})
|
|
print(f"[PREDICT+NDVI] Saved classification to {class_file}")
|
|
|
|
# Calculate statistics
|
|
ndvi_stats = {
|
|
"mean": float(np.nanmean(ndvi_mean)),
|
|
"min": float(np.nanmin(ndvi_mean)),
|
|
"max": float(np.nanmax(ndvi_mean)),
|
|
"std": float(np.nanstd(ndvi_mean))
|
|
}
|
|
|
|
# Count classes
|
|
unique_classes, counts = np.unique(predictions, return_counts=True)
|
|
class_distribution = {
|
|
int(cls): int(count) for cls, count in zip(unique_classes, counts)
|
|
}
|
|
|
|
return {
|
|
"success": True,
|
|
"message": "Prediction with NDVI completed",
|
|
"output_files": output_files,
|
|
"ndvi_stats": ndvi_stats,
|
|
"class_distribution": class_distribution,
|
|
"n_scenes": len(items),
|
|
"resolution": config.resolution,
|
|
"bbox": bbox
|
|
}
|
|
|
|
except Exception as e:
|
|
print(f"[PREDICT+NDVI ERROR] {str(e)}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
|
|
# ============ NDVI TIME SERIES API ============
|
|
|
|
@app.post("/api/ndvi/timeseries")
|
|
async def calculate_ndvi_timeseries(config: NDVIConfig):
|
|
"""Tính NDVI time series cho một khu vực"""
|
|
try:
|
|
import numpy as np
|
|
import xarray as xr
|
|
from pystac_client import Client
|
|
import planetary_computer
|
|
import odc.stac
|
|
|
|
print(f"[NDVI] Starting calculation for bbox: {config.bbox}, time: {config.start_date} to {config.end_date}")
|
|
|
|
# Connect to Microsoft Planetary Computer STAC API
|
|
catalog = Client.open(
|
|
"https://planetarycomputer.microsoft.com/api/stac/v1",
|
|
modifier=planetary_computer.sign_inplace
|
|
)
|
|
|
|
bbox = config.bbox
|
|
time_range = f"{config.start_date}/{config.end_date}"
|
|
|
|
# Search for Sentinel-2 data
|
|
search = catalog.search(
|
|
collections=["sentinel-2-l2a"],
|
|
bbox=bbox,
|
|
datetime=time_range,
|
|
query={"eo:cloud_cover": {"lt": config.max_cloud_cover}}
|
|
)
|
|
|
|
items = list(search.items())
|
|
print(f"[NDVI] Found {len(items)} Sentinel-2 scenes")
|
|
|
|
if len(items) == 0:
|
|
raise HTTPException(status_code=404, detail="Không tìm thấy dữ liệu Sentinel-2 cho khu vực và thời gian này")
|
|
|
|
# Load data for each time step
|
|
ndvi_timeseries = []
|
|
|
|
for item in items:
|
|
try:
|
|
# Load NIR (B08) and Red (B04) bands
|
|
data = odc.stac.load(
|
|
[item],
|
|
bbox=bbox,
|
|
bands=["B04", "B08"], # Red and NIR
|
|
resolution=config.resolution,
|
|
chunks={"x": 2048, "y": 2048}
|
|
).compute()
|
|
|
|
if data is None or len(data.keys()) == 0:
|
|
continue
|
|
|
|
# Calculate NDVI = (NIR - Red) / (NIR + Red)
|
|
nir = data["B08"].values
|
|
red = data["B04"].values
|
|
|
|
# Avoid division by zero
|
|
denominator = nir + red
|
|
denominator = np.where(denominator == 0, np.nan, denominator)
|
|
|
|
ndvi = (nir - red) / denominator
|
|
|
|
# Calculate mean NDVI (ignore NaN values)
|
|
mean_ndvi = float(np.nanmean(ndvi))
|
|
|
|
# Get date from item
|
|
date_str = item.datetime.strftime("%Y-%m-%d")
|
|
|
|
ndvi_timeseries.append({
|
|
"date": date_str,
|
|
"ndvi": mean_ndvi
|
|
})
|
|
|
|
print(f"[NDVI] {date_str}: NDVI = {mean_ndvi:.3f}")
|
|
|
|
except Exception as e:
|
|
print(f"[NDVI WARNING] Failed to process item {item.id}: {e}")
|
|
continue
|
|
|
|
if len(ndvi_timeseries) == 0:
|
|
raise HTTPException(status_code=500, detail="Không thể tính NDVI cho bất kỳ ảnh nào")
|
|
|
|
# Sort by date
|
|
ndvi_timeseries.sort(key=lambda x: x["date"])
|
|
|
|
# Calculate statistics
|
|
ndvi_values = [item["ndvi"] for item in ndvi_timeseries]
|
|
mean_ndvi = float(np.mean(ndvi_values))
|
|
min_ndvi = float(np.min(ndvi_values))
|
|
max_ndvi = float(np.max(ndvi_values))
|
|
|
|
result = {
|
|
"timeseries": ndvi_timeseries,
|
|
"n_images": len(ndvi_timeseries),
|
|
"mean_ndvi": mean_ndvi,
|
|
"min_ndvi": min_ndvi,
|
|
"max_ndvi": max_ndvi,
|
|
"bbox": bbox,
|
|
"time_range": time_range
|
|
}
|
|
|
|
print(f"[NDVI] Calculation complete. Mean NDVI: {mean_ndvi:.3f}, Images: {len(ndvi_timeseries)}")
|
|
|
|
return result
|
|
|
|
except HTTPException:
|
|
raise
|
|
except Exception as e:
|
|
print(f"[NDVI ERROR] {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
raise HTTPException(status_code=500, detail=f"Lỗi khi tính NDVI: {str(e)}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
print("=" * 70)
|
|
print("🚀 LAND CLASSIFICATION TRAINING API SERVER")
|
|
print("=" * 70)
|
|
print("\n📍 Endpoints:")
|
|
print(" - Web Interface: http://localhost:8000")
|
|
print(" - API Docs: http://localhost:8000/docs")
|
|
print(" - Start Training: POST http://localhost:8000/api/training/start")
|
|
print(" - Check Status: GET http://localhost:8000/api/training/status")
|
|
print("\n" + "=" * 70)
|
|
|
|
uvicorn.run(app, host="0.0.0.0", port=8000, log_level="info")
|