{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "912ed572-1658-406b-976c-cd6de2d4e89e",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "%matplotlib inline\n",
    "\n",
    "import importlib\n",
    "import new_import_ODC  \n",
    "\n",
    "importlib.reload(new_import_ODC)\n",
    "\n",
    "from new_import_ODC import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d824dc4f-994b-4d1c-8d24-ce6674da141c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "# Cấu hình Daskgateway\n",
    "cluster, client = notebook_utils.initialize_dask(use_gateway=True, workers=(1, 10))\n",
    "# Khai báo 1 Datacube là dc\n",
    "dc = datacube.Datacube()\n",
    "\n",
    "# Cấu hình truy cập dịch vụ S3\n",
    "configure_s3_access(aws_unsigned=False, requester_pays=True, client=client)\n",
    "\n",
    "client"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fbed4c80-bbf8-4ea8-aa45-2460b2ba04c7",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "## cấu hình thời gian lấy ảnh và tọa độ\n",
    "date_range = (\"2022-09-01\", \"2023-10-01\")\n",
    "longtitude_range = (105.5, 106.4)\n",
    "latitude_range = (9.2, 10.0)\n",
    "\n",
    "coordinates = (longtitude_range, latitude_range)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b90c49b-0665-4478-a23b-d111ef88eb79",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "## truy vấn ảnh vệ tinh sen2\n",
    "data = load_data(dc, date_range, longtitude_range, latitude_range)\n",
    "notebook_utils.heading(notebook_utils.xarray_object_size(data))\n",
    "display(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2f6938b6-82e2-4916-bc1d-719c169e25e4",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "# Tiến hành loại bỏ các vị trí bị mây ảnh hưởng\n",
    "result = mask_clean(data)\n",
    "progress(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "435f9f78-a9a4-4226-86ca-d4bec42d454e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Tiến hành tính toán NDVI\n",
    "ds1 = calculate_indices(result, index=\"NDVI\", satellite_mission=\"s2\")\n",
    "ndvi = ds1[\"NDVI\"]\n",
    "display(ndvi)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "84992d28-8e3f-468e-be08-ded511f2c662",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "## Hiển thị ảnh NDVI chưa điền các giá trị mây (chưa fill nan)\n",
    "plt.imshow(ndvi.isel(time=6))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "72318b60-532a-4f08-a5f7-94762d08a42c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Thiết lập giá trị trung bình mùa vụ để xử lý các điểm ảnh bị mây dựa vào sự thay đổi theo mùa\n",
    "time_split = [\n",
    "    slice(\"2022-09-01\", \"2023-01-01\"),\n",
    "    slice(\"2023-01-01\", \"2023-05-01\"),\n",
    "    slice(\"2023-05-01\", \"2023-07-01\"),\n",
    "    slice(\"2023-07-01\", \"2023-10-01\"),\n",
    "]\n",
    "\n",
    "# Điền mây ở các vị trí mang giá trị nan (fill nan)\n",
    "fill_nan_ndvi = fill_nan(ndvi, time_split)\n",
    "\n",
    "# In kết quả ảnh NDVI đã điền mây (đã fill nan)\n",
    "plt.imshow(fill_nan_ndvi.isel(time=6))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "375b1cfb-37f5-49fe-8061-ea32eb47f9f6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "## tính ndvi theo tháng\n",
    "average_ndvi = fill_nan_ndvi.resample(time=\"1M\").mean().persist()\n",
    "progress(average_ndvi)\n",
    "\n",
    "# compute average_ndvi\n",
    "average_ndvi = average_ndvi.compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "187cc640-aef9-476b-91fc-b63f4d3ff2e3",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#Load dữ liệu ảnh Sentinel 1\n",
    "dsvh, dsvv = load_data_sen1(dc, date_range, coordinates)\n",
    "average_vv = calculate_average(dsvv, time_pattern='1M')\n",
    "average_vh = calculate_average(dsvh, time_pattern='1M')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d2585562-88aa-4c7d-bf70-1f6affcf65d4",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "## cấu hình bộ dữ liệu điểm huấn luyện mô hình (train file)\n",
    "train_path = \"train/ST_training data_updated_1130points_new.shp\"  # đường dẫn shp file train\n",
    "\n",
    "## load dữ liệu điểm huấn luyện mô hình (train file)\n",
    "train = load_train_data(train_path)\n",
    "train.head()\n",
    "\n",
    "# cấu hình nhãn dữ liệu \n",
    "label_mapping = {\n",
    "    \"Lua tom\": \"0\",\n",
    "    \"Lua\": \"1\",\n",
    "    \"CHN\": \"2\",\n",
    "    \"CLN\": \"3\",\n",
    "    \"TS\": \"4\",\n",
    "    \"Song\": \"5\",\n",
    "    \"Dat xay dung\": \"6\",\n",
    "    \"Rung\": \"7\",\n",
    "}\n",
    "\n",
    "# xây dựng tập dữ liệu (dataset) chứa dữ liệu VH, VV, NDVI\n",
    "datasets = get_data_sen1_and_sen2(train, average_ndvi, average_vh, average_vv)\n",
    "\n",
    "# chia tập dữ liệu thành các phần theo tỉ lệ 80(80-20)-20 tương ứng với tập train, validate, test\n",
    "X_train, X_val, X_test, y_train, y_val, y_test = split_train_data(\n",
    "    train, label_mapping, datasets\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2e955884-d4af-422d-a8e6-d436199540e0",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "# Import XGBoost\n",
    "import xgboost as xgb\n",
    "from sklearn.metrics import accuracy_score\n",
    "import numpy as np\n",
    "\n",
    "# Convert to numpy arrays\n",
    "X_train_np = np.asarray(X_train, dtype=np.float32)\n",
    "X_val_np = np.asarray(X_val, dtype=np.float32)\n",
    "y_train_np = np.asarray(y_train, dtype=np.int32)\n",
    "y_val_np = np.asarray(y_val, dtype=np.int32)\n",
    "\n",
    "print(\"🚀 Training XGBoost model...\")\n",
    "print(f\"   Train samples: {len(X_train_np)}\")\n",
    "print(f\"   Val samples: {len(X_val_np)}\")\n",
    "print(f\"   Features: {X_train_np.shape[1]}\")\n",
    "print(f\"   Classes: 8\\n\")\n",
    "\n",
    "# XGBoost parameters\n",
    "params = {\n",
    "    'objective': 'multi:softmax',  # Multi-class classification\n",
    "    'num_class': 8,                 # 8 land use classes\n",
    "    'max_depth': 6,                 # Maximum tree depth\n",
    "    'learning_rate': 0.1,           # Learning rate\n",
    "    'n_estimators': 200,            # Number of trees\n",
    "    'subsample': 0.8,               # Subsample ratio\n",
    "    'colsample_bytree': 0.8,        # Feature sampling ratio\n",
    "    'random_state': 42,\n",
    "    'n_jobs': -1,                   # Use all CPU cores\n",
    "    'eval_metric': 'mlogloss'       # Multi-class log loss\n",
    "}\n",
    "\n",
    "# Train XGBoost model\n",
    "model = xgb.XGBClassifier(**params)\n",
    "\n",
    "model.fit(\n",
    "    X_train_np, y_train_np,\n",
    "    eval_set=[(X_train_np, y_train_np), (X_val_np, y_val_np)],\n",
    "    verbose=True\n",
    ")\n",
    "\n",
    "# Validation accuracy\n",
    "y_val_pred = model.predict(X_val_np)\n",
    "val_accuracy = accuracy_score(y_val_np, y_val_pred)\n",
    "print(f\"\\n✅ Training completed!\")\n",
    "print(f\"   Validation Accuracy: {val_accuracy:.4f} ({val_accuracy*100:.2f}%)\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b2a1e42c-cf1b-4d82-a6af-b06e3496918f",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%time\n",
    "# Evaluate on test set\n",
    "X_test_np = np.asarray(X_test, dtype=np.float32)\n",
    "y_test_np = np.asarray(y_test, dtype=np.int32)\n",
    "\n",
    "print(\"📊 Evaluating XGBoost model on test set...\\n\")\n",
    "\n",
    "# Predictions\n",
    "y_pred_test = model.predict(X_test_np)\n",
    "\n",
    "# Metrics\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix\n",
    "\n",
    "test_accuracy = accuracy_score(y_test_np, y_pred_test)\n",
    "precision = precision_score(y_test_np, y_pred_test, average='weighted', zero_division=0)\n",
    "recall = recall_score(y_test_np, y_pred_test, average='weighted', zero_division=0)\n",
    "f1 = f1_score(y_test_np, y_pred_test, average='weighted', zero_division=0)\n",
    "\n",
    "print(f\"📈 Test Results:\")\n",
    "print(f\"   Accuracy:  {test_accuracy:.4f} ({test_accuracy*100:.2f}%)\")\n",
    "print(f\"   Precision: {precision:.4f}\")\n",
    "print(f\"   Recall:    {recall:.4f}\")\n",
    "print(f\"   F1-Score:  {f1:.4f}\\n\")\n",
    "\n",
    "# Confusion Matrix\n",
    "from sklearn.metrics import ConfusionMatrixDisplay\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Create figure first\n",
    "fig, ax = plt.subplots(figsize=(10, 8))\n",
    "\n",
    "class_names = list(label_mapping.keys())\n",
    "cm = confusion_matrix(y_test_np, y_pred_test)\n",
    "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=class_names)\n",
    "disp.plot(cmap='Blues', ax=ax)\n",
    "plt.xticks(rotation=45, ha='right')\n",
    "plt.title('XGBoost Confusion Matrix')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1a14379-ed6e-4897-9ca4-2669743fab40",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Lưu mô hình huấn luyện\n",
    "import json\n",
    "import joblib\n",
    "\n",
    "# Save XGBoost model\n",
    "model_path = \"model_xgboost.joblib\"\n",
    "joblib.dump(model, model_path)\n",
    "print(f\"✅ Model saved to {model_path}\")\n",
    "\n",
    "# Save model info\n",
    "info = {\n",
    "    \"model_type\": \"XGBoost\",\n",
    "    \"num_classes\": 8,\n",
    "    \"classes\": list(label_mapping.keys()),\n",
    "    \"num_features\": X_train_np.shape[1],\n",
    "    \"params\": params,\n",
    "    \"accuracy\": float(test_accuracy),\n",
    "    \"precision\": float(precision),\n",
    "    \"recall\": float(recall),\n",
    "    \"f1_score\": float(f1),\n",
    "}\n",
    "\n",
    "with open(\"model_xgboost_info.json\", \"w\") as f:\n",
    "    json.dump(info, f, indent=2)\n",
    "\n",
    "print(f\"✅ Model info saved to model_xgboost_info.json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "33dd516d-9824-499e-96b9-5cd9224c194c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# đóng client, cluster\n",
    "client.close()\n",
    "cluster.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ee0ecd6a-733b-4655-8864-bc037a539ce2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}