{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b05aa740",
   "metadata": {},
   "outputs": [],
   "source": [
    "import importlib\n",
    "import new_import_ODC as odc_tools\n",
    "importlib.reload(odc_tools)\n",
    "from new_import_ODC import *\n",
    "print(\"✅ Import thành công\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b794d005",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Khởi tạo Dask + Datacube + S3\n",
    "cluster, client = initialize_dask(use_gateway=True)\n",
    "dc = datacube.Datacube()\n",
    "configure_s3_access(aws_unsigned=True)\n",
    "print(\"✅ Dask + Datacube + S3 sẵn sàng\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5bc42a3c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Cấu hình vùng và thời gian\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",
    "# Tải dữ liệu Sentinel-2\n",
    "data_sen2 = load_data(\n",
    "    dc=dc,\n",
    "    date_range=date_range,\n",
    "    longtitude_range=longtitude_range,\n",
    "    latitude_range=latitude_range,\n",
    ")\n",
    "print(f\"✅ Sentinel-2 raw: {data_sen2.dims}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0ef51e7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Tiền xử lý Sentinel-2: cloud mask + NDVI + resampling\n",
    "data_clean = mask_clean(data_sen2)\n",
    "data_ndvi  = calculate_indices(data_clean, index=\"NDVI\")\n",
    "data_fill  = fill_nan(data_ndvi)\n",
    "data_sen2_monthly = data_fill.resample(time=\"1MS\").mean().compute()\n",
    "print(f\"✅ S2 monthly shape: {data_sen2_monthly.dims}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0da4f86d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Tải Sentinel-1 (SAR VV/VH)\n",
    "data_sen1 = load_data_sen1(\n",
    "    dc=dc,\n",
    "    date_range=date_range,\n",
    "    longtitude_range=longtitude_range,\n",
    "    latitude_range=latitude_range,\n",
    ")\n",
    "data_sen1_monthly = calculate_average(data_sen1, [\"VV\", \"VH\"], resample=\"1MS\").compute()\n",
    "print(f\"✅ S1 monthly shape: {data_sen1_monthly.dims}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "412b3716",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "# Ánh xạ nhãn lớp đất\n",
    "label_mapping = {\n",
    "    \"Lua tom\": \"0\", \"Lua\": \"1\", \"CHN\": \"2\", \"CLN\": \"3\",\n",
    "    \"TS\": \"4\", \"Song\": \"5\", \"Dat xay dung\": \"6\", \"Rung\": \"7\",\n",
    "}\n",
    "\n",
    "# Tải và ghép dữ liệu train từ S1 + S2\n",
    "train_data = load_train_data(label_mapping=label_mapping)\n",
    "X, y = get_data_sen1_and_sen2(train_data, data_sen2_monthly, data_sen1_monthly)\n",
    "\n",
    "# Chia tập train / val / test\n",
    "X_train, X_val, X_test, y_train, y_val, y_test = split_train_data(X, y, test_size=0.2, val_size=0.1)\n",
    "\n",
    "X_train_np = np.array(X_train, dtype=np.float32)\n",
    "X_val_np   = np.array(X_val,   dtype=np.float32)\n",
    "X_test_np  = np.array(X_test,  dtype=np.float32)\n",
    "y_train_np = np.array(y_train, dtype=np.int64)\n",
    "y_val_np   = np.array(y_val,   dtype=np.int64)\n",
    "y_test_np  = np.array(y_test,  dtype=np.int64)\n",
    "\n",
    "# Gộp train + val cho sklearn\n",
    "X_fit = np.concatenate([X_train_np, X_val_np], axis=0)\n",
    "y_fit = np.concatenate([y_train_np, y_val_np], axis=0)\n",
    "\n",
    "print(f\"✅ X_fit: {X_fit.shape}  |  X_test: {X_test_np.shape}\")\n",
    "print(f\"   Classes: {sorted(set(y_fit.tolist()))}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "84a8a1d0",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "# ── Xây dựng và train mô hình Decision Tree ─────────────────────────────────\n",
    "model = DecisionTreeClassifier(\n",
    "    max_depth=30,\n",
    "    min_samples_leaf=2,\n",
    "    min_samples_split=5,\n",
    "    class_weight=\"balanced\",\n",
    "    random_state=42,\n",
    ")\n",
    "\n",
    "print(\"🚀 Training Decision Tree...\")\n",
    "model.fit(X_fit, y_fit)\n",
    "\n",
    "val_acc = model.score(X_val_np, y_val_np)\n",
    "print(f\"✅ Training hoàn tất!  Depth: {model.get_depth()}  \"\n",
    "      f\"Leaves: {model.get_n_leaves()}  Val accuracy: {val_acc:.4f}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8248d748",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "# ═══════════════════════════════════════════════════════════════════════════════\n",
    "# PHÂN TÍCH ĐIỂM HỘI TỤ — Decision Tree\n",
    "# Phương pháp: quét max_depth từ 1→50 và theo dõi train/val accuracy\n",
    "# Điểm hội tụ = độ sâu tại đó val_acc đạt cực đại rồi bắt đầu giảm (overfitting)\n",
    "# ═══════════════════════════════════════════════════════════════════════════════\n",
    "DEPTH_RANGE = list(range(1, 51))\n",
    "THRESHOLD   = 0.001    # cải thiện val_acc < 0.1% → coi là hội tụ\n",
    "\n",
    "train_accs_d, val_accs_d = [], []\n",
    "print(\"🔍 Phân tích hội tụ theo max_depth ...\")\n",
    "for d in DEPTH_RANGE:\n",
    "    m = DecisionTreeClassifier(\n",
    "        min_samples_leaf=2, min_samples_split=5,\n",
    "        class_weight=\"balanced\", random_state=42, max_depth=d,\n",
    "    )\n",
    "    m.fit(X_fit, y_fit)\n",
    "    train_accs_d.append(m.score(X_fit,    y_fit))\n",
    "    val_accs_d.append(  m.score(X_val_np, y_val_np))\n",
    "\n",
    "train_accs_d = np.array(train_accs_d)\n",
    "val_accs_d   = np.array(val_accs_d)\n",
    "improvements = np.diff(val_accs_d)\n",
    "\n",
    "# ── Tìm điểm hội tụ ───────────────────────────────────────────────────────────\n",
    "best_depth      = DEPTH_RANGE[int(np.argmax(val_accs_d))]\n",
    "best_val_acc    = float(np.max(val_accs_d))\n",
    "\n",
    "# Điểm hội tụ sớm: lần đầu cải thiện < threshold\n",
    "conv_depth = None\n",
    "for i, imp in enumerate(improvements):\n",
    "    if abs(imp) < THRESHOLD:\n",
    "        conv_depth = DEPTH_RANGE[i + 1]\n",
    "        break\n",
    "\n",
    "# Điểm overfit: val_acc bắt đầu giảm so với peak\n",
    "overfit_depth = None\n",
    "peak_idx = int(np.argmax(val_accs_d))\n",
    "for i in range(peak_idx + 1, len(val_accs_d)):\n",
    "    if val_accs_d[i] < best_val_acc - 0.005:   # giảm > 0.5%\n",
    "        overfit_depth = DEPTH_RANGE[i]\n",
    "        break\n",
    "\n",
    "# Khoảng cách train-val (generalization gap)\n",
    "gap = train_accs_d - val_accs_d\n",
    "\n",
    "# ── Vẽ đồ thị ─────────────────────────────────────────────────────────────────\n",
    "fig, axes = plt.subplots(1, 3, figsize=(18, 5))\n",
    "\n",
    "# --- Trái: accuracy curves ---\n",
    "axes[0].plot(DEPTH_RANGE, train_accs_d, \"b-o\", markersize=3, label=\"Train\")\n",
    "axes[0].plot(DEPTH_RANGE, val_accs_d,   \"g-o\", markersize=3, label=\"Val\")\n",
    "axes[0].axvline(x=best_depth, color=\"red\", linestyle=\"--\", linewidth=1.5,\n",
    "                label=f\"Best depth={best_depth} ({best_val_acc*100:.2f}%)\")\n",
    "if conv_depth:\n",
    "    axes[0].axvline(x=conv_depth, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
    "                    label=f\"Hội tụ depth={conv_depth}\")\n",
    "if overfit_depth:\n",
    "    axes[0].axvline(x=overfit_depth, color=\"purple\", linestyle=\"-.\", linewidth=1.5,\n",
    "                    label=f\"Overfit depth={overfit_depth}\")\n",
    "axes[0].set_xlabel(\"max_depth\")\n",
    "axes[0].set_ylabel(\"Accuracy\")\n",
    "axes[0].set_title(\"Train / Val Accuracy vs max_depth\")\n",
    "axes[0].legend(fontsize=8)\n",
    "axes[0].grid(True, alpha=0.3)\n",
    "\n",
    "# --- Giữa: marginal improvement ---\n",
    "axes[1].bar(DEPTH_RANGE[1:], improvements * 100,\n",
    "            color=[\"green\" if v > 0 else \"red\" for v in improvements], alpha=0.7)\n",
    "axes[1].axhline(y=0, color=\"black\", linewidth=0.8)\n",
    "axes[1].axhline(y=THRESHOLD * 100, color=\"orange\", linestyle=\"--\",\n",
    "                label=f\"Threshold={THRESHOLD*100:.2f}%\")\n",
    "if conv_depth:\n",
    "    axes[1].axvline(x=conv_depth, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
    "                    label=f\"Hội tụ depth={conv_depth}\")\n",
    "axes[1].set_xlabel(\"max_depth\")\n",
    "axes[1].set_ylabel(\"ΔVal Accuracy (%)\")\n",
    "axes[1].set_title(\"Marginal Val Improvement per Depth Step\")\n",
    "axes[1].legend(fontsize=8)\n",
    "axes[1].grid(True, alpha=0.3)\n",
    "\n",
    "# --- Phải: generalization gap ---\n",
    "axes[2].fill_between(DEPTH_RANGE, gap * 100, alpha=0.5, color=\"tomato\", label=\"Gap = Train − Val\")\n",
    "axes[2].plot(DEPTH_RANGE, gap * 100, \"r-o\", markersize=3)\n",
    "if best_depth:\n",
    "    axes[2].axvline(x=best_depth, color=\"red\", linestyle=\"--\", linewidth=1.5,\n",
    "                    label=f\"Best depth={best_depth}\")\n",
    "axes[2].set_xlabel(\"max_depth\")\n",
    "axes[2].set_ylabel(\"Gap (%)\")\n",
    "axes[2].set_title(\"Generalization Gap (Overfitting Risk)\")\n",
    "axes[2].legend(fontsize=8)\n",
    "axes[2].grid(True, alpha=0.3)\n",
    "\n",
    "plt.suptitle(\"Decision Tree — Convergence Analysis\", fontsize=13, fontweight=\"bold\")\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# ── Tổng kết ──────────────────────────────────────────────────────────────────\n",
    "print(f\"\\n{'═'*58}\")\n",
    "print(f\"  Độ sâu TỐI ƯU (best val acc) : max_depth = {best_depth}  ({best_val_acc*100:.4f}%)\")\n",
    "if conv_depth:\n",
    "    print(f\"  Điểm HỘI TỤ (Δacc < {THRESHOLD*100:.1f}%)  : max_depth = {conv_depth}\")\n",
    "if overfit_depth:\n",
    "    print(f\"  Điểm OVERFIT bắt đầu         : max_depth ≥ {overfit_depth}\")\n",
    "    print(f\"  → Nên dùng max_depth ≤ {best_depth} để tránh overfit\")\n",
    "print(f\"{'═'*58}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5660e2ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# ── Đánh giá trên tập test ─────────────────────────────────────────────────────\n",
    "y_pred = model.predict(X_test_np)\n",
    "\n",
    "acc = accuracy_score(y_test_np, y_pred)\n",
    "print(f\"Test Accuracy : {acc:.4f} ({acc*100:.2f}%)\\n\")\n",
    "print(classification_report(y_test_np, y_pred, digits=4))\n",
    "\n",
    "# ── Feature importance ──────────────────────────────────────────────────────────\n",
    "feat_imp = model.feature_importances_\n",
    "idx = feat_imp.argsort()[::-1][:20]\n",
    "plt.figure(figsize=(12, 4))\n",
    "plt.bar(range(len(idx)), feat_imp[idx])\n",
    "plt.xticks(range(len(idx)), idx, rotation=45)\n",
    "plt.title(\"Top-20 Feature Importances\")\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# ── Confusion matrix ────────────────────────────────────────────────────────────\n",
    "class_names = list(label_mapping.keys())\n",
    "cm = confusion_matrix(y_test_np, y_pred)\n",
    "plt.figure(figsize=(9, 7))\n",
    "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Greens\",\n",
    "            xticklabels=class_names, yticklabels=class_names)\n",
    "plt.xlabel(\"Predicted\")\n",
    "plt.ylabel(\"Actual\")\n",
    "plt.title(\"Confusion Matrix — Decision Tree\")\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e416c2aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "import joblib, json\n",
    "from datetime import datetime\n",
    "\n",
    "# ── Lưu mô hình ────────────────────────────────────────────────────────────────\n",
    "model_path = \"model_decision_tree_land_use.joblib\"\n",
    "joblib.dump(model, model_path)\n",
    "print(f\"✅ Model saved → {model_path}\")\n",
    "\n",
    "# ── Lưu thông tin mô hình ──────────────────────────────────────────────────────\n",
    "info = {\n",
    "    \"model_type\": \"DecisionTree\",\n",
    "    \"max_depth\": model.get_depth(),\n",
    "    \"n_leaves\": model.get_n_leaves(),\n",
    "    \"class_weight\": \"balanced\",\n",
    "    \"n_features\": int(X_fit.shape[1]),\n",
    "    \"label_mapping\": label_mapping,\n",
    "    \"test_accuracy\": float(acc),\n",
    "    \"train_samples\": int(len(X_fit)),\n",
    "    \"test_samples\": int(len(X_test_np)),\n",
    "    \"saved_at\": datetime.now().isoformat(),\n",
    "}\n",
    "info_path = \"model_decision_tree_land_use_info.json\"\n",
    "with open(info_path, \"w\") as f:\n",
    "    json.dump(info, f, indent=2, ensure_ascii=False)\n",
    "print(f\"✅ Info saved  → {info_path}\")\n",
    "print(json.dumps(info, indent=2, ensure_ascii=False))\n",
    "\n",
    "# ── Đóng kết nối Dask ──────────────────────────────────────────────────────────\n",
    "try:\n",
    "    client.close()\n",
    "    cluster.close()\n",
    "    print(\"✅ Dask cluster closed.\")\n",
    "except Exception:\n",
    "    pass\n"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}