update 01 file train_odc.py

01.train_ODC.ipynb

@@ -726,7 +726,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "id": "2e955884-d4af-422d-a8e6-d436199540e0",
    "metadata": {
     "tags": []
@@ -772,9 +772,37 @@
     "    print(\"    (Sử dụng nhiều spectral indices để cải thiện accuracy)\")\n",
     "    \n",
     "    try:\n",
+    "        # ── FIX 1: Reproject training points to match raster CRS ──────────────\n",
+    "        # Shapefile thường ở WGS84 (EPSG:4326, lon/lat ~105-106)\n",
+    "        # Raster data ở UTM (EPSG:32648, easting ~500000+)\n",
+    "        # Nếu không reproject → .sel() sẽ chọn sai pixel hoàn toàn!\n",
+    "        raster_crs = None\n",
+    "        try:\n",
+    "            # Ưu tiên lấy CRS từ rioxarray\n",
+    "            raster_crs = data.rio.crs\n",
+    "        except Exception:\n",
+    "            pass\n",
+    "        if raster_crs is None:\n",
+    "            # Fallback: dùng biến native_crs đã định nghĩa ở cell load data\n",
+    "            raster_crs = native_crs if 'native_crs' in dir() else 'EPSG:32648'\n",
+    "\n",
+    "        train_src_crs = train.crs if train.crs is not None else 'EPSG:4326'\n",
+    "        print(f\"    Training CRS  : {train_src_crs}\")\n",
+    "        print(f\"    Raster CRS    : {raster_crs}\")\n",
+    "\n",
+    "        if str(train_src_crs).upper() != str(raster_crs).upper():\n",
+    "            train_proj = train.to_crs(raster_crs)\n",
+    "            print(f\"    ✅ Reprojected training points → {raster_crs}\")\n",
+    "        else:\n",
+    "            train_proj = train\n",
+    "            print(f\"    ✅ CRS already match, no reprojection needed\")\n",
+    "\n",
     "        # Extract features at training point locations\n",
     "        X = []\n",
     "        y = []\n",
+    "        skipped_nan   = 0\n",
+    "        skipped_label = 0\n",
+    "        skipped_other = 0\n",
     "\n",
     "        # Available features from data\n",
     "        available_features = ['ndvi_mean', 'ndvi_min', 'ndvi_max', 'ndvi_std', 'ndvi_range',\n",
@@ -790,33 +818,48 @@
     "        else:\n",
     "            print(f\"    Using {len(features_to_use)} features: {features_to_use}\")\n",
     "\n",
-    "            for idx, point in train.iterrows():\n",
+    "            for idx, point in train_proj.iterrows():\n",
     "                try:\n",
+    "                    # ── FIX 2: Dùng tọa độ đã reproject ──────────────────────\n",
+    "                    px, py = point.geometry.x, point.geometry.y\n",
+    "\n",
     "                    # Extract all available features at this point\n",
     "                    feature_vec = []\n",
     "                    for feat_name in features_to_use:\n",
     "                        feat_val = float(data[feat_name].sel(\n",
-    "                            x=point.geometry.x, \n",
+    "                            x=px, y=py, method='nearest'\n",
-    "                            y=point.geometry.y, \n",
-    "                            method='nearest'\n",
     "                        ).values)\n",
     "                        feature_vec.append(feat_val)\n",
     "\n",
     "                    # Get label\n",
+    "                    try:\n",
     "                        label = label_mapping[point.Hientrang]\n",
+    "                    except KeyError:\n",
+    "                        skipped_label += 1\n",
+    "                        continue\n",
+    "\n",
+    "                    # ── FIX 3: np.isnan phải nhận numpy array, không phải list ─\n",
+    "                    feature_arr = np.array(feature_vec, dtype=np.float32)\n",
+    "                    if np.isnan(feature_arr).any():\n",
+    "                        skipped_nan += 1\n",
+    "                        continue\n",
     "\n",
-    "                    # Only add if no NaN values\n",
-    "                    if not np.isnan(feature_vec).any():\n",
     "                    X.append(feature_vec)\n",
     "                    y.append(int(label))\n",
+    "\n",
     "                except Exception as e:\n",
-    "                    # Skip points with errors\n",
+    "                    skipped_other += 1\n",
     "                    continue\n",
     "\n",
+    "            print(f\"\\n    Points extracted : {len(X)}\")\n",
+    "            print(f\"    Skipped (NaN)    : {skipped_nan}\")\n",
+    "            print(f\"    Skipped (label)  : {skipped_label}\")\n",
+    "            print(f\"    Skipped (other)  : {skipped_other}\")\n",
+    "\n",
     "            if len(X) > 0:\n",
     "                X = np.array(X)\n",
     "                y = np.array(y)\n",
-    "                print(f\"    ✅ Extracted {len(X)} samples with {X.shape[1]} features each\")\n",
+    "                print(f\"    ✅ {len(X)} samples × {X.shape[1]} features\")\n",
     "\n",
     "                # Show feature statistics\n",
     "                print(f\"\\n    Feature statistics:\")\n",
@@ -844,7 +887,7 @@
     "                from sklearn.metrics import accuracy_score, classification_report\n",
     "\n",
     "                model = RandomForestClassifier(\n",
-    "                    n_estimators=200,  # More trees for better accuracy\n",
+    "                    n_estimators=200,\n",
     "                    max_depth=30,\n",
     "                    min_samples_split=5,\n",
     "                    random_state=42,\n",
@@ -865,8 +908,8 @@
     "                print(f\"\\n    Feature importance:\")\n",
     "                importances = model.feature_importances_\n",
     "                indices = np.argsort(importances)[::-1]\n",
-    "                for i, idx in enumerate(indices):\n",
+    "                for i, idx_fi in enumerate(indices):\n",
-    "                    print(f\"      {i+1}. {features_to_use[idx]:15s}: {importances[idx]:.4f}\")\n",
+    "                    print(f\"      {i+1}. {features_to_use[idx_fi]:15s}: {importances[idx_fi]:.4f}\")\n",
     "\n",
     "                # Classification report\n",
     "                print(f\"\\n[4] Classification Report:\")\n",
@@ -874,7 +917,7 @@
     "                print(classification_report(y_test, y_pred, target_names=class_names, zero_division=0))\n",
     "\n",
     "            else:\n",
-    "                print(f\"    ❌ No samples extracted\")\n",
+    "                print(f\"    ❌ No valid samples extracted — kiểm tra CRS và tọa độ!\")\n",
     "                model = None\n",
     "\n",
     "    except Exception as e:\n",
@@ -890,7 +933,7 @@
     "print(\"📝 NOTE: Model này dự đoán PHÂN LOẠI SỬ DỤNG ĐẤT (8 lớp)\")\n",
     "print(\"    NDVI là một trong các features đầu vào, không phải mục tiêu dự đoán\")\n",
     "print(\"    Sau khi predict → có thể hiển thị NDVI map như chỉ số phụ\")\n",
-    "print(\"=\"*70)"
+    "print(\"=\"*70)\n"
    ]
   },
   {
@@ -1094,14 +1137,6 @@
     "print(\"✅ PIPELINE COMPLETE\")\n",
     "print(\"=\"*70)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ef65aa25-9032-4e1c-8808-64747e8005c6",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {