đã áp dụng file shapefile vào train và predict

feature_extractor.py

@@ -36,6 +36,14 @@ class FeatureExtractor:
                 'VH_db_mean', 'VV_db_mean', 'VH_VV_ratio'
             ],
             'description': 'Extended aggregate features with statistics'
+        },
+        'odc': {
+            'n_features': 8,
+            'features': [
+                'ndvi_mean', 'ndvi_min', 'ndvi_max', 'ndvi_std', 'ndvi_range',
+                'ndwi_mean', 'ndbi_mean', 'evi_mean'
+            ],
+            'description': 'ODC mode: 8 aggregate features (NDVI stats + NDWI/NDBI/EVI mean) - matches 01.train_ODC.ipynb'
         }
     }
     
@@ -229,6 +237,80 @@ class FeatureExtractor:
         
         return features
     
+    def extract_odc_features(
+        self,
+        s2_data: xr.Dataset,
+        vh_data: Optional[xr.DataArray] = None,
+        vv_data: Optional[xr.DataArray] = None
+    ) -> np.ndarray:
+        """
+        Extract ODC aggregate features (8 features matching 01.train_ODC.ipynb):
+        ndvi_mean, ndvi_min, ndvi_max, ndvi_std, ndvi_range, ndwi_mean, ndbi_mean, evi_mean
+        
+        Args:
+            s2_data: Sentinel-2 Dataset with B02, B03, B04, B08, B11
+            vh_data: Not used in ODC mode
+            vv_data: Not used in ODC mode
+        
+        Returns:
+            Feature array shape (n_pixels, 8)
+        """
+        # Calculate spectral indices
+        nir = s2_data["B08"].astype('float32')
+        red = s2_data["B04"].astype('float32')
+        green = s2_data["B03"].astype('float32')
+        blue = s2_data["B02"].astype('float32')
+        swir = s2_data["B11"].astype('float32') if "B11" in s2_data else s2_data["B02"]
+        
+        # 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)
+        ndbi = (swir - nir) / (swir + nir + 1e-8)
+        
+        # EVI = 2.5 * (NIR - Red) / (NIR + 6*Red - 7.5*Blue + 1)
+        evi = 2.5 * (nir - red) / (nir + 6*red - 7.5*blue + 1)
+        
+        features_list = []
+        
+        # NDVI statistics (5 features)
+        if 'time' in ndvi.dims:
+            features_list.append(ndvi.mean(dim='time').values.flatten())  # ndvi_mean
+            features_list.append(ndvi.min(dim='time').values.flatten())   # ndvi_min
+            features_list.append(ndvi.max(dim='time').values.flatten())   # ndvi_max
+            features_list.append(ndvi.std(dim='time').values.flatten())   # ndvi_std
+            ndvi_range = (ndvi.max(dim='time') - ndvi.min(dim='time')).values.flatten()
+            features_list.append(ndvi_range)  # ndvi_range
+        else:
+            ndvi_flat = ndvi.values.flatten()
+            features_list.extend([ndvi_flat, ndvi_flat, ndvi_flat, np.zeros_like(ndvi_flat), np.zeros_like(ndvi_flat)])
+        
+        # NDWI mean (1 feature)
+        if 'time' in ndwi.dims:
+            features_list.append(ndwi.mean(dim='time').values.flatten())  # ndwi_mean
+        else:
+            features_list.append(ndwi.values.flatten())
+        
+        # NDBI mean (1 feature)
+        if 'time' in ndbi.dims:
+            features_list.append(ndbi.mean(dim='time').values.flatten())  # ndbi_mean
+        else:
+            features_list.append(ndbi.values.flatten())
+        
+        # EVI mean (1 feature)
+        if 'time' in evi.dims:
+            features_list.append(evi.mean(dim='time').values.flatten())  # evi_mean
+        else:
+            features_list.append(evi.values.flatten())
+        
+        # Stack all features (total: 8 features)
+        features = np.column_stack(features_list)
+        
+        return features
+    
     def extract_extended_features(
         self,
         s2_data: xr.Dataset,
@@ -319,7 +401,7 @@ class FeatureExtractor:
         Extract features theo mode đã chọn
         
         Args:
-            s2_data: Sentinel-2 Dataset (cần cho temporal và extended modes)
+            s2_data: Sentinel-2 Dataset (cần cho temporal, extended, và odc modes)
             ndvi_data: NDVI DataArray (cần cho simple mode)
             vh_data: VH radar DataArray
             vv_data: VV radar DataArray
@@ -342,6 +424,11 @@ class FeatureExtractor:
                 raise ValueError("s2_data required for extended mode")
             return self.extract_extended_features(s2_data, vh_data, vv_data)
         
+        elif self.mode == 'odc':
+            if s2_data is None:
+                raise ValueError("s2_data required for odc mode")
+            return self.extract_odc_features(s2_data, vh_data, vv_data)
+        
         else:
             raise ValueError(f"Unknown mode: {self.mode}")
     
@@ -359,7 +446,7 @@ def get_feature_extractor(mode: str = 'simple') -> FeatureExtractor:
     Factory function để tạo FeatureExtractor
     
     Args:
-        mode: 'simple', 'temporal', hoặc 'extended'
+        mode: 'simple', 'temporal', 'extended', hoặc 'odc'
     
     Returns:
         FeatureExtractor instance