From 0db4148a40f1176fd3104018227a86018cbc0b09 Mon Sep 17 00:00:00 2001
From: Victor Phan <me@victorphan.net>
Date: Thu, 26 Feb 2026 15:33:36 +0700
Subject: [PATCH] update 01 file train_odc.py

---
 01.train_ODC.ipynb | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/01.train_ODC.ipynb b/01.train_ODC.ipynb
index 285ddfe..533460c 100755
--- a/01.train_ODC.ipynb
+++ b/01.train_ODC.ipynb
@@ -523,19 +523,32 @@
     "        print(\"   Trying unsigned access as fallback...\")\n",
     "        configure_s3_access(aws_unsigned=True)\n",
     "        print(\"   Switched to aws_unsigned=True (public buckets only)\")\n",
-    "        # Get all scenes from datacube metadata (filtered to Vietnam region)\n",
+    "\n",
     "    # ===== CHECK IF SHOULD SKIP DOWNLOAD =====\n",
     "    if use_cache and data is not None:\n",
+    "        print(f\"\\n✅ Using cached dataset - skipping download!\")\n",
+    "        print(f\"   Variables: {len(data.data_vars)}\")\n",
+    "        print(f\"   Shape: {data.dims}\")\n",
+    "        display(data)\n",
+    "    \n",
+    "    else:\n",
+    "        # ===== DOWNLOAD FROM S3 =====\n",
+    "        print(f\"\\n📥 Downloading from S3...\")\n",
+    "        \n",
+    "        # Get all scenes from datacube metadata (filtered to Vietnam region)\n",
+    "        datasets = list(dc.find_datasets(\n",
+    "            product='s2_l2a',\n",
     "            time=date_range,\n",
     "            lat=latitude_range,\n",
     "            lon=longtitude_range\n",
     "        ))\n",
     "        \n",
     "        if not datasets:\n",
-    "            raise ValueError(\"No datasets found for date range\")\n",
+    "            raise ValueError(\"No datasets found for date range and region\")\n",
     "        \n",
     "        print(f\"\\n📦 Found {len(datasets)} available scenes\")\n",
     "        print(f\"   Date range: {date_range[0]} to {date_range[1]}\")\n",
+    "        print(f\"   Region: lon={longtitude_range}, lat={latitude_range}\")\n",
     "        \n",
     "        # ===== LOAD ALL SCENES WITH ALL AVAILABLE BANDS (NO MAGNIFICATION) =====\n",
     "        # num_scenes = len(datasets)  # Load ALL scenes\n",
@@ -607,7 +620,7 @@
     "                    max_size = size\n",
     "                    ref_resolution = size\n",
     "                    max_band = band_name\n",
-    "        max_size = 0\n",
+    "        \n",
     "        print(f\"   Reference resolution: {max_size}×{max_size} pixels (native {max_band})\")\n",
     "        \n",
     "        # Resample all bands to match reference resolution (both up and down)\n",
@@ -631,7 +644,7 @@
     "                    if scene_idx == 0:  # Print for first scene only to reduce clutter\n",
     "                        print(f\"      Resampling {band_name}: {current_size}×{current_size} → {new_size}×{new_size}\")\n",
     "                    resampled_count += 1\n",
-    "                    if band_name == 'scl':\n",
+    "        \n",
     "        print(f\"✅ Resolution normalization complete! ({resampled_count} bands resampled)\")\n",
     "        \n",
     "        # ===== CALCULATE SPECTRAL INDICES FOR EACH SCENE =====\n",
@@ -679,7 +692,7 @@
     "                    \n",
     "            except Exception as e:\n",
     "                pass\n",
-    "                if 'nir' in scene_data and 'red' in scene_data and 'blue' in scene_data:\n",
+    "        \n",
     "        print(f\"✅ Calculated {indices_count} spectral indices per scene\")\n",
     "        \n",
     "        # ===== STACK SCENES ALONG TIME DIMENSION =====\n",
@@ -713,7 +726,7 @@
     "        \n",
     "        # ===== CALCULATE TEMPORAL FEATURES FOR ACCURACY =====\n",
     "        print(f\"\\n[TEMPORAL FEATURES] Computing temporal features from time-series...\")\n",
-    "            data_vars,\n",
+    "        \n",
     "        temporal_features_added = 0\n",
     "        \n",
     "        # For NDVI: temporal statistics\n",
@@ -746,7 +759,7 @@
     "                band_ts = data[band_name]\n",
     "                data[f'{band_name}_mean'] = band_ts.mean(dim='time')\n",
     "                temporal_features_added += 1\n",
-    "            # NDVI std (temporal consistency)\n",
+    "        \n",
     "        print(f\"✅ Added {temporal_features_added} temporal/aggregate features\")\n",
     "        \n",
     "        # ===== SAVE TO CACHE =====\n",
@@ -790,7 +803,7 @@
     "        print(f\"   Temporal aggregates ({len(temporal_vars)}):\")\n",
     "        for v in temporal_vars:\n",
     "            print(f\"     - {v}\")\n",
-    "                spatial_vars.append(f\"{var_name} {data[var_name].shape}\")\n",
+    "        \n",
     "        print(f\"   {'='*70}\")\n",
     "        \n",
     "        display(data)\n",
@@ -817,21 +830,8 @@
     "    traceback.print_exc()\n",
     "    data = None\n",
     "    ndvi = None\n",
-    "    else:\n",
     "\n",
-    "print(\"=\"*70)\n",
-    "        print(f\"❌ NDVI not found in dataset\")\n",
-    "\n",
-    "\n",
-    "        ndvi = Noneprint(\"=\"*70)\n",
-    "\n",
-    "    \n",
-    "\n",
-    "except Exception as e:    ndvi = None\n",
-    "\n",
-    "    print(f\"❌ Error: {e}\")    data = None\n",
-    "\n",
-    "    import traceback    traceback.print_exc()"
+    "print(\"=\"*70)\n"
    ]
   },
   {