add caculate accuracy

01.train.ipynb

@@ -3279,6 +3279,17 @@
     "progress(average_ndvi)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6be55b09-44d9-4957-a2d9-00f1c58d0aee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# compute average_ndvi\n",
+    "average_ndvi = average_ndvi.compute()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -3394,73 +3405,19 @@
     }
    ],
    "source": [
-    "# compute average_ndvi\n",
-    "average_ndvi = average_ndvi.compute()\n",
-    "\n",
-    "## cấu hình dữ liệu train và vh vv file\n",
-    "train_path = \"train/ST_training data_updated_1130points.shp\"  # đường dẫn shp file train\n",
+    "## cấu hình dữ liệu vh vv file\n",
     "name_vh = \"vh-0922_0923-full_ST.tif\"\n",
     "name_vv = \"vv-0922_0923-full_ST.tif\"\n",
     "\n",
-    "## load dữ liệu điểm train\n",
-    "train = load_train_data(train_path)\n",
-    "train.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "b32cfb3f-e267-4995-853d-8e0e26f5501f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 527 µs, sys: 111 µs, total: 638 µs\n",
-      "Wall time: 375 µs\n"
-     ]
-    }
-   ],
-   "source": [
     "%%time\n",
     "## tải về dữ liệu sen1\n",
-    "import os\n",
     "if not os.path.exists(name_vh):\n",
     "    !aws s3 cp s3://easi-asia-dc-data/staging/ctu/sentinel-1/vh-0922_0923-full_ST.tif vh-0922_0923-full_ST.tif\n",
     "if not os.path.exists(name_vv):\n",
-    "    !aws s3 cp s3://easi-asia-dc-data/staging/ctu/sentinel-1/vv-0922_0923-full_ST.tif vv-0922_0923-full_ST.tif"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "9838697a-2260-45ef-a810-533428a783e9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Warning 1: TIFFReadDirectory:Invalid data type for tag StripByteCounts\n",
-      "Warning 1: TIFFFetchNormalTag:ASCII value for tag \"GeoASCIIParams\" contains null byte in value; value incorrectly truncated during reading due to implementation limitations\n",
-      "Warning 1: TIFFReadDirectory:Sum of Photometric type-related color channels and ExtraSamples doesn't match SamplesPerPixel. Defining non-color channels as ExtraSamples.\n",
-      "Warning 1: TIFFReadDirectory:Invalid data type for tag StripByteCounts\n",
-      "Warning 1: TIFFFetchNormalTag:ASCII value for tag \"GeoASCIIParams\" contains null byte in value; value incorrectly truncated during reading due to implementation limitations\n",
-      "Warning 1: TIFFReadDirectory:Sum of Photometric type-related color channels and ExtraSamples doesn't match SamplesPerPixel. Defining non-color channels as ExtraSamples.\n"
-     ]
-    }
-   ],
-   "source": [
+    "    !aws s3 cp s3://easi-asia-dc-data/staging/ctu/sentinel-1/vv-0922_0923-full_ST.tif vv-0922_0923-full_ST.tif\n",
+    "    \n",
     "# load dữ liệu sen1\n",
-    "dsvh, dsvv = load_sen1(name_vh, name_vv)\n",
-    "\n",
-    "# xây dựng tập dataset\n",
-    "datasets = get_data_sen1_and_sen2(train, average_ndvi, dsvh, dsvv)"
+    "dsvh, dsvv = load_sen1(name_vh, name_vv)"
    ]
   },
   {
@@ -3472,6 +3429,11 @@
    },
    "outputs": [],
    "source": [
+    "## load dữ liệu điểm train\n",
+    "train_path = \"train/ST_training data_updated_1130points.shp\"  # đường dẫn shp file train\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",
@@ -3484,6 +3446,9 @@
     "    \"Rung\": \"7\"\n",
     "}\n",
     "\n",
+    "# xây dựng tập dataset\n",
+    "datasets = get_data_sen1_and_sen2(train, average_ndvi, dsvh, dsvv)\n",
+    "\n",
     "# chia tập dữ liệu train, val, test\n",
     "X_train, X_val, X_test, y_train, y_val, y_test = split_train_data(train, label_mapping, datasets)"
    ]
@@ -3530,26 +3495,8 @@
     "# kiểm tra độ chính xác với tập test\n",
     "y_pred_test = grid_search.predict(X_test)\n",
     "test_accuracy = accuracy_score(y_test, y_pred_test)\n",
-    "print(f\"Accuracy for test data {round(test_accuracy, 2)*100} %\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "f1a14379-ed6e-4897-9ca4-2669743fab40",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Done!\n"
-     ]
-    }
-   ],
-   "source": [
+    "print(f\"Accuracy for test data {round(test_accuracy, 2)*100} %\")\n",
+    "\n",
     "# Lưu mô hình huấn luyện\n",
     "save_model(\"model.joblib\", grid_search)"
    ]