Add example of validate_time_series_dataset

autogluon · Dec 17, 2024 · 0960eaf · 0960eaf
1 parent bbd81cf
commit 0960eaf
Showing 1 changed file with 33 additions and 18 deletions.
diff --git a/docs/02-dataset-format.ipynb b/docs/02-dataset-format.ipynb
@@ -90,16 +90,15 @@
     {
      "data": {
       "text/plain": [
-       "{'id': np.str_('T000000'),\n",
+       "{'id': 'T000000',\n",
        " 'timestamp': array(['2017-01-01T14:00:00.000', '2017-01-01T15:00:00.000',\n",
        "        '2017-01-01T16:00:00.000', ..., '2018-03-31T13:00:00.000',\n",
        "        '2018-03-31T14:00:00.000', '2018-03-31T15:00:00.000'],\n",
-       "       shape=(10898,), dtype='datetime64[ms]'),\n",
-       " 'target': array([453., 417., 395., ..., 132., 158., 118.],\n",
-       "       shape=(10898,), dtype=float32),\n",
-       " 'city': np.str_('Beijing'),\n",
-       " 'station': np.str_('aotizhongxin_aq'),\n",
-       " 'measurement': np.str_('PM2.5')}"
+       "       dtype='datetime64[ms]'),\n",
+       " 'target': array([453., 417., 395., ..., 132., 158., 118.], dtype=float32),\n",
+       " 'city': 'Beijing',\n",
+       " 'station': 'aotizhongxin_aq',\n",
+       " 'measurement': 'PM2.5'}"
       ]
      },
      "execution_count": 3,
@@ -120,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -206,12 +205,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "from fev.utils import convert_long_df_to_hf_dataset"
+    "import fev.utils"
    ]
   },
   {
@@ -381,7 +380,7 @@
     }
    ],
    "source": [
-    "ds = convert_long_df_to_hf_dataset(df, id_column=\"item_id\", static_columns=[\"product_code\", \"product_category\", \"product_subcategory\", \"location_code\"])\n",
+    "ds = fev.utils.convert_long_df_to_hf_dataset(df, id_column=\"item_id\", static_columns=[\"product_code\", \"product_category\", \"product_subcategory\", \"location_code\"])\n",
     "ds.features"
    ]
   },
@@ -393,11 +392,11 @@
     {
      "data": {
       "text/plain": [
-       "{'item_id': np.str_('1062_101'),\n",
-       " 'product_code': np.int64(1062),\n",
-       " 'product_category': np.str_('Beverages'),\n",
-       " 'product_subcategory': np.str_('Fruit Juice Mango'),\n",
-       " 'location_code': np.int64(101),\n",
+       "{'item_id': '1062_101',\n",
+       " 'product_code': 1062,\n",
+       " 'product_category': 'Beverages',\n",
+       " 'product_subcategory': 'Fruit Juice Mango',\n",
+       " 'location_code': 101,\n",
        " 'timestamp': array(['2018-01-01T00:00:00.000000', '2018-01-08T00:00:00.000000',\n",
        "        '2018-01-15T00:00:00.000000', '2018-01-22T00:00:00.000000',\n",
        "        '2018-01-29T00:00:00.000000', '2018-02-05T00:00:00.000000',\n",
@@ -442,6 +441,22 @@
     "ds.with_format(\"numpy\")[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To verify that the dataset was converted correctly, use the `fev.utils.validate_time_series_dataset` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fev.utils.validate_time_series_dataset(ds, id_column=\"item_id\", timestamp_column=\"timestamp\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -451,7 +466,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -467,7 +482,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [