Add UpdateFeatureGroup related APIs in sample notebook (aws#3515)

hchings · Aug 4, 2022 · b31be03 · b31be03
1 parent 2e8c261
commit b31be03
Show file tree

Hide file tree

Showing 2 changed files with 152 additions and 0 deletions.
diff --git a/sagemaker-featurestore/data/feature_store_introduction_customer_updated.csv b/sagemaker-featurestore/data/feature_store_introduction_customer_updated.csv
@@ -0,0 +1,5 @@
+customer_id,city_code,state_code,country_code,email,name
+573291,1,49,2,[email protected],John Lee
+109382,2,40,2,[email protected],Olive Quil
+828400,3,31,2,[email protected],Liz Knee
+124013,4,5,2,[email protected],Eileen Book
diff --git a/sagemaker-featurestore/feature_store_introduction.ipynb b/sagemaker-featurestore/feature_store_introduction.ipynb
@@ -473,6 +473,152 @@
     "all_records"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Add features to a feature group\n",
+    "\n",
+    "If we want to update a FeatureGroup that has done the data ingestion, we can use the `UpdateFeatureGroup` API and then re-ingest data by using the updated dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sagemaker.feature_store.feature_definition import StringFeatureDefinition\n",
+    "\n",
+    "customers_feature_group.update(\n",
+    "    feature_additions=[StringFeatureDefinition(\"email\"), StringFeatureDefinition(\"name\")]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Verify the FeatureGroup has been updated successfully or not."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_last_update_status(feature_group):\n",
+    "    last_update_status = feature_group.describe().get(\"LastUpdateStatus\")[\"Status\"]\n",
+    "    while last_update_status == \"InProgress\":\n",
+    "        print(\"Waiting for FeatureGroup to be updated\")\n",
+    "        time.sleep(5)\n",
+    "        last_update_status = feature_group.describe().get(\"LastUpdateStatus\")\n",
+    "    if last_update_status == \"Successful\":\n",
+    "        print(f\"FeatureGroup {feature_group.name} successfully updated.\")\n",
+    "    else:\n",
+    "        print(\n",
+    "            f\"FeatureGroup {feature_group.name} updated failed. The LastUpdateStatus is\"\n",
+    "            + str(last_update_status)\n",
+    "        )\n",
+    "\n",
+    "\n",
+    "check_last_update_status(customers_feature_group)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Inspect the new dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customer_data_updated = pd.read_csv(\"data/feature_store_introduction_customer_updated.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customer_data_updated.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Append `EventTime` feature to your data frame again."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customer_data_updated[\"EventTime\"] = pd.Series(\n",
+    "    [current_time_sec] * len(customer_data), dtype=\"float64\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ingest the new dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customers_feature_group.ingest(data_frame=customer_data_updated, max_workers=3, wait=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Use `batch_get_record` again to check that all updated data has been ingested into `customers_feature_group` by providing customer IDs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "updated_customers_records = sagemaker_session.boto_session.client(\n",
+    "    \"sagemaker-featurestore-runtime\", region_name=region\n",
+    ").batch_get_record(\n",
+    "    Identifiers=[\n",
+    "        {\n",
+    "            \"FeatureGroupName\": customers_feature_group_name,\n",
+    "            \"RecordIdentifiersValueAsString\": [\"573291\", \"109382\", \"828400\", \"124013\"],\n",
+    "        }\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "updated_customers_records"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -530,6 +676,7 @@
     "* `delete()`\n",
     "* `create()`\n",
     "* `load_feature_definitions()`\n",
+    "* `update()`\n",
     "* `update_feature_metadata()`\n",
     "* `describe_feature_metadata()`\n",
     "\n",