Fix notebook

blueprints/data-solutions/bq-ml/demo/bmql_pipeline.ipynb

@@ -14,6 +14,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Copyright 2023 Google LLC\n",
+    "#\n",
     "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
     "# you may not use this file except in compliance with the License.\n",
     "# You may obtain a copy of the License at\n",
@@ -51,8 +53,9 @@
    "outputs": [],
    "source": [
     "import kfp\n",
-    "from google.cloud import aiplatform as aip\n",
     "import google_cloud_pipeline_components.v1.bigquery as bqop\n",
+    "\n",
+    "from google.cloud import aiplatform as aip\n",
     "from google.cloud import bigquery"
    ]
   },
@@ -70,18 +73,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "PREFIX = 'your-prefix'\n",
-    "PROJECT_ID = 'your-project-id'\n",
-    "LOCATION = 'US'\n",
-    "REGION = 'us-central1'\n",
-    "PIPELINE_NAME = 'bqml-vertex-pipeline'\n",
-    "MODEL_NAME = 'bqml-model'\n",
     "EXPERIMENT_NAME = 'bqml-experiment'\n",
     "ENDPOINT_DISPLAY_NAME = 'bqml-endpoint'\n",
-    "\n",
-    "SERVICE_ACCOUNT = f\"vertex-sa@{PROJECT_ID}.iam.gserviceaccount.com\"\n",
+    "DATASET = \"{}_data\".format(PREFIX.replace(\"-\",\"_\")) \n",
+    "LOCATION = 'US'\n",
+    "MODEL_NAME = 'bqml-model'\n",
+    "PIPELINE_NAME = 'bqml-vertex-pipeline'\n",
     "PIPELINE_ROOT = f\"gs://{PREFIX}-data\"\n",
-    "DATASET = \"{}_data\".format(PREFIX.replace(\"-\",\"_\")) "
+    "PREFIX = 'your-prefix'\n",
+    "PROJECT_ID = 'your-project-id'\n",
+    "REGION = 'us-central1'\n",
+    "SERVICE_ACCOUNT = f\"vertex-sa@{PROJECT_ID}.iam.gserviceaccount.com\""
    ]
   },
   {
@@ -97,12 +99,12 @@
     "3. Evaluate the BigQuery ML model with the standard evaluation metrics\n",
     "\n",
     "The pipeline takes as input the following variables:\n",
-    "- ```model_name```: the display name of the BigQuery ML model\n",
-    "- ```split_fraction```: the percentage of data that will be used as an evaluation dataset\n",
-    "- ```evaluate_job_conf```: bq dict configuration to define where to store evaluation metrics\n",
     "- ```dataset```: name of the dataset where the artifacts will be stored\n",
+    "- ```evaluate_job_conf```: bq dict configuration to define where to store evaluation metrics\n",
+    "- ```location```: BigQuery location\n",
+    "- ```model_name```: the display name of the BigQuery ML model\n",
     "- ```project_id```: the project id where the GCP resources will be created\n",
-    "- ```location```: BigQuery location"
+    "- ```split_fraction```: the percentage of data that will be used as an evaluation dataset"
    ]
   },
   {
@@ -186,7 +188,7 @@
     "    description='This is a new experiment to keep track of bqml trainings',\n",
     "    project=PROJECT_ID,\n",
     "    location=REGION\n",
-    "    )"
+    ")"
    ]
   },
   {
@@ -218,7 +220,6 @@
     "        template_path=f'{PIPELINE_NAME}.json',\n",
     "        pipeline_root=PIPELINE_ROOT,\n",
     "        enable_caching=True\n",
-    "        \n",
     "    )\n",
     "\n",
     "    pipeline.submit(service_account=SERVICE_ACCOUNT, experiment=my_experiment)"
@@ -278,7 +279,8 @@
     "    'day_of_week': 'WEEKDAY',\n",
     "    'traffic_source': 'Facebook',\n",
     "    'browser': 'Firefox',\n",
-    "    'hour_of_day': 20}"
+    "    'hour_of_day': 20\n",
+    "}"
    ]
   },
   {
@@ -337,7 +339,7 @@
   },
   "language_info": {
    "name": "python",
-   "version": "3.10.9"
+   "version": "3.8.9"
   },
   "orig_nbformat": 4,
   "vscode": {