make CI corrections

Author: atqy

end_to_end/music_recommendation/01_data_exploration.ipynb

@@ -119,7 +119,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "new_data_paths = get_data([f\"{s3_bucket_music_data}/tracks.csv\", f\"{s3_bucket_music_data}/ratings.csv\"], bucket, sample_data=0.70)\n",
+    "new_data_paths = get_data(s3_client, [f\"{s3_bucket_music_data}/tracks.csv\", f\"{s3_bucket_music_data}/ratings.csv\"], bucket, prefix, sample_data=0.70)\n",
     "print(new_data_paths)"
    ]
   },

end_to_end/music_recommendation/03_train_deploy_debugger_explain_monitor_registry.ipynb

@@ -525,40 +525,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# # random user ID. You can try any other ID\n",
-    "# sample_user_id = 11005"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# featurestore_runtime = boto_session.client(service_name='sagemaker-featurestore-runtime', region_name=region)\n",
-    "\n",
-    "# feature_store_session = sagemaker.Session(\n",
-    "#     boto_session=boto_session,\n",
-    "#     sagemaker_client=sagemaker_client,\n",
-    "#     sagemaker_featurestore_runtime_client=featurestore_runtime\n",
-    "# )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # pull the sample user's 5 star preferences record from the feature store\n",
-    "# fg_response = featurestore_runtime.get_record(\n",
-    "#     FeatureGroupName='user-5star-track-features-music-rec', \n",
-    "#     RecordIdentifierValueAsString=str(sample_user_id)\n",
-    "# )\n",
-    "\n",
-    "# record = fg_response['Record']\n",
-    "# df_user = pd.DataFrame(record).set_index('FeatureName')\n",
-    "# df_user.to_csv(\"./data/sample_user.csv\")\n",
     "df_user = pd.read_csv(\"./data/sample_user.csv\")\n",
     "df_user = df_user.set_index('FeatureName')"
    ]
@@ -576,20 +542,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# # pull a sample of the tracks data (multiple records) from the feature store using athena query\n",
-    "# fg_name_tracks_obj = FeatureGroup(name='track-features-music-rec', sagemaker_session=feature_store_session)\n",
-    "# tracks_query = fg_name_tracks_obj.athena_query()\n",
-    "# tracks_table = tracks_query.table_name\n",
-    "\n",
-    "# # use escaped quotes aound table name since it contains '-' symbols\n",
-    "# query_string = (\"SELECT * FROM \\\"{}\\\" LIMIT 1000\".format(tracks_table))\n",
-    "# print(\"Running \" + query_string)\n",
-    "\n",
-    "# # run Athena query. The output is loaded to a Pandas dataframe.\n",
-    "# tracks_query.run(query_string=query_string, output_location=f\"s3://{bucket}/{prefix}/query_results/\")\n",
-    "# tracks_query.wait()\n",
-    "# df_tracks = tracks_query.as_dataframe()\n",
-    "# df_tracks.to_csv(\"./data/sample_tracks.csv\")\n",
     "df_tracks = pd.read_csv(\"./data/sample_tracks.csv\")"
    ]
   },
@@ -676,7 +628,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_train = pd.read_csv(train_data_uri)\n",
+    "s3_client.download_file(bucket, f\"{prefix}/data/train/train_data.csv\", f\"train_data.csv\")\n",
+    "df_train = pd.read_csv(\"train_data.csv\")\n",
     "\n",
     "label = 'rating'"
    ]

end_to_end/music_recommendation/end_to_end_pipeline.ipynb

@@ -114,7 +114,10 @@
     "    sagemaker_client=sagemaker_boto_client)\n",
     "sagemaker_role = sagemaker.get_execution_role()\n",
     "\n",
-    "account_id = boto3.client('sts').get_caller_identity()[\"Account\"]"
+    "account_id = boto3.client('sts').get_caller_identity()[\"Account\"]\n",
+    "\n",
+    "bucket = sess.default_bucket()\n",
+    "prefix='music-recommendation'"
    ]
   },
   {