Enable automation test for all feature store notebooks (#2657)

* Enable automation test for all feature store notebooks * Update feature store uai * Update uai name * Add test for 5th notebook * Convert 5th notebook to py * Fix the syntax error * Update random generator * Update redis name * Change conda file used for test * Update to use dynamic version * Fix the format * Use the same conda for all notebooks * Check mounted folder * Exclude 5th notebook * Update feature_version to version * Sample updates for AML Spark managed VNet GA. (#2656) * Sample updates for AML Spark managed VNet GA. * Updated notebook title. Triggering build to test. * Updated workspace name to include timestamp. Triggering build to test. * Shortened VNet workspace name to meet validation. * README.md clean-up and fixes for AML Spark samples. * README.md clean-up and fixes for AML Spark samples. * chore: Remove 'Send IcM on Failure' step from tutorial workflows (#2670) * chore: Remove 'Send IcM on Failure' step that hasn't been in use for a while * chore: Run tutorials/readme.py * chore: Remove unused local 'generate-icm' action * update cron schedules to avoid endpoint deletion from automated resource cleanup (#2672) * change starting hour for workflow * update cron for text mc mlflow * use python 3.8.* (#2678) * use python 3.8.18 * Update cleanup.yml * update usepython v4 * Update workstation_env.yml (#2680) * Examples for online inference for LLaVA (#2671) * Rough version of ITT notebook. * Working version of the notebook. * Minor improvements. * Rough version of the CLI demo. * Reformat with black. * Remove mode parameter in call to prepare_data.py. * Make code cells easier to read. * Minor readability improvement. * Format with black. * Minor fixes and reformatting. * Reformat with black. * Update workstation_env.yml (#2681) delete extraneous space * update vision FT examples corresponding to recent component update (#2650) * updating changes with ME component * updating MMOD as well * update MMOD cli * separate section for model evaluation component * remove ds ort true for classification * black check * Remove v1 references (#2675) * Remove v1 samples from v2 repo * Remove v1 from table of contents * Remove v1 test files * Remove v1 test files * Remove v1 folder from README * Remove v1 folder * Remove v1 tests * Delete v1 files * Restore custom-container directory * Restore custom-container/triton directory * Update the notebook format --------- Co-authored-by: Yogi Pandey <[email protected]> Co-authored-by: kdestin <[email protected]> Co-authored-by: Rehaan Bhimani <[email protected]> Co-authored-by: Ada <[email protected]> Co-authored-by: Sheri Gilley <[email protected]> Co-authored-by: rdondera-microsoft <[email protected]> Co-authored-by: shubhamiit <[email protected]> Co-authored-by: Diondra <[email protected]>
Azure · Sep 27, 2023 · b19a056 · b19a056
1 parent 55dffe9
commit b19a056
Show file tree

Hide file tree

Showing 7 changed files with 107 additions and 52 deletions.
diff --git a/sdk/python/featurestore_sample/featurestore_sdk_job.py b/sdk/python/featurestore_sample/featurestore_sdk_job.py
@@ -2,25 +2,35 @@
 
 spark = SparkSession.builder.appName("AccessData").getOrCreate()
 
+import os
+
+for path, subdirs, files in os.walk("./"):
+    for name in files:
+        print(os.path.join(path, name))
+
 print("=======Test Notebook 1============")
 with open(
     "notebooks/sdk_only/1. Develop a feature set and register with managed feature store.py"
 ) as f:
     exec(f.read())
 
-## Enable test for notebook 1 first
-# print("=======Test Notebook 2============")
-# with open(
-#     "notebooks/sdk_only/2. Enable materialization and backfill feature data.py"
-# ) as f:
-#     exec(f.read())
+print("=======Test Notebook 2============")
+with open(
+    "notebooks/sdk_only/2. Enable materialization and backfill feature data.py"
+) as f:
+    exec(f.read())
 
-# print("=======Test Notebook 3============")
-# with open("notebooks/sdk_only/3. Experiment and train models using features.py") as f:
-#     exec(f.read())
+print("=======Test Notebook 3============")
+with open("notebooks/sdk_only/3. Experiment and train models using features.py") as f:
+    exec(f.read())
+
+print("=======Test Notebook 4============")
+with open(
+    "notebooks/sdk_only/4. Enable recurrent materialization and run batch inference.py"
+) as f:
+    exec(f.read())
 
-# print("=======Test Notebook 3============")
-# with open(
-#     "notebooks/sdk_only/4. Enable recurrent materialization and run batch inference.py"
-# ) as f:
+# # exclude 5th notebook for now
+# print("=======Test Notebook 5============")
+# with open("notebooks/sdk_only/5. Enable online store and run online inference.py") as f:
 #     exec(f.read())
diff --git a/...notebooks/sdk_only/1. Develop a feature set and register with managed feature store.ipynb b/...notebooks/sdk_only/1. Develop a feature set and register with managed feature store.ipynb
@@ -287,7 +287,8 @@
     "featurestore_name = \"my-featurestore\"\n",
     "featurestore_location = \"eastus\"\n",
     "featurestore_subscription_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
-    "featurestore_resource_group_name = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]"
+    "featurestore_resource_group_name = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
+    "version = \"<VERSION>\""
    ]
   },
   {
@@ -698,7 +699,7 @@
     "\n",
     "account_entity_config = FeatureStoreEntity(\n",
     "    name=\"account\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    index_columns=[DataColumn(name=\"accountID\", type=DataColumnType.STRING)],\n",
     "    stage=\"Development\",\n",
     "    description=\"This entity represents user account index key accountID.\",\n",
@@ -750,9 +751,9 @@
     "\n",
     "transaction_fset_config = FeatureSet(\n",
     "    name=\"transactions\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    description=\"7-day and 3-day rolling aggregation of transactions featureset\",\n",
-    "    entities=[\"azureml:account:1\"],\n",
+    "    entities=[f\"azureml:account:{version}\"],\n",
     "    stage=\"Development\",\n",
     "    specification=FeatureSetSpecification(path=transactions_featureset_spec_folder),\n",
     "    tags={\"data_type\": \"nonPII\"},\n",
@@ -878,7 +879,7 @@
    "outputs": [],
    "source": [
     "# look up the featureset by providing name and version\n",
-    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", \"1\")\n",
+    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", version)\n",
     "# list its features\n",
     "transactions_featureset.features"
    ]
@@ -952,8 +953,8 @@
     "\n",
     "# you can also specify features in string form: featurestore:featureset:version:feature\n",
     "more_features = [\n",
-    "    \"transactions:1:transaction_3d_count\",\n",
-    "    \"transactions:1:transaction_amount_3d_avg\",\n",
+    "    f\"transactions:{version}:transaction_3d_count\",\n",
+    "    f\"transactions:{version}:transaction_amount_3d_avg\",\n",
     "]\n",
     "\n",
     "more_features = featurestore.resolve_feature_uri(more_features)\n",

diff --git a/...store_sample/notebooks/sdk_only/2. Enable materialization and backfill feature data.ipynb b/...store_sample/notebooks/sdk_only/2. Enable materialization and backfill feature data.ipynb
@@ -209,7 +209,7 @@
     "project_ws_sub_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "project_ws_rg = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
     "project_ws_name = os.environ[\"AZUREML_ARM_WORKSPACE_NAME\"]\n",
-    "\n",
+    "version = \"<VERSION>\"\n",
     "# connect to the project workspace\n",
     "ws_client = MLClient(\n",
     "    AzureMLOnBehalfOfCredential(), project_ws_sub_id, project_ws_rg, project_ws_name\n",
@@ -562,7 +562,7 @@
     "# User assigned managed identity values. Optionally you may change the values.\n",
     "uai_subscription_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "uai_resource_group_name = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
-    "uai_name = \"fstoreuai\"\n",
+    "uai_name = \"<FEATURE_STORE_UAI_NAME>\"\n",
     "uai_location = ws_location"
    ]
   },
@@ -754,7 +754,10 @@
      "transient": {
       "deleting": false
      }
-    }
+    },
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [
@@ -868,7 +871,9 @@
     "    MaterializationComputeResource,\n",
     ")\n",
     "\n",
-    "transactions_fset_config = fs_client._featuresets.get(name=\"transactions\", version=\"1\")\n",
+    "transactions_fset_config = fs_client._featuresets.get(\n",
+    "    name=\"transactions\", version=version\n",
+    ")\n",
     "\n",
     "transactions_fset_config.materialization_settings = MaterializationSettings(\n",
     "    offline_enabled=True,\n",
@@ -968,7 +973,7 @@
     "\n",
     "poller = fs_client.feature_sets.begin_backfill(\n",
     "    name=\"transactions\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    feature_window_start_time=st,\n",
     "    feature_window_end_time=ed,\n",
     ")\n",
@@ -978,7 +983,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "active-ipynb"
+    ]
+   },
    "outputs": [],
    "source": [
     "# get the job URL, and stream the job logs\n",
@@ -1019,7 +1028,7 @@
    "outputs": [],
    "source": [
     "# look up the featureset by providing name and version\n",
-    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", \"1\")\n",
+    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", version)\n",
     "display(transactions_featureset.to_spark_dataframe().head(5))"
    ]
   },

diff --git a/...eaturestore_sample/notebooks/sdk_only/3. Experiment and train models using features.ipynb b/...eaturestore_sample/notebooks/sdk_only/3. Experiment and train models using features.ipynb
@@ -226,6 +226,7 @@
     "project_ws_sub_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "project_ws_rg = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
     "project_ws_name = os.environ[\"AZUREML_ARM_WORKSPACE_NAME\"]\n",
+    "version = \"<VERSION>\"\n",
     "\n",
     "# connect to the project workspace\n",
     "ws_client = MLClient(\n",
@@ -612,7 +613,7 @@
    "outputs": [],
    "source": [
     "# get the registered transactions feature set, version 1\n",
-    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", \"1\")\n",
+    "transactions_featureset = featurestore.feature_sets.get(\"transactions\", version)\n",
     "# Notice that account feature set spec is in your local dev environment (this notebook): not registered with feature store yet\n",
     "features = [\n",
     "    accounts_featureset_spec.get_feature(\"accountAge\"),\n",
@@ -717,9 +718,9 @@
     "\n",
     "accounts_fset_config = FeatureSet(\n",
     "    name=\"accounts\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    description=\"accounts featureset\",\n",
-    "    entities=[\"azureml:account:1\"],\n",
+    "    entities=[f\"azureml:account:{version}\"],\n",
     "    stage=\"Development\",\n",
     "    specification=FeatureSetSpecification(path=accounts_featureset_spec_folder),\n",
     "    tags={\"data_type\": \"nonPII\"},\n",
@@ -764,7 +765,7 @@
    "outputs": [],
    "source": [
     "# look up the featureset by providing name and version\n",
-    "accounts_featureset = featurestore.feature_sets.get(\"accounts\", \"1\")\n",
+    "accounts_featureset = featurestore.feature_sets.get(\"accounts\", version)\n",
     "# get access to the feature data\n",
     "accounts_feature_df = accounts_featureset.to_spark_dataframe()\n",
     "display(accounts_feature_df.head(5))\n",
@@ -853,7 +854,7 @@
     "    print(fs)\n",
     "\n",
     "# See properties of the transactions featureset including list of features\n",
-    "featurestore.feature_sets.get(name=\"transactions\", version=\"1\").features"
+    "featurestore.feature_sets.get(name=\"transactions\", version=version).features"
    ]
   },
   {
@@ -914,8 +915,8 @@
     "\n",
     "# you can also specify features in string form: featurestore:featureset:version:feature\n",
     "more_features = [\n",
-    "    \"accounts:1:numPaymentRejects1dPerUser\",\n",
-    "    \"transactions:1:transaction_amount_7d_avg\",\n",
+    "    f\"accounts:{version}:numPaymentRejects1dPerUser\",\n",
+    "    f\"transactions:{version}:transaction_amount_7d_avg\",\n",
     "]\n",
     "\n",
     "more_features = featurestore.resolve_feature_uri(more_features)\n",
@@ -1027,7 +1028,10 @@
      "transient": {
       "deleting": false
      }
-    }
+    },
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [

diff --git a/...mple/notebooks/sdk_only/4. Enable recurrent materialization and run batch inference.ipynb b/...mple/notebooks/sdk_only/4. Enable recurrent materialization and run batch inference.ipynb
@@ -223,6 +223,7 @@
     "project_ws_sub_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "project_ws_rg = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
     "project_ws_name = os.environ[\"AZUREML_ARM_WORKSPACE_NAME\"]\n",
+    "version = \"<VERSION>\"\n",
     "\n",
     "# connect to the project workspace\n",
     "ws_client = MLClient(\n",
@@ -374,7 +375,9 @@
     "from datetime import datetime\n",
     "from azure.ai.ml.entities import RecurrenceTrigger\n",
     "\n",
-    "transactions_fset_config = fs_client.feature_sets.get(name=\"transactions\", version=\"1\")\n",
+    "transactions_fset_config = fs_client.feature_sets.get(\n",
+    "    name=\"transactions\", version=version\n",
+    ")\n",
     "\n",
     "# create a schedule that runs the materialization job every 3 hours\n",
     "transactions_fset_config.materialization_settings.schedule = RecurrenceTrigger(\n",
@@ -483,7 +486,10 @@
      "transient": {
       "deleting": false
      }
-    }
+    },
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [
@@ -539,7 +545,10 @@
      "transient": {
       "deleting": false
      }
-    }
+    },
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [

diff --git a/...turestore_sample/notebooks/sdk_only/5. Enable online store and run online inference.ipynb b/...turestore_sample/notebooks/sdk_only/5. Enable online store and run online inference.ipynb
@@ -127,7 +127,7 @@
     "\n",
     "# Please update the dir to ./Users/{your-alias} (or any custom directory you uploaded the samples to).\n",
     "# You can find the name from the directory structure inm the left navigation panel.\n",
-    "root_dir = \"./Users/<your user alias>/featurestore_sample\"\n",
+    "root_dir = \"./Users/<your_user_alias>/featurestore_sample\"\n",
     "\n",
     "if os.path.isdir(root_dir):\n",
     "    print(\"The folder exists.\")\n",
@@ -171,6 +171,7 @@
     "project_ws_sub_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "project_ws_rg = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
     "project_ws_name = os.environ[\"AZUREML_ARM_WORKSPACE_NAME\"]\n",
+    "version = \"<VERSION>\"\n",
     "\n",
     "# Connect to the project workspace\n",
     "ws_client = MLClient(\n",
@@ -199,7 +200,7 @@
     "from azure.ai.ml.identity import AzureMLOnBehalfOfCredential\n",
     "\n",
     "# Feature store\n",
-    "featurestore_name = \"featurestore\"  # use the same name from part #1 of the tutorial\n",
+    "featurestore_name = \"my-featurestore\"  # use the same name from part #1 of the tutorial\n",
     "featurestore_subscription_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "featurestore_resource_group_name = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
     "\n",
@@ -282,7 +283,7 @@
     "\n",
     "redis_subscription_id = os.environ[\"AZUREML_ARM_SUBSCRIPTION\"]\n",
     "redis_resource_group_name = os.environ[\"AZUREML_ARM_RESOURCEGROUP\"]\n",
-    "redis_name = \"redis1\"\n",
+    "redis_name = \"<REDIS_NAME>\"\n",
     "redis_location = ws_location"
    ]
   },
@@ -598,7 +599,7 @@
     "\n",
     "# Turn on both offline and online materialization on the \"accounts\" featureset.\n",
     "\n",
-    "accounts_fset_config = fs_client._featuresets.get(name=\"accounts\", version=\"1\")\n",
+    "accounts_fset_config = fs_client._featuresets.get(name=\"accounts\", version=version)\n",
     "\n",
     "accounts_fset_config.materialization_settings = MaterializationSettings(\n",
     "    offline_enabled=True,\n",
@@ -651,7 +652,7 @@
     "\n",
     "poller = fs_client.feature_sets.begin_backfill(\n",
     "    name=\"accounts\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    feature_window_start_time=st,\n",
     "    feature_window_end_time=ed,\n",
     ")\n",
@@ -676,7 +677,10 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "name": "track-accounts-backfill"
+    "name": "track-accounts-backfill",
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [
@@ -720,7 +724,9 @@
    "source": [
     "# Enable materialization to online store for the \"transactions\" feature set.\n",
     "\n",
-    "transactions_fset_config = fs_client._featuresets.get(name=\"transactions\", version=\"1\")\n",
+    "transactions_fset_config = fs_client._featuresets.get(\n",
+    "    name=\"transactions\", version=version\n",
+    ")\n",
     "transactions_fset_config.materialization_settings.online_enabled = True\n",
     "\n",
     "fs_poller = fs_client.feature_sets.begin_create_or_update(transactions_fset_config)\n",
@@ -765,7 +771,7 @@
     "\n",
     "poller = fs_client.feature_sets.begin_backfill(\n",
     "    name=\"transactions\",\n",
-    "    version=\"1\",\n",
+    "    version=version,\n",
     "    feature_window_start_time=st,\n",
     "    feature_window_end_time=ed,\n",
     ")\n",
@@ -795,7 +801,10 @@
      "transient": {
       "deleting": false
      }
-    }
+    },
+    "tags": [
+     "active-ipynb"
+    ]
    },
    "outputs": [],
    "source": [