Feature store preview (#226)

Author: mrDzurb

.pre-commit-config.yaml

@@ -10,6 +10,7 @@ repos:
     -   id: check-json
     -   id: check-merge-conflict
     -   id: check-yaml
+        exclude: feature_store_*.yaml
         args: ['--allow-multiple-documents']
     -   id: detect-private-key
     -   id: end-of-file-fixer

THIRD_PARTY_LICENSES.txt

@@ -229,6 +229,12 @@ pandavro
 * Source code: https://github.com/ynqa/pandavro
 * Project home: https://github.com/ynqa/pandavro
 
+plotly
+* Copyright (c) 2016-2018 Plotly, Inc
+* License: MIT License
+* Source code: https://github.com/plotly/plotly.py
+* Project home: https://plotly.com/
+
 protobuf
 * Copyright 2008 Google Inc.  All rights reserved.
 * License: Google Protobuf License
@@ -253,6 +259,12 @@ pyspark
 * Source code: https://github.com/apache/spark/tree/master/python
 * Project home: https://spark.apache.org/
 
+pyarrow
+* Copyright 2004 and onwards The Apache Software Foundation.
+* License: Apache-2.0 LICENSE
+* Source code: https://github.com/apache/arrow/tree/main/python
+* Project home: https://arrow.apache.org/
+
 python_jsonschema_objects
 * Copyright (c) 2014 Chris Wacek
 * License: MIT License
@@ -369,6 +381,18 @@ xgboost
 * Source code: https://github.com/dmlc/xgboost
 * Project home: https://xgboost.ai/
 
+great-expectations
+* No listed copyright holder
+* License: Apache License 2.0
+* Source code: https://github.com/great-expectations/great_expectations
+* Project home: https://greatexpectations.io/
+
+delta
+* Copyright (2021) The Delta Lake Project Authors.  All rights reserved.
+* License: Apache License 2.0
+* Source code: https://github.com/delta-io/delta/
+* Project home: https://delta.io/
+
 =============================== Licenses ===============================
 ------------------------------------------------------------------------
 

ads/common/decorator/runtime_dependency.py

@@ -64,6 +64,9 @@ class OptionalDependency:
     OPTUNA = "oracle-ads[optuna]"
     SPARK = "oracle-ads[spark]"
     HUGGINGFACE = "oracle-ads[huggingface]"
+    FEATURE_STORE = "oracle-ads[feature-store]"
+    GRAPHVIZ = "oracle-ads[graphviz]"
+    MLM_INSIGHTS = "oracle-ads[mlm_insights]"
 
 
 def runtime_dependency(

ads/common/oci_client.py

@@ -1,21 +1,22 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2021, 2023 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import logging
 
 from oci.ai_language import AIServiceLanguageClient
+from oci.data_catalog import DataCatalogClient
 from oci.data_flow import DataFlowClient
 from oci.data_labeling_service import DataLabelingManagementClient
 from oci.data_labeling_service_dataplane import DataLabelingClient
 from oci.data_science import DataScienceClient
 from oci.identity import IdentityClient
 from oci.object_storage import ObjectStorageClient
+from oci.resource_search import ResourceSearchClient
 from oci.secrets import SecretsClient
 from oci.vault import VaultsClient
-
 logger = logging.getLogger(__name__)
 
 
@@ -62,7 +63,15 @@ def _client_impl(self, client):
             "ai_language": AIServiceLanguageClient,
             "data_labeling_dp": DataLabelingClient,
             "data_labeling_cp": DataLabelingManagementClient,
+            "resource_search": ResourceSearchClient,
+            "data_catalog": DataCatalogClient
         }
+        try:
+            from oci.feature_store import FeatureStoreClient
+            client_map["feature_store"] = FeatureStoreClient
+        except ImportError:
+            logger.warning("OCI SDK with feature store support is not installed")
+            pass
 
         assert (
             client in client_map
@@ -124,6 +133,18 @@ def ai_language(self):
     def data_labeling_cp(self):
         return self.create_client("data_labeling_cp")
 
+    @property
+    def feature_store(self):
+        return self.create_client("feature_store")
+
     @property
     def data_labeling_dp(self):
         return self.create_client("data_labeling_dp")
+
+    @property
+    def resource_search(self):
+        return self.create_client("resource_search")
+
+    @property
+    def data_catalog(self):
+        return self.create_client("data_catalog")

ads/common/oci_mixin.py

@@ -41,7 +41,7 @@ class MergeStrategy(Enum):
     MERGE = "merge"
 
 
-class OCIModelNotExists(Exception):   # pragma: no cover
+class OCIModelNotExists(Exception):  # pragma: no cover
     pass
 
 
@@ -383,7 +383,7 @@ class OCIModelMixin(OCISerializableMixin):
     """
 
     # Regex pattern matching the module name of an OCI model.
-    OCI_MODEL_PATTERN = r"oci.[^.]+\.models[\..*]?"
+    OCI_MODEL_PATTERN = r"(oci|feature_store_client).[^.]+\.models[\..*]?"
     # Constants
     CONS_COMPARTMENT_ID = "compartment_id"
 
@@ -937,11 +937,11 @@ def get_work_request_response(
         return work_request_response
 
     def wait_for_progress(
-        self, 
-        work_request_id: str, 
-        num_steps: int = DEFAULT_WORKFLOW_STEPS, 
-        max_wait_time: int = DEFAULT_WAIT_TIME, 
-        poll_interval: int = DEFAULT_POLL_INTERVAL
+        self,
+        work_request_id: str,
+        num_steps: int = DEFAULT_WORKFLOW_STEPS,
+        max_wait_time: int = DEFAULT_WAIT_TIME,
+        poll_interval: int = DEFAULT_POLL_INTERVAL,
     ):
         """Waits for the work request progress bar to be completed.
 
@@ -969,10 +969,10 @@ def wait_for_progress(
             seconds_since = time.time() - start_time
             exceed_max_time = max_wait_time > 0 and seconds_since >= max_wait_time
             if exceed_max_time:
-                logger.error(
-                    f"Max wait time ({max_wait_time} seconds) exceeded."
-                )
-            while not exceed_max_time and (not work_request_logs or len(work_request_logs) < num_steps):
+                logger.error(f"Max wait time ({max_wait_time} seconds) exceeded.")
+            while not exceed_max_time and (
+                not work_request_logs or len(work_request_logs) < num_steps
+            ):
                 time.sleep(poll_interval)
                 new_work_request_logs = []
 

ads/dataset/progress.py

@@ -41,7 +41,7 @@ def __init__(self, max_progress=100, description="Running", verbose=False):
             self.start_time = time.time()
             self.description = description
 
-    def update(self, description=None):
+    def update(self, description=None, n=1):
         """
         Updates the progress bar
         """
@@ -57,7 +57,7 @@ def update(self, description=None):
                 description if description is not None else self.description
             )
             self.start_time = time.time()
-        self.progress_bar.update(1)
+        self.progress_bar.update(n)
         if description is not None:
             self.progress_bar.set_description(description, refresh=True)
 

ads/feature_store/.readthedocs.yaml

@@ -0,0 +1,19 @@
+# Read the Docs configuration file
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: ads/feature_store/docs/source/conf.py
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: ads/feature_store/docs/requirements.txt

ads/feature_store/__init__.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2023 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+import logging
+
+logger = logging.getLogger(__name__)