Merge branch 'main' into ODSC-64644/enhance_model_artifact_handler

ads/aqua/common/decorator.py

@@ -69,6 +69,16 @@ def inner_function(
                 reason=error.message,
                 service_payload=error.args[0] if error.args else None,
                 exc_info=sys.exc_info(),
+                aqua_api_details=dict(
+                    # __qualname__ gives information of class and name of api
+                    aqua_api_name=func.__qualname__,
+                    oci_api_name=getattr(
+                        error, "operation_name", "Unknown OCI Operation"
+                    ),
+                    service_endpoint=getattr(
+                        error, "request_endpoint", "Unknown Request Endpoint"
+                    )
+                )
             )
         except (
             ClientError,

ads/aqua/evaluation/entities.py

@@ -9,11 +9,12 @@
 This module contains dataclasses for aqua evaluation.
 """
 
+from typing import Any, Dict, List, Optional
+
 from pydantic import Field
-from typing import Any, Dict, List, Optional, Union
 
-from ads.aqua.data import AquaResourceIdentifier
 from ads.aqua.config.utils.serializer import Serializable
+from ads.aqua.data import AquaResourceIdentifier
 
 
 class CreateAquaEvaluationDetails(Serializable):
@@ -87,6 +88,8 @@ class CreateAquaEvaluationDetails(Serializable):
 
     class Config:
         extra = "ignore"
+        protected_namespaces = ()
+
 
 class AquaEvalReport(Serializable):
     evaluation_id: str = ""
@@ -95,6 +98,7 @@ class AquaEvalReport(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvalParams(Serializable):
     shape: str = ""
     dataset_path: str = ""
@@ -103,6 +107,7 @@ class AquaEvalParams(Serializable):
     class Config:
         extra = "allow"
 
+
 class AquaEvalMetric(Serializable):
     key: str
     name: str
@@ -111,6 +116,7 @@ class AquaEvalMetric(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvalMetricSummary(Serializable):
     metric: str = ""
     score: str = ""
@@ -119,6 +125,7 @@ class AquaEvalMetricSummary(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvalMetrics(Serializable):
     id: str
     report: str
@@ -128,6 +135,7 @@ class AquaEvalMetrics(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvaluationCommands(Serializable):
     evaluation_id: str
     evaluation_target_id: str
@@ -139,6 +147,7 @@ class AquaEvaluationCommands(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvaluationSummary(Serializable):
     """Represents a summary of Aqua evalution."""
 
@@ -157,6 +166,7 @@ class AquaEvaluationSummary(Serializable):
     class Config:
         extra = "ignore"
 
+
 class AquaEvaluationDetail(AquaEvaluationSummary):
     """Represents a details of Aqua evalution."""
 

ads/aqua/evaluation/evaluation.py

@@ -1305,7 +1305,7 @@ def _process(
             "id": model_id,
             "name": model.display_name,
             "console_url": console_url,
-            "time_created": model.time_created,
+            "time_created": str(model.time_created),
             "tags": tags,
             "experiment": self._build_resource_identifier(
                 id=experiment_id,

ads/aqua/extension/aqua_ws_msg_handler.py

@@ -78,10 +78,12 @@ def write_error(self, status_code, **kwargs):
                 logger.warning(reply["message"])
         # telemetry may not be present if there is an error while initializing
         if hasattr(self, "telemetry"):
+            aqua_api_details = kwargs.get("aqua_api_details", {})
             self.telemetry.record_event_async(
                 category="aqua/error",
                 action=str(status_code),
                 value=reason,
+                **aqua_api_details
             )
         response = AquaWsError(
             status=status_code,

ads/aqua/extension/base_handler.py

@@ -98,10 +98,12 @@ def write_error(self, status_code, **kwargs):
 
         # telemetry may not be present if there is an error while initializing
         if hasattr(self, "telemetry"):
+            aqua_api_details = kwargs.get("aqua_api_details", {})
             self.telemetry.record_event_async(
                 category="aqua/error",
                 action=str(status_code),
                 value=reason,
+                **aqua_api_details
             )
 
         self.finish(json.dumps(reply))

ads/aqua/finetuning/constants.py

@@ -15,3 +15,6 @@ class FineTuneCustomMetadata(str, metaclass=ExtendedEnumMeta):
     SERVICE_MODEL_ARTIFACT_LOCATION = "artifact_location"
     SERVICE_MODEL_DEPLOYMENT_CONTAINER = "deployment-container"
     SERVICE_MODEL_FINE_TUNE_CONTAINER = "finetune-container"
+
+
+ENV_AQUA_FINE_TUNING_CONTAINER = "AQUA_FINE_TUNING_CONTAINER"

ads/aqua/finetuning/finetuning.py

@@ -31,7 +31,10 @@
     UNKNOWN_DICT,
 )
 from ads.aqua.data import AquaResourceIdentifier
-from ads.aqua.finetuning.constants import *
+from ads.aqua.finetuning.constants import (
+    ENV_AQUA_FINE_TUNING_CONTAINER,
+    FineTuneCustomMetadata,
+)
 from ads.aqua.finetuning.entities import *
 from ads.common.auth import default_signer
 from ads.common.object_storage_details import ObjectStorageDetails
@@ -310,6 +313,15 @@ def create(
         except Exception:
             pass
 
+        if not is_custom_container and ENV_AQUA_FINE_TUNING_CONTAINER in os.environ:
+            ft_container = os.environ[ENV_AQUA_FINE_TUNING_CONTAINER]
+            logger.info(
+                "Using container set by environment variable %s=%s",
+                ENV_AQUA_FINE_TUNING_CONTAINER,
+                ft_container,
+            )
+            is_custom_container = True
+
         ft_parameters.batch_size = ft_parameters.batch_size or (
             ft_config.get("shape", UNKNOWN_DICT)
             .get(create_fine_tuning_details.shape_name, UNKNOWN_DICT)
@@ -559,7 +571,6 @@ def get_finetuning_config(self, model_id: str) -> Dict:
         Dict:
             A dict of allowed finetuning configs.
         """
-
         config = self.get_config(model_id, AQUA_MODEL_FINETUNING_CONFIG)
         if not config:
             logger.debug(

ads/opctl/operator/lowcode/anomaly/model/anomaly_merlion.py

@@ -4,9 +4,11 @@
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import importlib
+import logging
 
 import numpy as np
 import pandas as pd
+import report_creator as rc
 from merlion.post_process.threshold import AggregateAlarms
 from merlion.utils import TimeSeries
 
@@ -21,6 +23,8 @@
 from .anomaly_dataset import AnomalyOutput
 from .base_model import AnomalyOperatorBaseModel
 
+logging.getLogger("report_creator").setLevel(logging.WARNING)
+
 
 class AnomalyMerlionOperatorModel(AnomalyOperatorBaseModel):
     """Class representing Merlion Anomaly Detection operator model."""
@@ -84,7 +88,7 @@ def _build_model(self) -> AnomalyOutput:
         for target, df in self.datasets.full_data_dict.items():
             data = df.set_index(date_column)
             data = TimeSeries.from_pd(data)
-            for model_name, (model_config, model) in model_config_map.items():
+            for _, (model_config, model) in model_config_map.items():
                 if self.spec.model == SupportedModels.BOCPD:
                     model_config = model_config(**self.spec.model_kwargs)
                 else:
@@ -115,7 +119,7 @@ def _build_model(self) -> AnomalyOutput:
                     y_pred = (y_pred.to_pd().reset_index()["anom_score"] > 0).astype(
                         int
                     )
-                except Exception as e:
+                except Exception:
                     y_pred = (
                         scores["anom_score"]
                         > np.percentile(
@@ -135,15 +139,12 @@ def _build_model(self) -> AnomalyOutput:
                         OutputColumns.SCORE_COL: scores["anom_score"],
                     }
                 ).reset_index(drop=True)
-                # model_objects[model_name].append(model)
 
                 anomaly_output.add_output(target, anomaly, score)
         return anomaly_output
 
     def _generate_report(self):
         """Genreates a report for the model."""
-        import report_creator as rc
-
         other_sections = [
             rc.Heading("Selected Models Overview", level=2),
             rc.Text(

ads/opctl/operator/lowcode/anomaly/model/automlx.py

@@ -1,16 +1,21 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
 # Copyright (c) 2023, 2024 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
+
 import pandas as pd
+import report_creator as rc
 
 from ads.common.decorator.runtime_dependency import runtime_dependency
-from .anomaly_dataset import AnomalyOutput
+from ads.opctl import logger
+from ads.opctl.operator.lowcode.anomaly.const import OutputColumns
 
+from .anomaly_dataset import AnomalyOutput
 from .base_model import AnomalyOperatorBaseModel
-from ads.opctl.operator.lowcode.anomaly.const import OutputColumns
+
+logging.getLogger("report_creator").setLevel(logging.WARNING)
 
 
 class AutoMLXOperatorModel(AnomalyOperatorBaseModel):
@@ -25,16 +30,17 @@ class AutoMLXOperatorModel(AnomalyOperatorBaseModel):
         ),
     )
     def _build_model(self) -> pd.DataFrame:
-        from automlx import init
         import logging
 
+        import automlx
+
         try:
-            init(
+            automlx.init(
                 engine="ray",
                 engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},
                 loglevel=logging.CRITICAL,
             )
-        except Exception as e:
+        except Exception:
             logger.info("Ray already initialized")
         date_column = self.spec.datetime_column.name
         anomaly_output = AnomalyOutput(date_column=date_column)
@@ -73,8 +79,6 @@ def _build_model(self) -> pd.DataFrame:
         return anomaly_output
 
     def _generate_report(self):
-        import report_creator as rc
-
         """The method that needs to be implemented on the particular model level."""
         other_sections = [
             rc.Heading("Selected Models Overview", level=2),

ads/opctl/operator/lowcode/anomaly/model/autots.py

@@ -1,9 +1,12 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
 # Copyright (c) 2023, 2024 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
+
+import report_creator as rc
+
 from ads.common.decorator.runtime_dependency import runtime_dependency
 from ads.opctl import logger
 from ads.opctl.operator.lowcode.anomaly.const import OutputColumns
@@ -12,6 +15,8 @@
 from .anomaly_dataset import AnomalyOutput
 from .base_model import AnomalyOperatorBaseModel
 
+logging.getLogger("report_creator").setLevel(logging.WARNING)
+
 
 class AutoTSOperatorModel(AnomalyOperatorBaseModel):
     """Class representing AutoTS Anomaly Detection operator model."""
@@ -91,8 +96,6 @@ def _build_model(self) -> AnomalyOutput:
         return anomaly_output
 
     def _generate_report(self):
-        import report_creator as rc
-
         """The method that needs to be implemented on the particular model level."""
         other_sections = [
             rc.Heading("Selected Models Overview", level=2),

ads/opctl/operator/lowcode/anomaly/model/base_model.py

@@ -3,6 +3,7 @@
 # Copyright (c) 2023, 2024 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
 import os
 import tempfile
 import time
@@ -12,6 +13,7 @@
 import fsspec
 import numpy as np
 import pandas as pd
+import report_creator as rc
 from sklearn import linear_model
 
 from ads.common.object_storage_details import ObjectStorageDetails
@@ -33,6 +35,8 @@
 from ..operator_config import AnomalyOperatorConfig, AnomalyOperatorSpec
 from .anomaly_dataset import AnomalyDatasets, AnomalyOutput, TestData
 
+logging.getLogger("report_creator").setLevel(logging.WARNING)
+
 
 class AnomalyOperatorBaseModel(ABC):
     """The base class for the anomaly detection operator models."""
@@ -59,8 +63,8 @@ def __init__(self, config: AnomalyOperatorConfig, datasets: AnomalyDatasets):
     def generate_report(self):
         """Generates the report."""
         import matplotlib.pyplot as plt
-        plt.rcParams.update({'figure.max_open_warning': 0})
-        import report_creator as rc
+
+        plt.rcParams.update({"figure.max_open_warning": 0})
 
         start_time = time.time()
         # fallback using sklearn oneclasssvm when the sub model _build_model fails
@@ -84,7 +88,13 @@ def generate_report(self):
                 anomaly_output, test_data, elapsed_time
             )
         table_blocks = [
-            rc.DataTable(df.head(SUBSAMPLE_THRESHOLD) if self.spec.subsample_report_data and len(df) > SUBSAMPLE_THRESHOLD else df, label=col, index=True)
+            rc.DataTable(
+                df.head(SUBSAMPLE_THRESHOLD)
+                if self.spec.subsample_report_data and len(df) > SUBSAMPLE_THRESHOLD
+                else df,
+                label=col,
+                index=True,
+            )
             for col, df in self.datasets.full_data_dict.items()
         ]
         data_table = rc.Select(blocks=table_blocks)
@@ -144,7 +154,9 @@ def generate_report(self):
             else:
                 figure_blocks = None
 
-            blocks.append(rc.Group(*figure_blocks, label=target)) if figure_blocks else None
+            blocks.append(
+                rc.Group(*figure_blocks, label=target)
+            ) if figure_blocks else None
         plots = rc.Select(blocks)
 
         report_sections = []
@@ -154,7 +166,9 @@ def generate_report(self):
         yaml_appendix = rc.Yaml(self.config.to_dict())
         summary = rc.Block(
             rc.Group(
-                rc.Text(f"You selected the **`{self.spec.model}`** model.\n{model_description.text}\n"),
+                rc.Text(
+                    f"You selected the **`{self.spec.model}`** model.\n{model_description.text}\n"
+                ),
                 rc.Text(
                     "Based on your dataset, you could have also selected "
                     f"any of the models: `{'`, `'.join(SupportedModels.keys() if self.spec.datetime_column else NonTimeADSupportedModels.keys())}`."
@@ -285,8 +299,6 @@ def _save_report(
         test_metrics: pd.DataFrame,
     ):
         """Saves resulting reports to the given folder."""
-        import report_creator as rc
-
         unique_output_dir = self.spec.output_directory.url
 
         if ObjectStorageDetails.is_oci_path(unique_output_dir):