oracle-ads 2.13.8__tar.gz → 2.13.9rc1__tar.gz

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/PKG-INFO

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: oracle_ads
-Version: 2.13.8
+Version: 2.13.9rc1
 Summary: Oracle Accelerated Data Science SDK
-Keywords: Oracle Cloud Infrastructure,OCI,Machine Learning,ML,Artificial Intelligence,AI,Data Science,Cloud,Oracle
+Keywords: Oracle Cloud Infrastructure,OCI,Machine Learning,ML,Artificial Intelligence,AI,Data Science,Cloud,Oracle,GenAI,Generative AI,Forecast,Anomaly,Document Understanding
 Author: Oracle Data Science
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-Expression: UPL-1.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Universal Permissive License (UPL)
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/common/entities.py

@@ -151,6 +151,8 @@ class AquaMultiModelRef(Serializable):
         The name of the model.
     gpu_count : Optional[int]
         Number of GPUs required for deployment.
+    model_task : Optional[str]
+        The task that model operates on. Supported tasks are in MultiModelSupportedTaskType
     env_var : Optional[Dict[str, Any]]
         Optional environment variables to override during deployment.
     artifact_location : Optional[str]
@@ -162,6 +164,7 @@ class AquaMultiModelRef(Serializable):
     gpu_count: Optional[int] = Field(
         None, description="The gpu count allocation for the model."
     )
+    model_task: Optional[str] = Field(None, description="The task that model operates on. Supported tasks are in MultiModelSupportedTaskType")
     env_var: Optional[dict] = Field(
         default_factory=dict, description="The environment variables of the model."
     )

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/constants.py

@@ -43,6 +43,8 @@ HF_METADATA_FOLDER = ".cache/"
 HF_LOGIN_DEFAULT_TIMEOUT = 2
 MODEL_NAME_DELIMITER = ";"
 AQUA_TROUBLESHOOTING_LINK = "https://github.com/oracle-samples/oci-data-science-ai-samples/blob/main/ai-quick-actions/troubleshooting-tips.md"
+MODEL_FILE_DESCRIPTION_VERSION = "1.0"
+MODEL_FILE_DESCRIPTION_TYPE = "modelOSSReferenceDescription"
 
 TRAINING_METRICS_FINAL = "training_metrics_final"
 VALIDATION_METRICS_FINAL = "validation_metrics_final"

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/finetuning/finetuning.py

@@ -58,6 +58,7 @@ from ads.jobs.ads_job import Job
 from ads.jobs.builders.infrastructure.dsc_job import DataScienceJob
 from ads.jobs.builders.runtimes.base import Runtime
 from ads.jobs.builders.runtimes.container_runtime import ContainerRuntime
+from ads.model.common.utils import MetadataArtifactPathType
 from ads.model.model_metadata import (
     MetadataTaxonomyKeys,
     ModelCustomMetadata,
@@ -315,6 +316,23 @@ class AquaFineTuningApp(AquaApp):
             model_by_reference=True,
             defined_tags=create_fine_tuning_details.defined_tags,
         )
+        defined_metadata_dict = {}
+        defined_metadata_list_source = source.defined_metadata_list._to_oci_metadata()
+        for defined_metadata in defined_metadata_list_source:
+            if (
+                defined_metadata.has_artifact
+                and defined_metadata.key.lower()
+                != AquaModelMetadataKeys.FINE_TUNING_CONFIGURATION.lower()
+            ):
+                content = self.ds_client.get_model_defined_metadatum_artifact_content(
+                    source.id, defined_metadata.key
+                ).data.content
+                defined_metadata_dict[defined_metadata.key] = content
+
+        for key, value in defined_metadata_dict.items():
+            ft_model.create_defined_metadata_artifact(
+                key, value, MetadataArtifactPathType.CONTENT
+            )
 
         ft_job_freeform_tags = {
             Tags.AQUA_TAG: UNKNOWN,

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/model/entities.py

@@ -15,12 +15,19 @@ from typing import List, Optional
 
 import oci
 from huggingface_hub import hf_api
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
+from pydantic.alias_generators import to_camel
 
 from ads.aqua import logger
 from ads.aqua.app import CLIBuilderMixin
 from ads.aqua.common import utils
-from ads.aqua.constants import LIFECYCLE_DETAILS_MISSING_JOBRUN, UNKNOWN_VALUE
+from ads.aqua.config.utils.serializer import Serializable
+from ads.aqua.constants import (
+    LIFECYCLE_DETAILS_MISSING_JOBRUN,
+    MODEL_FILE_DESCRIPTION_TYPE,
+    MODEL_FILE_DESCRIPTION_VERSION,
+    UNKNOWN_VALUE,
+)
 from ads.aqua.data import AquaResourceIdentifier
 from ads.aqua.model.enums import FineTuningDefinedMetadata
 from ads.aqua.training.exceptions import exit_code_dict
@@ -304,3 +311,75 @@ class ImportModelDetails(CLIBuilderMixin):
 
     def __post_init__(self):
         self._command = "model register"
+
+
+class ModelFileInfo(Serializable):
+    """Describes the file information of this model.
+
+    Attributes:
+        name (str): The name of the model artifact file.
+        version (str): The version of the model artifact file.
+        size_in_bytes (int): The size of the model artifact file in bytes.
+    """
+
+    name: str = Field(..., description="The name of model artifact file.")
+    version: str = Field(..., description="The version of model artifact file.")
+    size_in_bytes: int = Field(
+        ..., description="The size of model artifact file in bytes."
+    )
+
+    class Config:
+        alias_generator = to_camel
+        extra = "allow"
+
+
+class ModelArtifactInfo(Serializable):
+    """Describes the artifact information of this model.
+
+    Attributes:
+        namespace (str): The namespace of the model artifact location.
+        bucket_name (str): The bucket name of model artifact location.
+        prefix (str): The prefix of model artifact location.
+        objects: (List[ModelFileInfo]): A list of model artifact objects.
+    """
+
+    namespace: str = Field(
+        ..., description="The name space of model artifact location."
+    )
+    bucket_name: str = Field(
+        ..., description="The bucket name of model artifact location."
+    )
+    prefix: str = Field(..., description="The prefix of model artifact location.")
+    objects: List[ModelFileInfo] = Field(
+        ..., description="List of model artifact objects."
+    )
+
+    class Config:
+        alias_generator = to_camel
+        extra = "allow"
+
+
+class ModelFileDescription(Serializable):
+    """Describes the model file description.
+
+    Attributes:
+        version (str): The version of the model file description. Defaults to `1.0`.
+        type (str): The type of model file description. Defaults to `modelOSSReferenceDescription`.
+        models List[ModelArtifactInfo]: A list of model artifact information.
+    """
+
+    version: str = Field(
+        default=MODEL_FILE_DESCRIPTION_VERSION,
+        description="The version of model file description.",
+    )
+    type: str = Field(
+        default=MODEL_FILE_DESCRIPTION_TYPE,
+        description="The type of model file description.",
+    )
+    models: List[ModelArtifactInfo] = Field(
+        ..., description="List of model artifact information."
+    )
+
+    class Config:
+        alias_generator = to_camel
+        extra = "allow"

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/model/enums.py

@@ -26,5 +26,7 @@ class FineTuningCustomMetadata(ExtendedEnum):
 
 
 class MultiModelSupportedTaskType(ExtendedEnum):
-    TEXT_GENERATION = "text-generation"
-    TEXT_GENERATION_ALT = "text_generation"
+    TEXT_GENERATION = "text_generation"
+    IMAGE_TEXT_TO_TEXT = "image_text_to_text"
+    CODE_SYNTHESIS = "code_synthesis"
+    EMBEDDING = "text_embedding"

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/model/model.py

@@ -4,6 +4,7 @@
 import json
 import os
 import pathlib
+import re
 from datetime import datetime, timedelta
 from threading import Lock
 from typing import Any, Dict, List, Optional, Set, Union
@@ -78,6 +79,7 @@ from ads.aqua.model.entities import (
     AquaModelReadme,
     AquaModelSummary,
     ImportModelDetails,
+    ModelFileDescription,
     ModelValidationResult,
 )
 from ads.aqua.model.enums import MultiModelSupportedTaskType
@@ -184,8 +186,12 @@ class AquaModelApp(AquaApp):
         target_project = project_id or PROJECT_OCID
         target_compartment = compartment_id or COMPARTMENT_OCID
 
-        # Skip model copying if it is registered model
-        if service_model.freeform_tags.get(Tags.BASE_MODEL_CUSTOM, None) is not None:
+        # Skip model copying if it is registered model or fine-tuned model
+        if (
+            service_model.freeform_tags.get(Tags.BASE_MODEL_CUSTOM, None) is not None
+            or service_model.freeform_tags.get(Tags.AQUA_FINE_TUNED_MODEL_TAG)
+            is not None
+        ):
             logger.info(
                 f"Aqua Model {model_id} already exists in the user's compartment."
                 "Skipped copying."
@@ -266,8 +272,8 @@ class AquaModelApp(AquaApp):
                 "Model list cannot be empty. Please provide at least one model for deployment."
             )
 
-        artifact_list = []
         display_name_list = []
+        model_file_description_list: List[ModelFileDescription] = []
         model_custom_metadata = ModelCustomMetadata()
 
         service_inference_containers = (
@@ -294,6 +300,7 @@ class AquaModelApp(AquaApp):
         for model in models:
             source_model = DataScienceModel.from_id(model.model_id)
             display_name = source_model.display_name
+            model_file_description = source_model.model_file_description
             # Update model name in user's input model
             model.model_name = model.model_name or display_name
 
@@ -304,18 +311,10 @@ class AquaModelApp(AquaApp):
             #         "Currently only service models are supported for multi model deployment."
             #     )
 
-            # TODO uncomment the section below if only the specific types of models should be allowed for multi-model deployment
-            # if (
-            #     source_model.freeform_tags.get(Tags.TASK, UNKNOWN).lower()
-            #     not in MultiModelSupportedTaskType
-            # ):
-            #     raise AquaValueError(
-            #         f"Invalid or missing {Tags.TASK} tag for selected model {display_name}. "
-            #         f"Currently only `{MultiModelSupportedTaskType.values()}` models are supported for multi model deployment."
-            #     )
-
             display_name_list.append(display_name)
 
+            self._extract_model_task(model, source_model)
+
             # Retrieve model artifact
             model_artifact_path = source_model.artifact
             if not model_artifact_path:
@@ -327,7 +326,15 @@ class AquaModelApp(AquaApp):
             # Update model artifact location in user's input model
             model.artifact_location = model_artifact_path
 
-            artifact_list.append(model_artifact_path)
+            if not model_file_description:
+                raise AquaValueError(
+                    f"Model '{display_name}' (ID: {model.model_id}) has no file description. "
+                    "Please register the model first."
+                )
+
+            model_file_description_list.append(
+                ModelFileDescription(**model_file_description)
+            )
 
             # Validate deployment container consistency
             deployment_container = source_model.custom_metadata_list.get(
@@ -405,9 +412,16 @@ class AquaModelApp(AquaApp):
             .with_custom_metadata_list(model_custom_metadata)
         )
 
-        # Attach artifacts
-        for artifact in artifact_list:
-            custom_model.add_artifact(uri=artifact)
+        # Update multi model file description to attach artifacts
+        custom_model.with_model_file_description(
+            json_dict=ModelFileDescription(
+                models=[
+                    models
+                    for model_file_description in model_file_description_list
+                    for models in model_file_description.models
+                ]
+            ).model_dump(by_alias=True)
+        )
 
         # Finalize creation
         custom_model.create(model_by_reference=True)
@@ -704,6 +718,26 @@ class AquaModelApp(AquaApp):
         else:
             raise AquaRuntimeError("Only registered unverified models can be edited.")
 
+    def _extract_model_task(
+        self,
+        model: AquaMultiModelRef,
+        source_model: DataScienceModel,
+    ) -> None:
+        """In a Multi Model Deployment, will set model_task parameter in AquaMultiModelRef from freeform tags or user"""
+        # user does not supply model task, we extract from model metadata
+        if not model.model_task:
+            model.model_task = source_model.freeform_tags.get(Tags.TASK, UNKNOWN)
+
+        task_tag = re.sub(r"-", "_", model.model_task).lower()
+        # re-visit logic when more model task types are supported
+        if task_tag in MultiModelSupportedTaskType:
+            model.model_task = task_tag
+        else:
+            raise AquaValueError(
+                f"Invalid or missing {task_tag} tag for selected model {source_model.display_name}. "
+                f"Currently only `{MultiModelSupportedTaskType.values()}` models are supported for multi model deployment."
+            )
+
     def _fetch_metric_from_metadata(
         self,
         custom_metadata_list: ModelCustomMetadata,

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/aqua/modeldeployment/deployment.py

@@ -178,9 +178,7 @@ class AquaDeploymentApp(AquaApp):
         # validate instance shape availability in compartment
         available_shapes = [
             shape.name.lower()
-            for shape in self.list_shapes(
-                compartment_id=compartment_id
-            )
+            for shape in self.list_shapes(compartment_id=compartment_id)
         ]
 
         if create_deployment_details.instance_shape.lower() not in available_shapes:
@@ -645,7 +643,11 @@ class AquaDeploymentApp(AquaApp):
                 os_path = ObjectStorageDetails.from_path(artifact_path_prefix)
                 artifact_path_prefix = os_path.filepath.rstrip("/")
 
-            model_config.append({"params": params, "model_path": artifact_path_prefix})
+            # override by-default completion/ chat endpoint with other endpoint (embedding)
+            config_data = {"params": params, "model_path": artifact_path_prefix}
+            if model.model_task:
+                config_data["model_task"] = model.model_task
+            model_config.append(config_data)
             model_name_list.append(model.model_name)
 
         env_var.update({AQUA_MULTI_MODEL_CONFIG: json.dumps({"models": model_config})})

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/opctl/operator/lowcode/common/utils.py

@@ -11,6 +11,7 @@ import sys
 import tempfile
 from typing import List, Union
 
+import cloudpickle
 import fsspec
 import oracledb
 import pandas as pd
@@ -126,7 +127,26 @@ def load_data(data_spec, storage_options=None, **kwargs):
     return data
 
 
+def _safe_write(fn, **kwargs):
+    try:
+        fn(**kwargs)
+    except Exception:
+        logger.warning(f'Failed to write file {kwargs.get("filename", "UNKNOWN")}')
+
+
 def write_data(data, filename, format, storage_options=None, index=False, **kwargs):
+    return _safe_write(
+        fn=_write_data,
+        data=data,
+        filename=filename,
+        format=format,
+        storage_options=storage_options,
+        index=index,
+        **kwargs,
+    )
+
+
+def _write_data(data, filename, format, storage_options=None, index=False, **kwargs):
     disable_print()
     if not format:
         _, format = os.path.splitext(filename)
@@ -143,11 +163,24 @@ def write_data(data, filename, format, storage_options=None, index=False, **kwar
 
 
 def write_json(json_dict, filename, storage_options=None):
+    return _safe_write(
+        fn=_write_json,
+        json_dict=json_dict,
+        filename=filename,
+        storage_options=storage_options,
+    )
+
+
+def _write_json(json_dict, filename, storage_options=None):
     with fsspec.open(filename, mode="w", **storage_options) as f:
         f.write(json.dumps(json_dict))
 
 
 def write_simple_json(data, path):
+    return _safe_write(fn=_write_simple_json, data=data, path=path)
+
+
+def _write_simple_json(data, path):
     if ObjectStorageDetails.is_oci_path(path):
         storage_options = default_signer()
     else:
@@ -156,6 +189,60 @@ def write_simple_json(data, path):
         json.dump(data, f, indent=4)
 
 
+def write_file(local_filename, remote_filename, storage_options, **kwargs):
+    return _safe_write(
+        fn=_write_file,
+        local_filename=local_filename,
+        remote_filename=remote_filename,
+        storage_options=storage_options,
+        **kwargs,
+    )
+
+
+def _write_file(local_filename, remote_filename, storage_options, **kwargs):
+    with open(local_filename) as f1:
+        with fsspec.open(
+            remote_filename,
+            "w",
+            **storage_options,
+        ) as f2:
+            f2.write(f1.read())
+
+
+def load_pkl(filepath):
+    return _safe_write(fn=_load_pkl, filepath=filepath)
+
+
+def _load_pkl(filepath):
+    storage_options = {}
+    if ObjectStorageDetails.is_oci_path(filepath):
+        storage_options = default_signer()
+
+    with fsspec.open(filepath, "rb", **storage_options) as f:
+        return cloudpickle.load(f)
+    return None
+
+
+def write_pkl(obj, filename, output_dir, storage_options):
+    return _safe_write(
+        fn=_write_pkl,
+        obj=obj,
+        filename=filename,
+        output_dir=output_dir,
+        storage_options=storage_options,
+    )
+
+
+def _write_pkl(obj, filename, output_dir, storage_options):
+    pkl_path = os.path.join(output_dir, filename)
+    with fsspec.open(
+        pkl_path,
+        "wb",
+        **storage_options,
+    ) as f:
+        cloudpickle.dump(obj, f)
+
+
 def merge_category_columns(data, target_category_columns):
     result = data.apply(
         lambda x: "__".join([str(x[col]) for col in target_category_columns]), axis=1
@@ -290,4 +377,8 @@ def disable_print():
 
 # Restore
 def enable_print():
+    try:
+        sys.stdout.close()
+    except Exception:
+        pass
     sys.stdout = sys.__stdout__

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/opctl/operator/lowcode/forecast/model/automlx.py

@@ -38,6 +38,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         super().__init__(config, datasets)
         self.global_explanation = {}
         self.local_explanation = {}
+        self.explainability_kwargs = {}
 
     def set_kwargs(self):
         model_kwargs_cleaned = self.spec.model_kwargs
@@ -54,6 +55,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
             self.spec.preprocessing.enabled
             or model_kwargs_cleaned.get("preprocessing", True)
         )
+        sample_ratio = model_kwargs_cleaned.pop("sample_to_feature_ratio", None)
+        if sample_ratio is not None:
+            self.explainability_kwargs = {"sample_to_feature_ratio": sample_ratio}
         return model_kwargs_cleaned, time_budget
 
     def preprocess(self, data, series_id):  # TODO: re-use self.le for explanations
@@ -445,6 +449,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                         else None,
                         pd.DataFrame(data_i[self.spec.target_column]),
                         task="forecasting",
+                        **self.explainability_kwargs,
                     )
 
                     # Generate explanations for the forecast
@@ -518,7 +523,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         model_params = model.selected_model_params_
         if len(trials) > 0:
             score_col = [col for col in trials.columns if "Score" in col][0]
-            validation_score = trials[trials.Hyperparameters == model_params][score_col].iloc[0]
+            validation_score = trials[trials.Hyperparameters == model_params][
+                score_col
+            ].iloc[0]
         else:
             validation_score = 0
         return -1 * validation_score
@@ -531,8 +538,12 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         for s_id in self.forecast_output.list_series_ids():
             try:
                 metrics = {self.spec.metric.upper(): self.models[s_id]["score"]}
-                metrics_df = pd.DataFrame.from_dict(metrics, orient="index", columns=[s_id])
-                logger.warning("AutoMLX failed to generate training metrics. Recovering validation loss instead")
+                metrics_df = pd.DataFrame.from_dict(
+                    metrics, orient="index", columns=[s_id]
+                )
+                logger.warning(
+                    "AutoMLX failed to generate training metrics. Recovering validation loss instead"
+                )
                 total_metrics = pd.concat([total_metrics, metrics_df], axis=1)
             except Exception as e:
                 logger.debug(

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/opctl/operator/lowcode/forecast/model/base_model.py

@@ -11,7 +11,6 @@ import traceback
 from abc import ABC, abstractmethod
 from typing import Tuple
 
-import fsspec
 import numpy as np
 import pandas as pd
 import report_creator as rc
@@ -25,10 +24,13 @@ from ads.opctl.operator.lowcode.common.utils import (
     disable_print,
     enable_print,
     human_time_friendly,
+    load_pkl,
     merged_category_column_name,
     seconds_to_datetime,
     write_data,
+    write_file,
     write_json,
+    write_pkl,
 )
 from ads.opctl.operator.lowcode.forecast.utils import (
     _build_metrics_df,
@@ -38,8 +40,6 @@ from ads.opctl.operator.lowcode.forecast.utils import (
     evaluate_train_metrics,
     get_auto_select_plot,
     get_forecast_plots,
-    load_pkl,
-    write_pkl,
 )
 
 from ..const import (
@@ -493,13 +493,11 @@ class ForecastOperatorBaseModel(ABC):
                 enable_print()
 
                 report_path = os.path.join(unique_output_dir, self.spec.report_filename)
-                with open(report_local_path) as f1:
-                    with fsspec.open(
-                        report_path,
-                        "w",
-                        **storage_options,
-                    ) as f2:
-                        f2.write(f1.read())
+                write_file(
+                    local_filename=report_local_path,
+                    remote_filename=report_path,
+                    storage_options=storage_options,
+                )
 
         # forecast csv report
         # todo: add test data into forecast.csv
@@ -573,9 +571,16 @@ class ForecastOperatorBaseModel(ABC):
         if self.spec.generate_explanations:
             try:
                 if not self.formatted_global_explanation.empty:
+                    # Round to 4 decimal places before writing
+                    global_expl_rounded = self.formatted_global_explanation.copy()
+                    global_expl_rounded = global_expl_rounded.apply(
+                        lambda col: np.round(col, 4)
+                        if np.issubdtype(col.dtype, np.number)
+                        else col
+                    )
                     if self.spec.generate_explanation_files:
                         write_data(
-                            data=self.formatted_global_explanation,
+                            data=global_expl_rounded,
                             filename=os.path.join(
                                 unique_output_dir, self.spec.global_explanation_filename
                             ),
@@ -583,16 +588,23 @@ class ForecastOperatorBaseModel(ABC):
                             storage_options=storage_options,
                             index=True,
                         )
-                    results.set_global_explanations(self.formatted_global_explanation)
+                    results.set_global_explanations(global_expl_rounded)
                 else:
                     logger.warning(
                         f"Attempted to generate global explanations for the {self.spec.global_explanation_filename} file, but an issue occured in formatting the explanations."
                     )
 
                 if not self.formatted_local_explanation.empty:
+                    # Round to 4 decimal places before writing
+                    local_expl_rounded = self.formatted_local_explanation.copy()
+                    local_expl_rounded = local_expl_rounded.apply(
+                        lambda col: np.round(col, 4)
+                        if np.issubdtype(col.dtype, np.number)
+                        else col
+                    )
                     if self.spec.generate_explanation_files:
                         write_data(
-                            data=self.formatted_local_explanation,
+                            data=local_expl_rounded,
                             filename=os.path.join(
                                 unique_output_dir, self.spec.local_explanation_filename
                             ),
@@ -600,7 +612,7 @@ class ForecastOperatorBaseModel(ABC):
                             storage_options=storage_options,
                             index=True,
                         )
-                    results.set_local_explanations(self.formatted_local_explanation)
+                    results.set_local_explanations(local_expl_rounded)
                 else:
                     logger.warning(
                         f"Attempted to generate local explanations for the {self.spec.local_explanation_filename} file, but an issue occured in formatting the explanations."

{oracle_ads-2.13.8 → oracle_ads-2.13.9rc1}/ads/opctl/operator/lowcode/forecast/model/neuralprophet.py

@@ -19,12 +19,10 @@ from ads.opctl import logger
 from ads.opctl.operator.lowcode.common.utils import (
     disable_print,
     enable_print,
-)
-from ads.opctl.operator.lowcode.forecast.utils import (
-    _select_plot_list,
     load_pkl,
     write_pkl,
 )
+from ads.opctl.operator.lowcode.forecast.utils import _select_plot_list
 
 from ..const import DEFAULT_TRIALS, SupportedModels
 from ..operator_config import ForecastOperatorConfig
@@ -159,20 +157,18 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 upper_bound=self.get_horizon(forecast[upper_bound_col_name]).values,
                 lower_bound=self.get_horizon(forecast[lower_bound_col_name]).values,
             )
-            core_columns = set(forecast.columns) - set(
-                [
-                    "y",
-                    "yhat1",
-                    upper_bound_col_name,
-                    lower_bound_col_name,
-                    "future_regressors_additive",
-                    "future_regressors_multiplicative",
-                ]
-            )
+            core_columns = set(forecast.columns) - {
+                "y",
+                "yhat1",
+                upper_bound_col_name,
+                lower_bound_col_name,
+                "future_regressors_additive",
+                "future_regressors_multiplicative",
+            }
             exog_variables = set(
                 filter(lambda x: x.startswith("future_regressor_"), list(core_columns))
             )
-            combine_terms = list(core_columns - exog_variables - set(["ds"]))
+            combine_terms = list(core_columns - exog_variables - {"ds"})
             temp_df = (
                 forecast[list(core_columns)]
                 .rename({"ds": "Date"}, axis=1)