oracle-ads 2.12.11__py3-none-any.whl → 2.13.1__py3-none-any.whl

ads/opctl/operator/common/utils.py

@@ -9,6 +9,7 @@ import os
 import sys
 import time
 import traceback
+import uuid
 from string import Template
 from typing import Any, Dict, List, Tuple
 
@@ -17,6 +18,7 @@ import yaml
 from cerberus import Validator
 
 from ads.opctl import logger, utils
+from ads.common.oci_logging import OCILog
 
 CONTAINER_NETWORK = "CONTAINER_NETWORK"
 
@@ -190,3 +192,17 @@ def print_traceback():
     if logger.level == logging.DEBUG:
         ex_type, ex, tb = sys.exc_info()
         traceback.print_tb(tb)
+
+
+def create_log_in_log_group(compartment_id, log_group_id, auth, log_name=None):
+    """
+    Creates a log within a given log group
+    """
+    if not log_name:
+        log_name = f"log-{int(time.time())}-{uuid.uuid4()}"
+    log = OCILog(display_name=log_name,
+                 log_group_id=log_group_id,
+                 compartment_id=compartment_id,
+                 **auth).create()
+    logger.info(f"Created log with log OCID {log.id}")
+    return log.id

ads/opctl/operator/lowcode/anomaly/const.py

@@ -1,14 +1,13 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
-from ads.common.extended_enum import ExtendedEnumMeta
+from ads.common.extended_enum import ExtendedEnum
 from ads.opctl.operator.lowcode.common.const import DataColumns
 
 
-class SupportedModels(str, metaclass=ExtendedEnumMeta):
+class SupportedModels(ExtendedEnum):
     """Supported anomaly models."""
 
     AutoTS = "autots"
@@ -38,7 +37,7 @@ class SupportedModels(str, metaclass=ExtendedEnumMeta):
     BOCPD = "bocpd"
 
 
-class NonTimeADSupportedModels(str, metaclass=ExtendedEnumMeta):
+class NonTimeADSupportedModels(ExtendedEnum):
     """Supported non time-based anomaly detection models."""
 
     OneClassSVM = "oneclasssvm"
@@ -48,7 +47,7 @@ class NonTimeADSupportedModels(str, metaclass=ExtendedEnumMeta):
     # DBScan = "dbscan"
 
 
-class TODSSubModels(str, metaclass=ExtendedEnumMeta):
+class TODSSubModels(ExtendedEnum):
     """Supported TODS sub models."""
 
     OCSVM = "ocsvm"
@@ -78,7 +77,7 @@ TODS_MODEL_MAP = {
 }
 
 
-class MerlionADModels(str, metaclass=ExtendedEnumMeta):
+class MerlionADModels(ExtendedEnum):
     """Supported Merlion AD sub models."""
 
     # point anomaly
@@ -126,7 +125,7 @@ MERLIONAD_MODEL_MAP = {
 }
 
 
-class SupportedMetrics(str, metaclass=ExtendedEnumMeta):
+class SupportedMetrics(ExtendedEnum):
     UNSUPERVISED_UNIFY95 = "unsupervised_unify95"
     UNSUPERVISED_UNIFY95_LOG_LOSS = "unsupervised_unify95_log_loss"
     UNSUPERVISED_N1_EXPERTS = "unsupervised_n-1_experts"
@@ -158,7 +157,7 @@ class SupportedMetrics(str, metaclass=ExtendedEnumMeta):
     ELAPSED_TIME = "Elapsed Time"
 
 
-class OutputColumns(str, metaclass=ExtendedEnumMeta):
+class OutputColumns(ExtendedEnum):
     ANOMALY_COL = "anomaly"
     SCORE_COL = "score"
     Series = DataColumns.Series

ads/opctl/operator/lowcode/common/data.py

@@ -19,13 +19,16 @@ from .transformations import Transformations
 
 
 class AbstractData(ABC):
-    def __init__(self, spec: dict, name="input_data"):
+    def __init__(self, spec, name="input_data", data=None):
         self.Transformations = Transformations
         self.data = None
         self._data_dict = dict()
         self.name = name
         self.spec = spec
-        self.load_transform_ingest_data(spec)
+        if data is not None:
+            self.data = data
+        else:
+            self.load_transform_ingest_data(spec)
 
     def get_raw_data_by_cat(self, category):
         mapping = self._data_transformer.get_target_category_columns_map()

ads/opctl/operator/lowcode/common/transformations.py

@@ -31,7 +31,6 @@ class Transformations(ABC):
             dataset_info : ForecastOperatorConfig
         """
         self.name = name
-        self.has_artificial_series = False
         self.dataset_info = dataset_info
         self.target_category_columns = dataset_info.target_category_columns
         self.target_column_name = dataset_info.target_column
@@ -136,7 +135,6 @@ class Transformations(ABC):
         self._target_category_columns_map = {}
         if not self.target_category_columns:
             df[DataColumns.Series] = "Series 1"
-            self.has_artificial_series = True
         else:
             df[DataColumns.Series] = merge_category_columns(
                 df, self.target_category_columns
@@ -209,7 +207,7 @@ class Transformations(ABC):
 
     def _missing_value_imputation_add(self, df):
         """
-        Function fills missing values in the pandas dataframe using liner interpolation
+        Function fills missing values with zero
 
         Parameters
         ----------
@@ -219,15 +217,7 @@ class Transformations(ABC):
         -------
             A new Pandas DataFrame without missing values.
         """
-        # find columns that all all NA and replace with 0
-        for col in df.columns:
-            # find next int not in list
-            i = 0
-            vals = df[col].unique()
-            while i in vals:
-                i = i + 1
-            df[col] = df[col].fillna(0)
-        return df
+        return df.fillna(0)
 
     def _outlier_treatment(self, df):
         """

ads/opctl/operator/lowcode/feature_store_marketplace/operator_utils.py

@@ -1,71 +1,66 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2024 Oracle and/or its affiliates.
+# Copyright (c) 2024, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import ast
 import base64
-from typing import Optional, List, Dict
+from typing import TYPE_CHECKING, Dict, List, Optional
 
 import oci
 import requests
-from typing import TYPE_CHECKING
 
 try:
     from kubernetes.client import (
-        V1ServiceStatus,
-        V1Service,
-        V1LoadBalancerStatus,
         V1LoadBalancerIngress,
+        V1LoadBalancerStatus,
+        V1Service,
+        V1ServiceStatus,
     )
 except ImportError:
     if TYPE_CHECKING:
         from kubernetes.client import (
-            V1ServiceStatus,
-            V1Service,
-            V1LoadBalancerStatus,
             V1LoadBalancerIngress,
+            V1LoadBalancerStatus,
+            V1Service,
+            V1ServiceStatus,
         )
 
-from oci.resource_manager.models import StackSummary, AssociatedResourceSummary
-
-from ads.opctl.operator.lowcode.feature_store_marketplace.models.apigw_config import (
-    APIGatewayConfig,
-)
+import click
+from oci.resource_manager.models import AssociatedResourceSummary, StackSummary
 
-from ads.common.oci_client import OCIClientFactory
-from ads.opctl.operator.lowcode.feature_store_marketplace.const import (
-    LISTING_ID,
-    APIGW_STACK_NAME,
-    STACK_URL,
-    NLB_RULES_ADDRESS,
-    NODES_RULES_ADDRESS,
-)
 from ads import logger
-import click
+from ads.common import auth as authutil
+from ads.common.oci_client import OCIClientFactory
 from ads.opctl import logger
-
 from ads.opctl.backend.marketplace.marketplace_utils import (
     Color,
     print_heading,
     print_ticker,
 )
-from ads.opctl.operator.lowcode.feature_store_marketplace.models.mysql_config import (
-    MySqlConfig,
+from ads.opctl.operator.lowcode.feature_store_marketplace.const import (
+    APIGW_STACK_NAME,
+    LISTING_ID,
+    NLB_RULES_ADDRESS,
+    NODES_RULES_ADDRESS,
+    STACK_URL,
+)
+from ads.opctl.operator.lowcode.feature_store_marketplace.models.apigw_config import (
+    APIGatewayConfig,
 )
-
 from ads.opctl.operator.lowcode.feature_store_marketplace.models.db_config import (
     DBConfig,
 )
-from ads.common import auth as authutil
+from ads.opctl.operator.lowcode.feature_store_marketplace.models.mysql_config import (
+    MySqlConfig,
+)
 
 
 def get_db_details() -> DBConfig:
     jdbc_url = "jdbc:mysql://{}/{}?createDatabaseIfNotExist=true"
     mysql_db_config = MySqlConfig()
     print_heading(
-        f"MySQL database configuration",
+        "MySQL database configuration",
         colors=[Color.BOLD, Color.BLUE],
         prefix_newline_count=2,
     )
@@ -76,12 +71,12 @@ def get_db_details() -> DBConfig:
             "Is password provided as plain-text or via a Vault secret?\n"
             "(https://docs.oracle.com/en-us/iaas/Content/KeyManagement/Concepts/keyoverview.htm)",
             type=click.Choice(MySqlConfig.MySQLAuthType.values()),
-            default=MySqlConfig.MySQLAuthType.BASIC.value,
+            default=MySqlConfig.MySQLAuthType.BASIC,
         )
     )
     if mysql_db_config.auth_type == MySqlConfig.MySQLAuthType.BASIC:
         basic_auth_config = MySqlConfig.BasicConfig()
-        basic_auth_config.password = click.prompt(f"Password", hide_input=True)
+        basic_auth_config.password = click.prompt("Password", hide_input=True)
         mysql_db_config.basic_config = basic_auth_config
 
     elif mysql_db_config.auth_type == MySqlConfig.MySQLAuthType.VAULT:
@@ -176,12 +171,12 @@ def detect_or_create_stack(apigw_config: APIGatewayConfig):
     ).data
 
     if len(stacks) >= 1:
-        print(f"Auto-detected feature store stack(s) in tenancy:")
+        print("Auto-detected feature store stack(s) in tenancy:")
         for stack in stacks:
             _print_stack_detail(stack)
     choices = {"1": "new", "2": "existing"}
     stack_provision_method = click.prompt(
-        f"Select stack provisioning method:\n1.Create new stack\n2.Existing stack\n",
+        "Select stack provisioning method:\n1.Create new stack\n2.Existing stack\n",
         type=click.Choice(list(choices.keys())),
         show_choices=False,
     )
@@ -240,20 +235,20 @@ def get_api_gw_details(compartment_id: str) -> APIGatewayConfig:
 
 
 def get_nlb_id_from_service(service: "V1Service", apigw_config: APIGatewayConfig):
-    status: "V1ServiceStatus" = service.status
-    lb_status: "V1LoadBalancerStatus" = status.load_balancer
-    lb_ingress: "V1LoadBalancerIngress" = lb_status.ingress[0]
+    status: V1ServiceStatus = service.status
+    lb_status: V1LoadBalancerStatus = status.load_balancer
+    lb_ingress: V1LoadBalancerIngress = lb_status.ingress[0]
     resource_client = OCIClientFactory(**authutil.default_signer()).create_client(
         oci.resource_search.ResourceSearchClient
     )
     search_details = oci.resource_search.models.FreeTextSearchDetails()
     search_details.matching_context_type = "NONE"
     search_details.text = lb_ingress.ip
-    resources: List[
-        oci.resource_search.models.ResourceSummary
-    ] = resource_client.search_resources(
-        search_details, tenant_id=apigw_config.root_compartment_id
-    ).data.items
+    resources: List[oci.resource_search.models.ResourceSummary] = (
+        resource_client.search_resources(
+            search_details, tenant_id=apigw_config.root_compartment_id
+        ).data.items
+    )
     private_ips = list(filter(lambda obj: obj.resource_type == "PrivateIp", resources))
     if len(private_ips) != 1:
         return click.prompt(
@@ -264,12 +259,12 @@ def get_nlb_id_from_service(service: "V1Service", apigw_config: APIGatewayConfig
         nlb_client = OCIClientFactory(**authutil.default_signer()).create_client(
             oci.network_load_balancer.NetworkLoadBalancerClient
         )
-        nlbs: List[
-            oci.network_load_balancer.models.NetworkLoadBalancerSummary
-        ] = nlb_client.list_network_load_balancers(
-            compartment_id=nlb_private_ip.compartment_id,
-            display_name=nlb_private_ip.display_name,
-        ).data.items
+        nlbs: List[oci.network_load_balancer.models.NetworkLoadBalancerSummary] = (
+            nlb_client.list_network_load_balancers(
+                compartment_id=nlb_private_ip.compartment_id,
+                display_name=nlb_private_ip.display_name,
+            ).data.items
+        )
         if len(nlbs) != 1:
             return click.prompt(
                 f"Please enter OCID of load balancer associated with ip: {lb_ingress.ip}"

ads/opctl/operator/lowcode/forecast/__main__.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import json
@@ -15,17 +14,17 @@ from ads.opctl import logger
 from ads.opctl.operator.common.const import ENV_OPERATOR_ARGS
 from ads.opctl.operator.common.utils import _parse_input_args
 
+from .model.forecast_datasets import ForecastDatasets, ForecastResults
 from .operator_config import ForecastOperatorConfig
-from .model.forecast_datasets import ForecastDatasets
 from .whatifserve import ModelDeploymentManager
 
 
-def operate(operator_config: ForecastOperatorConfig) -> None:
+def operate(operator_config: ForecastOperatorConfig) -> ForecastResults:
     """Runs the forecasting operator."""
     from .model.factory import ForecastOperatorModelFactory
 
     datasets = ForecastDatasets(operator_config)
-    ForecastOperatorModelFactory.get_model(
+    results = ForecastOperatorModelFactory.get_model(
         operator_config, datasets
     ).generate_report()
     # saving to model catalog
@@ -36,6 +35,7 @@ def operate(operator_config: ForecastOperatorConfig) -> None:
         if spec.what_if_analysis.model_deployment:
             mdm.create_deployment()
         mdm.save_deployment_info()
+    return results
 
 
 def verify(spec: Dict, **kwargs: Dict) -> bool:

ads/opctl/operator/lowcode/forecast/const.py

@@ -1,13 +1,13 @@
 #!/usr/bin/env python
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
-from ads.common.extended_enum import ExtendedEnumMeta
+from ads.common.extended_enum import ExtendedEnum
 from ads.opctl.operator.lowcode.common.const import DataColumns
 
 
-class SupportedModels(str, metaclass=ExtendedEnumMeta):
+class SupportedModels(ExtendedEnum):
     """Supported forecast models."""
 
     Prophet = "prophet"
@@ -19,7 +19,7 @@ class SupportedModels(str, metaclass=ExtendedEnumMeta):
     # Auto = "auto"
 
 
-class SpeedAccuracyMode(str, metaclass=ExtendedEnumMeta):
+class SpeedAccuracyMode(ExtendedEnum):
     """
     Enum representing different modes based on time taken and accuracy for explainability.
     """
@@ -35,7 +35,7 @@ class SpeedAccuracyMode(str, metaclass=ExtendedEnumMeta):
     ratio[AUTOMLX] = 0  # constant
 
 
-class SupportedMetrics(str, metaclass=ExtendedEnumMeta):
+class SupportedMetrics(ExtendedEnum):
     """Supported forecast metrics."""
 
     MAPE = "MAPE"
@@ -62,7 +62,7 @@ class SupportedMetrics(str, metaclass=ExtendedEnumMeta):
     ELAPSED_TIME = "Elapsed Time"
 
 
-class ForecastOutputColumns(str, metaclass=ExtendedEnumMeta):
+class ForecastOutputColumns(ExtendedEnum):
     """The column names for the forecast.csv output file"""
 
     DATE = "Date"

ads/opctl/operator/lowcode/forecast/model/arima.py

@@ -116,7 +116,10 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
                 lower_bound=self.get_horizon(forecast["yhat_lower"]).values,
             )
 
-            self.models[s_id] = model
+            self.models[s_id] = {}
+            self.models[s_id]["model"] = model
+            self.models[s_id]["le"] = self.le[s_id]
+            self.models[s_id]["predict_component_cols"] = X_pred.columns
 
             params = vars(model).copy()
             for param in ["arima_res_", "endog_index_"]:
@@ -163,7 +166,7 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
             sec5_text = rc.Heading("ARIMA Model Parameters", level=2)
             blocks = [
                 rc.Html(
-                    m.summary().as_html(),
+                    m['model'].summary().as_html(),
                     label=s_id if self.target_cat_col else None,
                 )
                 for i, (s_id, m) in enumerate(self.models.items())
@@ -251,7 +254,7 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
     def get_explain_predict_fn(self, series_id):
         def _custom_predict(
             data,
-            model=self.models[series_id],
+            model=self.models[series_id]["model"],
             dt_column_name=self.datasets._datetime_column_name,
             target_col=self.original_target_column,
         ):

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

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 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
@@ -56,8 +56,8 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         )
         return model_kwargs_cleaned, time_budget
 
-    def preprocess(self, data):  # TODO: re-use self.le for explanations
-        _, df_encoded = _label_encode_dataframe(
+    def preprocess(self, data, series_id):  # TODO: re-use self.le for explanations
+        self.le[series_id], df_encoded = _label_encode_dataframe(
             data,
             no_encode={self.spec.datetime_column.name, self.original_target_column},
         )
@@ -66,8 +66,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
     @runtime_dependency(
         module="automlx",
         err_msg=(
-            "Please run `pip3 install oracle-automlx>=23.4.1` and "
-            "`pip3 install oracle-automlx[forecasting]>=23.4.1` "
+            "Please run `pip3 install oracle-automlx[forecasting]>=25.1.1` "
             "to install the required dependencies for automlx."
         ),
     )
@@ -105,7 +104,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
             engine_opts = (
                 None
                 if engine_type == "local"
-                else ({"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},)
+                else {"ray_setup": {"_temp_dir": "/tmp/ray-temp"}}
             )
             init(
                 engine=engine_type,
@@ -125,7 +124,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 self.forecast_output.init_series_output(
                     series_id=s_id, data_at_series=df
                 )
-                data = self.preprocess(df)
+                data = self.preprocess(df, s_id)
                 data_i = self.drop_horizon(data)
                 X_pred = self.get_horizon(data).drop(target, axis=1)
 
@@ -157,7 +156,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                     target
                 ].values
 
-                self.models[s_id] = model
+                self.models[s_id] = {}
+                self.models[s_id]["model"] = model
+                self.models[s_id]["le"] = self.le[s_id]
 
                 # In case of Naive model, model.forecast function call does not return confidence intervals.
                 if f"{target}_ci_upper" not in summary_frame:
@@ -218,7 +219,8 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         other_sections = []
 
         if len(self.models) > 0:
-            for s_id, m in models.items():
+            for s_id, artifacts in models.items():
+                m = artifacts["model"]
                 selected_models[s_id] = {
                     "series_id": s_id,
                     "selected_model": m.selected_model_,
@@ -247,17 +249,17 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 self.explain_model()
 
                 global_explanation_section = None
-                if self.spec.explanations_accuracy_mode != SpeedAccuracyMode.AUTOMLX:
-                    # Convert the global explanation data to a DataFrame
-                    global_explanation_df = pd.DataFrame(self.global_explanation)
+                # Convert the global explanation data to a DataFrame
+                global_explanation_df = pd.DataFrame(self.global_explanation)
 
-                    self.formatted_global_explanation = (
-                        global_explanation_df / global_explanation_df.sum(axis=0) * 100
-                    )
-                    self.formatted_global_explanation = self.formatted_global_explanation.rename(
-                        {self.spec.datetime_column.name: ForecastOutputColumns.DATE},
-                        axis=1,
-                    )
+                self.formatted_global_explanation = (
+                    global_explanation_df / global_explanation_df.sum(axis=0) * 100
+                )
+
+                self.formatted_global_explanation.rename(
+                    columns={self.spec.datetime_column.name: ForecastOutputColumns.DATE},
+                    inplace=True,
+                )
 
                 aggregate_local_explanations = pd.DataFrame()
                 for s_id, local_ex_df in self.local_explanation.items():
@@ -269,11 +271,15 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 self.formatted_local_explanation = aggregate_local_explanations
 
                 if not self.target_cat_col:
-                    self.formatted_global_explanation = self.formatted_global_explanation.rename(
-                        {"Series 1": self.original_target_column},
-                        axis=1,
+                    self.formatted_global_explanation = (
+                        self.formatted_global_explanation.rename(
+                            {"Series 1": self.original_target_column},
+                            axis=1,
+                        )
+                    )
+                    self.formatted_local_explanation.drop(
+                        "Series", axis=1, inplace=True
                     )
-                    self.formatted_local_explanation.drop("Series", axis=1, inplace=True)
 
                 # Create a markdown section for the global explainability
                 global_explanation_section = rc.Block(
@@ -320,7 +326,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         )
 
     def get_explain_predict_fn(self, series_id):
-        selected_model = self.models[series_id]
+        selected_model = self.models[series_id]["model"]
 
         # If training date, use method below. If future date, use forecast!
         def _custom_predict_fn(
@@ -338,12 +344,12 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
             data[dt_column_name] = seconds_to_datetime(
                 data[dt_column_name], dt_format=self.spec.datetime_column.format
             )
-            data = self.preprocess(data)
+            data = self.preprocess(data, series_id)
             horizon_data = horizon_data.drop(target_col, axis=1)
             horizon_data[dt_column_name] = seconds_to_datetime(
                 horizon_data[dt_column_name], dt_format=self.spec.datetime_column.format
             )
-            horizon_data = self.preprocess(horizon_data)
+            horizon_data = self.preprocess(horizon_data, series_id)
 
             rows = []
             for i in range(data.shape[0]):
@@ -421,8 +427,10 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 if self.spec.explanations_accuracy_mode == SpeedAccuracyMode.AUTOMLX:
                     # Use the MLExplainer class from AutoMLx to generate explanations
                     explainer = automlx.MLExplainer(
-                        self.models[s_id],
-                        self.datasets.additional_data.get_data_for_series(series_id=s_id)
+                        self.models[s_id]["model"],
+                        self.datasets.additional_data.get_data_for_series(
+                            series_id=s_id
+                        )
                         .drop(self.spec.datetime_column.name, axis=1)
                         .head(-self.spec.horizon)
                         if self.spec.additional_data
@@ -433,7 +441,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
 
                     # Generate explanations for the forecast
                     explanations = explainer.explain_prediction(
-                        X=self.datasets.additional_data.get_data_for_series(series_id=s_id)
+                        X=self.datasets.additional_data.get_data_for_series(
+                            series_id=s_id
+                        )
                         .drop(self.spec.datetime_column.name, axis=1)
                         .tail(self.spec.horizon)
                         if self.spec.additional_data
@@ -445,7 +455,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                     explanations_df = pd.concat(
                         [exp.to_dataframe() for exp in explanations]
                     )
-                    explanations_df["row"] = explanations_df.groupby("Feature").cumcount()
+                    explanations_df["row"] = explanations_df.groupby(
+                        "Feature"
+                    ).cumcount()
                     explanations_df = explanations_df.pivot(
                         index="row", columns="Feature", values="Attribution"
                     )
@@ -453,9 +465,27 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
 
                     # Store the explanations in the local_explanation dictionary
                     self.local_explanation[s_id] = explanations_df
+
+                    self.global_explanation[s_id] = dict(
+                        zip(
+                            self.local_explanation[s_id].columns,
+                            np.nanmean(np.abs(self.local_explanation[s_id]), axis=0),
+                        )
+                    )
                 else:
                     # Fall back to the default explanation generation method
                     super().explain_model()
             except Exception as e:
-                logger.warning(f"Failed to generate explanations for series {s_id} with error: {e}.")
+                if s_id in self.errors_dict:
+                    self.errors_dict[s_id]["explainer_error"] = str(e)
+                    self.errors_dict[s_id]["explainer_error_trace"] = traceback.format_exc()
+                else:
+                    self.errors_dict[s_id] = {
+                        "model_name": self.spec.model,
+                        "explainer_error": str(e),
+                        "explainer_error_trace": traceback.format_exc(),
+                    }
+                logger.warning(
+                    f"Failed to generate explanations for series {s_id} with error: {e}."
+                )
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")