oracle-ads 2.11.5__tar.gz → 2.11.7__tar.gz

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: oracle_ads
-Version: 2.11.5
+Version: 2.11.7
 Summary: Oracle Accelerated Data Science SDK
 Keywords: Oracle Cloud Infrastructure,OCI,Machine Learning,ML,Artificial Intelligence,AI,Data Science,Cloud,Oracle
 Author: Oracle Data Science
@@ -80,7 +80,8 @@ Requires-Dist: oracledb ; extra == "forecast"
 Requires-Dist: geopandas ; extra == "geo"
 Requires-Dist: oracle_ads[viz] ; extra == "geo"
 Requires-Dist: transformers ; extra == "huggingface"
-Requires-Dist: langchain>=0.1.10 ; extra == "llm"
+Requires-Dist: langchain-community<0.0.32 ; extra == "llm"
+Requires-Dist: langchain>=0.1.10,<0.1.14 ; extra == "llm"
 Requires-Dist: evaluate>=0.4.0 ; extra == "llm"
 Requires-Dist: ipython>=7.23.1, <8.0 ; extra == "notebook"
 Requires-Dist: ipywidgets~=7.6.3 ; extra == "notebook"
@@ -357,5 +358,5 @@ Consult the security guide [SECURITY.md](https://github.com/oracle/accelerated-d
 
 ## License
 
-Copyright (c) 2020, 2022 Oracle and/or its affiliates. Licensed under the [Universal Permissive License v1.0](https://oss.oracle.com/licenses/upl/)
+Copyright (c) 2020, 2024 Oracle and/or its affiliates. Licensed under the [Universal Permissive License v1.0](https://oss.oracle.com/licenses/upl/)
 

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/README.md

@@ -181,4 +181,4 @@ Consult the security guide [SECURITY.md](https://github.com/oracle/accelerated-d
 
 ## License
 
-Copyright (c) 2020, 2022 Oracle and/or its affiliates. Licensed under the [Universal Permissive License v1.0](https://oss.oracle.com/licenses/upl/)
+Copyright (c) 2020, 2024 Oracle and/or its affiliates. Licensed under the [Universal Permissive License v1.0](https://oss.oracle.com/licenses/upl/)

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/aqua/utils.py

@@ -268,9 +268,12 @@ def is_valid_ocid(ocid: str) -> bool:
     bool:
         Whether the given ocid is valid.
     """
-    pattern = r"^ocid1\.([a-z0-9_]+)\.([a-z0-9]+)\.([a-z0-9]*)(\.[^.]+)?\.([a-z0-9_]+)$"
+    # TODO: revisit pattern
+    pattern = (
+        r"^ocid1\.([a-z0-9_]+)\.([a-z0-9]+)\.([a-z0-9-]*)(\.[^.]+)?\.([a-z0-9_]+)$"
+    )
     match = re.match(pattern, ocid)
-    return bool(match)
+    return True
 
 
 def get_resource_type(ocid: str) -> str:

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/catalog/model.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2020, 2023 Oracle and/or its affiliates.
+# Copyright (c) 2020, 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 warnings
@@ -404,13 +404,13 @@ class Model:
     def _repr_html_(self):
         """Shows model in dataframe format."""
         return (
-            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).render()
+            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).to_html()
         )
 
     def __repr__(self):
         """Shows model in dataframe format."""
         return (
-            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).render()
+            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).to_html()
         )
 
     def activate(self) -> None:

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/catalog/notebook.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2020, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2020, 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 warnings
@@ -220,7 +220,7 @@ class NotebookCatalog:
                 lambda x: "<a href='%s'>%s</a>"
                 % (x if x.startswith("http") else "http://%s" % x, "open")
             )
-            return df.style.set_properties(**{"margin-left": "0px"}).render()
+            return df.style.set_properties(**{"margin-left": "0px"}).to_html()
 
         notebook.commit = MethodType(commit, notebook)
         notebook.rollback = MethodType(rollback, notebook)
@@ -295,7 +295,7 @@ class NotebookCatalog:
         shape=None,
         block_storage_size_in_gbs=None,
         subnet_id=None,
-        **kwargs
+        **kwargs,
     ):
         """
         Create a new notebook session with the supplied details.

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/catalog/project.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2020, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2020, 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 warnings
@@ -237,7 +237,7 @@ class ProjectCatalog(Mapping):
             return (
                 project_self.to_dataframe()
                 .style.set_properties(**{"margin-left": "0px"})
-                .render()
+                .to_html()
             )
 
         project.commit = MethodType(commit, project)

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/catalog/summary.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2020, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2020, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from __future__ import print_function, absolute_import
@@ -98,7 +98,6 @@ class SummaryList(list, metaclass=ABCMeta):
         pass
 
     def to_dataframe(self, datetime_format=None):
-
         """
         Returns the model catalog summary as a pandas dataframe
 
@@ -121,7 +120,6 @@ class SummaryList(list, metaclass=ABCMeta):
 
     @runtime_dependency(module="IPython", install_from=OptionalDependency.NOTEBOOK)
     def show_in_notebook(self, datetime_format=None):
-
         """
         Displays the model catalog summary in a Jupyter Notebook cell
 
@@ -144,7 +142,7 @@ class SummaryList(list, metaclass=ABCMeta):
     def _repr_html_(self):
         return self.df.style.applymap(
             self._color_lifecycle_state, subset=["lifecycle_state"]
-        ).render()
+        ).to_html()
 
     def _sort_by(self, cols, reverse=False):
         return sorted(

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/cli.py

@@ -9,7 +9,6 @@ import sys
 
 import fire
 from ads.common import logger
-from ads.aqua.cli import AquaCommand
 
 try:
     import click
@@ -73,6 +72,8 @@ fire.core.parser.SeparateFlagArgs = _SeparateFlagArgs
 
 def cli():
     if len(sys.argv) > 1 and sys.argv[1] == "aqua":
+        from ads.aqua.cli import AquaCommand
+
         fire.Fire(AquaCommand, command=sys.argv[2:], name="ads aqua")
     else:
         click_cli()

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/common/serializer.py

@@ -464,7 +464,7 @@ class DataClassSerializable(Serializable):
             )
 
         obj = cls(
-            **{key: obj_dict.get(key) for key in allowed_fields if key in obj_dict}
+            **{key: obj_dict.get(key) for key in allowed_fields}
         )
 
         for key, value in obj_dict.items():

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/data_labeling/metadata.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2021, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2021, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from dataclasses import asdict, dataclass, field
@@ -75,7 +75,7 @@ class Metadata(DataClassSerializable):
     def _repr_html_(self):
         """Shows metadata in dataframe format."""
         return (
-            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).render()
+            self.to_dataframe().style.set_properties(**{"margin-left": "0px"}).to_html()
         )
 
     @classmethod

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/dataset/dataset.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2020, 2023 Oracle and/or its affiliates.
+# Copyright (c) 2020, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from __future__ import print_function, absolute_import, division
@@ -85,7 +85,6 @@ class ADSDataset(PandasDataset):
         interactive=False,
         **kwargs,
     ):
-
         #
         # to keep performance high and linear no matter the size of the distributed dataset we
         # create a pandas df that's used internally because this has a fixed upper size.
@@ -204,7 +203,7 @@ class ADSDataset(PandasDataset):
                     .style.set_table_styles(utils.get_dataframe_styles())
                     .set_table_attributes("class=table")
                     .hide_index()
-                    .render()
+                    .to_html()
                 )
             )
         )
@@ -263,7 +262,7 @@ class ADSDataset(PandasDataset):
                             self.style.set_table_styles(utils.get_dataframe_styles())
                             .set_table_attributes("class=table")
                             .hide_index()
-                            .render()
+                            .to_html()
                         )
                     )
                 )
@@ -1265,7 +1264,6 @@ class ADSDataset(PandasDataset):
         n=None,
         **init_kwargs,
     ):
-
         prev_doc_mode = utils.is_documentation_mode()
 
         set_documentation_mode(False)

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/dataset/factory.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2020, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2020, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from __future__ import print_function, absolute_import
@@ -367,7 +367,7 @@ class DatasetFactory:
                 HTML(
                     list_df.style.set_table_attributes("class=table")
                     .hide_index()
-                    .render()
+                    .to_html()
                 )
             )
         return list_df
@@ -884,7 +884,6 @@ class CustomFormatReaders:
         import xml.etree.cElementTree as et
 
         def get_children(df, node, parent, i):
-
             for name in node.attrib.keys():
                 df.at[i, parent + name] = node.attrib[name]
             for child in list(node):

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/dataset/label_encoder.py

@@ -52,7 +52,7 @@ class DataFrameLabelEncoder(TransformerMixin):
 
         """
         for column in X.columns:
-            if X[column].dtype.name in ["object", "category"]:
+            if X[column].dtype.name in ["object", "category", "bool"]:
                 X[column] = X[column].astype(str)
                 self.label_encoders[column] = LabelEncoder()
                 self.label_encoders[column].fit(X[column])

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/dataset/sampled_dataset.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
 
-# Copyright (c) 2020, 2022 Oracle and/or its affiliates.
+# Copyright (c) 2020, 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 matplotlib
@@ -49,6 +49,7 @@ from ads.common.decorator.runtime_dependency import (
 
 NATURAL_EARTH_DATASET = "naturalearth_lowres"
 
+
 class PandasDataset(object):
     """
     This class provides APIs that can work on a sampled dataset.
@@ -107,7 +108,6 @@ class PandasDataset(object):
         self.sampled_df = self.sampled_df.reset_index(drop=True)
 
     def _find_feature_subset(self, df, target_name, include_n_features=32):
-
         if len(df.columns) <= include_n_features:
             return self.sampled_df
         else:
@@ -212,7 +212,6 @@ class PandasDataset(object):
     def _generate_features_html(
         self, is_wide_dataset, n_features, df_stats, visualizations_follow
     ):
-
         html = utils.get_bootstrap_styles()
 
         if is_wide_dataset:
@@ -233,7 +232,7 @@ class PandasDataset(object):
                 if ("float" in str(type(x))) or ("int" in str(type(x)))
                 else x
             )
-            .render()
+            .to_html()
         )
 
         if visualizations_follow:
@@ -244,7 +243,6 @@ class PandasDataset(object):
     def _generate_warnings_html(
         self, is_wide_dataset, n_rows, n_features, df_stats, out, accordion
     ):
-
         #
         # create the "Warnings" accordion section:
         #  - show high cardinal categoricals

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/jobs/ads_job.py

@@ -10,6 +10,7 @@ from urllib.parse import urlparse
 
 import fsspec
 import oci
+import yaml
 from ads.common.auth import default_signer
 from ads.common.decorator.utils import class_or_instance_method
 from ads.jobs.builders.base import Builder
@@ -263,6 +264,9 @@ class Job(Builder):
             Job runtime, by default None.
 
         """
+        # Saves a copy of the auth object from the class to the instance.
+        # Future changes to the class level Job.auth will not affect the auth of existing instances.
+        self.auth = self.auth.copy()
         for key in ["config", "signer", "client_kwargs"]:
             if kwargs.get(key):
                 self.auth[key] = kwargs.pop(key)
@@ -545,6 +549,26 @@ class Job(Builder):
             "spec": spec,
         }
 
+    @class_or_instance_method
+    def from_yaml(
+        cls,
+        yaml_string: str = None,
+        uri: str = None,
+        loader: callable = yaml.SafeLoader,
+        **kwargs,
+    ):
+        if inspect.isclass(cls):
+            job = cls(**cls.auth)
+        else:
+            job = cls.__class__(**cls.auth)
+
+        if yaml_string:
+            return job.from_dict(yaml.load(yaml_string, Loader=loader))
+        if uri:
+            yaml_dict = yaml.load(cls._read_from_file(uri=uri, **kwargs), Loader=loader)
+            return job.from_dict(yaml_dict)
+        raise ValueError("Must provide either YAML string or URI location")
+
     @class_or_instance_method
     def from_dict(cls, config: dict) -> "Job":
         """Initializes a job from a dictionary containing the configurations.
@@ -573,9 +597,9 @@ class Job(Builder):
             "runtime": cls._RUNTIME_MAPPING,
         }
         if inspect.isclass(cls):
-            job = cls()
+            job = cls(**cls.auth)
         else:
-            job = cls.__class__()
+            job = cls.__class__(**cls.auth)
 
         for key, value in spec.items():
             if key in mappings:

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/jobs/builders/infrastructure/dsc_job.py

@@ -6,8 +6,8 @@
 from __future__ import annotations
 
 import datetime
+import inspect
 import logging
-import oci
 import os
 import time
 import traceback
@@ -17,11 +17,12 @@ from string import Template
 from typing import Any, Dict, List, Optional, Union
 
 import fsspec
+import oci
 import oci.data_science
 import oci.util as oci_util
-import yaml
 from oci.data_science.models import JobInfrastructureConfigurationDetails
 from oci.exceptions import ServiceError
+import yaml
 from ads.common import utils
 from ads.common.oci_datascience import DSCNotebookSession, OCIDataScienceMixin
 from ads.common.oci_logging import OCILog
@@ -782,7 +783,7 @@ class DataScienceJobRun(
         # Update runtime from job run
         from ads.jobs import Job
 
-        job = Job.from_dict(job_dict)
+        job = Job(**self.auth).from_dict(job_dict)
         envs = job.runtime.envs
         run_config_override = run_dict.get("jobConfigurationOverrideDetails", {})
         envs.update(run_config_override.get("environmentVariables", {}))
@@ -811,7 +812,7 @@ class DataScienceJobRun(
         """
         from ads.jobs import Job
 
-        return Job.from_datascience_job(self.job_id)
+        return Job(**self.auth).from_datascience_job(self.job_id)
 
     def download(self, to_dir):
         """Downloads files from job run output URI to local.
@@ -953,9 +954,9 @@ class DataScienceJob(Infrastructure):
             if key not in attribute_map and key.lower() in snake_to_camel_map:
                 value = spec.pop(key)
                 if isinstance(value, dict):
-                    spec[
-                        snake_to_camel_map[key.lower()]
-                    ] = DataScienceJob.standardize_spec(value)
+                    spec[snake_to_camel_map[key.lower()]] = (
+                        DataScienceJob.standardize_spec(value)
+                    )
                 else:
                     spec[snake_to_camel_map[key.lower()]] = value
         return spec
@@ -971,6 +972,9 @@ class DataScienceJob(Infrastructure):
             Specification as keyword arguments.
             If spec contains the same key as the one in kwargs, the value from kwargs will be used.
         """
+        # Saves a copy of the auth object from the class to the instance.
+        # Future changes to the class level Job.auth will not affect the auth of existing instances.
+        self.auth = self.auth.copy()
         for key in ["config", "signer", "client_kwargs"]:
             if kwargs.get(key):
                 self.auth[key] = kwargs.pop(key)
@@ -1710,6 +1714,15 @@ class DataScienceJob(Infrastructure):
         """
         return cls.from_dsc_job(DSCJob(**cls.auth).from_ocid(job_id))
 
+    @class_or_instance_method
+    def from_dict(cls, obj_dict: dict):
+        """Initialize the object from a Python dictionary"""
+        if inspect.isclass(cls):
+            job_cls = cls
+        else:
+            job_cls = cls.__class__
+        return job_cls(spec=obj_dict.get("spec"), **cls.auth)
+
     @class_or_instance_method
     def list_jobs(cls, compartment_id: str = None, **kwargs) -> List[DataScienceJob]:
         """Lists all jobs in a compartment.

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/model/model_artifact_boilerplate/artifact_introspection_test/model_artifact_validate.py

@@ -29,7 +29,7 @@ _cwd = os.path.dirname(__file__)
 TESTS_PATH = os.path.join(_cwd, "resources", "tests.yaml")
 HTML_PATH = os.path.join(_cwd, "resources", "template.html")
 CONFIG_PATH = os.path.join(_cwd, "resources", "config.yaml")
-PYTHON_VER_PATTERN = "^([3])(\.[6-9])(\.\d+)?$"
+PYTHON_VER_PATTERN = "^([3])(\.([6-9]|1[0-2]))(\.\d+)?$"
 PAR_URL = "https://objectstorage.us-ashburn-1.oraclecloud.com/p/WyjtfVIG0uda-P3-2FmAfwaLlXYQZbvPZmfX1qg0-sbkwEQO6jpwabGr2hMDBmBp/n/ociodscdev/b/service-conda-packs/o/service_pack/index.json"
 
 TESTS = {

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/anomaly/model/anomaly_dataset.py

@@ -10,7 +10,6 @@ from ads.opctl.operator.lowcode.common.utils import (
     merge_category_columns,
 )
 from ads.opctl.operator.lowcode.common.data import AbstractData
-from ads.opctl.operator.lowcode.common.data import AbstractData
 from ads.opctl.operator.lowcode.anomaly.utils import get_frequency_of_datetime
 from ads.opctl import logger
 import pandas as pd
@@ -56,6 +55,10 @@ class AnomalyDatasets:
             self.X_valid_dict = self.valid_data.X_valid_dict
             self.y_valid_dict = self.valid_data.y_valid_dict
 
+    # Returns raw data based on the series_id i.e; the merged target_category_column value
+    def get_raw_data_by_cat(self, category):
+        return self._data.get_raw_data_by_cat(category)
+
 
 class AnomalyOutput:
     def __init__(self, date_column):
@@ -94,38 +97,28 @@ class AnomalyOutput:
             outliers = pd.merge(outliers, scores, on=self.date_column, how="inner")
         return outliers
 
-    def get_inliers(self, data):
+    def get_inliers(self, datasets):
         inliers = pd.DataFrame()
 
         for category in self.list_categories():
             inliers = pd.concat(
                 [
                     inliers,
-                    self.get_inliers_by_cat(
-                        category,
-                        data[data[OutputColumns.Series] == category]
-                        .reset_index(drop=True)
-                        .drop(OutputColumns.Series, axis=1),
-                    ),
+                    self.get_inliers_by_cat(category, datasets.get_raw_data_by_cat(category)),
                 ],
                 axis=0,
                 ignore_index=True,
             )
         return inliers
 
-    def get_outliers(self, data):
+    def get_outliers(self, datasets):
         outliers = pd.DataFrame()
 
         for category in self.list_categories():
             outliers = pd.concat(
                 [
                     outliers,
-                    self.get_outliers_by_cat(
-                        category,
-                        data[data[OutputColumns.Series] == category]
-                        .reset_index(drop=True)
-                        .drop(OutputColumns.Series, axis=1),
-                    ),
+                    self.get_outliers_by_cat(category, datasets.get_raw_data_by_cat(category)),
                 ],
                 axis=0,
                 ignore_index=True,

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/anomaly/model/automlx.py

@@ -26,8 +26,9 @@ class AutoMLXOperatorModel(AnomalyOperatorBaseModel):
     )
     def _build_model(self) -> pd.DataFrame:
         from automlx import init
+        import logging
         try:
-            init(engine="ray", engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}})
+            init(engine="ray", engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}}, loglevel=logging.CRITICAL)
         except Exception as e:
             logger.info("Ray already initialized")
         date_column = self.spec.datetime_column.name

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/anomaly/model/base_model.py

@@ -272,7 +272,7 @@ class AnomalyOperatorBaseModel(ABC):
                     f2.write(f1.read())
 
         if self.spec.generate_inliers:
-            inliers = anomaly_output.get_inliers(self.datasets.data)
+            inliers = anomaly_output.get_inliers(self.datasets)
             write_data(
                 data=inliers,
                 filename=os.path.join(unique_output_dir, self.spec.inliers_filename),
@@ -280,7 +280,7 @@ class AnomalyOperatorBaseModel(ABC):
                 storage_options=storage_options,
             )
 
-        outliers = anomaly_output.get_outliers(self.datasets.data)
+        outliers = anomaly_output.get_outliers(self.datasets)
         write_data(
             data=outliers,
             filename=os.path.join(unique_output_dir, self.spec.outliers_filename),

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/anomaly/operator_config.py

@@ -36,6 +36,21 @@ class TestData(InputData):
     """Class representing operator specification test data details."""
 
 
+@dataclass(repr=True)
+class PreprocessingSteps(DataClassSerializable):
+    """Class representing preprocessing steps for operator."""
+
+    missing_value_imputation: bool = True
+    outlier_treatment: bool = False
+
+
+@dataclass(repr=True)
+class DataPreprocessor(DataClassSerializable):
+    """Class representing operator specification preprocessing details."""
+
+    enabled: bool = True
+    steps: PreprocessingSteps = field(default_factory=PreprocessingSteps)
+
 @dataclass(repr=True)
 class AnomalyOperatorSpec(DataClassSerializable):
     """Class representing operator specification."""
@@ -74,7 +89,9 @@ class AnomalyOperatorSpec(DataClassSerializable):
             self.generate_inliers if self.generate_inliers is not None else False
         )
         self.model_kwargs = self.model_kwargs or dict()
-
+        self.preprocessing = (
+            self.preprocessing if self.preprocessing is not None else DataPreprocessor(enabled=True)
+        )
 
 @dataclass(repr=True)
 class AnomalyOperatorConfig(OperatorConfig):

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/anomaly/schema.yaml

@@ -307,11 +307,23 @@ spec:
         description: "When provided, target_category_columns [list] indexes the data into multiple related datasets for anomaly detection"
 
     preprocessing:
-      type: boolean
+      type: dict
       required: false
-      default: true
-      meta:
-        description: "preprocessing and feature engineering can be disabled using this flag, Defaults to true"
+      schema:
+        enabled:
+          type: boolean
+          required: false
+          default: true
+          meta:
+            description: "preprocessing and feature engineering can be disabled using this flag, Defaults to true"
+        steps:
+          type: dict
+          required: false
+          schema:
+            missing_value_imputation:
+              type: boolean
+              required: false
+              default: true
 
     generate_report:
       type: boolean

{oracle_ads-2.11.5 → oracle_ads-2.11.7}/ads/opctl/operator/lowcode/common/data.py

@@ -16,6 +16,7 @@ from ads.opctl.operator.lowcode.common.errors import (
     DataMismatchError,
 )
 from abc import ABC
+import pandas as pd
 
 
 class AbstractData(ABC):
@@ -26,6 +27,19 @@ class AbstractData(ABC):
         self.name = name
         self.load_transform_ingest_data(spec)
 
+    def get_raw_data_by_cat(self, category):
+        mapping = self._data_transformer.get_target_category_columns_map()
+        # For given category, mapping gives the target_category_columns and it's values.
+        # condition filters raw_data based on the values of target_category_columns for the given category
+        condition = pd.Series(True, index=self.raw_data.index)
+        if category in mapping:
+            for col, val in mapping[category].items():
+                condition &= (self.raw_data[col] == val)
+        data_by_cat = self.raw_data[condition].reset_index(drop=True)
+        data_by_cat = self._data_transformer._format_datetime_col(data_by_cat)
+        return data_by_cat
+
+
     def get_dict_by_series(self):
         if not self._data_dict:
             for s_id in self.list_series_ids():
@@ -73,8 +87,8 @@ class AbstractData(ABC):
         return data
 
     def load_transform_ingest_data(self, spec):
-        raw_data = self._load_data(getattr(spec, self.name))
-        self.data = self._transform_data(spec, raw_data)
+        self.raw_data = self._load_data(getattr(spec, self.name))
+        self.data = self._transform_data(spec, self.raw_data)
         self._ingest_data(spec)
 
     def _ingest_data(self, spec):