oracle-ads 2.11.6__py3-none-any.whl → 2.11.8__py3-none-any.whl

ads/cli.py

@@ -8,8 +8,8 @@ import traceback
 import sys
 
 import fire
+from dataclasses import is_dataclass
 from ads.common import logger
-from ads.aqua.cli import AquaCommand
 
 try:
     import click
@@ -71,9 +71,28 @@ def _SeparateFlagArgs(args):
 fire.core.parser.SeparateFlagArgs = _SeparateFlagArgs
 
 
+def serialize(data):
+    """Serialize dataclass objects or lists of dataclass objects.
+    Parameters:
+        data: A dataclass object or a list of dataclass objects.
+    Returns:
+        None
+    Prints:
+        The string representation of each dataclass object.
+    """
+    if isinstance(data, list):
+        [print(str(item)) for item in data]
+    else:
+        print(str(data))
+
+
 def cli():
     if len(sys.argv) > 1 and sys.argv[1] == "aqua":
-        fire.Fire(AquaCommand, command=sys.argv[2:], name="ads aqua")
+        from ads.aqua.cli import AquaCommand
+
+        fire.Fire(
+            AquaCommand, command=sys.argv[2:], name="ads aqua", serialize=serialize
+        )
     else:
         click_cli()
 

ads/common/serializer.py

@@ -195,7 +195,10 @@ class Serializable(ABC):
             `None` in case when `uri` provided.
         """
         json_string = json.dumps(
-            self.to_dict(**kwargs), cls=encoder, default=default or self.serialize
+            self.to_dict(**kwargs),
+            cls=encoder,
+            default=default or self.serialize,
+            indent=4,
         )
         if uri:
             self._write_to_file(s=json_string, uri=uri, **kwargs)
@@ -463,9 +466,7 @@ class DataClassSerializable(Serializable):
                 "These fields will be ignored."
             )
 
-        obj = cls(
-            **{key: obj_dict.get(key) for key in allowed_fields if key in obj_dict}
-        )
+        obj = cls(**{key: obj_dict.get(key) for key in allowed_fields})
 
         for key, value in obj_dict.items():
             if (

ads/common/utils.py

@@ -102,6 +102,8 @@ DIMENSION = 2
 # The number of worker processes to use in parallel for uploading individual parts of a multipart upload.
 DEFAULT_PARALLEL_PROCESS_COUNT = 9
 
+LOG_LEVELS = ["NOTSET", "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"]
+
 
 class FileOverwriteError(Exception):  # pragma: no cover
     pass
@@ -1751,7 +1753,7 @@ def get_log_links(
 ) -> str:
     """
     This method returns the web console link for the given log ids.
-    
+
     Parameters
     ----------
     log_group_id: str, required
@@ -1776,7 +1778,9 @@ def get_log_links(
         query_range = f'''search "{compartment_id}/{log_group_id}/{log_id}"'''
         query_source = f"source='{source_id}'"
         sort_condition = f"sort by datetime desc&regions={region}"
-        search_query = f"search?searchQuery={query_range} | {query_source} | {sort_condition}"
+        search_query = (
+            f"search?searchQuery={query_range} | {query_source} | {sort_condition}"
+        )
         console_link_url = f"https://cloud.oracle.com/logging/{search_query}"
     elif log_group_id:
         console_link_url = f"https://cloud.oracle.com/logging/log-groups/{log_group_id}?region={region}"

ads/config.py

@@ -79,6 +79,7 @@ AQUA_TELEMETRY_BUCKET = os.environ.get(
     "AQUA_TELEMETRY_BUCKET", "service-managed-models"
 )
 AQUA_TELEMETRY_BUCKET_NS = os.environ.get("AQUA_TELEMETRY_BUCKET_NS", CONDA_BUCKET_NS)
+
 DEBUG_TELEMETRY = os.environ.get("DEBUG_TELEMETRY", None)
 AQUA_SERVICE_NAME = "aqua"
 DATA_SCIENCE_SERVICE_NAME = "data-science"

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

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)

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):

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])

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

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:

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.

ads/llm/serializers/runnable_parallel.py

@@ -1,3 +1,9 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 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 langchain.schema.runnable import RunnableParallel
 from langchain.load.dump import dumpd
 from langchain.load.load import load
@@ -10,7 +16,7 @@ class RunnableParallelSerializer:
 
     @staticmethod
     def load(config: dict, **kwargs):
-        steps = config["kwargs"]["steps"]
+        steps = config.get("kwargs", dict()).get("steps", dict())
         steps = {k: load(v, **kwargs) for k, v in steps.items()}
         return RunnableParallel(**steps)
 

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 = {

ads/opctl/operator/lowcode/anomaly/README.md

@@ -35,7 +35,7 @@ All generated configurations should be ready to use without the need for any add
 To run anomaly detection locally, create and activate a new conda environment (`ads-anomaly`). Install all the required libraries listed in the `environment.yaml` file.
 
 ```yaml
-- datapane
+- report-creator
 - cerberus
 - oracle-automlx==23.4.1
 - oracle-automlx[classic]==23.4.1

ads/opctl/operator/lowcode/anomaly/environment.yaml

@@ -5,7 +5,7 @@ dependencies:
   - python=3.8
   - pip
   - pip:
-      - datapane
+      - report-creator
       - cerberus
       - oracle-automlx==23.4.1
       - oracle-automlx[classic]==23.4.1

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,

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

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# 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 pandas as pd
@@ -26,8 +26,14 @@ 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
@@ -67,21 +73,21 @@ class AutoMLXOperatorModel(AnomalyOperatorBaseModel):
         return anomaly_output
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
 
         """The method that needs to be implemented on the particular model level."""
-        selected_models_text = dp.Text(
-            f"## Selected Models Overview \n "
-            "The following tables provide information regarding the chosen model."
-        )
-        all_sections = [selected_models_text]
+        other_sections = [
+            rc.Heading("Selected Models Overview", level=2),
+            rc.Text(
+                "The following tables provide information regarding the chosen model."
+            ),
+        ]
 
-        model_description = dp.Text(
+        model_description = rc.Text(
             "The automlx model automatically pre-processes, selects and engineers "
             "high-quality features in your dataset, which then given to an automatically "
             "chosen and optimized machine learning model.."
         )
-        other_sections = all_sections
 
         return (
             model_description,

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

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# 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 pandas as pd
@@ -81,21 +81,20 @@ class AutoTSOperatorModel(AnomalyOperatorBaseModel):
         return anomaly_output
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
 
         """The method that needs to be implemented on the particular model level."""
-        selected_models_text = dp.Text(
-            f"## Selected Models Overview \n "
-            "The following tables provide information regarding the chosen model."
-        )
-        all_sections = [selected_models_text]
-
-        model_description = dp.Text(
+        other_sections = [
+            rc.Heading("Selected Models Overview", level=2),
+            rc.Text(
+                "The following tables provide information regarding the chosen model."
+            ),
+        ]
+        model_description = rc.Text(
             "The automlx model automatically pre-processes, selects and engineers "
             "high-quality features in your dataset, which then given to an automatically "
             "chosen and optimized machine learning model.."
         )
-        other_sections = all_sections
 
         return (
             model_description,