oracle-ads 2.12.7__tar.gz → 2.12.8__tar.gz

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: oracle_ads
-Version: 2.12.7
+Version: 2.12.8
 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

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/aqua/modeldeployment/deployment.py

@@ -185,7 +185,7 @@ class AquaDeploymentApp(AquaApp):
                 tags[tag] = aqua_model.freeform_tags[tag]
 
         tags.update({Tags.AQUA_MODEL_NAME_TAG: aqua_model.display_name})
-        tags.update({Tags.TASK: aqua_model.freeform_tags.get(Tags.TASK, None)})
+        tags.update({Tags.TASK: aqua_model.freeform_tags.get(Tags.TASK, UNKNOWN)})
 
         # Set up info to get deployment config
         config_source_id = model_id
@@ -533,16 +533,22 @@ class AquaDeploymentApp(AquaApp):
         return results
 
     @telemetry(entry_point="plugin=deployment&action=delete", name="aqua")
-    def delete(self,model_deployment_id:str):
-        return self.ds_client.delete_model_deployment(model_deployment_id=model_deployment_id).data
+    def delete(self, model_deployment_id: str):
+        return self.ds_client.delete_model_deployment(
+            model_deployment_id=model_deployment_id
+        ).data
 
-    @telemetry(entry_point="plugin=deployment&action=deactivate",name="aqua")
-    def deactivate(self,model_deployment_id:str):
-        return self.ds_client.deactivate_model_deployment(model_deployment_id=model_deployment_id).data
+    @telemetry(entry_point="plugin=deployment&action=deactivate", name="aqua")
+    def deactivate(self, model_deployment_id: str):
+        return self.ds_client.deactivate_model_deployment(
+            model_deployment_id=model_deployment_id
+        ).data
 
-    @telemetry(entry_point="plugin=deployment&action=activate",name="aqua")
-    def activate(self,model_deployment_id:str):
-        return self.ds_client.activate_model_deployment(model_deployment_id=model_deployment_id).data
+    @telemetry(entry_point="plugin=deployment&action=activate", name="aqua")
+    def activate(self, model_deployment_id: str):
+        return self.ds_client.activate_model_deployment(
+            model_deployment_id=model_deployment_id
+        ).data
 
     @telemetry(entry_point="plugin=deployment&action=get", name="aqua")
     def get(self, model_deployment_id: str, **kwargs) -> "AquaDeploymentDetail":

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/common/utils.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
 # Copyright (c) 2023, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
@@ -18,7 +17,6 @@ import yaml
 from cerberus import Validator
 
 from ads.opctl import logger, utils
-from ads.opctl.operator import __operators__
 
 CONTAINER_NETWORK = "CONTAINER_NETWORK"
 
@@ -26,7 +24,11 @@ CONTAINER_NETWORK = "CONTAINER_NETWORK"
 class OperatorValidator(Validator):
     """The custom validator class."""
 
-    pass
+    def validate(self, obj_dict, **kwargs):
+        # Model should be case insensitive
+        if "model" in obj_dict["spec"]:
+            obj_dict["spec"]["model"] = str(obj_dict["spec"]["model"]).lower()
+        return super().validate(obj_dict, **kwargs)
 
 
 def create_output_folder(name):
@@ -34,7 +36,7 @@ def create_output_folder(name):
     protocol = fsspec.utils.get_protocol(output_folder)
     storage_options = {}
     if protocol != "file":
-        storage_options = auth or default_signer()
+        storage_options = default_signer()
 
     fs = fsspec.filesystem(protocol, **storage_options)
     name_suffix = 1

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/anomaly/model/base_model.py

@@ -166,9 +166,8 @@ class AnomalyOperatorBaseModel(ABC):
         yaml_appendix = rc.Yaml(self.config.to_dict())
         summary = rc.Block(
             rc.Group(
-                rc.Text(
-                    f"You selected the **`{self.spec.model}`** model.\n{model_description.text}\n"
-                ),
+                rc.Text(f"You selected the **`{self.spec.model}`** model.\n"),
+                model_description,
                 rc.Text(
                     "Based on your dataset, you could have also selected "
                     f"any of the models: `{'`, `'.join(SupportedModels.keys() if self.spec.datetime_column else NonTimeADSupportedModels.keys())}`."

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/anomaly/model/factory.py

@@ -26,9 +26,9 @@ class UnSupportedModelError(Exception):
 
     def __init__(self, operator_config: AnomalyOperatorConfig, model_type: str):
         supported_models = (
-            SupportedModels.values
+            SupportedModels.values()
             if operator_config.spec.datetime_column
-            else NonTimeADSupportedModels.values
+            else NonTimeADSupportedModels.values()
         )
         message = (
             f"Model: `{model_type}` is not supported. "

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/common/transformations.py

@@ -1,18 +1,19 @@
 #!/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/
 
+from abc import ABC
+
+import pandas as pd
+
 from ads.opctl import logger
+from ads.opctl.operator.lowcode.common.const import DataColumns
 from ads.opctl.operator.lowcode.common.errors import (
-    InvalidParameterError,
     DataMismatchError,
+    InvalidParameterError,
 )
-from ads.opctl.operator.lowcode.common.const import DataColumns
 from ads.opctl.operator.lowcode.common.utils import merge_category_columns
-import pandas as pd
-from abc import ABC
 
 
 class Transformations(ABC):
@@ -58,6 +59,7 @@ class Transformations(ABC):
 
         """
         clean_df = self._remove_trailing_whitespace(data)
+        # clean_df = self._normalize_column_names(clean_df)
         if self.name == "historical_data":
             self._check_historical_dataset(clean_df)
         clean_df = self._set_series_id_column(clean_df)
@@ -95,8 +97,11 @@ class Transformations(ABC):
     def _remove_trailing_whitespace(self, df):
         return df.apply(lambda x: x.str.strip() if x.dtype == "object" else x)
 
+    # def _normalize_column_names(self, df):
+    #     return df.rename(columns=lambda x: re.sub("[^A-Za-z0-9_]+", "", x))
+
     def _set_series_id_column(self, df):
-        self._target_category_columns_map = dict()
+        self._target_category_columns_map = {}
         if not self.target_category_columns:
             df[DataColumns.Series] = "Series 1"
             self.has_artificial_series = True
@@ -125,10 +130,10 @@ class Transformations(ABC):
             df[self.dt_column_name] = pd.to_datetime(
                 df[self.dt_column_name], format=self.dt_column_format
             )
-        except:
+        except Exception as ee:
             raise InvalidParameterError(
                 f"Unable to determine the datetime type for column: {self.dt_column_name} in dataset: {self.name}. Please specify the format explicitly. (For example adding 'format: %d/%m/%Y' underneath 'name: {self.dt_column_name}' in the datetime_column section of the yaml file if you haven't already. For reference, here is the first datetime given: {df[self.dt_column_name].values[0]}"
-            )
+            ) from ee
         return df
 
     def _set_multi_index(self, df):
@@ -242,7 +247,6 @@ class Transformations(ABC):
                 "Class": "A",
                 "Num": 2
             },
-            
         }
     """
 

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/common/utils.py

@@ -1,42 +1,32 @@
 #!/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/
 
-import argparse
 import logging
 import os
 import shutil
 import sys
 import tempfile
-import time
-from string import Template
-from typing import Any, Dict, List, Tuple
-import pandas as pd
-from ads.opctl import logger
-import oracledb
+from typing import List, Union
 
 import fsspec
-import yaml
-from typing import Union
+import oracledb
+import pandas as pd
 
+from ads.common.object_storage_details import ObjectStorageDetails
 from ads.opctl import logger
+from ads.opctl.operator.common.operator_config import OutputDirectory
 from ads.opctl.operator.lowcode.common.errors import (
-    InputDataError,
     InvalidParameterError,
-    PermissionsError,
-    DataMismatchError,
 )
-from ads.opctl.operator.common.operator_config import OutputDirectory
-from ads.common.object_storage_details import ObjectStorageDetails
 from ads.secrets import ADBSecretKeeper
 
 
 def call_pandas_fsspec(pd_fn, filename, storage_options, **kwargs):
-    if fsspec.utils.get_protocol(filename) == "file":
-        return pd_fn(filename, **kwargs)
-    elif fsspec.utils.get_protocol(filename) in ["http", "https"]:
+    if fsspec.utils.get_protocol(filename) == "file" or fsspec.utils.get_protocol(
+        filename
+    ) in ["http", "https"]:
         return pd_fn(filename, **kwargs)
 
     storage_options = storage_options or (
@@ -48,7 +38,7 @@ def call_pandas_fsspec(pd_fn, filename, storage_options, **kwargs):
 
 def load_data(data_spec, storage_options=None, **kwargs):
     if data_spec is None:
-        raise InvalidParameterError(f"No details provided for this data source.")
+        raise InvalidParameterError("No details provided for this data source.")
     filename = data_spec.url
     format = data_spec.format
     columns = data_spec.columns
@@ -67,7 +57,7 @@ def load_data(data_spec, storage_options=None, **kwargs):
         if not format:
             _, format = os.path.splitext(filename)
             format = format[1:]
-        if format in ["json", "clipboard", "excel", "csv", "feather", "hdf"]:
+        if format in ["json", "clipboard", "excel", "csv", "feather", "hdf", "parquet"]:
             read_fn = getattr(pd, f"read_{format}")
             data = call_pandas_fsspec(
                 read_fn, filename, storage_options=storage_options
@@ -84,19 +74,31 @@ def load_data(data_spec, storage_options=None, **kwargs):
         with tempfile.TemporaryDirectory() as temp_dir:
             if vault_secret_id is not None:
                 try:
-                    with ADBSecretKeeper.load_secret(vault_secret_id, wallet_dir=temp_dir) as adwsecret:
-                        if 'wallet_location' in adwsecret and 'wallet_location' not in connect_args:
-                            shutil.unpack_archive(adwsecret["wallet_location"], temp_dir)
-                            connect_args['wallet_location'] = temp_dir
-                        if 'user_name' in adwsecret and 'user' not in connect_args:
-                            connect_args['user'] = adwsecret['user_name']
-                        if 'password' in adwsecret and 'password' not in connect_args:
-                            connect_args['password'] = adwsecret['password']
-                        if 'service_name' in adwsecret and 'service_name' not in connect_args:
-                            connect_args['service_name'] = adwsecret['service_name']
+                    with ADBSecretKeeper.load_secret(
+                        vault_secret_id, wallet_dir=temp_dir
+                    ) as adwsecret:
+                        if (
+                            "wallet_location" in adwsecret
+                            and "wallet_location" not in connect_args
+                        ):
+                            shutil.unpack_archive(
+                                adwsecret["wallet_location"], temp_dir
+                            )
+                            connect_args["wallet_location"] = temp_dir
+                        if "user_name" in adwsecret and "user" not in connect_args:
+                            connect_args["user"] = adwsecret["user_name"]
+                        if "password" in adwsecret and "password" not in connect_args:
+                            connect_args["password"] = adwsecret["password"]
+                        if (
+                            "service_name" in adwsecret
+                            and "service_name" not in connect_args
+                        ):
+                            connect_args["service_name"] = adwsecret["service_name"]
 
                 except Exception as e:
-                    raise Exception(f"Could not retrieve database credentials from vault {vault_secret_id}: {e}")
+                    raise Exception(
+                        f"Could not retrieve database credentials from vault {vault_secret_id}: {e}"
+                    )
 
             con = oracledb.connect(**connect_args)
             if table_name is not None:
@@ -105,11 +107,11 @@ def load_data(data_spec, storage_options=None, **kwargs):
                 data = pd.read_sql(sql, con)
             else:
                 raise InvalidParameterError(
-                    f"Database `connect_args` provided without sql query or table name. Please specify either `sql` or `table_name`."
+                    "Database `connect_args` provided without sql query or table name. Please specify either `sql` or `table_name`."
                 )
     else:
         raise InvalidParameterError(
-            f"No filename/url provided, and no connect_args provided. Please specify one of these if you want to read data from a file or a database respectively."
+            "No filename/url provided, and no connect_args provided. Please specify one of these if you want to read data from a file or a database respectively."
         )
     if columns:
         # keep only these columns, done after load because only CSV supports stream filtering
@@ -232,7 +234,7 @@ def human_time_friendly(seconds):
             accumulator.append(
                 "{} {}{}".format(int(amount), unit, "" if amount == 1 else "s")
             )
-    accumulator.append("{} secs".format(round(seconds, 2)))
+    accumulator.append(f"{round(seconds, 2)} secs")
     return ", ".join(accumulator)
 
 
@@ -248,9 +250,7 @@ def find_output_dirname(output_dir: OutputDirectory):
         unique_output_dir = f"{output_dir}_{counter}"
         counter += 1
     logger.warn(
-        "Since the output directory was not specified, the output will be saved to {} directory.".format(
-            unique_output_dir
-        )
+        f"Since the output directory was not specified, the output will be saved to {unique_output_dir} directory."
     )
     return unique_output_dir
 

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/forecast/model/automlx.py

@@ -2,6 +2,7 @@
 # Copyright (c) 2023, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 import logging
+import os
 import traceback
 
 import numpy as np
@@ -80,10 +81,17 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
 
         from automlx import Pipeline, init
 
+        cpu_count = os.cpu_count()
         try:
+            if cpu_count < 4:
+                engine = "local"
+                engine_opts = None
+            else:
+                engine = "ray"
+                engine_opts = ({"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},)
             init(
-                engine="ray",
-                engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},
+                engine=engine,
+                engine_opts=engine_opts,
                 loglevel=logging.CRITICAL,
             )
         except Exception as e:

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/forecast/model/base_model.py

@@ -148,8 +148,9 @@ class ForecastOperatorBaseModel(ABC):
                 header_section = rc.Block(
                     rc.Heading("Forecast Report", level=1),
                     rc.Text(
-                        f"You selected the {self.spec.model} model.\n{model_description}\nBased on your dataset, you could have also selected any of the models: {SupportedModels.keys()}."
+                        f"You selected the {self.spec.model} model.\nBased on your dataset, you could have also selected any of the models: {SupportedModels.keys()}."
                     ),
+                    model_description,
                     rc.Group(
                         rc.Metric(
                             heading="Analysis was completed in ",

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/forecast/model/factory.py

@@ -11,6 +11,7 @@ from .automlx import AutoMLXOperatorModel
 from .autots import AutoTSOperatorModel
 from .base_model import ForecastOperatorBaseModel
 from .forecast_datasets import ForecastDatasets
+from .ml_forecast import MLForecastOperatorModel
 from .neuralprophet import NeuralProphetOperatorModel
 from .prophet import ProphetOperatorModel
 
@@ -19,7 +20,7 @@ class UnSupportedModelError(Exception):
     def __init__(self, model_type: str):
         super().__init__(
             f"Model: `{model_type}` "
-            f"is not supported. Supported models: {SupportedModels.values}"
+            f"is not supported. Supported models: {SupportedModels.values()}"
         )
 
 
@@ -32,7 +33,7 @@ class ForecastOperatorModelFactory:
         SupportedModels.Prophet: ProphetOperatorModel,
         SupportedModels.Arima: ArimaOperatorModel,
         SupportedModels.NeuralProphet: NeuralProphetOperatorModel,
-        # SupportedModels.LGBForecast: MLForecastOperatorModel,
+        SupportedModels.LGBForecast: MLForecastOperatorModel,
         SupportedModels.AutoMLX: AutoMLXOperatorModel,
         SupportedModels.AutoTS: AutoTSOperatorModel,
     }

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/forecast/model/prophet.py

@@ -142,6 +142,9 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
             dt_column=self.spec.datetime_column.name,
         )
 
+        # if os.environ["OCI__IS_SPARK"]:
+        #     pass
+        # else:
         Parallel(n_jobs=-1, require="sharedmem")(
             delayed(ProphetOperatorModel._train_model)(
                 self, i, series_id, df, model_kwargs.copy()
@@ -354,7 +357,7 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 logger.warn(f"Failed to generate Explanations with error: {e}.")
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")
 
-        model_description = (
+        model_description = rc.Text(
             "Prophet is a procedure for forecasting time series data based on an additive "
             "model where non-linear trends are fit with yearly, weekly, and daily seasonality, "
             "plus holiday effects. It works best with time series that have strong seasonal "

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/forecast/schema.yaml

@@ -311,7 +311,7 @@ spec:
             missing_value_imputation:
               type: boolean
               required: false
-              default: false
+              default: true
             outlier_treatment:
               type: boolean
               required: false

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/pii/model/factory.py

@@ -1,7 +1,6 @@
 #!/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 uuid
@@ -18,7 +17,7 @@ class UnSupportedDetectorError(Exception):
     def __init__(self, dtype: str):
         super().__init__(
             f"Detector: `{dtype}` "
-            f"is not supported. Supported models: {SupportedDetector.values}"
+            f"is not supported. Supported models: {SupportedDetector.values()}"
         )
 
 
@@ -42,7 +41,10 @@ class SpacyDetector(PiiBaseDetector):
     @runtime_dependency(module="scrubadub", install_from=OptionalDependency.PII)
     @runtime_dependency(module="scrubadub_spacy", install_from=OptionalDependency.PII)
     def construct(cls, entity, model, **kwargs):
-        spacy_entity_detector = scrubadub_spacy.detectors.spacy.SpacyEntityDetector(
+        from scrubadub.filth import Filth
+        from scrubadub_spacy.detectors.spacy import SpacyEntityDetector
+
+        spacy_entity_detector = SpacyEntityDetector(
             named_entities=[entity],
             name=f"spacy_{uuid.uuid4()}",
             model=model,
@@ -50,7 +52,7 @@ class SpacyDetector(PiiBaseDetector):
         if entity.upper() not in cls.DEFAULT_SPACY_NAMED_ENTITIES:
             filth_cls = type(
                 construct_filth_cls_name(entity),
-                (scrubadub.filth.Filth,),
+                (Filth,),
                 {"type": entity.upper()},
             )
             spacy_entity_detector.filth_cls_map[entity.upper()] = filth_cls

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/recommender/model/base_model.py

@@ -61,8 +61,9 @@ class RecommenderOperatorBaseModel(ABC):
             header_section = rc.Block(
                 rc.Heading("Recommender Report", level=1),
                 rc.Text(
-                    f"The recommendations was generated using {SupportedModels.SVD.upper()}. {model_description}"
+                    f"The recommendations was generated using {SupportedModels.SVD.upper()}."
                 ),
+                model_description,
                 rc.Group(
                     rc.Metric(
                         heading="Recommendations was generated in ",

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/recommender/model/factory.py

@@ -1,7 +1,6 @@
 #!/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/
 
 from ..constant import SupportedModels
@@ -10,11 +9,12 @@ from .base_model import RecommenderOperatorBaseModel
 from .recommender_dataset import RecommenderDatasets
 from .svd import SVDOperatorModel
 
+
 class UnSupportedModelError(Exception):
     def __init__(self, model_type: str):
         super().__init__(
             f"Model: `{model_type}` "
-            f"is not supported. Supported models: {SupportedModels.values}"
+            f"is not supported. Supported models: {SupportedModels.values()}"
         )
 
 
@@ -23,9 +23,7 @@ class RecommenderOperatorModelFactory:
     The factory class helps to instantiate proper model operator based on the model type.
     """
 
-    _MAP = {
-        SupportedModels.SVD: SVDOperatorModel
-    }
+    _MAP = {SupportedModels.SVD: SVDOperatorModel}
 
     @classmethod
     def get_model(

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/ads/opctl/operator/lowcode/recommender/model/svd.py

@@ -78,11 +78,11 @@ class SVDOperatorModel(RecommenderOperatorBaseModel):
         return recommendations_df, metric
 
     def _generate_report(self):
-        model_description = """
-            Singular Value Decomposition (SVD) is a matrix factorization technique used in recommendation systems to
-            decompose a user-item interaction matrix into three constituent matrices. These matrices capture the
-            latent factors that explain the observed interactions.
-            """
+        model_description = rc.Text(
+            "Singular Value Decomposition (SVD) is a matrix factorization technique used in recommendation systems to \
+            decompose a user-item interaction matrix into three constituent matrices. These matrices capture the \
+            latent factors that explain the observed interactions."
+        )
         new_user_recommendations = self._get_recommendations(
             "__new_user__", self.spec.top_k
         )

{oracle_ads-2.12.7 → oracle_ads-2.12.8}/pyproject.toml

@@ -21,7 +21,7 @@ build-backend = "flit_core.buildapi"
 
 # Required
 name = "oracle_ads" # the install (PyPI) name; name for local build in [tool.flit.module] section below
-version = "2.12.7"
+version = "2.12.8"
 
 # Optional
 description = "Oracle Accelerated Data Science SDK"