oracle-ads 2.12.7__py3-none-any.whl → 2.12.9__py3-none-any.whl

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
 

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

@@ -87,3 +87,4 @@ SUMMARY_METRICS_HORIZON_LIMIT = 10
 PROPHET_INTERNAL_DATE_COL = "ds"
 RENDER_LIMIT = 5000
 AUTO_SELECT = "auto-select"
+BACKTEST_REPORT_NAME = "back_test.csv"

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:

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

@@ -47,6 +47,7 @@ from ..const import (
     SpeedAccuracyMode,
     SupportedMetrics,
     SupportedModels,
+    BACKTEST_REPORT_NAME
 )
 from ..operator_config import ForecastOperatorConfig, ForecastOperatorSpec
 from .forecast_datasets import ForecastDatasets
@@ -148,8 +149,9 @@ 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 ",
@@ -255,12 +257,9 @@ class ForecastOperatorBaseModel(ABC):
 
                 backtest_sections = []
                 output_dir = self.spec.output_directory.url
-                backtest_report_name = "backtest_stats.csv"
-                file_path = f"{output_dir}/{backtest_report_name}"
+                file_path = f"{output_dir}/{BACKTEST_REPORT_NAME}"
                 if self.spec.model == AUTO_SELECT:
-                    backtest_sections.append(
-                        rc.Heading("Auto-select statistics", level=2)
-                    )
+                    backtest_sections.append(rc.Heading("Auto-Select Backtesting and Performance Metrics", level=2))
                     if not os.path.exists(file_path):
                         failure_msg = rc.Text(
                             "auto-select could not be executed. Please check the "
@@ -269,19 +268,15 @@ class ForecastOperatorBaseModel(ABC):
                         backtest_sections.append(failure_msg)
                     else:
                         backtest_stats = pd.read_csv(file_path)
-                        average_dict = backtest_stats.mean().to_dict()
-                        del average_dict["backtest"]
+                        model_metric_map = backtest_stats.drop(columns=['metric', 'backtest'])
+                        average_dict = {k: round(v, 4) for k, v in model_metric_map.mean().to_dict().items()}
                         best_model = min(average_dict, key=average_dict.get)
-                        backtest_text = rc.Heading("Back Testing Metrics", level=3)
                         summary_text = rc.Text(
-                            f"Overall, the average scores for the models are {average_dict}, with {best_model}"
-                            f" being identified as the top-performing model during backtesting."
-                        )
+                            f"Overall, the average {self.spec.metric} scores for the models are {average_dict}, with"
+                            f" {best_model} being identified as the top-performing model during backtesting.")
                         backtest_table = rc.DataTable(backtest_stats, index=True)
                         liner_plot = get_auto_select_plot(backtest_stats)
-                        backtest_sections.extend(
-                            [backtest_text, backtest_table, summary_text, liner_plot]
-                        )
+                        backtest_sections.extend([backtest_table, summary_text, liner_plot])
 
                 forecast_plots = []
                 if len(self.forecast_output.list_series_ids()) > 0:

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,
     }

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 "

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

@@ -10,6 +10,7 @@ from pathlib import Path
 
 from ads.opctl import logger
 from ads.opctl.operator.lowcode.common.const import DataColumns
+from ads.opctl.operator.lowcode.forecast.const import BACKTEST_REPORT_NAME
 from .model.forecast_datasets import ForecastDatasets
 from .operator_config import ForecastOperatorConfig
 from ads.opctl.operator.lowcode.forecast.model.factory import SupportedModels
@@ -156,8 +157,8 @@ class ModelEvaluator:
         best_model = min(avg_backtests_metric, key=avg_backtests_metric.get)
         logger.info(f"Among models {self.models}, {best_model} model shows better performance during backtesting.")
         backtest_stats = pd.DataFrame(nonempty_metrics).rename_axis('backtest')
+        backtest_stats["metric"] = operator_config.spec.metric
         backtest_stats.reset_index(inplace=True)
         output_dir = operator_config.spec.output_directory.url
-        backtest_report_name = "backtest_stats.csv"
-        backtest_stats.to_csv(f"{output_dir}/{backtest_report_name}", index=False)
+        backtest_stats.to_csv(f"{output_dir}/{BACKTEST_REPORT_NAME}", index=False)
         return best_model

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

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

@@ -261,10 +261,11 @@ def _add_unit(num, unit):
 
 def get_auto_select_plot(backtest_results):
     fig = go.Figure()
-    columns = backtest_results.columns.tolist()
+    back_test_csv_columns = backtest_results.columns.tolist()
     back_test_column = "backtest"
-    columns.remove(back_test_column)
-    for column in columns:
+    metric_column = "metric"
+    models = [x for x in back_test_csv_columns if x not in [back_test_column, metric_column]]
+    for i, column in enumerate(models):
         fig.add_trace(
             go.Scatter(
                 x=backtest_results[back_test_column],

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

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 ",

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(

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.dist-info → oracle_ads-2.12.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: oracle_ads
-Version: 2.12.7
+Version: 2.12.9
 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
@@ -30,7 +30,7 @@ Requires-Dist: pandas>=2.2.0; python_version>='3.9'
 Requires-Dist: psutil>=5.7.2
 Requires-Dist: python_jsonschema_objects>=0.3.13
 Requires-Dist: requests
-Requires-Dist: scikit-learn>=1.0
+Requires-Dist: scikit-learn>=1.0,<1.6.0
 Requires-Dist: tabulate>=0.8.9
 Requires-Dist: tqdm>=4.59.0
 Requires-Dist: pydantic>=2.6.3
@@ -39,7 +39,7 @@ Requires-Dist: autots ; extra == "anomaly"
 Requires-Dist: oracledb ; extra == "anomaly"
 Requires-Dist: report-creator==1.0.28 ; extra == "anomaly"
 Requires-Dist: rrcf==0.4.4 ; extra == "anomaly"
-Requires-Dist: scikit-learn ; extra == "anomaly"
+Requires-Dist: scikit-learn<1.6.0 ; extra == "anomaly"
 Requires-Dist: salesforce-merlion[all]==2.0.4 ; extra == "anomaly"
 Requires-Dist: jupyter_server ; extra == "aqua"
 Requires-Dist: hdfs[kerberos] ; extra == "bds"