oracle-ads 2.13.17__py3-none-any.whl → 2.13.18rc0__py3-none-any.whl

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

@@ -18,13 +18,14 @@ from ads.opctl.operator.lowcode.common.utils import (
     get_frequency_of_datetime,
 )
 
-from ..const import ForecastOutputColumns, SupportedModels
+from ..const import ForecastOutputColumns, SupportedModels, TROUBLESHOOTING_GUIDE
 from ..operator_config import ForecastOperatorConfig
 
 
 class HistoricalData(AbstractData):
-    def __init__(self, spec, historical_data=None):
-        super().__init__(spec=spec, name="historical_data", data=historical_data)
+    def __init__(self, spec, historical_data=None, subset=None):
+        super().__init__(spec=spec, name="historical_data", data=historical_data, subset=subset)
+        self.subset = subset
 
     def _ingest_data(self, spec):
         try:
@@ -48,25 +49,29 @@ class HistoricalData(AbstractData):
                 f"{SupportedModels.AutoMLX} requires data with a frequency of at least one hour. Please try using a different model,"
                 " or select the 'auto' option."
             )
-            raise InvalidParameterError(message)
+            raise InvalidParameterError(f"{message}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps.")
 
 
 class AdditionalData(AbstractData):
-    def __init__(self, spec, historical_data, additional_data=None):
+    def __init__(self, spec, historical_data, additional_data=None, subset=None):
+        self.subset = subset
         if additional_data is not None:
-            super().__init__(spec=spec, name="additional_data", data=additional_data)
+            super().__init__(spec=spec, name="additional_data", data=additional_data, subset=subset)
             self.additional_regressors = list(self.data.columns)
         elif spec.additional_data is not None:
-            super().__init__(spec=spec, name="additional_data")
+            super().__init__(spec=spec, name="additional_data", subset=subset)
             add_dates = self.data.index.get_level_values(0).unique().tolist()
             add_dates.sort()
             if historical_data.get_max_time() > add_dates[-spec.horizon]:
                 raise DataMismatchError(
                     f"The Historical Data ends on {historical_data.get_max_time()}. The additional data horizon starts on {add_dates[-spec.horizon]}. The horizon should have exactly {spec.horizon} dates after the Historical at a frequency of {historical_data.freq}"
+                    f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
                 )
             elif historical_data.get_max_time() != add_dates[-(spec.horizon + 1)]:
                 raise DataMismatchError(
                     f"The Additional Data must be present for all historical data and the entire horizon. The Historical Data ends on {historical_data.get_max_time()}. The additonal data horizon starts after {add_dates[-(spec.horizon+1)]}. These should be the same date."
+                    f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
                 )
         else:
             self.name = "additional_data"
@@ -127,6 +132,7 @@ class ForecastDatasets:
         historical_data=None,
         additional_data=None,
         test_data=None,
+        subset=None,  # New parameter for subsetting by group
     ):
         """Instantiates the DataIO instance.
 
@@ -134,26 +140,28 @@ class ForecastDatasets:
         ----------
         config: ForecastOperatorConfig
             The forecast operator configuration.
+        subset: list, optional
+            List of group keys to subset the data on initialization.
         """
+        self.config = config  # Store the config for later use
         self.historical_data: HistoricalData = None
         self.additional_data: AdditionalData = None
         self._horizon = config.spec.horizon
         self._datetime_column_name = config.spec.datetime_column.name
         self._target_col = config.spec.target_column
         if historical_data is not None:
-            self.historical_data = HistoricalData(config.spec, historical_data)
+            self.historical_data = HistoricalData(config.spec, historical_data, subset=subset)
             self.additional_data = AdditionalData(
-                config.spec, self.historical_data, additional_data
+                config.spec, self.historical_data, additional_data, subset=subset
             )
         else:
-            self._load_data(config.spec)
+            self._load_data(config.spec, subset=subset)
         self.test_data = TestData(config.spec, test_data)
 
-    def _load_data(self, spec):
+    def _load_data(self, spec, subset=None):
         """Loads forecasting input data."""
-        self.historical_data = HistoricalData(spec)
-        self.additional_data = AdditionalData(spec, self.historical_data)
-
+        self.historical_data = HistoricalData(spec, subset=subset)
+        self.additional_data = AdditionalData(spec, self.historical_data, subset=subset)
         if spec.generate_explanations and spec.additional_data is None:
             logger.warning(
                 "Unable to generate explanations as there is no additional data passed in. Either set generate_explanations to False, or pass in additional data."
@@ -210,6 +218,7 @@ class ForecastDatasets:
         except Exception as e:
             raise InvalidParameterError(
                 f"Unable to retrieve series id: {s_id} from data. Available series ids are: {self.list_series_ids()}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             ) from e
 
     def get_horizon_at_series(self, s_id):
@@ -291,6 +300,7 @@ class ForecastOutput:
         if not overwrite and series_id in self.series_id_map:
             raise ValueError(
                 f"Attempting to update ForecastOutput for series_id {series_id} when this already exists. Set overwrite to True."
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
         forecast = self._check_forecast_format(forecast)
         self.series_id_map[series_id] = forecast
@@ -331,6 +341,7 @@ class ForecastOutput:
         except KeyError as e:
             raise ValueError(
                 f"Attempting to update output for series: {series_id}, however no series output has been initialized."
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             ) from e
 
         if (output_i.shape[0] - self.horizon) == len(fit_val):
@@ -351,18 +362,21 @@ class ForecastOutput:
         if len(forecast_val) != self.horizon:
             raise ValueError(
                 f"Attempting to set forecast along horizon ({self.horizon}) for series: {series_id}, however forecast is only length {len(forecast_val)}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
         output_i["forecast_value"].iloc[-self.horizon :] = forecast_val
 
         if len(upper_bound) != self.horizon:
             raise ValueError(
                 f"Attempting to set upper_bound along horizon ({self.horizon}) for series: {series_id}, however upper_bound is only length {len(upper_bound)}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
         output_i[self.upper_bound_name].iloc[-self.horizon :] = upper_bound
 
         if len(lower_bound) != self.horizon:
             raise ValueError(
                 f"Attempting to set lower_bound along horizon ({self.horizon}) for series: {series_id}, however lower_bound is only length {len(lower_bound)}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
         output_i[self.lower_bound_name].iloc[-self.horizon :] = lower_bound
 
@@ -490,3 +504,25 @@ class ForecastResults:
 
     def get_errors_dict(self):
         return getattr(self, "errors_dict", None)
+
+    def merge(self, other: 'ForecastResults'):
+        """Merge another ForecastResults object into this one."""
+        # Merge DataFrames if they exist, else just set
+        for attr in [
+            'forecast', 'metrics', 'test_metrics', 'local_explanations', 'global_explanations', 'model_parameters', 'models', 'errors_dict']:
+            val_self = getattr(self, attr, None)
+            val_other = getattr(other, attr, None)
+            if val_self is not None and val_other is not None:
+                if isinstance(val_self, pd.DataFrame) and isinstance(val_other, pd.DataFrame):
+                    setattr(self, attr, pd.concat([val_self, val_other], ignore_index=True, axis=0))
+                elif isinstance(val_self, dict) and isinstance(val_other, dict):
+                    val_self.update(val_other)
+                    setattr(self, attr, val_self)
+                elif isinstance(val_self, list) and isinstance(val_other, list):
+                    setattr(self, attr, val_self + val_other)
+                else:
+                    # If not mergeable, just keep self's value
+                    pass
+            elif val_other is not None:
+                setattr(self, attr, val_other)
+        return self

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

@@ -10,7 +10,10 @@ 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 InsufficientDataError
-from ads.opctl.operator.lowcode.forecast.const import BACKTEST_REPORT_NAME
+from ads.opctl.operator.lowcode.forecast.const import (
+    BACKTEST_REPORT_NAME,
+    TROUBLESHOOTING_GUIDE,
+)
 from ads.opctl.operator.lowcode.forecast.model.factory import SupportedModels
 
 from .model.forecast_datasets import ForecastDatasets
@@ -79,6 +82,7 @@ class ModelEvaluator:
             raise InsufficientDataError(
                 "Insufficient data to evaluate multiple models. Please specify a model "
                 "instead of using auto-select."
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
         training_datasets = [
             sampled_historical_data[sampled_historical_data[date_col] <= cut_off_date]
@@ -223,6 +227,7 @@ class ModelEvaluator:
             model = SupportedModels.Prophet
             logger.error(
                 f"Running {model} model as auto-select failed with the following error: {e.message}"
+                f"\nPlease refer to the troubleshooting guide at {TROUBLESHOOTING_GUIDE} for resolution steps."
             )
             return model
         nonempty_metrics = {

ads/opctl/operator/lowcode/forecast/schema.yaml

@@ -459,6 +459,7 @@ spec:
         - automlx
         - autots
         - auto-select
+        - auto-select-series
 
     model_kwargs:
       type: dict

{oracle_ads-2.13.17.dist-info → oracle_ads-2.13.18rc0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oracle_ads
-Version: 2.13.17
+Version: 2.13.18rc0
 Summary: Oracle Accelerated Data Science SDK
 Keywords: Oracle Cloud Infrastructure,OCI,Machine Learning,ML,Artificial Intelligence,AI,Data Science,Cloud,Oracle,GenAI,Generative AI,Forecast,Anomaly,Document Understanding,Anomaly Detection
 Author: Oracle Data Science

{oracle_ads-2.13.17.dist-info → oracle_ads-2.13.18rc0.dist-info}/RECORD

@@ -698,10 +698,10 @@ ads/opctl/operator/lowcode/anomaly/model/randomcutforest.py,sha256=eZVtLTRCcA6Er
 ads/opctl/operator/lowcode/anomaly/model/tods.py,sha256=_v0KkdTKD3nqzOu3P5tE7bSV63Jy91h6Hr88Eequ0RU,4175
 ads/opctl/operator/lowcode/common/__init__.py,sha256=rZrmh1nho40OCeabXCNWtze-mXi-PGKetcZdxZSn3_0,204
 ads/opctl/operator/lowcode/common/const.py,sha256=1dUhgup4L_U0s6BSYmgLPpZAe6xqfSHPPoLqW0j46U8,265
-ads/opctl/operator/lowcode/common/data.py,sha256=_0UbW-A0kVQjNOO2aeZoRiebgmKqDqcprPPjZ6KDWdk,4188
+ads/opctl/operator/lowcode/common/data.py,sha256=kGR7k2tQofb4qbFgEv8QywCIKrVQEk1gBpIuA_1BOuY,4628
 ads/opctl/operator/lowcode/common/errors.py,sha256=LvQ_Qzh6cqD6uP91DMFFVXPrcc3010EE8LfBH-CH0ho,1534
-ads/opctl/operator/lowcode/common/transformations.py,sha256=n-Yac9WtI9GLEc5sDKSq75-2q0j59bR_pxlV5EAmkO0,11048
-ads/opctl/operator/lowcode/common/utils.py,sha256=9wVM7lNZX_RRO0MVxZrN0FkWBPZweKq_D3_0ON7wjnM,12159
+ads/opctl/operator/lowcode/common/transformations.py,sha256=byjx1_ALRmE0U3j7mt2np-V6v5TXrx6HT2kRTF3Aphk,19869
+ads/opctl/operator/lowcode/common/utils.py,sha256=pKUcyJWopMbZQbbMXuJc1rR1VJIz2o_6RQbsy3znCfE,12486
 ads/opctl/operator/lowcode/feature_store_marketplace/MLoperator,sha256=JO5ulr32WsFnbpk1KN97h8-D70jcFt1kRQ08UMkP4rU,346
 ads/opctl/operator/lowcode/feature_store_marketplace/README.md,sha256=fN9ROzOPdEZdRgSP_uYvAmD5bD983NC7Irfe_D-mvrw,1356
 ads/opctl/operator/lowcode/feature_store_marketplace/__init__.py,sha256=rZrmh1nho40OCeabXCNWtze-mXi-PGKetcZdxZSn3_0,204
@@ -718,23 +718,24 @@ ads/opctl/operator/lowcode/feature_store_marketplace/models/mysql_config.py,sha2
 ads/opctl/operator/lowcode/feature_store_marketplace/models/serializable_yaml_model.py,sha256=Fd5K1q30mIyCbU6WDH8nDXyCJFlo_kSAEKxqr4dQSSc,1135
 ads/opctl/operator/lowcode/forecast/MLoperator,sha256=xM8yBUQObjG_6Mg36f3Vv8b9N3L8_5RUZJE2riOjXuw,5981
 ads/opctl/operator/lowcode/forecast/README.md,sha256=kbCCEdo-0pwKlZp9ctnWUK6Z31n69IsnG0i26b202Zg,9768
-ads/opctl/operator/lowcode/forecast/__init__.py,sha256=sAqmLhogrLXb3xI7dPOj9HmSkpTnLh9wkzysuGd8AXk,204
-ads/opctl/operator/lowcode/forecast/__main__.py,sha256=FTQhYCZEAbQO2sCOpepermKimSktFd9pERNu1rC-K3A,2926
+ads/opctl/operator/lowcode/forecast/__init__.py,sha256=CIcan-f0OAJR8JRMmPKlh-PXI1dTuOUnHS97eHa8F4A,243
+ads/opctl/operator/lowcode/forecast/__main__.py,sha256=k5VltDUfkEKOgz09zqsu9ljuixd7iVEN9e9rPILyrl4,4951
 ads/opctl/operator/lowcode/forecast/cmd.py,sha256=uwU-QvnYwxoRFXZv7_JFkzAUnjTNoSsHEme2FF-9Rl0,1151
-ads/opctl/operator/lowcode/forecast/const.py,sha256=Vt03VuFCbm5y9y-NomJsLX6wd3GzWwcCx7di8cnQ9dY,2611
+ads/opctl/operator/lowcode/forecast/const.py,sha256=55wUyJQJfItsL_bEZvwpaoRm706D_s3dmFLosxByn8Q,2783
 ads/opctl/operator/lowcode/forecast/environment.yaml,sha256=eVMf9pcjADI14_GRGdZOB_gK5_MyG_-cX037TXqzFho,330
-ads/opctl/operator/lowcode/forecast/errors.py,sha256=X9zuV2Lqb5N9FuBHHshOFYyhvng5r9KGLHnQijZ5b8c,911
-ads/opctl/operator/lowcode/forecast/model_evaluator.py,sha256=crtCQ4KIWCueOf2zU-AKD_i3h_cJA_-qAGakdgBazVI,10257
+ads/opctl/operator/lowcode/forecast/errors.py,sha256=2SrdsIPEXKDs4iYvUV9oeBcXwdHE3pUl5bZaiPCJQL4,1205
+ads/opctl/operator/lowcode/forecast/meta_selector.py,sha256=whM33RK68u0v41UOwy9Ly46jlsFictzrfmq1TFNYRJw,13505
+ads/opctl/operator/lowcode/forecast/model_evaluator.py,sha256=2nqRagzVgi21SOyjbVvDBtyWS5OdFhrLE_ADDB5VqpM,10517
 ads/opctl/operator/lowcode/forecast/operator_config.py,sha256=3pJzgbSqgPzE7vkce6KkthPQJEgWRRdDOAf1l6aSZpg,8318
-ads/opctl/operator/lowcode/forecast/schema.yaml,sha256=RoNwjg5jxXMbljtregMkV_rJbax8ir7zdJltC5YfYM8,12438
+ads/opctl/operator/lowcode/forecast/schema.yaml,sha256=5ipXmlGV9Opxw-KaPOCToWR4AMb71UtRZi2RlOeHta8,12467
 ads/opctl/operator/lowcode/forecast/utils.py,sha256=00prJFK1F3esHlPsPp1WSJ3YoT0NK95f3cH2qNH8AJQ,13578
 ads/opctl/operator/lowcode/forecast/model/__init__.py,sha256=sAqmLhogrLXb3xI7dPOj9HmSkpTnLh9wkzysuGd8AXk,204
 ads/opctl/operator/lowcode/forecast/model/arima.py,sha256=PvHoTdDr6RIC4I-YLzed91td6Pq6uxbgluEdu_h0e3c,11766
-ads/opctl/operator/lowcode/forecast/model/automlx.py,sha256=f11WY1gsGrUIuzbgJd0c-t1nM3416nAxqj_ylvYtC7k,23669
+ads/opctl/operator/lowcode/forecast/model/automlx.py,sha256=PVUslP6Qae3glD3xkgN77bTH9ilTeHOESW40VDe_jgw,23661
 ads/opctl/operator/lowcode/forecast/model/autots.py,sha256=UThBBGsEiC3WLSn-BPAuNWT_ZFa3bYMu52keB0vvSt8,13137
-ads/opctl/operator/lowcode/forecast/model/base_model.py,sha256=ENrizwJwhHbJa8DPMqCDEUKqwQaGfR5-fYdTxreQrHU,36613
-ads/opctl/operator/lowcode/forecast/model/factory.py,sha256=5a9A3ql-bU412BiTB20ob6OxQlkdk8z_tGONMwDXT1k,3900
-ads/opctl/operator/lowcode/forecast/model/forecast_datasets.py,sha256=2NsWE2WtD_O7uAXw42_3tmG3vb5lk3mdnzCZTph4hao,18903
+ads/opctl/operator/lowcode/forecast/model/base_model.py,sha256=X3s7qhHUbExicFq61UG3876LWAQEUiSlpTjGFnib3IY,40401
+ads/opctl/operator/lowcode/forecast/model/factory.py,sha256=odJAKV1rtu1wkAgDoPy_n4viJCpxnUUzPlJvyMYUr0c,5234
+ads/opctl/operator/lowcode/forecast/model/forecast_datasets.py,sha256=b141jsR7k8qCaUA-_xgjtyNfR-MMUlnMNgqGa5OhBeA,21619
 ads/opctl/operator/lowcode/forecast/model/ml_forecast.py,sha256=t5x6EBxOd7XwfT3FGdt-n9gscxaHMm3R2A4Evvxbj38,9646
 ads/opctl/operator/lowcode/forecast/model/neuralprophet.py,sha256=-AS3PPd8Fqn1uaMybJwTnFbmIfUxNPDlgYjGtjy9-E8,19944
 ads/opctl/operator/lowcode/forecast/model/prophet.py,sha256=U0M3M7yzy7ea-mEG1c-dELL6t1Pf_LnnnbrZB08CG_Y,17402
@@ -860,8 +861,8 @@ ads/type_discovery/unknown_detector.py,sha256=yZuYQReO7PUyoWZE7onhhtYaOg6088wf1y
 ads/type_discovery/zipcode_detector.py,sha256=3AlETg_ZF4FT0u914WXvTT3F3Z6Vf51WiIt34yQMRbw,1421
 ads/vault/__init__.py,sha256=x9tMdDAOdF5iDHk9u2di_K-ze5Nq068x25EWOBoWwqY,245
 ads/vault/vault.py,sha256=hFBkpYE-Hfmzu1L0sQwUfYcGxpWmgG18JPndRl0NOXI,8624
-oracle_ads-2.13.17.dist-info/entry_points.txt,sha256=9VFnjpQCsMORA4rVkvN8eH6D3uHjtegb9T911t8cqV0,35
-oracle_ads-2.13.17.dist-info/licenses/LICENSE.txt,sha256=zoGmbfD1IdRKx834U0IzfFFFo5KoFK71TND3K9xqYqo,1845
-oracle_ads-2.13.17.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-oracle_ads-2.13.17.dist-info/METADATA,sha256=W2KPCH2yRAHZF4aAF65yaOIZS6a4150R7hWAmbXRH5c,16994
-oracle_ads-2.13.17.dist-info/RECORD,,
+oracle_ads-2.13.18rc0.dist-info/entry_points.txt,sha256=9VFnjpQCsMORA4rVkvN8eH6D3uHjtegb9T911t8cqV0,35
+oracle_ads-2.13.18rc0.dist-info/licenses/LICENSE.txt,sha256=zoGmbfD1IdRKx834U0IzfFFFo5KoFK71TND3K9xqYqo,1845
+oracle_ads-2.13.18rc0.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+oracle_ads-2.13.18rc0.dist-info/METADATA,sha256=aBsbjgZiA8uiXNt9O106xFGvyCjnd-9PbftwTGXyolk,16997
+oracle_ads-2.13.18rc0.dist-info/RECORD,,