Merge branch 'main' into forecast_series_failure_bugfixes

Author: ahosler

.github/workflows/run-operators-unit-tests.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.10.8"]
+        python-version: ["3.8"]
 
     steps:
       - uses: actions/checkout@v4

CODEOWNERS

@@ -0,0 +1 @@
+* @darenr @mayoor @mrDzurb @VipulMascarenhas @qiuosier

ads/common/serializer.py

@@ -464,7 +464,7 @@ def from_dict(
             )
 
         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():

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

@@ -10,7 +10,6 @@
     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

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

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 @@ def __post_init__(self):
             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):

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

ads/opctl/operator/lowcode/common/transformations.py

@@ -58,20 +58,26 @@ def run(self, data):
         clean_df = self._format_datetime_col(clean_df)
         clean_df = self._set_multi_index(clean_df)
 
-        if self.name == "historical_data":
-            try:
-                clean_df = self._missing_value_imputation_hist(clean_df)
-            except Exception as e:
-                logger.debug(f"Missing value imputation failed with {e.args}")
-            if self.preprocessing:
-                try:
-                    clean_df = self._outlier_treatment(clean_df)
-                except Exception as e:
-                    logger.debug(f"Outlier Treatment failed with {e.args}")
-            else:
-                logger.debug("Skipping outlier treatment as preprocessing is disabled")
-        elif self.name == "additional_data":
-            clean_df = self._missing_value_imputation_add(clean_df)
+        if self.preprocessing and self.preprocessing.enabled:
+            if self.name == "historical_data":
+                if self.preprocessing.steps.missing_value_imputation:
+                    try:
+                        clean_df = self._missing_value_imputation_hist(clean_df)
+                    except Exception as e:
+                        logger.debug(f"Missing value imputation failed with {e.args}")
+                else:
+                    logger.info("Skipping missing value imputation because it is disabled")
+                if self.preprocessing.steps.outlier_treatment:
+                    try:
+                        clean_df = self._outlier_treatment(clean_df)
+                    except Exception as e:
+                        logger.debug(f"Outlier Treatment failed with {e.args}")
+                else:
+                    logger.info("Skipping outlier treatment because it is disabled")
+            elif self.name == "additional_data":
+                clean_df = self._missing_value_imputation_add(clean_df)
+        else:
+            logger.info("Skipping all preprocessing steps because preprocessing is disabled")
         return clean_df
 
     def _remove_trailing_whitespace(self, df):

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

@@ -18,3 +18,4 @@ dependencies:
       - optuna==3.1.0
       - oracle-automlx==23.4.1
       - oracle-automlx[forecasting]==23.4.1
+      - fire

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

@@ -76,17 +76,15 @@ def preprocess(self, data, series_id=None):  # TODO: re-use self.le for explanat
     )
     def _build_model(self) -> pd.DataFrame:
         from automlx import init
-        from sktime.forecasting.model_selection import temporal_train_test_split
+        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")
 
-
         full_data_dict = self.datasets.get_data_by_series()
 
         self.models = dict()
-        date_column = self.spec.datetime_column.name
         horizon = self.spec.horizon
         self.spec.confidence_interval_width = self.spec.confidence_interval_width or 0.8
         self.forecast_output = ForecastOutput(