Merge branch 'main' into feature/aquav1.0.2

Author: VipulMascarenhas

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

@@ -27,7 +27,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8"]
+        python-version: ["3.8", "3.9", "3.10"]
 
     steps:
       - uses: actions/checkout@v4
@@ -56,4 +56,7 @@ jobs:
           $CONDA/bin/conda init
           source /home/runner/.bashrc
           pip install -r test-requirements-operators.txt
+          pip install "oracle-automlx[classic]>=24.2.0"
+          pip install "oracle-automlx[forecasting]>=24.2.0"
+          pip install pandas>=2.2.0
           python -m pytest -v -p no:warnings --durations=5 tests/operators/forecast

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

@@ -27,7 +27,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8"]
+        python-version: ["3.8", "3.9", "3.10"]
 
     steps:
       - uses: actions/checkout@v4

ads/opctl/operator/lowcode/anomaly/__main__.py

@@ -40,11 +40,11 @@ def operate(operator_config: AnomalyOperatorConfig) -> None:
                 AnomalyOperatorModelFactory.get_model(
                     operator_config, datasets
                 ).generate_report()
-            except Exception as e2:
+            except Exception as ee:
                 logger.debug(
-                    f"Failed to backup forecast with error {e2.args}. Raising original error."
+                    f"Failed to backup forecast with error {ee.args}. Raising original error."
                 )
-            raise e
+            raise ee
         else:
             raise e
 

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

@@ -91,7 +91,7 @@ def _generate_report(self):
             ),
         ]
         model_description = rc.Text(
-            "The automlx model automatically pre-processes, selects and engineers "
+            "The autots 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.."
         )

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

@@ -4,33 +4,29 @@
 # 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 fsspec
+import numpy as np
 import os
+import pandas as pd
 import tempfile
 import time
 from abc import ABC, abstractmethod
-from typing import Tuple
-
-import fsspec
-import pandas as pd
-import numpy as np
 from sklearn import linear_model
+from typing import Tuple
 
+from ads.common.object_storage_details import ObjectStorageDetails
 from ads.opctl import logger
-
-from ..operator_config import AnomalyOperatorConfig, AnomalyOperatorSpec
-from .anomaly_dataset import AnomalyDatasets, AnomalyOutput, TestData
 from ads.opctl.operator.lowcode.anomaly.const import OutputColumns, SupportedMetrics
-from ..const import SupportedModels
+from ads.opctl.operator.lowcode.anomaly.utils import _build_metrics_df, default_signer
 from ads.opctl.operator.lowcode.common.utils import (
     human_time_friendly,
     enable_print,
     disable_print,
     write_data,
-    merge_category_columns,
-    find_output_dirname,
 )
-from ads.opctl.operator.lowcode.anomaly.utils import _build_metrics_df, default_signer
-from ads.common.object_storage_details import ObjectStorageDetails
+from .anomaly_dataset import AnomalyDatasets, AnomalyOutput, TestData
+from ..const import SupportedModels
+from ..operator_config import AnomalyOperatorConfig, AnomalyOperatorSpec
 
 
 class AnomalyOperatorBaseModel(ABC):
@@ -246,7 +242,7 @@ def _save_report(
         """Saves resulting reports to the given folder."""
         import report_creator as rc
 
-        unique_output_dir = find_output_dirname(self.spec.output_directory)
+        unique_output_dir = self.spec.output_directory.url
 
         if ObjectStorageDetails.is_oci_path(unique_output_dir):
             storage_options = default_signer()
@@ -320,11 +316,11 @@ def _fallback_build_model(self):
         # Iterate over the full_data_dict items
         for target, df in self.datasets.full_data_dict.items():
             est = linear_model.SGDOneClassSVM(random_state=42)
-            est.fit(df[target].values.reshape(-1, 1))
+            est.fit(df[self.spec.target_column].fillna(0).values.reshape(-1, 1))
             y_pred = np.vectorize(self.outlier_map.get)(
-                est.predict(df[target].values.reshape(-1, 1))
+                est.predict(df[self.spec.target_column].fillna(0).values.reshape(-1, 1))
             )
-            scores = est.score_samples(df[target].values.reshape(-1, 1))
+            scores = est.score_samples(df[self.spec.target_column].fillna(0).values.reshape(-1, 1))
 
             anomaly = pd.DataFrame(
                 {date_column: df[date_column], OutputColumns.ANOMALY_COL: y_pred}

ads/opctl/operator/lowcode/anomaly/operator_config.py

@@ -16,6 +16,7 @@
     InputData,
 )
 from .const import SupportedModels
+from ads.opctl.operator.lowcode.common.utils import find_output_dirname
 
 
 @dataclass(repr=True)
@@ -79,6 +80,7 @@ class AnomalyOperatorSpec(DataClassSerializable):
 
     def __post_init__(self):
         """Adjusts the specification details."""
+        self.output_directory = self.output_directory or OutputDirectory(url=find_output_dirname(self.output_directory))
         self.report_file_name = self.report_file_name or "report.html"
         self.report_theme = self.report_theme or "light"
         self.inliers_filename = self.inliers_filename or "inliers.csv"

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

@@ -349,9 +349,8 @@ spec:
     model:
       type: string
       required: false
-      default: automlx
+      default: autots
       allowed:
-        - automlx
         - autots
         - auto
       meta:

ads/opctl/operator/lowcode/anomaly/utils.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 os
@@ -77,5 +77,6 @@ def default_signer(**kwargs):
 
     return default_signer(**kwargs)
 
+
 def select_auto_model(datasets, operator_config):
-    return SupportedModels.AutoMLX
+    return SupportedModels.AutoTS

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

@@ -97,7 +97,8 @@ def _set_series_id_column(self, df):
                 for value in merged_values:
                     self._target_category_columns_map[value] = df[df[DataColumns.Series] == value][self.target_category_columns].drop_duplicates().iloc[0].to_dict()
 
-            df = df.drop(self.target_category_columns, axis=1)
+            if self.target_category_columns != [DataColumns.Series]:
+                df = df.drop(self.target_category_columns, axis=1)
         return df
 
     def _format_datetime_col(self, df):

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

@@ -215,7 +215,7 @@ def human_time_friendly(seconds):
 
 
 def find_output_dirname(output_dir: OutputDirectory):
-    if output_dir:
+    if output_dir and output_dir.url:
         return output_dir.url
     output_dir = "results"