add options to disable file generation

Author: ahosler

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

@@ -469,17 +469,18 @@ def _save_report(
         result_df: pd.DataFrame,
         metrics_df: pd.DataFrame,
         test_metrics_df: pd.DataFrame,
-        # test_data: pd.DataFrame,
+        test_data: pd.DataFrame,
     ):
         """Saves resulting reports to the given folder."""
 
         unique_output_dir = self.spec.output_directory.url
         results = ForecastResults()
 
-        if ObjectStorageDetails.is_oci_path(unique_output_dir):
-            storage_options = default_signer()
-        else:
-            storage_options = {}
+        storage_options = (
+            default_signer()
+            if ObjectStorageDetails.is_oci_path(unique_output_dir)
+            else {}
+        )
 
         # report-creator html report
         if self.spec.generate_report:
@@ -510,12 +511,13 @@ def _save_report(
             if self.target_cat_col
             else result_df.drop(DataColumns.Series, axis=1)
         )
-        write_data(
-            data=result_df,
-            filename=os.path.join(unique_output_dir, self.spec.forecast_filename),
-            format="csv",
-            storage_options=storage_options,
-        )
+        if self.spec.generate_forecast_file:
+            write_data(
+                data=result_df,
+                filename=os.path.join(unique_output_dir, self.spec.forecast_filename),
+                format="csv",
+                storage_options=storage_options,
+            )
         results.set_forecast(result_df)
 
         # metrics csv report
@@ -529,15 +531,16 @@ def _save_report(
                 metrics_df_formatted = metrics_df.reset_index().rename(
                     {"index": "metrics", "Series 1": metrics_col_name}, axis=1
                 )
-                write_data(
-                    data=metrics_df_formatted,
-                    filename=os.path.join(
-                        unique_output_dir, self.spec.metrics_filename
-                    ),
-                    format="csv",
-                    storage_options=storage_options,
-                    index=False,
-                )
+                if self.spec.generate_metrics_file:
+                    write_data(
+                        data=metrics_df_formatted,
+                        filename=os.path.join(
+                            unique_output_dir, self.spec.metrics_filename
+                        ),
+                        format="csv",
+                        storage_options=storage_options,
+                        index=False,
+                    )
                 results.set_metrics(metrics_df_formatted)
             else:
                 logger.warn(
@@ -550,15 +553,16 @@ def _save_report(
                     test_metrics_df_formatted = test_metrics_df.reset_index().rename(
                         {"index": "metrics", "Series 1": metrics_col_name}, axis=1
                     )
-                    write_data(
-                        data=test_metrics_df_formatted,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.test_metrics_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=False,
-                    )
+                    if self.spec.generate_metrics_file:
+                        write_data(
+                            data=test_metrics_df_formatted,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.test_metrics_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=False,
+                        )
                     results.set_test_metrics(test_metrics_df_formatted)
                 else:
                     logger.warn(
@@ -568,31 +572,33 @@ def _save_report(
         if self.spec.generate_explanations:
             try:
                 if not self.formatted_global_explanation.empty:
-                    write_data(
-                        data=self.formatted_global_explanation,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.global_explanation_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=True,
-                    )
+                    if not self.spec.generate_explanations_file:
+                        write_data(
+                            data=self.formatted_global_explanation,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.global_explanation_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=True,
+                        )
                     results.set_global_explanations(self.formatted_global_explanation)
                 else:
                     logger.warn(
                         f"Attempted to generate global explanations for the {self.spec.global_explanation_filename} file, but an issue occured in formatting the explanations."
                     )
 
                 if not self.formatted_local_explanation.empty:
-                    write_data(
-                        data=self.formatted_local_explanation,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.local_explanation_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=True,
-                    )
+                    if not self.spec.generate_explanations_file:
+                        write_data(
+                            data=self.formatted_local_explanation,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.local_explanation_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=True,
+                        )
                     results.set_local_explanations(self.formatted_local_explanation)
                 else:
                     logger.warn(

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

@@ -18,19 +18,23 @@
 
 from .const import SpeedAccuracyMode, SupportedMetrics, SupportedModels
 
+
 @dataclass
 class AutoScaling(DataClassSerializable):
     """Class representing simple autoscaling policy"""
+
     minimum_instance: int = 1
     maximum_instance: int = None
     cool_down_in_seconds: int = 600
     scale_in_threshold: int = 10
     scale_out_threshold: int = 80
     scaling_metric: str = "CPU_UTILIZATION"
 
+
 @dataclass(repr=True)
 class ModelDeploymentServer(DataClassSerializable):
     """Class representing model deployment server specification for whatif-analysis."""
+
     display_name: str = None
     initial_shape: str = None
     description: str = None
@@ -42,10 +46,13 @@ class ModelDeploymentServer(DataClassSerializable):
 @dataclass(repr=True)
 class WhatIfAnalysis(DataClassSerializable):
     """Class representing operator specification for whatif-analysis."""
+
     model_display_name: str = None
     compartment_id: str = None
     project_id: str = None
-    model_deployment: ModelDeploymentServer = field(default_factory=ModelDeploymentServer)
+    model_deployment: ModelDeploymentServer = field(
+        default_factory=ModelDeploymentServer
+    )
 
 
 @dataclass(repr=True)
@@ -106,8 +113,11 @@ class ForecastOperatorSpec(DataClassSerializable):
     datetime_column: DateTimeColumn = field(default_factory=DateTimeColumn)
     target_category_columns: List[str] = field(default_factory=list)
     generate_report: bool = None
+    generate_forecast_file: bool = None
     generate_metrics: bool = None
+    generate_metrics_file: bool = None
     generate_explanations: bool = None
+    generate_explanations_file: bool = None
     explanations_accuracy_mode: str = None
     horizon: int = None
     model: str = None
@@ -126,7 +136,9 @@ def __post_init__(self):
         self.output_directory = self.output_directory or OutputDirectory(
             url=find_output_dirname(self.output_directory)
         )
-        self.generate_model_pickle = True if self.generate_model_pickle or self.what_if_analysis else False
+        self.generate_model_pickle = (
+            True if self.generate_model_pickle or self.what_if_analysis else False
+        )
         self.metric = (self.metric or "").lower() or SupportedMetrics.SMAPE.lower()
         self.model = self.model or SupportedModels.Prophet
         self.confidence_interval_width = self.confidence_interval_width or 0.80
@@ -144,6 +156,21 @@ def __post_init__(self):
         self.generate_metrics = (
             self.generate_metrics if self.generate_metrics is not None else True
         )
+        self.generate_metrics_file = (
+            self.generate_metrics_file
+            if self.generate_metrics_file is not None
+            else True
+        )
+        self.generate_forecast_file = (
+            self.generate_forecast_file
+            if self.generate_forecast_file is not None
+            else True
+        )
+        self.generate_explanations_file = (
+            self.generate_explanations_file
+            if self.generate_explanations_file is not None
+            else True
+        )
         # For Explanations Generation. When user doesn't specify defaults to False
         self.generate_explanations = (
             self.generate_explanations

docs/source/user_guide/operators/forecast_operator/development.rst

@@ -125,6 +125,35 @@ Before running operators on a job, users must configure their output directory.
         horizon: 3
         target_column: y
 
+
+Exclude Writing Certain Output Files
+====================================
+
+You can choose to exclude certain files from being written to the output folder. This may be because you are calling the API, and not using the output folder. The yaml options below are ``True`` by default, but can be set to ``False`` to prevent file generation.
+
+.. code-block:: yaml
+
+    kind: operator
+    type: forecast
+    version: v1
+    spec:
+        datetime_column:
+            name: ds
+        historical_data:
+            url: oci://<bucket_name>@<namespace_name>/example_yosemite_temps.csv
+        output_directory:
+            url: oci://<bucket_name>@<namespace_name>/my_results/
+        horizon: 3
+        target_column: y
+        generate_report: True
+        generate_forecast_file: False
+        generate_metrics_file: False
+        generate_explanations: True
+        generate_explanations_file: False
+
+The above example will save a report.html to ``oci://<bucket_name>@<namespace_name>/my_results/``, but it will NOT save other files.
+
+
 Ingesting and Interpreting Outputs
 ==================================
 

tests/operators/forecast/test_errors.py

@@ -921,5 +921,40 @@ def test_report_title(operator_setup, model):
         assert False, "Report Title was not set"
 
 
+@pytest.mark.parametrize("model", ["prophet"])
+def test_generate_files(operator_setup, model):
+    from ads.opctl.operator.lowcode.forecast.__main__ import operate
+    from ads.opctl.operator.lowcode.forecast.operator_config import (
+        ForecastOperatorConfig,
+    )
+
+    yaml_i = TEMPLATE_YAML.copy()
+    yaml_i["spec"]["horizon"] = 10
+    yaml_i["spec"]["model"] = model
+    yaml_i["spec"]["historical_data"] = {"format": "pandas"}
+    yaml_i["spec"]["target_column"] = TARGET_COL.name
+    yaml_i["spec"]["datetime_column"]["name"] = HISTORICAL_DATETIME_COL.name
+    yaml_i["spec"]["report_title"] = "Skibidi ADS Skibidi"
+    yaml_i["spec"]["output_directory"]["url"] = operator_setup
+    yaml_i["spec"]["generate_explanations_file"] = False
+    yaml_i["spec"]["generate_forecast_file"] = False
+    yaml_i["spec"]["generate_metrics_file"] = False
+
+    df = pd.concat([HISTORICAL_DATETIME_COL[:15], TARGET_COL[:15]], axis=1)
+    yaml_i["spec"]["historical_data"]["data"] = df
+    operator_config = ForecastOperatorConfig.from_dict(yaml_i)
+    results = operate(operator_config)
+    files = os.listdir(operator_setup)
+    assert "report.html" in files, "Failed to generate report"
+    assert (
+        "forecast.csv" not in files
+    ), "Generated forecast file, but `generate_forecast_file` was set False"
+    assert (
+        "metrics.csv" not in files
+    ), "Generated metrics file, but `generate_metrics_file` was set False"
+    assert not results.get_forecast().empty
+    assert not results.get_metrics().empty
+
+
 if __name__ == "__main__":
     pass