Recipes¶

class datarobot.models.recipe.Recipe¶

Data wrangling entity, which contains all information needed to transform dataset and generate SQL.

classmethod update_downsampling(recipe_id, downsampling)¶

Set downsampling for the recipe, applied during publishing.

• Return type: Recipe

retrieve_preview(max_wait=600, number_of_operations_to_use=None)¶

Retrieve preview and compute it, if absent.

• Parameters:
  • max_wait (int) – The number of seconds to wait for the result.
  • number_of_operations_to_use (Optional[int]) – Request preview for particular number of operations.
• Returns: preview
• Return type: dict

retrieve_insights(max_wait=600, number_of_operations_to_use=None)¶

Retrieve insights for the sample. When preview is requested, the insights job starts automatically.

• Parameters:
  • max_wait (int) – The number of seconds to wait for the result.
  • number_of_operations_to_use (Optional[int]) – Retrieves insights for the specified number of operations. First, preview computation for the same number of operations must be submitted.
• Return type: Any

classmethod set_inputs(recipe_id, inputs)¶

Set inputs for the recipe.

• Return type: Recipe

classmethod set_operations(recipe_id, operations)¶

Set operations for the recipe.

• Return type: Recipe

classmethod set_recipe_metadata(recipe_id, metadata)¶

Update metadata for the recipe.

• Parameters:
  • recipe_id (str) – Recipe ID.
  • metadata (Dict[str, str]) – Dictionary of metadata to be updated.
• Returns: recipe – New recipe with updated metadata.
• Return type: Recipe

get_sql(operations=None)¶

Generate sql for the given recipe in a transient way, recipe is not modified. if operations is None, recipe operations are used to generate sql. if operations = [], recipe operations are ignored during sql generation. if operations is not empty list, generate sql for them.

• Return type: str

classmethod from_data_store(use_case, data_store, data_source_type, dialect, data_source_inputs, recipe_type=RecipeType.WRANGLING)¶

Create a wrangling recipe from data store.

• Return type: Recipe

classmethod from_dataset(use_case, dataset, dialect=None, inputs=None, recipe_type=RecipeType.WRANGLING, snapshot_policy=DataWranglingSnapshotPolicy.LATEST)¶

Create a wrangling recipe from dataset.

• Return type: Recipe

class datarobot.models.recipe.RecipeSettings¶

Settings, for example to apply at downsampling stage.

class datarobot.models.recipe.RecipeDatasetInput¶

Object, describing inputs for recipe transformations.

class datarobot.models.recipe.DatasetInput¶

class datarobot.models.recipe.DataSourceInput¶

Inputs required to create a new recipe from data store.

Recipe Operations¶

class datarobot.models.recipe_operation.WranglingOperation¶

class datarobot.models.recipe_operation.DownsamplingOperation¶

class datarobot.models.recipe_operation.SamplingOperation¶

class datarobot.models.recipe_operation.BaseTimeAwareTask¶

class datarobot.models.recipe_operation.TaskPlanElement¶

class datarobot.models.recipe_operation.CategoricalStats¶

class datarobot.models.recipe_operation.NumericStats¶

class datarobot.models.recipe_operation.Lags¶

class datarobot.models.recipe_operation.LagsOperation¶

Generate lags in a window.

class datarobot.models.recipe_operation.WindowCategoricalStatsOperation¶

Generate rolling statistics in a window for categorical features.

class datarobot.models.recipe_operation.WindowNumericStatsOperation¶

Generate various rolling numeric statistics in a window. Output could be a several columns.

class datarobot.models.recipe_operation.TimeSeriesOperation¶

Operation to generate a dataset ready for time series modeling: with forecast point, forecast distances, known in advance columns, etc.

class datarobot.models.recipe_operation.ComputeNewOperation¶

class datarobot.models.recipe_operation.RenameColumnsOperation¶

class datarobot.models.recipe_operation.FilterCondition¶

class datarobot.models.recipe_operation.FilterOperation¶

Filter rows.

class datarobot.models.recipe_operation.DropColumnsOperation¶

class datarobot.models.recipe_operation.RandomSamplingOperation¶

class datarobot.models.recipe_operation.DatetimeSamplingOperation¶