quartic_sdk.model.BaseReckonExpression¶
Module Contents¶
Classes¶
A Base Class Model for Wrapping User Models into Quartic Deployments. |
-
class
quartic_sdk.model.BaseReckonExpression.BaseReckonExpression(log_level: str = 'INFO')¶ A Base Class Model for Wrapping User Models into Quartic Deployments. User needs to inherit this class and override the evaluate method with his operations
Note: Please do not overwrite method :func: save as it contains utilities to validate and deploy expression to the Quartic AI Platform
save : private save method to save expression to the Quartic AI Platform predict : abstract predict method which needs to overridden
-
save(self, client, output_tag_name: str, needs: List[int], asset: int, is_streaming: bool, tag_category: str, test_df: pandas.DataFrame, update: bool = False)¶ - Parameters
client – Quartic GraphQLClient
output_tag_name – name for Expression output tag
needs – Feature Tag ids used in the model
asset – Asset Id
is_streaming – Streaming
tag_category – Tag Category
test_df – Test input dataframe to validate input and prediction output in agreement with Quartic AI Platform
update – Optional - Update the model if already exists
- Returns
None on successfully storing the model to the Quartic AI Platform
-
abstract
evaluate(self, input_df: pandas.DataFrame) → pandas.Series¶ Abstract method for custom predict method :param input_df: Input Data frame for prediction :return: Returns pd
-
with_window(duration)¶ This is decorator method for window support User can decorate predict method with this decorator for window support :param duration: window duration in sec :return: None
-
moving_window_evaluate(self, input_df: pandas.DataFrame, previous_df: pandas.DataFrame)¶ This method calls predict for with window model along with respective window data for each row in input_df. :param input_df: input dataframe :param previous_df: previous dataframe for with window model :return: pandas series of predictions along with timestamps respective to input_df records
-