quartic_sdk.model.helpers
¶
Module Contents¶
Classes¶
Contains utils to pickle model and add checksum |
-
class
quartic_sdk.model.helpers.
Validation
¶ Bases:
object
-
classmethod
get_model_prediction_and_time
(cls, model, test_df)¶ evaluates prediction of model with test data frame :param model: Instance BaseQuarticModel :param test_df: Test Dataframe :return: tuple of prediction and processing time
-
classmethod
validate_prediction_output
(cls, result: pandas.Series)¶ Validates if prediction output is of type Series and values of series are float64 :param result: pandas series :return: None :raises: InvalidPredictionException
-
classmethod
validate_window_prediction_output
(cls, result: Union[int, float, None])¶ Validates if the prediction for window model is returning a single value or None (allowed - int/float/None)
-
classmethod
validate_model
(cls, model, test_df)¶ Validates the model for size and performance :param model: Instance of BaseQuarticModel :param test_df: Test dataframe
-
classmethod
-
class
quartic_sdk.model.helpers.
ModelUtils
¶ Bases:
object
Contains utils to pickle model and add checksum
-
classmethod
get_checksum
(cls, model_bytes)¶ Calculates the checksum for given byte array :param model_bytes: pickeled model :return: Returns the checksum of model
-
classmethod
get_pickled_object
(cls, object)¶ Generates pickle for model and adds checksum to it :param object: Model to pickle :return: Pickled Model as string
-
classmethod
get_performance_test_df
(cls, test_df: pandas.DataFrame)¶ Creates a Test data frame of size 100 rows(for 30sec batch approximation) :param test_df: Test Data frame :return: Returns test dataframe with configured number of rows
-
classmethod