Skip to main content
Version: Beta 🚧

Dataset

Summary​

Persisted data consisting of entity & request keys, timestamps, and calculated features. Datasets are associated with either a FeatureService or FeatureView.
 
There are 2 types of Datasets: Saved and Logged.
 
Saved Datasets are generated manually when calling .start_dataset_job() on Tecton DataFrame, ie:
 
Logged Datasets are generated automatically when declaring a FeatureService with LoggingConfig, and the data is continuously added to it when requesting online data from the FeatureService.
 
To get an existing Dataset, call workspace.get_dataset().

Example

data_frame = get_features_for_events(my_spine)
data_frame.start_dataset_job(dataset_name='my_training_dataset:V1')

Attributes​

NameData TypeDescription
is_archivedboolBoolean indicating if the dataset is archived.
namestrName of the dataset.

Methods​

NameDescription
__init__(...)Initialize self. See help(type(self)) for accurate signature.
to_dataframe(...)Loads the data and returns it as TectonDataFrame

to_dataframe(...)​

Loads the data and returns it as TectonDataFrame

Parameters

Returns

TectonDataFrame

Was this page helpful?