The feature engineering process involves three key stages: experimentation, production, and evaluation. Collaboration among data scientists is crucial during these stages, as it often leads to the creation of innovative features and insights. Featureform streamlines the feature engineering workflow, facilitating collaboration and enhancing the efficiency of the entire process.
register_table
, register_file
, and register_directory
for registering initial data sets. Subsequently, you define transformations that build derivative training sets. Transformations involve decorating a method with metadata, specifying where it runs, inputs, and other relevant details.
client.dataframe
call.
client.dataframe
accepts either a tuple specifying the name and variant or the function object or data set object itself:
ff.register_training_set
method to create training sets by joining labels and features based on entity keys.
client.features
or client.training_set
methods.