time_stamp¶

getml.data.roles.time_stamp = 'time_stamp'¶

Ensures causality in the data model and marks time column as numerical ingredient

Role required to establish a relation between two Placeholder, the abstract representation of the DataFrame, by using the join() method (see Data model). See chapter Data model for details.

This role ensures causality by incorporating only those rows of a second Placeholder in the join() operation for which the time stamp is at most as recent as the one of the associated column. Since usually it’s the peripheral table that is joined on the population table (see Tables), this ensures no information from the future is considered during training.

columns of this role will be handled by the feature engineering algorithm the same way as Numerical are.

Please note that getML does not handle UNIX time stamps but, instead, encodes time as multiples and fractions of days since the 01.01.1970 (1970-01-01T00:00:00). For example $7.334722222222222 = 7 + 6/24 + 2/(24*60)$ would be interpreted 1970-01-08T06:02:00.