Post-Processing#
Most sources of battery data provide the voltage and current over time, but the other properties which are derived from them may be missing. The battery data toolkit provides “post-processing” classes which add compute these derived data sources.
All post-processing tools are based on the BaseFeatureComputer
class
and, as a result, provide a compute_features()
function that adds
new information to a battery dataset.
Use them by first creating the tool and invoking that method with
a BatteryDataset
:
computer = FeatureComputer()
new_columns = computer.compute_features(data)
New columns will be added to a part of the dataset (e.g., the cycle-level statistics) and those new columns will be returned from the function.
The feature computers fall into two categories:
RawDataEnhancer
, which add information to the raw data as a function of timeCycleSummarizer
, which summarize the raw data and add new columns to thecycle_stats
Note
Post-processing is only supported for battdat.data.CellDataset
for now.
Integral Quantities#
Functions which add columns associated with the accumulated values of data in other columns.
Time#
Compute columns which are derived fields associated with the relative time or timespans of data.