train_across_buildings and train_across_buildings_chunk about neural-disaggregator HOT 4 CLOSED

Hello,
Every disaggregator has two methods train and train_across_buildings. The first one trains using one meter while the second receives an array of meters. Each of these methods use the train_on_chunk and the train_across_buildings_chunk. They separate a chunk of the data and train the model.

Basically the only difference is that train_across_buildings_chunk supports chunks from multiple buildings.

from neural-disaggregator.

Hello,
Every disaggregator has two methods train and train_across_buildings. The first one trains using one meter while the second receives an array of meters. Each of these methods use the train_on_chunk and the train_across_buildings_chunk. They separate a chunk of the data and train the model.

Basically the only difference is that train_across_buildings_chunk supports chunks from multiple buildings.

Thank you for your answer, I will try to train with the data of the series table to evaluate the performance of both ways.

from neural-disaggregator.

Hello,
Every disaggregator has two methods train and train_across_buildings. The first one trains using one meter while the second receives an array of meters. Each of these methods use the train_on_chunk and the train_across_buildings_chunk. They separate a chunk of the data and train the model.
Basically the only difference is that train_across_buildings_chunk supports chunks from multiple buildings.

Thank you for your answer, I will try to train with the data of the series table to evaluate the performance of both ways.
Hello, sorry to bother you, if I want to use a series of tables for training, how can I modify the code on the original code, does the "nilmtk" toolkit provide training data using some table data, I don't seem to find it. Hope to get your help, thank you.

from neural-disaggregator.

Hello,
Every disaggregator has two methods train and train_across_buildings. The first one trains using one meter while the second receives an array of meters. Each of these methods use the train_on_chunk and the train_across_buildings_chunk. They separate a chunk of the data and train the model.
Basically the only difference is that train_across_buildings_chunk supports chunks from multiple buildings.

Thank you for your answer, I will try to train with the data of the series table to evaluate the performance of both ways.

Please note that you are not supposed to call the train_on_chunk and train_across_buildings_chunk directly. Instead use the methods train and train_across_buildings.

from neural-disaggregator.