How to train a model on a data where there are multiple data inside a data point?

Question

How to train a model on a data where there are multiple data inside a data point?

Bhaskar Dhariyal

2022年5月17日 17:08

I'm trying to do prediction on capacity column, however each data point consist of more data.

Each data point represent a cycle data. Each cycle has a capacity. Each cycle runs for some time duration, and in that duration some data is collected over which capacity is dependant

I tried exploding the dataset and copying the capacity values to each row, but that shouldn't be the case because each row will get different capacity predicted. Is there a way to train such kind of dataset?

Topic data-mining machine-learning

Category Data Science

Joey Fueng · Accepted Answer · 2019年8月1日 20:12

1

Joey Fueng answered at 2019年8月1日 20:12

What's the difference between different rows. In addition to Nikita's answer, you may want to consider the temporal correlations.

Nikita Vikhe · Accepted Answer · 2019年8月1日 18:34

1

Nikita Vikhe answered at 2019年8月1日 18:34

If your list are of fixed size you can separate them in different columns.e.g. load1,load2... If thats not the case, you need to define some statistics for the cycles like average load, max_load, min_load..

How to train a model on a data where there are multiple data inside a data point?

About