search

gzerveas / mvts_transformer

Multivariate Time Series Transformer, public version
MIT License
718 stars 169 forks source link

how can the code be runnable for dataframe of column size 18260? #50

Open Shubhamsg17 opened 1 year ago

Shubhamsg17 commented 1 year ago

2023-04-12 17:47:26,636 | WARNING : Not all samples have same length: maximum length set to 18260 2023-04-12 17:47:28,605 | INFO : 1212 samples may be used for training 2023-04-12 17:47:28,605 | INFO : 304 samples will be used for validation 2023-04-12 17:47:28,605 | INFO : 0 samples will be used for testing

2023-04-12 17:53:36,348 | INFO : Total number of parameters: 3656002 2023-04-12 17:53:36,348 | INFO : Trainable parameters: 3656002

gzerveas commented 1 year ago

Hi, it's not clear to me what you are trying to achieve. Does your time series really have 18260 features/variables per time step?

Shubhamsg17 commented 1 year ago

Currently i have dataset with single variant time series with dataframe size of 9000 columns..so when i run the same code using this datset im getting error..how should i make changes to make it work

gzerveas commented 1 year ago

Ok, so what do the columns represent? From what I understand, you have a dataset where a single training example is a time series of a single variable and length 18260? Do you have multiple training examples, or your entire dataset is a single long time series?

Shubhamsg17 commented 1 year ago

Its Single varient time series of length 9000