I know we use
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test= train_test_split(x,y,
test_size=0.4,
shuffle=True,
random_state=123)
to train the data and test the data
However I think it is not appropriate to use this in time series data.
To be more specific to time series data:
For example I have a data set A of 3 years of something.
and data set B, C, D, E, which each has 1 month of data.
and we need to have prediction of 3 days after the each data B, C, D, E.
In this case which model should I use to predict the above.
question from:
https://stackoverflow.com/questions/65557873/train-test-split-in-time-series-data 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…