Home>

I examined the arguments in model_selection.train_test_split.
Then the following contents will appear.

test_size: Specify the percentage of test data between 0.0 and 1.0.
train_size: Specifies the percentage of training data between 0.0 and 1.0.

I was wondering how to recognize training data and test data here.

Please check if your recognition of this function is correct below.

model_selection.train_test_split returns two lists for the given data.

Take the ratio of the previous list of the two lists as an argument: train_size
The ratio of the list after the two lists is specified by the argument: test_size.

Therefore
data_train, data_test =
Like
Training data, test data
Therefore, if you decide the ratio of the previous list, you can change the ratio of training data, and if you change the ratio of the latter list, you can change the ratio of test data.

Is it this recognition?

"" "Classified into learning data and verification data" ""
from sklearn import model_selection
data_train, data_test = model_selection.train_test_split (data, train_size = 0.8)