Seperate data into train and test datasets. Data can be returned in a single dataset or in multiple
1 2 3 | ezr.split_data(dataset, perc = c(0.75), strata = NULL,
return_as_single_df = FALSE, seed = 2019,
datasplit_identifiers = c("train", "test", "valid"))
|
dataset |
dataset. H2o or regular. |
strata |
Default is NULL. This is for startified sampling. Not valid for h2o dataframes. |
return_as_single_df |
Return as a single dataframe. |
prop |
A vector of values. Only a single valid is needed for standard train/test split. If a 2nd value is entered then a valid dataset will be created. |
datasplit_identifiers. |
Assumed to be in this order: train/test/valid. You may call things otherwise, but the returned dataset may be named differently. |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.