Description Usage Arguments Value
Returns cross validation data from folds (i.e. if 2 folds, then aggregate the data on fold 2 after training only on fold 1 & the data on fold 1 after training only on fold 2). This is helps in feature engineering.
1 2 | extractGenericJuice(X_train, Y_train, numFolds, parCV, numCores, seedNum,
verbose_p, fn, fn_params)
|
X_train |
Training Data (excludes the response/target we wish to predict ) that will be fed into the pipeline function. |
Y_train |
Training Response/Target - The response/target that will be fed into the pipeline function. |
numFolds |
Integer indicating the number of folds to use to extract data |
parCV |
Boolean indicating whether to parallelize the extraction prodcedure. |
numCores |
Integer indicating the number of cores to use when generating predictions. |
seedNum |
Integer indicating the seed number. Using the same seed will generate the same folds. |
verbose_p |
Boolean indicating if prediction extraction details should be printed out the screen. |
fn |
The pipeline function. The pipeline function must take parameters training data, training response, validation data, validation response. See examples for details. |
fn_params |
Additional parameters to supply to the pipeline function. See examples for details. |
CV Fold Predictions
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.