Available in: GBM, DRF, Deep Learning, GLM, GAM, PCA, GLRM, Naïve-Bayes, K-Means, Stacked Ensembles, AutoML, XGBoost
There may be instances when your dataset includes more information than you want to be included when building a model. Use the
x parameter to specify a vector containing the names or indices of the predictor variables to use when building the model. If
x is missing, then all columns except
y are used.
Note that this is a strict parameter that takes into account the exact string of the column name. So, for example, if your dataset includes one column named Type and another column named Types, and you specify
x=["type"], then the algorithm will only include the Type column and will ignore the Types column.