same_shape {dataPreparation} | R Documentation |
Give same shape
Description
Transform data_set
into the same shape as reference_set
. Especially this
function will be useful to make your test set have the same shape as your train set.
Usage
same_shape(data_set, reference_set, verbose = TRUE)
Arguments
data_set |
Matrix, data.frame or data.table to transform |
reference_set |
Matrix, data.frame or data.table |
verbose |
Should the algorithm talk? (logical, default to TRUE) |
Details
This function will make sure that data_set
and reference_set
have the same class
have exactly the same columns
have columns with exactly the same class
have factor factor with exactly the same levels
You should always use this function before applying your model on a new data set to make sure that everything will go smoothly. But if this function change a lot of stuff you should have a look to your preparation process, there might be something wrong.
Value
Return data_set
transformed in order to make it have the same shape as
reference_set
Examples
## Not run:
# Build a train and a test
data(tiny_messy_adult)
data(adult)
train <- messy_adult
test <- adult # So test will have missing columns
# Prepare them
train <- prepare_set(train, verbose = FALSE, key = "country")
test <- prepare_set(test, verbose = FALSE, key = "country")
# Give them the same shape
test <- same_shape(test, train)
# As one can see in log, a lot of small change had to be done.
# This is an extreme case but you get the idea.
## End(Not run)
# "##NOT RUN:" mean that this example hasn't been run on CRAN since its long. But you can run it!