NA impact in Caret Train

Question

Following the example reported in the link below I have the following error:

Using nnet for prediction, am i doing it right?

Error in na.fail.default(list(y = c(0, 0.0998334166468282, 0.198669330795061, : missing values in object

To solve this error I use the condition na.action = na.omit

#Fit model
model <- train(y ~ x1 + x2, te, method='nnet', linout=TRUE, trace = FALSE,
               #Grid of tuning parameters to try:
               tuneGrid=expand.grid(.size=c(1,5,10),.decay=c(0,0.001,0.1)),
               na.action = na.omit) 
ps <- predict(model, te)

is.na(te)
nrow(te)
nrow(ps)

Is this condition the only way to proceed?

In fact the consequence is that the number of rows of the ps is different to the number of ps data.

Answer 1

Please try again executing the same above code by removing steps_per_epoch and validation_steps from model.fit:

model.fit(training_set,
          #steps_per_epoch = 10,
          epochs = 25,
          validation_data = val_set,
         # validation_steps = 4
          )

Steps_per_epoch and validation_steps are not correct. Removing these from model will itself count the steps_per_epoch as per given images_count and batch_size. Check this similar answer for reference.

As from warning, it shows Model.fit_generator is deprecated. You can use model.fit instead to remove the warning. Please let us know if the issue still persists.