predict-methods function

predict method for fit objects (rminer)

Methods

• signature(object = "model"): describe this method here

Arguments

• object: a model object created by fit
• newdata: a data frame or matrix containing new data

Details

Returns predictions for a fit model. Note: the ... optional argument is currently only used by cubist model (see example).

Returns

If task is prob returns a matrix, where each column is the class probability.

If task is class returns a factor.

If task is reg returns a numeric vector.

See Also

fit, mining, mgraph, mmetric, savemining, CasesSeries, lforecast and Importance.

References

• To check for more details about rminer and for citation purposes:

  P. Cortez.

  Data Mining with Neural Networks and Support Vector Machines Using the R/rminer Tool.

  In P. Perner (Ed.), Advances in Data Mining - Applications and Theoretical Aspects 10th Industrial Conference on Data Mining (ICDM 2010), Lecture Notes in Artificial Intelligence 6171, pp. 572-583, Berlin, Germany, July, 2010. Springer. ISBN: 978-3-642-14399-1.

  @Springer: https://link.springer.com/chapter/10.1007/978-3-642-14400-4_44

  http://www3.dsi.uminho.pt/pcortez/2010-rminer.pdf

• This tutorial shows additional code examples:

  P. Cortez.

  A tutorial on using the rminer R package for data mining tasks.

  Teaching Report, Department of Information Systems, ALGORITMI Research Centre, Engineering School, University of Minho, Guimaraes, Portugal, July 2015.

  http://hdl.handle.net/1822/36210

Examples

### simple classification example with logistic regression
data(iris)
M=fit(Species~.,iris,model="lr")
P=predict(M,iris)
print(mmetric(iris$Species,P,"CONF")) # confusion matrix

### simple regression example
data(sa_ssin)
H=holdout(sa_ssin$y,ratio=0.5,seed=12345)
Y=sa_ssin[H$ts,]$y # desired test set
# fit multiple regression on training data (half of samples)
M=fit(y~.,sa_ssin[H$tr,],model="mr") # multiple regression
P1=predict(M,sa_ssin[H$ts,]) # predictions on test set
print(mmetric(Y,P1,"MAE")) # mean absolute error

### fit cubist model
M=fit(y~.,sa_ssin[H$tr,],model="cubist") #
P2=predict(M,sa_ssin[H$ts,],neighbors=3) #
print(mmetric(Y,P2,"MAE")) # mean absolute error
P3=predict(M,sa_ssin[H$ts,],neighbors=7) #
print(mmetric(Y,P3,"MAE")) # mean absolute error

### check fit for more examples