PriceIndices (version 0.0.7)

data_classifying: Predicting product COICOP levels via the machine learning model

Description

This function predicts product COICOP levels via the selected machine learning model.

Usage

data_classifying(model = list(), data)

Value

This function provides the indicated data set with an additional column, i.e. coicop_predicted, which is obtained by using the selected machine learning model.

Arguments

model

A list of 8 elements which identify the previously built machine learning model (the list is obtained via the model_classification function).

data

A data set for the model (products with their characteristics). This data set must contain all the columns which were used in the built model.

Examples

#Building the model
my.grid=list(eta=c(0.01,0.02,0.05),subsample=c(0.5))
data_train<-dplyr::filter(dataCOICOP,dataCOICOP$time<=as.Date("2020-08-01"))
data_test<-dplyr::filter(dataCOICOP,dataCOICOP$time>as.Date("2020-08-01"))
ML<-model_classification(data_train,data_test,grid=my.grid,
indicators=c("prodID","unit","description"),key_words=c("milk"),rounds=50)
#Data classification
data_classifying(ML, data_test)