Quick start
To get started:
Prepare a dataset using the catboost.load_pool function:
library(catboost) features <- data.frame(feature1 = c(1, 2, 3), feature2 = c('A', 'B', 'C')) labels <- c(0, 0, 1) train_pool <- catboost.load_pool(data = features, label = labels)
Copied to clipboardThe dataset is created from a synthetic
data.frame
calledfeatures
in this example. Thedata
argument can also reference a dataset file or a matrix of numerical features.- Train the model using the catboost.train function:
model <- catboost.train(train_pool, NULL, params = list(loss_function = 'Logloss', iterations = 100, metric_period=10))
Copied to clipboardThe second argument in this example (test_pool) is set to NULL. It can also be used to pass a validation dataset (the labelled data used for estimating the prediction error while training). The params argument is used to specify the training parameters.
Apply the trained model using the catboost.predict function:
real_data <- data.frame(feature1 = c(2, 1, 3), feature2 = c('D', 'B', 'C')) real_pool <- catboost.load_pool(real_data) prediction <- catboost.predict(model, real_pool) print(prediction)
Copied to clipboard