predict.cv_misvm {mildsvm}

Predict method for cv_misvm object

Description

Predict method for cv_misvm object

Usage

## S3 method for class 'cv_misvm'
predict(
  object,
  new_data,
  type = c("class", "raw"),
  layer = c("bag", "instance"),
  new_bags = "bag_name",
  ...
)

Arguments

object

An object of class cv_misvm.

new_data

A data frame to predict from. This needs to have all of the features that the data was originally fitted with.

type

If 'class', return predicted values with threshold of 0 as -1 or +1. If 'raw', return the raw predicted scores.

layer

If 'bag', return predictions at the bag level. If 'instance', return predictions at the instance level.

new_bags

A character or character vector. Can specify a singular character that provides the column name for the bag names in new_data (default 'bag_name'). Can also specify a vector of length nrow(new_data) that has bag name for each row.

...

Arguments passed to or from other methods.

Value

A tibble with nrow(new_data) rows. If type = 'class', the tibble will have a column '.pred_class'. If type = 'raw', the tibble will have a column '.pred'.

Author(s)

Sean Kent

Examples

mil_data <- generate_mild_df(
  nbag = 10,
  nsample = 20,
  positive_degree = 3
)
df1 <- build_instance_feature(mil_data, seq(0.05, 0.95, length.out = 10))
mdl1 <- cv_misvm(x = df1[, 4:123], y = df1$bag_label,
                 bags = df1$bag_name, cost_seq = 2^(-2:2),
                 n_fold = 3, method = "heuristic")

predict(mdl1, new_data = df1, type = "raw", layer = "bag")

# summarize predictions at the bag layer
suppressWarnings(library(dplyr))
df1 %>%
  bind_cols(predict(mdl1, df1, type = "class")) %>%
  bind_cols(predict(mdl1, df1, type = "raw")) %>%
  distinct(bag_name, bag_label, .pred_class, .pred)