midas: Multiple imputation (all-in-one)

In rMIDAS2: Multiple Imputation with 'MIDAS2' Denoising Autoencoders

Multiple imputation (all-in-one)

Description

Convenience function that fits a MIDAS model and generates imputations in a single call. Equivalent to calling midas_fit() followed by midas_transform().

Usage

midas(
  data,
  m = 5L,
  hidden_layers = c(256L, 128L, 64L),
  dropout_prob = 0.5,
  epochs = 75L,
  batch_size = 64L,
  lr = 0.001,
  corrupt_rate = 0.8,
  num_adj = 1,
  cat_adj = 1,
  bin_adj = 1,
  pos_adj = 1,
  omit_first = FALSE,
  seed = 89L,
  ...
)

Arguments

data	A data frame (may contain NA for missing values).
m	Integer. Number of imputations (default 5).
hidden_layers	Integer vector of hidden layer sizes (default c(256, 128, 64)).
dropout_prob	Numeric. Dropout probability (default 0.5).
epochs	Integer. Number of training epochs (default 75).
batch_size	Integer. Mini-batch size (default 64).
lr	Numeric. Learning rate (default 0.001).
corrupt_rate	Numeric. Corruption rate for denoising (default 0.8).
num_adj	Numeric. Loss multiplier for numeric columns (default 1).
cat_adj	Numeric. Loss multiplier for categorical columns (default 1).
bin_adj	Numeric. Loss multiplier for binary columns (default 1).
pos_adj	Numeric. Loss multiplier for positive columns (default 1).
omit_first	Logical. Omit first column from encoder input (default FALSE).
seed	Integer. Random seed (default 89).
...	Arguments forwarded to ensure_server().

Value

A list with model_id and imputations (a list of data frames).

Examples

## Not run: 
df <- data.frame(X1 = rnorm(200), X2 = rnorm(200))
df$X1[sample(200, 40)] <- NA
result <- midas(df, m = 5, epochs = 10)
head(result$imputations[[1]])

## End(Not run)

rMIDAS2 documentation built on March 12, 2026, 9:07 a.m.