Evaluate a Kerasnip Model

This function provides an kera_evaluate() method for model_fit objects created by kerasnip. It preprocesses the new data into the format expected by Keras and then calls keras3::evaluate() on the underlying model to compute the loss and any other metrics.

Usage

keras_evaluate(object, x, y = NULL, ...)

Arguments

object

A model_fit object produced by a kerasnip specification.

x

A data frame or matrix of new predictor data.

y

A vector or data frame of new outcome data corresponding to x.

...

Additional arguments passed on to keras3::evaluate() (e.g., batch_size).

Value

A named list containing the evaluation results (e.g., loss, accuracy). The names are determined by the metrics the model was compiled with.

Details

Evaluate a Fitted Kerasnip Model on New Data

Examples

if (FALSE) { # \dontrun{
if (keras::is_keras_available()) {

# 1. Define and fit a model ----
create_keras_sequential_spec(
  model_name = "my_mlp",
  layer_blocks = list(input_block, hidden_block, output_block),
  mode = "classification"
)

mlp_spec <- my_mlp(
  hidden_units = 32,
  compile_loss = "categorical_crossentropy",
  compile_optimizer = "adam",
  compile_metrics = "accuracy",
  fit_epochs = 5
) |> set_engine("keras")

x_train <- matrix(rnorm(100 * 10), ncol = 10)
y_train <- factor(sample(0:1, 100, replace = TRUE))
train_df <- data.frame(x = I(x_train), y = y_train)

fitted_mlp <- fit(mlp_spec, y ~ x, data = train_df)

# 2. Evaluate the model on new data ----
x_test <- matrix(rnorm(50 * 10), ncol = 10)
y_test <- factor(sample(0:1, 50, replace = TRUE))

eval_metrics <- keras_evaluate(fitted_mlp, x_test, y_test)
print(eval_metrics)

# 3. Extract the Keras model object ----
keras_model <- extract_keras_model(fitted_mlp)
summary(keras_model)

# 4. Extract the training history ----
history <- extract_keras_history(fitted_mlp)
plot(history)
}
} # }