# Fit orthogonal neural additive model Fits an interpretable neural additive model with post hoc orthogonalization for a given network architecture and user-specified feature sets. ```r onam( formula, list_of_deep_models, data, model = NULL, prediction_function = NULL, model_data = NULL, categorical_features = NULL, target = "continuous", n_ensemble = 10, epochs = 500, callback = NULL, progresstext = FALSE, verbose = 0 ) ``` ## Arguments - `formula`: Formula for model fitting. Specify deep parts with the same name as `list_of_deep_models`. - `list_of_deep_models`: List of named models used in `model_formula`. - `data`: Data to be fitted - `model`: Prediction model that is to be explained. Output of the model as returned from `prediction_function(model)` will be used as model output. If `NULL`(default), the outcome has to be present in `data`. - `prediction_function`: Prediction function to be used to generate the outcome. Only used if `model` is specified. If `NULL`(default), S3-method based on the `model`argument is used. - `model_data`: Data used for generating predictions of `model`. Necessary for some models that require specific data formats, i.e. xgboost. If `NULL`(default), `data` is used. Only used if `model` is specified. - `categorical_features`: Vector of feature names of categorical features. - `target`: Target of prediction task. Can be either "continuous" or "binary". For "continuous"(default), an additive model for the prediction of a continuous outcome is fitted. For "binary", a binary classification with sigmoid activation in the last layer is fitted. - `n_ensemble`: Number of orthogonal neural additive model ensembles - `epochs`: Number of epochs to train the model. See `fit` for details. - `callback`: Callback to be called during training. See `fit` for details. - `progresstext`: Show model fitting progress. If `TRUE`, shows current number of ensemble being fitted - `verbose`: Verbose argument for internal model fitting. used for debugging. See `fit` for details. ## Returns Returns a model object of class `onam`, containing all ensemble members, ensemble weights, and main and interaction effect outputs. ## Examples ```r # Basic example for a simple ONAM-model # Create training data n <- 1000 x1 <- runif(n, -2, 2) x2 <- runif(n, -2, 2) y <- sin(x1) + ifelse(x2 > 0, pweibull(x2, shape = 3), pweibull(-x2, shape = 0.5)) + x1 * x2 data_train <- cbind(x1, x2, y) # Define model model_formula <- y ~ mod1(x1) + mod1(x2) + mod1(x1, x2) mod1 <- function(inputs) { outputs <- inputs %>% layer_dense(units = 16, activation = "relu") %>% layer_dense(units = 8, activation = "linear", use_bias = TRUE) %>% layer_dense(units = 1, activation = "linear", use_bias = TRUE) keras_model(inputs, outputs) } list_of_deep_models <- list(mod1 = mod1) # Fit model mod <- onam(model_formula, list_of_deep_models, data_train, n_ensemble = 1, epochs = 10) summary(mod) ```

onam function