#' This function performs local diagnostic of residuals.

#' For a single instance its neighbors are identified in the validation data.

#' Residuals are calculated for neighbors and plotted against residuals for all data.

#'

#' @param explainer a model to be explained, preprocessed by the 'explain' function

#' @param new_observation a new observation for which predictions need to be explained

#' @return An object of the class 'predict_diagnostics'.

#' It's a data frame with calculated distribution of residuals.

#'

#' @export

#' @importFrom stats ks.test

#' @importFrom graphics plot

#'

#' This function calculates explanations on a dataset level set that explore model response as a function of selected variables.

#' The explanations can be calulated as Partial Dependence Profile or  Accumulated Local Dependence Profile.

#' The \code{variable_profile} function is a copy of \code{model_profile}.

#'

#' Underneath this function calls the \code{\link[ingredients]{partial_dependence}} or

#' @return An object of the class \code{model_profile}.

#' It's a data frame with calculated average model responses.

#'

#'

#' @name model_profile

#' @examples

#' \item \code{type} - character that specifies type of the task.

#' }

#'

#' @importFrom stats median weighted.mean

#' @export

#' @examples

#' Dataset Level Variable Importance as Change in Loss Function after Variable Permutations

#'

#' From DALEX version 1.0 this function calls the \code{\link[ingredients]{feature_importance}}

#'

#' @param explainer a model to be explained, preprocessed by the \code{explain} function

#' @param loss_function a function that will be used to assess variable importance. By default it is 1-AUC for classification, cross entropy for multilabel classification and RMSE for regression. Custom, user-made loss function should accept two obligatory parameters (observed, predicted), where \code{observed} states for actual values of the target, while \code{predicted} for predicted values. If attribute "loss_accuracy" is associated with function object, then it will be plotted as name of the loss function.

#' @param N number of observations that should be sampled for calculation of variable importance. If \code{NULL} then variable importance will be calculated on whole dataset (no sampling).

#' @param n_sample alias for \code{N} held for backwards compatibility. number of observations that should be sampled for calculation of variable importance.

#'

#' @return An object of the class \code{feature_importance}.

#' It's a data frame with calculated average response.

#'

#'

#' From DALEX version 1.0 this function calls the \code{\link[ingredients]{accumulated_dependence}} or

#' \code{\link[ingredients]{partial_dependence}} from the \code{ingredients} package.

#'

#' @param explainer a model to be explained, preprocessed by the 'explain' function

#' @param variables character - names of variables to be explained

#' @return An object of the class 'aggregated_profiles_explainer'.

#' It's a data frame with calculated average response.

#'

#' @export

#'

#' @examples

#' \item \code{model_info} named list contating basic information about model, like package, version of package and type.

#' }

#'

#' @rdname explain

#' @export

#' @importFrom stats predict

#'

#' This function calculated individual profiles aka Ceteris Paribus Profiles.

#' From DALEX version 1.0 this function calls the \code{\link[ingredients]{ceteris_paribus}} from the \code{ingredients} package.

#'

#' @param explainer a model to be explained, preprocessed by the \code{explain} function

#' @param new_observation a new observation for which predictions need to be explained

#' @return An object of the class \code{ceteris_paribus_explainer}.

#' It's a data frame with calculated average response.

#'

#' @export

#'

#' @examples

#'

#' This function performs model diagnostic of residuals.

#' Residuals are calculated and plotted against predictions, true y values or selected variables.

#'

#' @param explainer a model to be explained, preprocessed by the \code{explain} function

#' @param variables character - name of variables to be explained. Default \code{NULL} stands for all variables

#' @return An object of the class \code{model_diagnostics}.

#' It's a data frame with residuals and selected variables.

#'

#' @export

#' @examples

#' library(DALEX)

#' From DALEX version 1.0 this function calls the \code{\link[iBreakDown]{break_down}} or

#' \code{\link[iBreakDown:break_down_uncertainty]{shap}} functions from the \code{iBreakDown} package or

#' \code{\link[ingredients:ceteris_paribus]{ceteris_paribus}} from the \code{ingredients} package.

#'

#' @param explainer a model to be explained, preprocessed by the \code{explain} function

#' @param new_observation a new observation for which predictions need to be explained

#'

#'

#' @aliases predict_parts_break_down predict_parts predict_parts_ibreak_down predict_parts_shap

#'

#' @examples

#' library(DALEX)