plot_ice-methods: Plot individual conditional expectation plots.
In familiar: End-to-End Automated Machine Learning and Model Evaluation

plot_ice

R Documentation

Plot individual conditional expectation plots.

Description

This method creates individual conditional expectation plots based on data in a familiarCollection object.

Usage

plot_ice(
  object,
  draw = FALSE,
  dir_path = NULL,
  split_by = NULL,
  color_by = NULL,
  facet_by = NULL,
  facet_wrap_cols = NULL,
  ggtheme = NULL,
  discrete_palette = NULL,
  gradient_palette = NULL,
  gradient_palette_range = NULL,
  x_label = waiver(),
  y_label = waiver(),
  legend_label = waiver(),
  plot_title = NULL,
  plot_sub_title = NULL,
  caption = NULL,
  x_range = NULL,
  x_n_breaks = 5,
  x_breaks = NULL,
  y_range = NULL,
  y_n_breaks = 5,
  y_breaks = NULL,
  novelty_range = NULL,
  value_scales = waiver(),
  novelty_scales = waiver(),
  conf_int_style = c("ribbon", "step", "none"),
  conf_int_alpha = 0.4,
  ice_default_alpha = 0.6,
  n_max_samples_shown = 50L,
  show_ice = TRUE,
  show_pd = TRUE,
  show_novelty = TRUE,
  anchor_values = NULL,
  width = waiver(),
  height = waiver(),
  units = waiver(),
  export_collection = FALSE,
  ...
)

## S4 method for signature 'ANY'
plot_ice(
  object,
  draw = FALSE,
  dir_path = NULL,
  split_by = NULL,
  color_by = NULL,
  facet_by = NULL,
  facet_wrap_cols = NULL,
  ggtheme = NULL,
  discrete_palette = NULL,
  gradient_palette = NULL,
  gradient_palette_range = NULL,
  x_label = waiver(),
  y_label = waiver(),
  legend_label = waiver(),
  plot_title = NULL,
  plot_sub_title = NULL,
  caption = NULL,
  x_range = NULL,
  x_n_breaks = 5,
  x_breaks = NULL,
  y_range = NULL,
  y_n_breaks = 5,
  y_breaks = NULL,
  novelty_range = NULL,
  value_scales = waiver(),
  novelty_scales = waiver(),
  conf_int_style = c("ribbon", "step", "none"),
  conf_int_alpha = 0.4,
  ice_default_alpha = 0.6,
  n_max_samples_shown = 50L,
  show_ice = TRUE,
  show_pd = TRUE,
  show_novelty = TRUE,
  anchor_values = NULL,
  width = waiver(),
  height = waiver(),
  units = waiver(),
  export_collection = FALSE,
  ...
)

## S4 method for signature 'familiarCollection'
plot_ice(
  object,
  draw = FALSE,
  dir_path = NULL,
  split_by = NULL,
  color_by = NULL,
  facet_by = NULL,
  facet_wrap_cols = NULL,
  ggtheme = NULL,
  discrete_palette = NULL,
  gradient_palette = NULL,
  gradient_palette_range = NULL,
  x_label = waiver(),
  y_label = waiver(),
  legend_label = waiver(),
  plot_title = waiver(),
  plot_sub_title = waiver(),
  caption = NULL,
  x_range = NULL,
  x_n_breaks = 5,
  x_breaks = NULL,
  y_range = NULL,
  y_n_breaks = 5,
  y_breaks = NULL,
  novelty_range = NULL,
  value_scales = waiver(),
  novelty_scales = waiver(),
  conf_int_style = c("ribbon", "step", "none"),
  conf_int_alpha = 0.4,
  ice_default_alpha = 0.6,
  n_max_samples_shown = 50L,
  show_ice = TRUE,
  show_pd = TRUE,
  show_novelty = TRUE,
  anchor_values = NULL,
  width = waiver(),
  height = waiver(),
  units = waiver(),
  export_collection = FALSE,
  ...
)

Arguments

`object`	`familiarCollection` object, or one or more `familiarData` objects, that will be internally converted to a `familiarCollection` object. It is also possible to provide a `familiarEnsemble` or one or more `familiarModel` objects together with the data from which data is computed prior to export. Paths to such files can also be provided.
`draw`	(optional) Draws the plot if TRUE.
`dir_path`	(optional) Path to the directory where created individual conditional expectation plots are saved to. Output is saved in the `explanation` subdirectory. If `NULL`, figures are written to the folder, but are returned instead.
`split_by`	(optional) Splitting variables. This refers to column names on which datasets are split. A separate figure is created for each split. See details for available variables.
`color_by`	(optional) Variables used to determine fill colour of plot objects. The variables cannot overlap with those provided to the `split_by` argument, but may overlap with other arguments. See details for available variables.
`facet_by`	(optional) Variables used to determine how and if facets of each figure appear. In case the `facet_wrap_cols` argument is `NULL`, the first variable is used to define columns, and the remaing variables are used to define rows of facets. The variables cannot overlap with those provided to the `split_by` argument, but may overlap with other arguments. See details for available variables.
`facet_wrap_cols`	(optional) Number of columns to generate when facet wrapping. If NULL, a facet grid is produced instead.
`ggtheme`	(optional) `ggplot` theme to use for plotting.
`discrete_palette`	(optional) Palette to use to colour the different plot elements in case a value was provided to the `color_by` argument. For 2D individual conditional expectation plots without novelty, the initial colour determines the colour of the points indicating sample values.
`gradient_palette`	(optional) Sequential or divergent palette used to colour the raster in 2D individual conditional expectation or partial dependence plots. This argument is not used for 1D plots.
`gradient_palette_range`	(optional) Numerical range used to span the gradient for 2D plots. This should be a range of two values, e.g. `c(0, 1)`. By default, values are determined from the data, dependent on the `value_scales` parameter. This parameter is ignored for 1D plots.
`x_label`	(optional) Label to provide to the x-axis. If NULL, no label is shown.
`y_label`	(optional) Label to provide to the y-axis. If NULL, no label is shown.
`legend_label`	(optional) Label to provide to the legend. If NULL, the legend will not have a name.
`plot_title`	(optional) Label to provide as figure title. If NULL, no title is shown.
`plot_sub_title`	(optional) Label to provide as figure subtitle. If NULL, no subtitle is shown.
`caption`	(optional) Label to provide as figure caption. If NULL, no caption is shown.
`x_range`	(optional) Value range for the x-axis.
`x_n_breaks`	(optional) Number of breaks to show on the x-axis of the plot. `x_n_breaks` is used to determine the `x_breaks` argument in case it is unset.
`x_breaks`	(optional) Break points on the x-axis of the plot.
`y_range`	(optional) Value range for the y-axis.
`y_n_breaks`	(optional) Number of breaks to show on the y-axis of the plot. `y_n_breaks` is used to determine the `y_breaks` argument in case it is unset.
`y_breaks`	(optional) Break points on the y-axis of the plot.
`novelty_range`	(optional) Numerical range used to span the range of novelty values. This determines the size of the bubbles in 2D, and transparency of lines in 1D. This should be a range of two values, e.g. `c(0, 1)`. By default, values are determined from the data, dependent on the `value_scales` parameter. This parameter is ignored if `show_novelty=FALSE`.
`value_scales`	(optional) Sets scaling of predicted values. This parameter has several options: `fixed` (default): The value axis for all features will have the same range. `feature`: The value axis for each feature will have the same range. This option is unavailable for 2D plots. `figure`: The value axis for all facets in a figure will have the same range. `facet`: Each facet has its own range. This option is unavailable for 2D plots. For 1D plots, this option is ignored if the `y_range` is provided, whereas for 2D it is ignored if the `gradient_palette_range` is provided.
`novelty_scales`	(optional) Sets scaling of novelty values, similar to the `value_scales` parameter, but with more limited options: `fixed` (default): The novelty will have the same range for all features. `figure`: The novelty will have the same range for all facets in a figure.
`conf_int_style`	(optional) Confidence interval style. See details for allowed styles.
`conf_int_alpha`	(optional) Alpha value to determine transparency of confidence intervals or, alternatively, other plot elements with which the confidence interval overlaps. Only values between 0.0 (fully transparent) and 1.0 (fully opaque) are allowed.
`ice_default_alpha`	(optional) Default transparency (value) of sample lines in an 1D plot. When novelty is shown, this is the transparency corresponding to the least novel points. The confidence interval alpha values is scaled by this value.
`n_max_samples_shown`	(optional) Maximum number of samples shown in an individual conditional expectation plot. Defaults to 50. These samples are randomly picked from the samples present in the ICE data, but the same samples are consistently picked. Partial dependence is nonetheless computed from all available samples.
`show_ice`	(optional) Sets whether individual conditional expectation plots should be created.
`show_pd`	(optional) Sets whether partial dependence plots should be created. Note that if an anchor is set for a particular feature, its partial dependence cannot be shown.
`show_novelty`	(optional) Sets whether novelty is shown in plots.
`anchor_values`	(optional) A single value or a named list or array of values that are used to centre the individual conditional expectation plot. A single value is valid if and only if only a single feature is assessed. Otherwise, values Has no effect if the plot is not shown, i.e. `show_ice=FALSE`. A partial dependence plot cannot be shown for those features.
`width`	(optional) Width of the plot. A default value is derived from the number of facets.
`height`	(optional) Height of the plot. A default value is derived from the number of features and the number of facets.
`units`	(optional) Plot size unit. Either `cm` (default), `mm` or `⁠in⁠`.
`export_collection`	(optional) Exports the collection if TRUE.
`...`	Arguments passed on to `export_ice_data`, `ggplot2::ggsave`, `extract_ice` `aggregate_results` Flag that signifies whether results should be aggregated for export. `device` Device to use. Can either be a device function (e.g. png), or one of "eps", "ps", "tex" (pictex), "pdf", "jpeg", "tiff", "png", "bmp", "svg" or "wmf" (windows only). If `NULL` (default), the device is guessed based on the `filename` extension. `scale` Multiplicative scaling factor. `dpi` Plot resolution. Also accepts a string input: "retina" (320), "print" (300), or "screen" (72). Applies only to raster output types. `limitsize` When `TRUE` (the default), `ggsave()` will not save images larger than 50x50 inches, to prevent the common error of specifying dimensions in pixels. `bg` Background colour. If `NULL`, uses the `plot.background` fill value from the plot theme. `create.dir` Whether to create new directories if a non-existing directory is specified in the `filename` or `path` (`TRUE`) or return an error (`FALSE`, default). If `FALSE` and run in an interactive session, a prompt will appear asking to create a new directory when necessary. `features` Names of the feature or features (2) assessed simultaneously. By default `NULL`, which means that all features are assessed one-by-one. `feature_x_range` When one or two features are defined using `features`, `feature_x_range` can be used to set the range of values for the first feature. For numeric features, a vector of two values is assumed to indicate a range from which `n_sample_points` are uniformly sampled. A vector of more than two values is interpreted as is, i.e. these represent the values to be sampled. For categorical features, values should represent a (sub)set of available levels. `feature_y_range` As `feature_x_range`, but for the second feature in case two features are defined. `n_sample_points` Number of points used to sample continuous features. `data` A `dataObject` object, `data.table` or `data.frame` that constitutes the data that are assessed. `is_pre_processed` Flag that indicates whether the data was already pre-processed externally, e.g. normalised and clustered. Only used if the `data` argument is a `data.table` or `data.frame`. `cl` Cluster created using the `parallel` package. This cluster is then used to speed up computation through parallellisation. `evaluation_times` One or more time points that are used for in analysis of survival problems when data has to be assessed at a set time, e.g. calibration. If not provided explicitly, this parameter is read from settings used at creation of the underlying `familiarModel` objects. Only used for `survival` outcomes. `ensemble_method` Method for ensembling predictions from models for the same sample. Available methods are: `median` (default): Use the median of the predicted values as the ensemble value for a sample. `mean`: Use the mean of the predicted values as the ensemble value for a sample. `verbose` Flag to indicate whether feedback should be provided on the computation and extraction of various data elements. `message_indent` Number of indentation steps for messages shown during computation and extraction of various data elements. `sample_limit` (optional) Set the upper limit of the number of samples that are used during evaluation steps. Cannot be less than 20. This setting can be specified per data element by providing a parameter value in a named list with data elements, e.g. `list("sample_similarity"=100, "permutation_vimp"=1000)`. This parameter can be set for the following data elements: `sample_similarity` and `ice_data`. `detail_level` (optional) Sets the level at which results are computed and aggregated. `ensemble`: Results are computed at the ensemble level, i.e. over all models in the ensemble. This means that, for example, bias-corrected estimates of model performance are assessed by creating (at least) 20 bootstraps and computing the model performance of the ensemble model for each bootstrap. `hybrid` (default): Results are computed at the level of models in an ensemble. This means that, for example, bias-corrected estimates of model performance are directly computed using the models in the ensemble. If there are at least 20 trained models in the ensemble, performance is computed for each model, in contrast to `ensemble` where performance is computed for the ensemble of models. If there are less than 20 trained models in the ensemble, bootstraps are created so that at least 20 point estimates can be made. `model`: Results are computed at the model level. This means that, for example, bias-corrected estimates of model performance are assessed by creating (at least) 20 bootstraps and computing the performance of the model for each bootstrap. Note that each level of detail has a different interpretation for bootstrap confidence intervals. For `ensemble` and `model` these are the confidence intervals for the ensemble and an individual model, respectively. That is, the confidence interval describes the range where an estimate produced by a respective ensemble or model trained on a repeat of the experiment may be found with the probability of the confidence level. For `hybrid`, it represents the range where any single model trained on a repeat of the experiment may be found with the probability of the confidence level. By definition, confidence intervals obtained using `hybrid` are at least as wide as those for `ensemble`. `hybrid` offers the correct interpretation if the goal of the analysis is to assess the result of a single, unspecified, model. `hybrid` is generally computationally less expensive then `ensemble`, which in turn is somewhat less expensive than `model`. A non-default `detail_level` parameter can be specified for separate evaluation steps by providing a parameter value in a named list with data elements, e.g. `list("auc_data"="ensemble", "model_performance"="hybrid")`. This parameter can be set for the following data elements: `auc_data`, `decision_curve_analyis`, `model_performance`, `permutation_vimp`, `ice_data`, `prediction_data` and `confusion_matrix`. `estimation_type` (optional) Sets the type of estimation that should be possible. This has the following options: `point`: Point estimates. `bias_correction` or `bc`: Bias-corrected estimates. A bias-corrected estimate is computed from (at least) 20 point estimates, and `familiar` may bootstrap the data to create them. `bootstrap_confidence_interval` or `bci` (default): Bias-corrected estimates with bootstrap confidence intervals (Efron and Hastie, 2016). The number of point estimates required depends on the `confidence_level` parameter, and `familiar` may bootstrap the data to create them. As with `detail_level`, a non-default `estimation_type` parameter can be specified for separate evaluation steps by providing a parameter value in a named list with data elements, e.g. `list("auc_data"="bci", "model_performance"="point")`. This parameter can be set for the following data elements: `auc_data`, `decision_curve_analyis`, `model_performance`, `permutation_vimp`, `ice_data`, and `prediction_data`. `confidence_level` (optional) Numeric value for the level at which confidence intervals are determined. In the case bootstraps are used to determine the confidence intervals bootstrap estimation, `familiar` uses the rule of thumb `n = 20 / ci.level` to determine the number of required bootstraps. The default value is `0.95`. `bootstrap_ci_method` (optional) Method used to determine bootstrap confidence intervals (Efron and Hastie, 2016). The following methods are implemented: `percentile` (default): Confidence intervals obtained using the percentile method. `bc`: Bias-corrected confidence intervals. Note that the standard method is not implemented because this method is often not suitable due to non-normal distributions. The bias-corrected and accelerated (BCa) method is not implemented yet.

Details

This function generates individual conditional expectation plots. These plots come in two varieties, namely 1D and 2D. 1D plots show the predicted value as function of a single feature, whereas 2D plots show the predicted value as a function of two features.

Available splitting variables are: feature_x, feature_y (2D only), fs_method, learner, data_set and positive_class (categorical outcomes) or evaluation_time (survival outcomes). By default, for 1D ICE plots the data are split by feature_x, fs_method and learner, with faceting by data_set, positive_class or evaluation_time. If only partial dependence is shown, positive_class and evaluation_time are used to set colours instead. For 2D plots, by default the data are split by feature_x, fs_method and learner, with faceting by data_set, positive_class or evaluation_time. The color_by argument cannot be used with 2D plots, and attempting to do so causes an error. Attempting to specify feature_x or feature_y for color_by will likewise result in an error, as multiple features cannot be shown in the same facet.

The splitting variables indicated by color_by are coloured according to the discrete_palette parameter. This parameter is therefore only used for 1D plots. Available palettes for discrete_palette and gradient_palette are those listed by grDevices::palette.pals() (requires R >= 4.0.0), grDevices::hcl.pals() (requires R >= 3.6.0) and rainbow, heat.colors, terrain.colors, topo.colors and cm.colors, which correspond to the palettes of the same name in grDevices. If not specified, a default palette based on palettes in Tableau are used. You may also specify your own palette by using colour names listed by grDevices::colors() or through hexadecimal RGB strings.

Bootstrap confidence intervals of the partial dependence plots can be shown using various styles set by conf_int_style:

ribbon (default): confidence intervals are shown as a ribbon with an opacity of conf_int_alpha around the point estimate of the partial dependence.
step (default): confidence intervals are shown as a step function around the point estimate of the partial dependence.
none: confidence intervals are not shown. The point estimate of the partial dependence is shown as usual.

Note that when bootstrap confidence intervals were computed, they were also computed for individual samples in individual conditional expectation plots. To avoid clutter, only point estimates for individual samples are shown.

Labelling methods such as set_fs_method_names or set_data_set_names can be applied to the familiarCollection object to update labels, and order the output in the figure.