plot_events function

plot_events

Generates multiple bar plots to visualize the distribution of events over time, categorizing observations as either censored or non-censored.

plot_events(
  Y,
  max.breaks = 20,
  roundTo = 0.1,
  categories = c("Censored", "Event"),
  y.text = "Number of observations",
  decimals = 5,
  txt.x.angle = 0,
  verbose = FALSE
)

Arguments

• Y: Numeric matrix or data.frame. Response variables. Object must have two columns named as "time" and "event". For event column, accepted values are: 0/1 or FALSE/TRUE for censored and event observations.
• max.breaks: Numeric. Maximum number of breaks in X axis (default: 20).
• roundTo: Numeric. Value to round time. If roundTo = 0.1, the results will be rounded to the tenths (default: 0.1).
• categories: Character vector. Vector of length two to name both categories for censored and non-censored observations (default: c("Censored","Death")).
• y.text: Character. Y axis title (default: "Number of observations").
• decimals: Numeric. Number of decimals to use in round times. Must be a value greater or equal zero (default = 5).
• txt.x.angle: Numeric. Angle of the text for the x-axis labels (default: 0).
• verbose: Logical. If verbose = TRUE, extra messages could be displayed (default: FALSE).

Returns

A list of 8 elements. plot: Ggplot object for ploting distribution of events per group. plot_percent: Ggplot object for ploting % of distribution of events per total number of observations. plot_percent_class: Ggplot object for ploting % of distribution of events relative to group. plot_percent_time: Ggplot object for ploting % of distribution of events relative to break-time. df: Data.frame used for the plotting corresponding plot. df_percent: Data.frame used for the plotting corresponding plot. dd_percent_cat: Data.frame used for the plotting corresponding plot. dd_percent_time: Data.frame used for the plotting corresponding plot.

Details

The plot_events function is meticulously crafted to provide a visualization of event occurrences over a specified time frame. The primary objective of this function is to elucidate the distribution of events, distinguishing between censored and non-censored observations. The input response matrix, "Y", is expected to encompass two pivotal columns: "time" and "event". The "time" column delineates the temporal occurrence of each observation, while the "event" column demarcates whether an observation is censored or an event, with accepted binary representations being 0/1 or FALSE/TRUE.

The function employs a systematic approach to categorize the time variable into distinct intervals or "breaks". The number of these intervals is determined by the "max.breaks" parameter, and their size is influenced by the "roundTo" parameter. Each interval represents a range of time values, and the resulting plot showcases the number of censored and non-censored observations within each interval. The bars in the plot are color-coded based on the event type, offering a clear visual distinction between the two categories.

Examples

data("X_proteomic")
data("Y_proteomic")
Y_train <- Y_proteomic
plot_events(Y_train, categories = c("Censored","Event"))

Author(s)

Pedro Salguero Garcia. Maintainer: pedsalga@upv.edu.es