R/scatter_plot.R

In deandevl/R_plotter_pkg: Provides simple everyday plotting routines

#' Produce a scatter plot of x/y points. If x is a categorical/factor variable then its levels with respect to y
#' can be plotted in separate aligned panels or overlapped with different point colors.
#'
#'
#' Function returns a plot object of x/y scatter points where the x variable can possibly be a category/factor
#' type variable.
#'
#'
#' @param df The target data frame from which the scatter points are plotted.
#' @param aes_x A string that sets the x axis variable name from \code{df}.
#' @param aes_y A string that sets the y axis variable name from \code{df}.
#' @param title A string that sets the overall title.
#' @param subtitle A string that sets the overall subtitle.
#' @param x_label A string that sets the x axis title.
#' @param y_label A string that sets the y axis title.
#' @param x_limits A numeric vector that sets the minimum, maximum, and interval for the x axis.
#' @param y_limits A numeric vector that sets the minimum, maximum, and interval for the y axis.
#' @param pts_color A string that sets the color of the points.
#' @param pts_alpha A numeric value that sets the alpha level of \code{pts_color}.
#' @param pts_size A numeric value that sets the size of the points.
#' @param factor_var A string that sets the factor variable that has multiple levels from \code{df}.
#' @param factor_levels A character vector that sets the levels to be plotted from \code{factor_var}.
#' @param factor_colors A character vector that sets the colors for each of the values in \code{factor_levels}.
#' @param factor_level_panels A logical that if \code{TRUE} will draw the levels of \code{factor_var} in separate panels.
#'   Otherwise all levels of \code{factor_var} will plot on a single x axis with different colors.
#' @param n_rows An integer that defines the number of panel rows if \code{factor_level_panels} is \code{TRUE}.
#' @param n_cols An integer that defines the number of panel columns if \code{factor_level_panels} is \code{TRUE}.
#' @param connect A string that sets the variable from \code{df} that will connect its values as a line across \code{aes_x}.
#' @param connect_color A string that sets the color of the connect line.
#'
#'
#' @import ggplot2
#' @import patchwork
#' @import magrittr
#' @import purrr
#' @import scales
#' @import dplyr
#'
#' @return A plot object.
#'
#' @author Rick Dean
#'
#' @export
#'
scatter_plot <- function(
  df,
  aes_x,
  aes_y,
  title = NULL,
  subtitle = NULL,
  x_label = aes_x,
  y_label = aes_y,
  x_limits = c(0,10,1),
  y_limits = c(0,10,1),
  pts_color = "black",
  pts_alpha = 1.0,
  pts_size = 1,
  factor_var = NULL,
  factor_levels = NULL,
  factor_colors = NULL,
  factor_level_panels = FALSE,
  n_rows = 1,
  n_cols = length(factor_levels),
  connect = NULL,
  connect_color = "red"){
    if(!is.null(factor_var) && factor_level_panels){
      plots <- map(factor_levels, function(factor_level){
        p1 <- filter(df, !!sym(factor_var) == factor_level) %>%
          ggplot(aes_string(x = aes_x, y = aes_y)) +
          geom_point(color = pts_color, alpha = pts_alpha, size = pts_size) +
          theme(
            panel.background = element_rect(fill = "white", color = "black"),
            panel.grid.major = element_line(size = 0.5, linetype = "solid", color = "gray"),
            panel.grid.minor = element_line(size = 0.5, linetype = "solid", color = "gray"),
            axis.text.y = element_blank(),
            axis.ticks.y = element_blank(),
            axis.title.y = element_blank()) +
          labs(title = factor_level, x = x_label,  y = NULL) +
          scale_x_continuous(
            breaks = seq(x_limits[[1]], x_limits[[2]],by=x_limits[[3]]),
            limits = c(x_limits[[1]], x_limits[[2]]),
            oob = rescale_none) +
          scale_y_continuous(
            breaks = seq(y_limits[[1]], y_limits[[2]],by=y_limits[[3]]),
            limits = c(y_limits[[1]], y_limits[[2]]),
            oob = rescale_none)
        p1
      })
      plots[[1]] <- plots[[1]] +
        labs(y = y_label ) +
        theme(
          axis.text.y = element_text(color = "black"),
          axis.ticks.y = element_line(size = 1),
          axis.title.y = element_text(color = "black", angle = 90),
        )

      all_plots <- plots[[1]]
      for(i in 2:length(plots)){
        all_plots <- all_plots + plots[[i]]
      }
      all_plots <- all_plots + plot_layout(nrow = n_rows, ncol = n_cols) +
        plot_annotation(title = title, subtitle = subtitle)
    }else if(!is.null(factor_var)) {
      all_plots <- ggplot(df, aes_string(x = aes_x, y = aes_y, color = factor_var)) +
        geom_point(alpha = pts_alpha, size = pts_size) +
        labs(title = title, subtitle = subtitle, x = x_label, y = y_label ) +
        theme(
          panel.background = element_rect(fill = "white", color = "black"),
          panel.grid.major = element_line(size = 0.5, linetype = "solid", color = "gray"),
          panel.grid.minor = element_line(size = 0.5, linetype = "solid", color = "gray"),
          axis.text.y = element_text(color = "black"),
          axis.ticks.y = element_line(size = 1),
          axis.title.y = element_text(color = "black", angle = 90),
          legend.position = "top"
        ) +
        scale_x_continuous(
          breaks = seq(x_limits[[1]], x_limits[[2]],by=x_limits[[3]]),
          limits = c(x_limits[[1]], x_limits[[2]]),
          oob = rescale_none) +
        scale_y_continuous(
          breaks = seq(y_limits[[1]], y_limits[[2]],by=y_limits[[3]]),
          limits = c(y_limits[[1]], y_limits[[2]]),
          oob = rescale_none) +
        scale_color_manual(values = factor_colors)
    }else {
      all_plots <- ggplot(df, aes_string(x = aes_x, y = aes_y)) +
        geom_point(color = pts_color, alpha = pts_alpha, size = pts_size) +
        labs(title = title, subtitle = subtitle, x = x_label, y = y_label ) +
        theme(
          panel.background = element_rect(fill = "white", color = "black"),
          panel.grid.major = element_line(size = 0.5, linetype = "solid", color = "gray"),
          panel.grid.minor = element_line(size = 0.5, linetype = "solid", color = "gray"),
          axis.text.y = element_text(color = "black"),
          axis.ticks.y = element_line(size = 1),
          axis.title.y = element_text(color = "black", angle = 90),
        ) +
        scale_x_continuous(
          breaks = seq(x_limits[[1]], x_limits[[2]],by=x_limits[[3]]),
          limits = c(x_limits[[1]], x_limits[[2]]),
          oob = rescale_none) +
        scale_y_continuous(
          breaks = seq(y_limits[[1]], y_limits[[2]],by=y_limits[[3]]),
          limits = c(y_limits[[1]], y_limits[[2]]),
          oob = rescale_none)
      if(!is.null(connect)){
        all_plots <- all_plots +
          geom_line(data = df, aes_string(x = aes_x, y = connect), color = connect_color)
      }
    }
    all_plots
}