In sbalci/histopathR: Template and R Codes Used in Histopathologic Research

Plots

Codes for generating Plots.^[See childRmd/_13plots.Rmd file for other codes]

Categorical Variables

dependent <- c("dependent1",
               "dependent2"
                 )

explanatory <- c("explanatory1",
                 "explanatory2"
                 )

mydataCategorical <- mydata %>% 
    select(-var1,
           -var2
    )

mydataCategorical_variable <- explanatory[1]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[2]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[3]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[4]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[5]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[6]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[7]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[8]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[9]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[10]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[11]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[12]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[13]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[14]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[15]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

mydataCategorical_variable <- NA
dependent2 <- NA
mydataCategorical_variable <- explanatory[16]
dependent2 <- dependent[!dependent %in% mydataCategorical_variable]
source(here::here("R", "gc_plot_cat.R"))

## column chart
SmartEDA::ExpCatViz(
  Carseats,
  target = "Urban",
  fname = NULL,
  clim = 10,
  col = NULL,
  margin = 2,
  Page = c(2, 1),
  sample = 2
)

## Stacked bar graph
SmartEDA::ExpCatViz(
  Carseats,
  target = "Urban",
  fname = NULL,
  clim = 10,
  col = NULL,
  margin = 2,
  Page = c(2, 1),
  sample = 2
)

## Variable importance graph using information values
SmartEDA::ExpCatStat(
  Carseats,
  Target = "Urban",
  result = "Stat",
  Pclass = "Yes",
  plot = TRUE,
  top = 20,
  Round = 2
)

inspectdf::inspect_cat(starwars) %>% inspectdf::show_plot()

inspectdf::inspect_cat(starwars) %>% 
  inspectdf::show_plot(high_cardinality = 1)

inspectdf::inspect_cat(star_1, star_2) %>% inspectdf::show_plot()

Plots

Continious Variables

# mydataContinious

mydata %>%
    select(institution, starts_with("Slide")) %>%
    pivot_longer(cols = starts_with("Slide")) %>%
    ggplot(., aes(name, value)) -> p
p + geom_jitter() 
p + geom_jitter(aes(colour = institution))

dxchanges <- mydata %>%
    select(bx_no, starts_with("Slide")) %>% 
    filter(complete.cases(.)) %>%
    group_by(Slide1_infiltrative, Slide2_Medium, Slide3_Demarcated) %>% 
    tally()

library(ggalluvial)

ggplot(data = dxchanges,
       aes(axis1 = Slide1_infiltrative, axis2 = Slide2_Medium, axis3 = Slide3_Demarcated,
           y = n)) +
  scale_x_discrete(limits = c("Slide1", "Slide2", "Slide3"),
                   expand = c(.1, .05)
                   ) +
  xlab("Slide") +
  geom_alluvium(aes(fill = Slide1_infiltrative,
                    colour = Slide1_infiltrative
                    )) +
  geom_stratum() +
  geom_text(stat = "stratum", label.strata = TRUE) +
  theme_minimal() +
  ggtitle("PanNET")

## Generate Boxplot by category
SmartEDA::ExpNumViz(
  mtcars,
  target = "gear",
  type = 2,
  nlim = 25,
  fname = file.path(here::here(), "Mtcars2"),
  Page = c(2, 2)
)

## Generate Density plot
SmartEDA::ExpNumViz(
  mtcars,
  target = NULL,
  type = 3,
  nlim = 25,
  fname = file.path(here::here(), "Mtcars3"),
  Page = c(2, 2)
)

## Generate Scatter plot
SmartEDA::ExpNumViz(
  mtcars,
  target = "carb",
  type = 3,
  nlim = 25,
  fname = file.path(here::here(), "Mtcars4"),
  Page = c(2, 2)
)

SmartEDA::ExpNumViz(mtcars, target = "am", scatter = TRUE)

Interactive graphics {#interactive}

R allows to build any type of interactive graphic. My favourite library is plotly that will turn any of your ggplot2 graphic interactive in one supplementary line of code. Try to hover points, to select a zone, to click on the legend.

library(ggplot2)
library(plotly)
library(gapminder)

p <- gapminder %>%
  filter(year==1977) %>%
  ggplot( aes(gdpPercap, lifeExp, size = pop, color=continent)) +
  geom_point() +
  scale_x_log10() +
  theme_bw()

ggplotly(p)