In sbalci/histopathology-template: Template of R Codes Used in Histopathology Research.

Codes for overviewing the data.^[See childRmd/_07overView.Rmd file for other codes]

View Data

View(mydata)

reactable::reactable(data = mydata, sortable = TRUE, resizable = TRUE, filterable = TRUE, searchable = TRUE, pagination = TRUE, paginationType = "numbers", showPageSizeOptions = TRUE, highlight = TRUE, striped = TRUE, outlined = TRUE, compact = TRUE, wrap = FALSE, showSortIcon = TRUE, showSortable = TRUE)

Overview / Exploratory Data Analysis (EDA)

Summary of Data via summarytools 📦

summarytools::view(summarytools::dfSummary(mydata %>% dplyr::select(-keycolumns)))

if(!dir.exists(here::here("out"))) {dir.create(here::here("out"))}

summarytools::view(
  x = summarytools::dfSummary(
    mydata %>% 
      dplyr::select(-keycolumns)
    ),
  file = here::here("out", "mydata_summary.html")
)

Summary via dataMaid 📦

if(!dir.exists(here::here("out"))) {dir.create(here::here("out"))}

dataMaid::makeDataReport(data = mydata, 
                         file = here::here("out", "dataMaid_mydata.Rmd"),
                         replace = TRUE,
                         openResult = FALSE, 
                         render = FALSE,
                         quiet = TRUE
                         )

Summary via explore 📦

if(!dir.exists(here::here("out"))) {dir.create(here::here("out"))}

mydata %>% 
  dplyr::select(
    -dateVariables
  ) %>% 
  explore::report(
    output_file = "mydata_report.html",
    output_dir = here::here("out") 
    )

Glimpse of Data

dplyr::glimpse(mydata %>% dplyr::select(-keycolumns, -dateVariables))

mydata %>% explore::describe()

Explore

explore::explore(mydata)

mydata %>%
  explore::explore_all()

Control Data

Control Data if matching expectations

visdat::vis_expect(data = mydata,
                   expectation = ~.x == -1,
                   show_perc = TRUE)

visdat::vis_expect(mydata, ~.x >= 25)

See missing values

visdat::vis_miss(airquality,
                 cluster = TRUE)

visdat::vis_miss(airquality,
         sort_miss = TRUE)

xray::anomalies(mydata)

xray::distributions(mydata)

Explore Data

Summary of Data via DataExplorer 📦

DataExplorer::plot_str(mydata)

DataExplorer::plot_str(mydata, type = "r")

DataExplorer::introduce(mydata)

DataExplorer::plot_intro(mydata)

DataExplorer::plot_missing(mydata)

Drop columns

mydata2 <- DataExplorer::drop_columns(mydata, "TStage")

DataExplorer::plot_bar(mydata)

DataExplorer::plot_bar(mydata, with = "Death")

DataExplorer::plot_histogram(mydata)

---

if(!dir.exists(here::here("out"))) {dir.create(here::here("out"))}

# https://cran.r-project.org/web/packages/dataMaid/vignettes/extending_dataMaid.html
library("dataMaid")
dataMaid::makeDataReport(mydata,
  #add extra precheck function
  preChecks = c("isKey", "isSingular", "isSupported", "isID"),

  #Add the extra summaries - countZeros() for character, factor,
  #integer, labelled and numeric variables and meanSummary() for integer,
  #numeric and logical variables:
  summaries = setSummaries(
    character = defaultCharacterSummaries(add = "countZeros"),
    factor = defaultFactorSummaries(add = "countZeros"),
    labelled = defaultLabelledSummaries(add = "countZeros"),
    numeric = defaultNumericSummaries(add = c("countZeros", "meanSummary")),
    integer = defaultIntegerSummaries(add = c("countZeros", "meanSummary")),
    logical = defaultLogicalSummaries(add =  c("meanSummary"))
  ),

  #choose mosaicVisual() for categorical variables,
  #prettierHist() for all others:
  visuals = setVisuals(
    factor = "mosaicVisual",
    numeric = "prettierHist",
    integer = "prettierHist",
    Date = "prettierHist"
  ),

  #Add the new checkFunction, identifyColons, for character, factor and
  #labelled variables:
  checks = setChecks(
    character = defaultCharacterChecks(add = "identifyColons"),
    factor = defaultFactorChecks(add = "identifyColons"),
    labelled = defaultLabelledChecks(add = "identifyColons")
  ),

  #overwrite old versions of the report, render to html and don't
  #open the html file automatically:
  replace = TRUE,
  output = "html",
  open = FALSE,
  file = here::here("out/dataMaid_mydata.Rmd")
)

# https://cran.r-project.org/web/packages/summarytools/vignettes/Recommendations-rmarkdown.html
# https://github.com/dcomtois/summarytools
library(knitr)
opts_chunk$set(comment=NA,
               prompt=FALSE,
               cache=FALSE,
               echo=TRUE,
               results='asis' # add to individual summarytools chunks
               )

library(summarytools)
st_css()

st_options(bootstrap.css     = FALSE,       # Already part of the theme so no need for it
           plain.ascii       = FALSE,       # One of the essential settings
           style             = "rmarkdown", # Idem.
           dfSummary.silent  = TRUE,        # Suppresses messages about temporary files
           footnote          = NA,          # Keeping the results minimalistic
           subtitle.emphasis = FALSE)       # For the vignette theme, this gives
                                            # much better results. Your mileage may vary.

summarytools::freq(iris$Species, plain.ascii = FALSE, style = "rmarkdown")
summarytools::freq(iris$Species, report.nas = FALSE, headings = FALSE, cumul = TRUE, totals = TRUE)
summarytools::freq(tobacco$gender, style = 'rmarkdown')
summarytools::freq(tobacco[ ,c("gender", "age.gr", "smoker")])

print(freq(tobacco$gender), method = 'render')

view(dfSummary(iris))

dfSummary(tobacco, style = 'grid', graph.magnif = 0.75, tmp.img.dir = "/tmp")
dfSummary(tobacco, plain.ascii = FALSE, style = "grid",
          graph.magnif = 0.75, valid.col = FALSE, tmp.img.dir = "/tmp")

print(dfSummary(tobacco, graph.magnif = 0.75), method = 'render')

# https://github.com/rolkra/explore
# https://cran.r-project.org/web/packages/explore/vignettes/explore.html
# https://cran.r-project.org/web/packages/explore/vignettes/explore_mtcars.html


# library(dplyr)
# library(explore)

explore::explore(mydata)

# iris %>% report(output_file = "report.html", output_dir = here::here())


# iris$is_versicolor <- ifelse(iris$Species == "versicolor", 1, 0)
# iris %>%
#   report(output_file = "report.html",
#          output_dir = here::here(),
#          target = is_versicolor
# # , split = FALSE
# )

iris %>% explore::explore_tbl()

iris %>% explore::describe_tbl()

iris %>% explore::explore(Species)
iris %>% explore::explore(Sepal.Length)
iris %>% explore::explore(Sepal.Length, target = is_versicolor)
iris %>% explore::explore(Sepal.Length, target = is_versicolor, split = FALSE)
iris %>% explore::explore(Sepal.Length, target = Species)
iris %>% explore::explore(Sepal.Length, target = Petal.Length)


%>% %>%
  explore::explore_all()

iris %>%
  dplyr::select(Sepal.Length, Sepal.Width) %>%
  explore::explore_all()

iris %>%
  dplyr::select(Sepal.Length, Sepal.Width, is_versicolor) %>%
  explore::explore_all(target = is_versicolor)

iris %>%
  dplyr::select(Sepal.Length, Sepal.Width, is_versicolor) %>%
  explore::explore_all(target = is_versicolor, split = FALSE)

iris %>%
  dplyr::select(Sepal.Length, Sepal.Width, Species) %>%
  explore::explore_all(target = Species)

iris %>%
  dplyr::select(Sepal.Length, Sepal.Width, Petal.Length) %>%
  explore::explore_all(target = Petal.Length)

iris %>%
  explore::explore_all()

knitr::opts_current(fig.height=explore::total_fig_height(iris, target = Species))

explore::total_fig_height(iris, target = Species)

iris %>% explore::explore_all(target = Species)

iris %>% explore::explore(Sepal.Length, min_val = 4.5, max_val = 7)

iris %>% explore::explore(Sepal.Length, auto_scale = FALSE)

mtcars %>% explore::describe()

# https://cran.r-project.org/web/packages/dlookr/vignettes/EDA.html

dlookr::describe(mydata
                 # ,
                 # cols = c(statistic)
                 )

# dlookr::describe(carseats, Sales, CompPrice, Income)
# dlookr::describe(carseats, Sales:Income)
# dlookr::describe(carseats, -(Sales:Income))
mydata %>%
  dlookr::describe() %>%
  dplyr::select(variable, skewness, mean, p25, p50, p75) %>%
  dplyr::filter(!is.na(skewness)) %>%
  arrange(desc(abs(skewness)))

# https://cran.r-project.org/web/packages/dlookr/vignettes/EDA.html

carseats %>%
  dlookr::eda_report(target = Sales,
                     output_format = "pdf",
             output_file = "EDA.pdf"
             )

carseats %>%
  dlookr::eda_report(target = Sales,
             output_format = "html",
             output_file = "EDA.html"
             )

# install.packages("ISLR")
library("ISLR")
# install.packages("SmartEDA")
library("SmartEDA")
## Load sample dataset from ISLR pacakge
Carseats <- ISLR::Carseats

## overview of the data;
SmartEDA::ExpData(data=Carseats,type=1)
## structure of the data
SmartEDA::ExpData(data=Carseats,type=2)

sbalci/histopathology-template documentation built on June 29, 2023, 5:52 a.m.