In UBC-MDS/datascience.eda.R: Common Functions for EDA

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
options(rmarkdown.html_vignette.check_title = FALSE)

library(datascience.eda)

`explore_KMeans_clustering` and `explore_DBSCAN_clustering`:

library(datascience.eda)
library(palmerpenguins)

# you can call each clustering algorithm separately 
explore_KMeans_clustering(penguins, centers = seq(3, 5))
explore_DBSCAN_clustering(penguins, eps = c(1), minPts = c(5))

# OR you can just call explore_clustering(penguins) to apply both KMeans and DBSCAN at once

`explore_text_columns`:

library(sacred)
results <- explore_text_columns(apocrypha)

`explore_numeric_columns`:

results <- explore_numeric_columns(penguins)

`explore_categorical_columns`:

library(dplyr)
library(MASS)
df <- data.frame(lapply(survey[, c('Sex','Clap')], as.character),
                 stringsAsFactors=FALSE) %>% tibble()

results <- explore_categorical_columns(df, c('Sex','Clap'))
results[[1]] %>% knitr::kable()
results[[2]][[1]]
results[[2]][[2]]