In UBC-MDS/xplrrr: This package makes exploratory data analysis (EDA) simple and seamless. EDA is a crucial phase in the data science workflow as it allows us get a fist glimpse of the data. It is important to identify statistical characteristics of the data so that we can properly set up the rest of the analysis

knitr::opts_chunk$set(warning = FALSE,
                      message = FALSE,
                      # collapse = TRUE,
                      # comment = "#>",
                      dpi = 480)

xplrrr aims to simplify data exploration with R in four aspects:

• feature correlation visualization
• data summary
• outliers detection
• missing data

The package was developed as part of UBC MDS course.

First, start with loading the library

library(xplrrr)
library(dplyr)

In this vignette we will be working with the iris dataset.

At first, let's visualize our features and their pairwise correlations and distributions:

explore_feature_map(iris)

Now let's explore summary statistics:

explore_summary(iris)

Let's see if there are any outliers:

explore_outliers(iris %>% select('Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width'), 2)

Finally, lets test see if airquality dataset has any missing data:

explore_missing(airquality)

UBC-MDS/xplrrr documentation built on April 2, 2020, 4 a.m.