Data Science Desktop Survival Guide by Graham Williams
Desktop Survival Project Home Preface Data Science Introducing R R Constructs R Tasks R Strings R Read, Write, and Create Data Template Data Exploration Data Wrangling Data Visualisation Statistics ML Template ML Scenarios ML Activities ML Applications ML Algorithms Cluster Analysis Decision Trees Computer Vision Graph Data Privacy Literate Data Science Coding with Style Resources Bibliography Index

CLICK HERE TO VISIT THE UPDATED SURVIVAL GUIDE

Visualisation Setup

20200608

Packages used in this chapter include GGally, RColorBrewer, colorRamps, dplyr, epitools, ggplot2, randomForest, scales, stringr, magrittr, and rattle.

Packages are loaded into the currently running R session from your local library directories on disk. Missing packages can be installed using utils::install.packages() within R. On Ubuntu, for example, R packages can be installed using wajig install r-cran-<pkgname>.

# Load required packages from local library into the R session.

library(GGally)       # Pairs plots.
library(RColorBrewer) # Brew various colour ranges.
library(colorRamps)   # Generate colour ranges: blue2green2red().
library(dplyr)        # glimpse().
library(epitools)     # Colour selection: colors.plot().
library(ggplot2)      # Visualise data.
library(scales)       # commas(), percent().
library(stringr)      # str_replace_all().

The rattle::weatherAUS dataset is loaded into the template variable ds and further template variables are setup as introduced in Williams (2017). See Chapter 7 for details.

dsname <- "weatherAUS"
ds     <- get(dsname)

nobs   <- nrow(ds)

vnames <- names(ds)
ds    %<>% clean_names(numerals="right")
names(vnames) <- names(ds)

vars   <- names(ds)
target <- "rain_tomorrow"
vars   <- c(target, vars) %>% unique() %>% rev()

We also do a little more to set the data up for demonstrating various approaches to visualisation. As with the model template, a number of template variables are identified here. We also a little data wrangling to remove all missing values by performing a missing value imputation with randomForest::na.roughfix().

risk   <- "risk_mm"
id     <- c("date", "location")
ignore <- c(risk, id)
vars   <- setdiff(vars, ignore)
inputs <- setdiff(vars, target)
ds[vars] %<>% na.roughfix()