benmarwick

# function to do a dodged half-boxplot and jittered points next to each other
#
# data_in should be a data frame
# factor_col should be a bare column name (not a string)
#     although it will work if that column is factor or a character type
# numeric_col is the y axis continuous variable
# offset is the width of the boxplots and jittered point cloud
#
# the basic approach is to draw a boxplot without the tails
#   (e.g. only the interquartile range) and then use segments to add the

benmarwick

## GOAL:
## re-create a figure similar to Fig. 2 in Wilson et al. (2018), 
## Nature 554: 183-188. Available from:
## https://www.nature.com/articles/nature25479#s1
##
## combines a boxplot (or violin) with the raw data, by splitting each
## category location in two (box on left, raw data on right)


## call required packages

benmarwick

##############################################################################
## ##
## FORMATSNIPPETS.R ##
## ggplot format snippets ##
## ##
##############################################################################


#### LABELS ####
# Hide labels

benmarwick

# somewhat hackish solution to:
# https://twitter.com/EamonCaddigan/status/646759751242620928
# based mostly on copy/pasting from ggplot2 geom_violin source:
# https://github.com/hadley/ggplot2/blob/master/R/geom-violin.r

library(ggplot2)
library(dplyr)


"%||%" <- function(a, b) {

benmarwick

##' Function readDFile
##' 
##' Function readDFile
##' @param pathname       the pathname of the directory containing the data to import
##' @return outData       Output is a matrix of ion counts with rows as scantime and 
##' columns as mass, and the respective values as labels
##' @export
readDFile<-function(pathname){
  
  filename<-file.path(pathname,'DATA.MS')

benmarwick

## Correlation matrix with p-values. See http://goo.gl/nahmV for documentation of this function
cor.prob <- function (X, dfr = nrow(X) - 2) {
  R <- cor(X, use="pairwise.complete.obs")
  above <- row(R) < col(R)
  r2 <- R[above]^2
  Fstat <- r2 * dfr/(1 - r2)
  R[above] <- 1 - pf(Fstat, 1, dfr)
  R[row(R) == col(R)] <- NA
  R
}

benmarwick

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

benmarwick

# ipak function: install and load multiple R packages.
# check to see if packages are installed. Install them if they are not, then load them into the R session.

ipak <- function(pkg){
    new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
    if (length(new.pkg)) 
        install.packages(new.pkg, dependencies = TRUE)
    sapply(pkg, require, character.only = TRUE)
}

benmarwick

This gist is no longer updated, see this one the for the most current version: 
https://gist.github.com/benmarwick/6260541

# This script is a workflow for analysing 2D artefact outlines from 3D 
# scan objects captured by NextEngine and ScanStudio. Part of the process
# occurs in ScanStudio and GIMP and the quantative analysis of the outlines
# is done in R. In GIMP we process the images into B&W silhouettes ready for R. 
# In R we do elliptical fourier analysis to summarise the image outlines 
# then PCA and MANOVA to discriminate between shape variations
# and test for differences

benmarwick

library(ggplot2)
library(gridExtra)

mtcars$cyl <- ordered(mtcars$cyl)
p <- ggplot(mtcars, aes(mpg, hp, colour = cyl)) + geom_point()

p1 <- p + theme(legend.position = "none")

p2 <- ggplot(mtcars, aes(x=mpg, group=cyl, colour=cyl))
p2 <- p2 + stat_density(fill = NA, position="dodge")