In pbiecek/archivist: Tools for Storing, Restoring and Searching for R Objects

Data preparation

We are using datafrom National Consortium for the Study of Terrorism and Responses to Terrorism (START). (2016).Global Terrorism Database [Data file]. Retrieved from http://www.start.umd.edu/gtd

According to General Terms and Conditions of Use we cannot share whole data. Here is just a small portion. Find much more important data here: http://apps.start.umd.edu/gtd/

library("knitr")
opts_chunk$set(comment=NA, fig.width=6, fig.height=6, warning=FALSE, message=FALSE, cache=FALSE)

library("openxlsx")
data <- read.xlsx("globalterrorismdb_0616dist.xlsx", 1)
small_data <- data[,c("iyear", "country_txt", "nkill","nwound","weaptype1_txt")]
small_data <- small_data[small_data$iyear %in% c("2015","2014"),]

Store

Here the story with archivist begins.

library(dplyr)
library(ggplot2)
library(ggrepel)
library(ggthemes)

library(archivist)
setLocalRepo("~/GitHub/SmarterPoland_blog/arepo")

addHooksToPrint(class="ggplot",
                 repo = "SmarterPoland_blog", user = "pbiecek", subdir = "arepo")

sel <- small_data %a%
  dplyr::filter(iyear == "2015") %a%
  group_by(country_txt) %a%
  dplyr::summarise(sum_kills = sum(nkill, na.rm=TRUE),
            sum_wounds = sum(nwound, na.rm=TRUE),
            n = n()) %a%
  dplyr::filter(sum_kills > 2, sum_wounds>2)

And the plot

ggplot(sel, aes(sum_kills, sum_wounds)) +
  geom_point(aes(size=n)) + geom_text_repel(size=3,aes(label=country_txt)) +
  scale_x_log10() + scale_y_log10() + theme_classic() +
  theme(legend.position="none") + xlab("Total Number of Fatalities") + ylab("Total Number of Injured")+
  ggtitle("Victims of terrorism")

Restore

And here you can enjoy the magic

pl <- archivist::aread('pbiecek/SmarterPoland_blog/arepo/e44de65f1e56ea42d2df2598c083d1ce')
head(pl$data)

getTagsRemote("e44de65f1e56ea42d2df2598c083d1ce", "SmarterPoland_blog", "pbiecek", subdir = "arepo", tag = "")

digest::digest(pl$data)

dat <- archivist::aread('pbiecek/SmarterPoland_blog/arepo/ceed21e997efd00940cdbcba497559c7')
head(dat)

ahistory(md5hash = 'pbiecek/SmarterPoland_blog/arepo/ceed21e997efd00940cdbcba497559c7')

pl + ggtitle("Victims of terrorism in 2015\nCountries with > 2 Fatalities") + theme_bw()