rhxl-hdx.R

# this is just a script to test the rhxl package, I just quickly looked at the data

# Ethiopia Who is doing What Where - 3W December 2017 
# source: https://data.humdata.org/dataset/3w-december-2017
url <- "https://data.humdata.org/dataset/615416d2-457b-461a-8155-090f0ced0bf8/resource/f71bf111-8706-42f4-ba46-4ce3c8c949dc/download/3w_hxl.xlsx"

# load the rhxl package
# https://github.com/dirkschumacher/rhxl
library(rhxl)
download.file(url, "file.xlsx")
data <- as_hxl(readxl::read_xlsx("file.xlsx"))

# get the schema
hxl_schema(data)

# plot ongoing activities
library(ggplot2)
library(dplyr)
plot_data <- hxl_select(data, c("#org+impl", "#status", "#adm1+name"))

# set predictable column names
colnames(plot_data) <- c("org", "status", "admin1")

plot_data <- plot_data %>% 
  group_by(admin1, status) %>% 
  summarise(count_org = n())

ggplot(plot_data) +
  aes(x = status, y = count_org) +
  geom_bar(stat = "identity") + 
  facet_wrap(~admin1) +
  theme(axis.text.x = element_text(angle = 90)) + 
  ggtitle("Project overview by admin1 - Ethiopia Who is doing What Where - 3W December 2017 ") +
  ylab("#Projects") + xlab("Project status")

Uhh nice. 👍