Created
February 6, 2015 15:05
-
-
Save jmcastagnetto/7bf43be8aebd0ab6c1bc to your computer and use it in GitHub Desktop.
Code to cleanup and read WHO immunization monitoring tables into R data frames.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require(XML) | |
require(reshape2) | |
# node content cleanup | |
cleanup <- function(node) { | |
val <- xmlValue(node) | |
if(is.character(val) | is.factor(val)) { | |
out <- gsub("'","", val, fixed=TRUE) | |
} else { | |
out <- val | |
} | |
gsub("\U3e32633c","", gsub("\xa0","", out, useBytes=TRUE)) | |
} | |
# read table, parse, remove extraneous rows and put into a tidy data set | |
who2df <- function(url) { | |
tbs <- readHTMLTable(doc=url, elFun=cleanup, trim=TRUE, stringsAsFactors=FALSE) | |
df <- tbs[[2]][-c(1,2),] | |
fields <- df[1,] | |
df <- df[-1,] | |
colnames(df) <- fields | |
df <- df[-nrow(df),] | |
df[df=="_"] <- NA | |
for (fn in fields[-1]) { | |
df[,fn] <- as.numeric(df[,fn]) | |
} | |
df2 <- melt(df, id.vars="Diseases", variable.name="year", value.name="cases") | |
df2$year <- as.numeric(as.character(df2$year)) | |
df2 | |
} | |
# examples reading data for Peru (PER) and United States (USA) | |
url_who <- "http://apps.who.int/immunization_monitoring/globalsummary/incidences?c=" | |
url_pe <- paste0(url_who, "PER") | |
url_us <- paste0(url_who, "USA") | |
df_pe <- who2df(url_pe) | |
df_us <- who2df(url_us) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment