Tag Archives: genderizeR

Women in Orchestras

I believe in the truth of fairy-tales more than I believe in the truth in the newspaper (Lotte Reiniger)

In my opinion, this graph is a visual demonstration that we live in a male chauvinist world.

Orchestras2

In this experiment I download the members of ten top orchestras of the world with the amazing rvest package. After cleaning texts, I obtain the gender of names with genderizeR package as I did here. Since I only take into account names genderized with high probability, these numbers cannot be exact. Apart of this, the plot speaks by itself.

setwd("YOUR WORKING DIRECTORY HERE")
library(rvest)
library(dplyr)
library(genderizeR)
read_html("http://www.berliner-philharmoniker.de/en/orchestra/") %>%
html_nodes(".name") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
paste(collapse=" ") %>%
findGivenNames() -> berliner
saveRDS(berliner, file="berliner.RDS")
read_html("https://www.concertgebouworkest.nl/en/musicians") %>%
html_nodes(".u-padding--b2") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("\\s+", " ", .) %>%
paste(collapse=" ") %>%
findGivenNames() -> rco
saveRDS(rco, file="rco.RDS")
read_html("http://www.philharmonia.spb.ru/en/about/orchestra/zkrasof/contents/") %>%
html_nodes(".td") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
.[23] %>%
findGivenNames() -> spb
saveRDS(spb, file="spb.RDS")
read_html("http://ocne.mcu.es/conoce-a-la-ocne/orquesta-nacional-de-espana/componentes/") %>%
html_nodes(".col-main") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
gsub("([[:lower:]])([[:upper:]][[:lower:]])", "\\1 \\2", .) %>%
findGivenNames() -> one
saveRDS(one, file="one.RDS")
read_html("http://www.gewandhausorchester.de/en/orchester/") %>%
html_nodes("#content") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
findGivenNames() -> leipzig
saveRDS(leipzig, file="leipzig.RDS")
read_html("http://www.wienerphilharmoniker.at/orchestra/members") %>%
html_nodes(".ModSuiteMembersC") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n,\t,*]"," ", .) %>%
gsub("\\s+", " ", .) %>%
gsub("([[:lower:]])([[:upper:]][[:lower:]])", "\\1 \\2", .) %>%
paste(collapse=" ") %>%
.[-18] %>%
findGivenNames() -> wiener
saveRDS(wiener, file="wiener.RDS")
read_html("http://www.laphil.com/philpedia/orchestra-roster") %>%
html_nodes(".view-content") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("\\s+", " ", .) %>%
gsub("(?%
.[1] %>%
findGivenNames() -> laphil
saveRDS(laphil, file="laphil.RDS")
read_html("http://nyphil.org/about-us/meet/musicians-of-the-orchestra") %>%
html_nodes(".resp-tab-content-active") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
gsub("(?%
findGivenNames() -> nyphil
saveRDS(nyphil, file="nyphil.RDS")
urls=c("http://lso.co.uk/orchestra/players/strings.html",
"http://lso.co.uk/orchestra/players/woodwind.html",
"http://lso.co.uk/orchestra/players/brass.html",
"http://lso.co.uk/orchestra/players/percussion-harps-and-keyboards.html")
sapply(urls, function(x)
{
read_html(x) %>%
html_nodes(".clearfix") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n,\t,*]"," ", .) %>%
gsub("\\s+", " ", .)
}) %>% paste(., collapse=" ") %>%
findGivenNames() -> lso
saveRDS(lso, file="lso.RDS")
read_html("http://www.osm.ca/en/discover-osm/orchestra/musicians-osm") %>%
html_nodes("#content-column") %>%
html_text(trim=TRUE) %>%
iconv("UTF-8") %>%
gsub("[\r,\n]"," ", .) %>%
gsub("\\s+", " ", .) %>%
findGivenNames() -> osm
saveRDS(osm, file="osm.RDS")
rbind(c("berliner", "Berliner Philharmoniker"),
c("rco", "Royal Concertgebouw Amsterdam"),
c("spb", "St. Petersburg Philharmonic Orchestra"),
c("one", "Orquesta Nacional de España"),
c("leipzig", "Gewandhaus Orchester Leipzig"),
c("wiener", "Wiener Philarmoniker"),
c("laphil", "The Los Angeles Philarmonic"),
c("nyphil", "New York Philarmonic"),
c("lso", "London Symphony Orchestra"),
c("osm", "Orchestre Symphonique de Montreal")) %>% as.data.frame()-> Orchestras
colnames(Orchestras)=c("Id", "Orchestra")
list.files(getwd(),pattern = ".RDS") %>%
lapply(function(x)
readRDS(x) %>% as.data.frame(stringsAsFactors = FALSE) %>% cbind(Id=gsub(".RDS", "", x))
) %>% do.call("rbind", .) -> all
all %>% mutate(probability=as.numeric(probability)) %>%
filter(probability > 0.9 & count > 15) %>%
filter(!name %in% c("viola", "tuba", "harp")) %>%
group_by(Id, gender) %>%
summarize(Total=n())->all
all %>% filter(gender=="female") %>% mutate(females=Total) %>% select(Id, females) -> females
all %>% group_by(Id) %>% summarise(Total=sum(Total)) -> total
inner_join(total, females, by = "Id") %>% mutate(po_females=females/Total) %>%
inner_join(Orchestras, by="Id")-> df
library(ggplot2)
library(scales)
opts=theme(legend.position="none",
plot.background = element_rect(fill="gray85"),
panel.background = element_rect(fill="gray85"),
panel.grid.major.y=element_blank(),
panel.grid.major.x=element_line(colour="white", size=2),
panel.grid.minor=element_blank(),
axis.title = element_blank(),
axis.line.y = element_line(size = 2, color="black"),
axis.text = element_text(colour="black", size=18),
axis.ticks=element_blank(),
plot.title = element_text(size = 35, face="bold", margin=margin(10,0,10,0), hjust=0))
ggplot(df, aes(reorder(Orchestra, po_females), po_females)) +
geom_bar(stat="identity", fill="darkviolet", width=.5)+
scale_y_continuous(labels = percent, expand = c(0, 0), limits=c(0,.52))+
geom_text(aes(label=sprintf("%1.0f%%", 100*po_females)), hjust=-0.05, size=6)+
ggtitle(expression(atop(bold("Women in Orchestras"), atop("% of women among members", "")))) +
coord_flip()+opts

The Gender of Big Data

When I grow up I want to be a dancer (Carmen, my beautiful daughter)

The presence of women in positions of responsibility inside Big Data companies is quite far of parity: while approximately 5o% of world population are women, only 7% of CEOs of Top 100 Big Data Companies are.

Big_Data_Gender
To do this experiment, I did some webscraping to download the list of big data companies from here. I also used a very interesting package called genderizeR, which makes gender prediction based on first names (more info here).

Here you have the code:

library(rvest)
library(stringr)
library(dplyr)
library(genderizeR)
library(ggplot2)
library(googleVis)
paste0("http://www.crn.com/slide-shows/data-center/300076704/2015-big-data-100-business-analytics.htm/pgno/0/", 1:45) %>%
c(., paste0("http://www.crn.com/slide-shows/data-center/300076709/2015-big-data-100-data-management.htm/pgno/0/",1:30)) %>%
c(., paste0("http://www.crn.com/slide-shows/data-center/300076740/2015-big-data-100-infrastructure-tools-and-services.htm/pgno/0/",1:25)) -> webpages
results=data.frame()
for(x in webpages)
{
read_html(x) %>% html_nodes("p:nth-child(1)") %>% .[[2]] %>% html_text() -> Company
read_html(x) %>% html_nodes("p:nth-child(2)") %>% .[[1]] %>% html_text() -> Executive
results=rbind(results, data.frame(Company, Executive))
}
results=data.frame(lapply(results, as.character), stringsAsFactors=FALSE)
results[74,]=c("Trifacta", "Top Executive: CEO Adam Wilson")
results %>% mutate(Name=gsub("Top|\\bExec\\S*|\\bCEO\\S*|President|Founder|and|Co-Founder|\\:", "", Executive)) %>%
mutate(Name=word(str_trim(Name))) -> results
results %>%
select(Name) %>%
findGivenNames() %>%
filter(probability > 0.9 & count > 15) %>%
as.data.frame() -> data
data %>% group_by(gender) %>% summarize(Total=n()) -> dat
doughnut=gvisPieChart(dat,
options=list(
width=450,
height=450,
legend="{ position: 'bottom', textStyle: {fontSize: 10}}",
chartArea="{left:25,top:50}",
title='TOP 100 BIG DATA COMPANIES 2015
Gender of CEOs',
colors="['red','blue']",
pieHole=0.5),
chartid="doughnut")
plot(doughnut)