Category Archives: The World We Live In

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

Climatic Change At A Glance

Mmm. Lost a planet, Master Obi-Wan has. How embarrassing (Yoda, Attack Of The Clones)

Some time ago I published this post in KDnuggets in which I analyze historical temperatures to show how we are gradually heading toward a warmer planet. Simple data science to obtain a simple (and increasingly accepted) conclusion: the global warming is real. Despite I was criticized I still believe what I said then: you don’t have to be a climatologist to empirically confirm global warming.

This experiment is another example of that. It is still simpler than that since it is only based on visual perception but I think is also quite conclusive. In this case, I represent U.S. temperature outliers from 1964 to 2013; a map per year. Dataset contains station ID, name, min/max temperature, as well as degree coordinates of the recorded weather. Original weather data collected from NOAA and anomalies analysis by Enigma. You can download data here.

Anomalies are divided into four categories: Strong Hot, Weak Hot, Weak Cold and Strong Cold. For each station, I represent difference between number of Cold and Hot anomalies (independently of the strength) so Blue bubbles represent stations where total number of Cold anomalies during the year is greater that total number of Hot ones and Red ones represent the opposite. Size of bubbles is also proportional to this indicator. As an example, following you can see the map of year 1975:

tonopah
It seems 1975 was hot in the right a cold on the left side. Concretely, in TONOPAH Station (Nevada) were registered 30 anomalies and most of them (26) where due to cold temperatures. This is why bubble is blue. This GIF shows the evolution of all these maps from 1964 to 2013:

anomalies

Maybe it is just my personal feeling but don’t you see how red bubbles are gradually winning to blue ones? Maybe I am a demagogue.

This code generates a dynamic map by year in html format:

library(data.table)
library(stringr)
library(leaflet)
library(RColorBrewer)
library(classInt)
library(dplyr)
library(htmlwidgets)
anomalies = fread("enigma-enigma.weather.anomalies.outliers-1964-2013-05ce047dbf3e67f83db9ae841545a333.csv")
anomalies %>%
  mutate(year=substr(date_str, 1, 4)) %>%
  group_by(year, longitude, latitude, id, station_name) %>%
  summarise(
    Strong_Hot=sum(str_count(type,"Strong Hot")),
    Weak_Hot=sum(str_count(type,"Weak Hot")),
    Weak_Cold=sum(str_count(type,"Weak Cold")),
    Strong_Cold=sum(str_count(type,"Strong Cold")),
    total=n()) %>%
  mutate(score=sign(-Strong_Hot-Weak_Hot+Weak_Cold+Strong_Cold)) %>%
  mutate(color=ifelse(score==1, "Blue",ifelse(score==0, "White", "Red"))) -> anomalies2
for (i in unique(anomalies2$year))
{
  anomalies2 %>%
    filter(year==i) %>%
    leaflet() %>%
    fitBounds(-124, 34, -62, 40) %>%
    addProviderTiles("Stamen.TonerLite") %>%
    addCircleMarkers(lng = ~longitude,
                     lat = ~latitude,
                     radius = ~ifelse(total < 20, 2, ifelse(total < 27, 4, 8)),
                     color= ~color,
                     stroke=FALSE,
                     fillOpacity = 0.5,
                     popup = ~paste(sep = "
", paste0("<b>", station_name, "</b>"),
                                    paste0("Strong Hot: ", Strong_Hot),
                                    paste0("Weak Hot: ", Weak_Hot),
                                    paste0("Weak Cold: ", Weak_Cold),
                                    paste0("Strong Cold: ", Strong_Cold))) -> m
    saveWidget(m, file=paste0("m", i, ".html"))
}

Visualising The Evolution Of Migration Flows With rCharts

Heaven we hope is just up the road (Atlas, Coldplay)

Following with the analysis of migration flows, I have done next two visualizations. These charts are called bump charts and are very suitable to represent rankings. This is what I have done:

  • Obtaining top 20 countries of the world according to % of migrants respect its population
  • To do this, I divide total number of migrants between 1960 and 2009 by the mean population in the same period.
  • I do the same to obtain top 20 countries of the world according to % of immigrants.
  • In both cases, I only consider countries with population greater than 2 million.
  • For these countries, I calculate % of migrants in each decade (60’s, 70’s, 80’s, 90’s and 00’s), dividing total number of migrants by mean population each decade
  • I do the same in the case of immigrants.
  • Instead of representing directly % of migrants and immigrants, I represent the ranking of countries according these indicators by decade

This is the bump chart of migrants:

And this is the one of immigrants:

Some comments:

  • There is a permanent exodus in Puerto Rico: all decades (except 70’s) is located in the top 1 of countries with most migrants respect its population
  • Ireland is also living a diaspora although in the 00’s decade has lost some positions
  • Albania, Georgia and Bosnia and Herzegovina are gaining positions. Is East Europe gradually becoming uncomfortable?
  • Jamaica is also moving up in this sad competition.
  • On the other hand, Hong Kong and Israel are persistently leaders as receivers
  • Saudi Arabia has presented an impressive growth receiving immigrants since 70’s
  • United States does not appear in the immigrants ranking
  • Singapore is gaining positions: in the 00’s decade is the third receiver country
  • Also in the 00s, Switzerland is the first European country in the ranking, holding the fifth position

I like using rCharts as well as using Enigma data sets, as I have done previously. This is the code:

library(data.table)
library(rCharts)
library(dplyr)
setwd("YOUR WORKING DIRECTORY HERE")
populflows = read.csv(file="enigma-org.worldbank.migration-remittances.migrants.migration-flow-c57405e33412118c8757b1052e8a1490.csv", stringsAsFactors=FALSE)
population = fread("enigma-org.worldbank.hnp.data-eaa31d1a34fadb52da9d809cc3bec954.csv")
population %>% 
  filter(indicator_name=="Population, total") %>% 
  as.data.frame %>% 
  mutate(decade=(year-year%%10)) %>% 
  group_by(country_name, country_code, decade) %>% 
  summarise(population=mean(value)) %>% 
  plyr::rename(., c("country_name"="country")) -> population2
populflows %>% filter(!is.na(total_migrants)) %>% 
  group_by(migration_year, destination_country) %>% 
  summarise(inmigrants = sum(total_migrants))  %>% 
  plyr::rename(., c("destination_country"="country", "migration_year"="decade"))   -> inmigrants
populflows %>% filter(!is.na(total_migrants)) %>% 
  group_by(migration_year, country_of_origin) %>% 
  summarise(migrants = sum(total_migrants)) %>%  
  plyr::rename(., c("country_of_origin"="country", "migration_year"="decade"))   -> migrants
# Join of data sets
migrants %>% 
  merge(inmigrants, by = c("country", "decade")) %>%
  merge(population2, by = c("country", "decade")) %>%
  mutate(p_migrants=migrants/population, p_inmigrants=inmigrants/population) -> populflows2
# Global Indicators
populflows2 %>% 
  group_by(country) %>% 
  summarise(migrants=sum(migrants), inmigrants=sum(inmigrants), population=mean(population)) %>% 
  mutate(p_migrants=migrants/population, p_inmigrants=inmigrants/population)  %>% 
  filter(population > 2000000)  %>%
  mutate(rank_migrants = dense_rank(desc(p_migrants)), rank_inmigrants = dense_rank(desc(p_inmigrants))) -> global
# Migrants dataset
global %>% 
  filter(rank_migrants<=20) %>% 
  select(country) %>% 
  merge(populflows2, by = "country") %>% 
  arrange(decade, p_migrants) %>%
  mutate(decade2=as.numeric(as.POSIXct(paste0(as.character(decade), "-01-01"), origin="1900-01-01"))) %>%
  plyr::ddply("decade", transform, rank = dense_rank(p_migrants)) -> migrants_rank
# Migrants dataset
global %>% 
  filter(rank_inmigrants<=20) %>% 
  select(country) %>% 
  merge(populflows2, by = "country") %>% 
  arrange(decade, p_inmigrants) %>%
  mutate(decade2=as.numeric(as.POSIXct(paste0(as.character(decade), "-01-01"), origin="1900-01-01"))) %>%
  plyr::ddply("decade", transform, rank = dense_rank(p_inmigrants)) -> inmigrants_rank
# Function for plotting
plotBumpChart <- function(df){
  bump_chart = Rickshaw$new()
  mycolors = ggthemes::tableau_color_pal("tableau20")(20)
  bump_chart$layer(rank ~ decade2, group = 'country_code', data = df, type = 'line', interpolation = 'none', colors = mycolors)
  bump_chart$set(slider = TRUE, highlight = TRUE, legend=TRUE)
  bump_chart$yAxis(tickFormat = "#!  function(y) { if (y == 0) { return '' } else { return String((21-y)) } } !#")
  bump_chart$hoverDetail(yFormatter = "#! function(y){return (21-y)} !#")
  return(bump_chart)
}
plotBumpChart(migrants_rank)
plotBumpChart(inmigrants_rank)

The World We Live In #5: Calories And Kilograms

I enjoy doing new tunes; it gives me a little bit to perk up, to pay a little bit more attention (Earl Scruggs, American musician)

I recently finished reading The Signal and the Noise, a book by Nate Silver, creator of the also famous FiveThirtyEight blog. The book is a very good reading for all data science professionals, and is a must in particular for all those who work trying to predict the future. The book praises the bayesian way of thinking as the best way to face and modify predictions and criticizes rigid ways of thinking with many examples of disastrous predictions. I enjoyed a lot the chapter dedicated to chess and how Deep Blue finally took over Kasparov. In a nutshell: I strongly recommend it.
One of the plots of Silver’s book present a case of false negative showing the relationship between obesity and calorie consumption across the world countries. The plot shows that there is no evidence of a connection between both variables. Since it seemed very strange to me, I decided to reproduce the plot by myself.

I compared these two variables:

  • Dietary Energy Consumption (kcal/person/day) estimated by the FAO Food Balance Sheets.
  • Prevalence of Obesity as percentage of defined population with a body mass index (BMI) of 30 kg/m2 or higher estimated by the World Health Organization

And this is the resulting plot:

Calories And KilogramsAs you can see there is a strong correlation between two variables. Why the experiment of Nate Silver shows the opposite? Obviously we did not plot the same data (although, in principle, both of us went to the same source). Anyway: to be honest, I prefer my plot because shows what all of we know: the more calories you eat, the more weight you will see in your bathroom scale. Some final thoughts seeing the plot:

  • I would like to be Japanese: they don’t gain weight!
  • Why US people are fatter than Austrian?
  • What happens in Samoa?

Here you have the code to do the plot:

library(xlsx)
library(dplyr)
library(ggplot2)
library(scales)
setwd("YOUR WORKING DIRECTORY HERE")
url_calories = "http://www.fao.org/fileadmin/templates/ess/documents/food_security_statistics/FoodConsumptionNutrients_en.xls"
download.file(url_calories, method="internal", destfile = "FoodConsumptionNutrients_en.xls", mode = "ab")
calories = read.xlsx(file="FoodConsumptionNutrients_en.xls", startRow = 4, colIndex = c(2,6), colClasses = c("character", "numeric"), sheetName="Dietary Energy Cons. Countries", stringsAsFactors=FALSE) 
colnames(calories)=c("Country", "Kcal")
url_population = "http://esa.un.org/unpd/wpp/DVD/Files/1_Excel%20(Standard)/EXCEL_FILES/1_Population/WPP2015_POP_F01_1_TOTAL_POPULATION_BOTH_SEXES.XLS"
download.file(url_population, method="internal", destfile = "Population.xls", mode = "ab")
population = read.xlsx(file="Population.xls", startRow = 17, colIndex = c(3,71), colClasses = c("character", "numeric"), sheetName="ESTIMATES", stringsAsFactors=FALSE) 
colnames(population)=c("Country", "Population")
# http://apps.who.int/gho/data/node.main.A900A?lang=en
url_obesity = "http://apps.who.int/gho/athena/data/xmart.csv?target=GHO/NCD_BMI_30A&profile=crosstable&filter=AGEGROUP:*;COUNTRY:*;SEX:*&x-sideaxis=COUNTRY&x-topaxis=GHO;YEAR;AGEGROUP;SEX&x-collapse=true"
obesity = read.csv(file=url_obesity, stringsAsFactors=FALSE)
obesity %>% select(matches("Country|2014.*Both")) -> obesity
colnames(obesity)=c("Country", "Obesity")
obesity %>% filter(Obesity!="No data") -> obesity
obesity %>% mutate(Obesity=as.numeric(substr(Obesity, 1, regexpr(pattern = "[[]", obesity$Obesity)-1))) -> obesity
population %>% inner_join(calories,by = "Country") %>% inner_join(obesity,by = "Country") -> data
opts=theme(
  panel.background = element_rect(fill="gray98"),
  panel.border = element_rect(colour="black", fill=NA),
  axis.line = element_line(size = 0.5, colour = "black"),
  axis.ticks = element_line(colour="black"),
  panel.grid.major = element_line(colour="gray75", linetype = 2),
  panel.grid.minor = element_blank(),
  axis.text = element_text(colour="gray25", size=15),
  axis.title = element_text(size=18, colour="gray10"),
  legend.key = element_blank(),
  legend.position = "none",
  legend.background = element_blank(),
  plot.title = element_text(size = 40, colour="gray10"))
ggplot(data, aes(x=Kcal, y=Obesity/100, size=log(Population), label=Country), guide=FALSE)+
  geom_point(colour="white", fill="sandybrown", shape=21, alpha=.55)+
  scale_size_continuous(range=c(2,40))+
  scale_x_continuous(limits=c(1500,4100))+
  scale_y_continuous(labels = percent)+
  labs(title="The World We Live In #5: Calories And Kilograms",
       x="Dietary Energy Consumption (kcal/person/day)",
       y="% population with body mass index >= 30 kg/m2")+
  geom_text(data=subset(data, Obesity>35|Kcal>3700), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(data=subset(data, Kcal<2000), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(data=subset(data, Obesity<10 & Kcal>2600), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(aes(3100, .01), colour="gray25", hjust=0, label="Source: United Nations (size of bubble depending on population)", size=4.5)+opts

The World We Live In #4: Marriage Ages

It is time for women to stop being politely angry (Leymah Gbowee, Nobel Prize Peace Winner)

Sometimes very simple plots give insight into we live in a world of differences. This plot shows the mean age at marriage for men and women across countries:

Marriage Ages

Being a woman in some countries of this world must be a hard experience:

#Singulate mean age at marriage: http://data.un.org/Data.aspx?d=GenderStat&f=inID%3a20
#Population: http://data.un.org/Data.aspx?d=SOWC&f=inID%3a105
require("sqldf")
require("ggplot2")
setwd("YOUR WORKING DIRECTORY HERE")
mar=read.csv("UNdata_Export_20150309_171525152.csv", nrows=321, header=T, row.names=NULL)
pop=read.csv("UNdata_Export_20150309_172046384.csv", nrows=999, header=T, row.names=NULL)
colnames(mar)[1]="Country"
colnames(pop)[1]="Country"
data=sqldf("SELECT
  a.Country,
  a.Value as Pop,
  b.Value as Female,
  c.Value as Male
FROM
  pop a INNER JOIN mar b
  ON (a.Country=b.Country AND b.Subgroup='Female') INNER JOIN mar c
  ON (a.Country=c.Country AND c.Subgroup='Male')
WHERE a.Subgroup = 'Total'")
opts=theme(
  panel.background = element_rect(fill="gray98"),
  panel.border = element_rect(colour="black", fill=NA),
  axis.line = element_line(size = 0.5, colour = "black"),
  axis.ticks = element_line(colour="black"),
  panel.grid.major = element_line(colour="gray75", linetype = 2),
  panel.grid.minor = element_blank(),
  axis.text = element_text(colour="gray25", size=15),
  axis.title = element_text(size=18, colour="gray10"),
  legend.key = element_blank(),
  legend.position = "none",
  legend.background = element_blank(),
  plot.title = element_text(size = 40, colour="gray10"))
ggplot(data, aes(x=Female, y=Male, size=log(Pop), label=Country), guide=FALSE)+
  geom_point(colour="white", fill="chartreuse3", shape=21, alpha=.55)+
  scale_size_continuous(range=c(2,36))+
  scale_x_continuous(limits=c(16,36), breaks=seq(16, 36, by = 2), expand = c(0, 0))+
  scale_y_continuous(limits=c(16,36), breaks=seq(16, 36, by = 2), expand = c(0, 0))+
  geom_abline(intercept = 0, slope = 1, colour = "gray10", linetype=2)+
  labs(title="The World We Live In #4: Marriage Ages",
       x="Females mean age at marriage",
       y="Males mean age at marriage")+
  geom_text(data=subset(data, abs(Female-Male)>7), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(data=subset(data, Female>=32|Female<=18), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(aes(24, 17), colour="gray25", hjust=0, label="Source: United Nations (size of bubble depending on population)", size=5)+opts

The World We Live In #3: Breastfeeding

Facts are stubborn, but statistics are more pliable (Mark Twain)

According to World Health Organization, exclusive breastfeeding is recommended up to 6 months of age, with continued breastfeeding along with appropriate complementary foods up to two years of age or beyond. Thus, the defining characteristic of continued breastfeeding is that the infant between 6 months and 2 years of age receives at least some breast milk regardless of the quantity or the presence of other foods or liquids in the diet.

On the other hand, as can be read in The World Factbook of Central Intelligence Agency, the Total Fertility Rate (TFR) is the average number of children that would be born to a woman over her lifetime if she were to experience the exact current age-specific fertility rates through her lifetime and she were to survive from birth through the end of her reproductive life. It is obtained by summing the single-year age-specific rates at a given time.

This is how the world is arranged according to these two rates:

#Rstats #R There are many differences between countries. Both rates are very low in some east European countries like Ukraine, Bosnia, Belarus and Moldova. On the other hand both of them are very high in Benin, Rwanda, Burkina Faso and Malawi, all of them African. Also African countries are Angola, Nigeria and Somalia where fertility rate is very high but breastfeeding is not very established (Timor-Leste in Asia belongs to this segment as well); and women in Nepal, Bangladesh, Sri-Lanka and India feed their moderate number of descendants with their own milk.

We live in a complex and beautiful world which cannot be measured only with averages nor standard deviations:

#Continued breastfeeding rate: http://data.un.org/Data.aspx?d=SOWC&f=inID%3a89
#Total fertility rate (TFR): http://data.un.org/Data.aspx?d=SOWC&f=inID%3a127
#Population: http://data.un.org/Data.aspx?d=SOWC&f=inID%3a105
require("sqldf")
require("ggplot2")
require("scales")
breastfeeding=read.csv("UNdata_Export_20141122_122134175.csv", nrows=124, header=T, row.names=NULL)
fertility=read.csv("UNdata_Export_20141122_122330581.csv", nrows=570, header=T, row.names=NULL)
population=read.csv("UNdata_Export_20141122_142359579.csv", nrows=999, header=T, row.names=NULL)
colnames(breastfeeding)[1]="Country"
colnames(fertility)[1]="Country"
colnames(population)[1]="Country"
data=sqldf("SELECT a.Country, a.Value as Pop, b.Value as Fertility, c.Value as Breastfeeding
           FROM population a inner join fertility b
           on (a.Country=b.Country) INNER JOIN breastfeeding c
           on (a.Country=c.Country)
           where a.Subgroup = 'Total' AND b.Year = 2011
           AND a.Country NOT IN ('World', 'South Asia',
           'Sub-Saharan Africa', 'Least Developed Countries/Territories', 'Eastern and Southern Africa',
           'East Asia and Pacific')")
opts=theme(
  panel.background = element_rect(fill="gray98"),
  panel.border = element_rect(colour="black", fill=NA),
  axis.line = element_line(size = 0.5, colour = "black"),
  axis.ticks = element_line(colour="black"),
  panel.grid.major = element_line(colour="gray75", linetype = 2),
  panel.grid.minor = element_blank(),
  axis.text.y = element_text(colour="gray25", size=15),
  axis.text.x = element_text(colour="gray25", size=15),
  text = element_text(size=20),
  legend.key = element_blank(),
  legend.position = "none",
  legend.background = element_blank(),
  plot.title = element_text(size = 45))
ggplot(data, aes(x=Fertility, y=Breastfeeding/100, size=log(Pop), label=Country), guide=FALSE)+
  geom_point(colour="white", fill="darkorchid2", shape=21, alpha=.55)+
  scale_size_continuous(range=c(2,40))+
  scale_x_continuous(limits=c(1,7))+
  scale_y_continuous(limits=c(0,1), labels = percent)+
  labs(title="The World We Live In #3: Breastfeeding",
       x="Total fertility rate (TFR)",
       y="Continued breastfeeding rate")+
  geom_text(data=subset(data, Fertility>5 & (Breastfeeding>75|Breastfeeding<40)), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(data=subset(data, Fertility<3 & Breastfeeding>75), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(data=subset(data, Fertility<2 & Breastfeeding<12), size=5.5, colour="gray25", hjust=0, vjust=0)+
  geom_text(aes(5, 0), colour="gray25", hjust=0, label="Source: United Nations (size of bubble depending on population)", size=4)+opts

The World We Live In #2: To Study Or To Work

I was getting ready for school and about to wear my uniform when I remembered that our principal had told us not to wear uniforms. So I decided to wear my favorite pink dress (Malala Yousafzai)

After reading the diary of a Pakistani schoolgirl and Malala’s history, there is no doubt of being in front of a brave girl. A girl that will fight against monsters who deprive children of their childhood. A girl who knows that one book, one pen, one child and one teacher can change this unfair world. A girl who knew she had won the Nobel Prize of Peace in her chemistry lesson and finished the school time before making her first statement. A girl for whom the prize is just the beginning: a girl that gives us hope. Long live Malala:
TWWLI2
To know where to obtain data for this plot, check out this post. This is the code:

require("sqldf")
require("plyr")
require("stringdist")
childlabour=read.csv("UNdata_Export_20141013_ChildLabour.csv", nrows=335, header=T, row.names=NULL)
education=read.csv("UNdata_Export_20141013_Education.csv", nrows=2994, header=T, row.names=NULL)
population =read.csv("UNdata_Export_20140930_Population.csv",  nrows=12846, header=T, row.names=NULL)
population=rename(population, replace = c("Country.or.Area" = "Country"))
education=rename(education, replace = c("Reference.Area" = "Country"))
education=rename(education, replace = c("Time.Period" = "Year"))
childlabour=rename(childlabour, replace = c("Country.or.Area" = "Country"))
population=sqldf("SELECT a.Country, a.Year, a.Value as Pop
FROM population a INNER JOIN (SELECT Country, MAX(Year) AS Year FROM population GROUP BY 1) b
ON (a.Country=b.Country AND a.Year=b.Year)
WHERE (a.Country NOT LIKE '%INCOME%')
AND (a.Country NOT LIKE '%WORLD%')
AND (a.Country NOT LIKE '%developing%')
AND (a.Country NOT LIKE '%OECD%')
AND (a.Country NOT LIKE '%countries%')
AND (a.Country NOT LIKE '%South Asia%')
AND (a.Country NOT LIKE '%Small states%')
AND (a.Country NOT LIKE '%Euro area%')
AND (a.Country NOT LIKE '%European Union%')
AND (a.Country NOT LIKE '%North America%')")
childlabour=sqldf("SELECT * FROM childlabour WHERE Subgroup='Total 5-14 yr'")
education=sqldf("SELECT a.* FROM education a INNER JOIN (SELECT Country, MAX(Year) AS Year FROM education GROUP BY 1) b
ON (a.Country=b.Country AND a.Year=b.Year)")
data=sqldf("SELECT a.Country, a.Pop, b.Value as ChildLabour, c.Observation_Value as Education
FROM
population a INNER JOIN childlabour b
ON (a.Country=b.Country) INNER JOIN education c
ON (a.Country=c.Country)")
require(ggplot2)
require(scales)
opts=theme(
panel.background = element_rect(fill="gray98"),
panel.border = element_rect(colour="black", fill=NA),
axis.line = element_line(size = 0.5, colour = "black"),
axis.ticks = element_line(colour="black"),
panel.grid.major = element_line(colour="gray75", linetype = 2),
panel.grid.minor = element_blank(),
axis.text.y = element_text(colour="gray25", size=15),
axis.text.x = element_text(colour="gray25", size=15),
text = element_text(size=20),
legend.key = element_blank(),
legend.position = "none",
legend.background = element_blank(),
plot.title = element_text(size = 45)
)
ggplot(data, aes(x=ChildLabour/100, y=Education/100, size=log(Pop), label=Country), guide=FALSE)+
geom_point(colour="white", fill="red", shape=21, alpha=.55)+
scale_size_continuous(range=c(2,40))+
scale_x_continuous(limits=c(0,.5), labels = percent)+
scale_y_continuous(limits=c(0,.12), labels = percent)+
labs(title="The World We Live In #2: To Study Or To Work",
x="% of Child Workers between 5-14 years old",
y="Public Expenditure on Education as % of GNI")+
geom_text(data=subset(data, ChildLabour/100>.3 | Education/100>.07| Education/10<.022), size=5.5, colour="gray25", hjust=0, vjust=0)+
geom_text(aes(.2, .0), colour="gray25", hjust=0, label="Countries of the world (Source: United Nations Statistics Division) Size of bubble depending on population", size=5)+
opts

The World We Live In #1: Obesity And Cells

Lesson learned, and the wheels keep turning (The Killers – The world we live in)

I discovered this site with a huge amount of data waiting to be analyzed. The first thing I’ve done is this simple graph, where you can see relationship between cellular subscribers and obese people. Bubbles are countries and its size depends on the population:
TWWLI1
Some quick conclusions:

  • The more cellular subscribers, the more obese people
  • Pacific islands such as Kiribati, Palau and Tonga are plenty of happy people
  • Singapore people are thinner than they should be
  • How do Saudi Arabian and Panamanian manage two cellulars?

This is the world we live in.

cellular  =read.csv("UNdata_Export_20140930_cellular.csv",   nrows=193,   header=T, row.names=NULL)
obese     =read.csv("UNdata_Export_20140930_obese.csv",      nrows=567,   header=T, row.names=NULL)
population=read.csv("UNdata_Export_20140930_population.csv", nrows=12846, header=T, row.names=NULL)
require("sqldf")
require("plyr")
population=rename(population, replace = c("Country.or.Area" = "Country"))
population=sqldf("SELECT a.Country, a.Year, a.Value as Population
FROM population a INNER JOIN (SELECT Country, MAX(Year) AS Year FROM population GROUP BY 1) b
      ON (a.Country=b.Country AND a.Year=b.Year)")
cellular=rename(cellular, replace = c("Country.or.Area" = "Country"))
cellular=rename(cellular, replace = c("Value" = "Cellular"))
obese=rename(obese, replace = c("Country.or.Area" = "Country"))
obese=rename(obese, replace = c("Year.s." = "Year"))
obese=sqldf("SELECT a.Country, a.Year, SUBSTR(TRIM(Value), 1, CHARINDEX(' [', TRIM(Value))) as Obeses
FROM obese a INNER JOIN (SELECT Country, MAX(Year) AS Year FROM obese WHERE GENDER='Both sexes' GROUP BY 1) b
ON (a.Country=b.Country AND a.Year=b.Year AND a.GENDER='Both sexes')")
obese$Obeses=as.numeric(obese$Obeses)
data=sqldf("SELECT a.Country, a.Cellular, c.Obeses, b.Population FROM cellular a inner join population b on a.Country = b.Country
      inner join obese c on (a.Country = c.Country) WHERE a.Country NOT IN ('World', 'South Asia')")
require(ggplot2)
require(scales)
opts=theme(
  panel.background = element_rect(fill="gray98"),
  panel.border = element_rect(colour="black", fill=NA),
  axis.line = element_line(size = 0.5, colour = "black"),
  axis.ticks = element_line(colour="black"),
  panel.grid.major = element_line(colour="gray75", linetype = 2),
  panel.grid.minor = element_blank(),
  axis.text.y = element_text(colour="gray25", size=15),
  axis.text.x = element_text(colour="gray25", size=15),
  text = element_text(size=20),
  legend.key = element_blank(),
  legend.position = "none",
  legend.background = element_blank(),
  plot.title = element_text(size = 45)
    )
ggplot(data, aes(x=Cellular/100, y=Obeses/100, size=Population, label=Country), guide=FALSE)+
  geom_point(colour="white", fill="red", shape=21, alpha=.65)+
  scale_size_continuous(range=c(3,35))+
  scale_x_continuous(limits=c(0,2.1), labels = percent)+
  scale_y_continuous(limits=c(0,.6), labels = percent)+
  labs(title="The World We Live In #1: Obesity And Cells",
       x="Cellular Subscribers (per 100 population)",
       y="Adults aged >= 20 years who are obese (%)")+
  geom_text(data=subset(data, Cellular/100 > 1.9 | Obeses/100 > .4 | (Cellular/100 > 1.4 & Obeses/100 < .15)), size=5, colour="gray25", hjust=0, vjust=0)+
  geom_text(aes(.9, .0), colour="blue", hjust=0, label="World's Countries (Source: United Nations Statistics Division. Size of bubble depending on population", size=4)+
  opts