library(ggplot2)

#this file gives the source code for illustrations in the plot tool


#DISTRIBUTION

#distribution 1-var, few data points
##histogram
ID <- 1:200
values <- rnorm(200, mean=50, sd=15)
df <- data.frame(ID, values)
ggplot(df, aes(values)) +
 geom_histogram(binwidth=3) +
 theme(
  plot.title = element_blank(),
  axis.title.x = element_blank(),
  axis.title.y = element_blank())

##dotplot
ID <- 1:200
values <- rnorm(200, mean=50, sd=15)
df <- data.frame(ID, values)
ggplot(df, aes(values)) +
  geom_dotplot() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##freqpoly
ID <- 1:200
values <- rnorm(200, mean=50, sd=15)
df <- data.frame(ID, values)
ggplot(df, aes(values)) +
  geom_freqpoly(size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#distribution 1-var, many data points
##density distribution
ID <- 1:1000
values <- rnorm(1000, mean=50, sd=10)
df <- data.frame(ID, values)
ggplot(df, aes(values)) +
  geom_density(kernel="gaussian", size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#distribution 1-var, many data points
##violin
ID <- 1:1000
values <- rnorm(1000, mean=50, sd=10)
df <- data.frame(ID, values)
ggplot(df, aes(ID, values)) +
  geom_violin(trim=FALSE, width=.5, size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#distribution 2-var, 
##scatterplot
ID <- 1:400
values1 <- rnorm(200, mean=50, sd=10) 
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=40, sd=10))
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_point(size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#distribution 2-var, 
##hexbin
ID <- 1:4000
values1 <- rnorm(4000, mean=50, sd=10) 
values2 <- rnorm(4000, mean=5, sd=1)
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_hex(bins = 70) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#distribution 2-var, 
##2dhistogram
ID <- 1:4000
values1 <- rnorm(4000, mean=50, sd=10) 
values2 <- rnorm(4000, mean=5, sd=1)
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_bin2d(bins = 70) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#distribution 2-var, 
##2d density
ID <- 1:4000
values1 <- rnorm(4000, mean=50, sd=10) 
values2 <- rnorm(4000, mean=5, sd=1)
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  stat_density_2d(aes(fill = ..level..), geom = "polygon") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())



#distribution 2-var, 
##jitter
ID <- 1:600
values <- c(rnorm(200, mean=50, sd=15), rnorm(200, mean=80, sd=10), rnorm(200, mean=30, sd=5))
category <- c(rep("A", 200), rep("B",200), rep("C",200))
df <- data.frame(ID, category, values)
ggplot(df, aes(category, values)) +
  geom_jitter(width=.1) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#distribution 2-var, 
##violin
ID <- 1:600
values <- c(rnorm(200, mean=50, sd=15), rnorm(200, mean=80, sd=10), rnorm(200, mean=30, sd=5))
category <- c(rep("A", 200), rep("B",200), rep("C",200))
df <- data.frame(ID, category, values)
ggplot(df, aes(category, values)) +
  geom_violin(trim=FALSE, width=.8) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##################################################################################################

#COMPARISON

#comparison few items, few categories
##simple bar chart
ID <- 1:600
values <- c(rnorm(150, mean=25, sd=5), rnorm(150, mean=30, sd=4), rnorm(150, mean=15, 3), rnorm(150, mean=40, sd=5))
category <- c(rep("A", 150), rep("B", 150), rep("C", 150), rep("D", 150))
df <- data.frame(ID, category, values)
ggplot(df, aes(category, values)) +
  geom_bar(stat="summary", fun.y="mean") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##simple bar chart with error bars
ID <- 1:600
values <- c(rnorm(150, mean=25, sd=5), rnorm(150, mean=30, sd=4), rnorm(150, mean=15, 3), rnorm(150, mean=40, sd=5))
category <- c(rep("A", 150), rep("B", 150), rep("C", 150), rep("D", 150))
df <- data.frame(ID, category, values)
ggplot(df, aes(category, values)) +
  geom_bar(stat="summary", fun.y="mean") +
  stat_summary(fun.data=mean_sdl, geom="errorbar", colour = "red", width=.3, size=1.5) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##box plot
ID <- 1:600
values <- c(rnorm(150, mean=25, sd=5), rnorm(150, mean=30, sd=4), rnorm(150, mean=15, 3), rnorm(150, mean=40, sd=5))
category <- c(rep("A", 150), rep("B", 150), rep("C", 150), rep("D", 150))
df <- data.frame(ID, category, values)
ggplot(df, aes(category, values)) +
  geom_boxplot() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##clustered bar chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2")
category2 <- rep(undeux, 200)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())
  
  
##clustered bar chart with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2")
category2 <- rep(undeux, 200)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())
  
  
#comparison many items, few categories
##clustered bar chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2","3","4")
category2 <- rep(undeux, 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##clustered bar chart with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2","3","4")
category2 <- rep(undeux, 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##horizontal clustered bar chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2","3","4")
category2 <- rep(undeux, 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) + 
  scale_fill_viridis_d() +
  coord_flip() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##horizontal clustered bar chart with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeux <- c("1","2","3","4")
category2 <- rep(undeux, 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  coord_flip() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##grid of clustered bar charts
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeuxtroisquatre <- c("1","2","3","4")
firstsecond <- c("first", "second")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  facet_wrap( ~ category3, ncol=2) +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##grid of clustered bar charts with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeuxtroisquatre <- c("1","2","3","4")
firstsecond <- c("first", "second")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  facet_wrap( ~ category3, ncol=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##clustered boxplots
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeuxtroisquatre <- c("1","2","3","4")
category2 <- rep(undeuxtroisquatre, 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  geom_boxplot() +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##clustered boxplots
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
category2 <- rep(c("1","2"), 100)
df <- data.frame(ID, category1, category2, values)
ggplot(df, aes(category1, values, fill=category2)) +
  geom_boxplot() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())
head(df)
##grid of boxplots
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=15, 3), rnorm(100, mean=40, sd=5))
category1 <- c(rep("A", 100), rep("B", 100), rep("C", 100), rep("D", 100))
undeuxtroisquatre <- c("1","2","3","4")
firstsecond <- c("first", "second")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  geom_boxplot() +
  facet_wrap( ~ category3, ncol=2) +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#comparison many items, many categories
##grid of clustered box plots
ID <- 1:800
values <- c(rnorm(200, mean=25, sd=5), rnorm(200, mean=30, sd=4), rnorm(200, mean=15, 3), rnorm(200, mean=40, sd=5))
category1 <- c(rep("A", 200), rep("B", 200), rep("C", 200), rep("D", 200))
undeuxtroisquatre <- c("1","2","3","4","5","6","7","8")
firstsecond <- c("first", "second", "third", "fourth")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  geom_boxplot() +
  facet_wrap( ~ category3, ncol=2) +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##grid of clustered bar charts
ID <- 1:800
values <- c(rnorm(200, mean=25, sd=5), rnorm(200, mean=30, sd=4), rnorm(200, mean=15, 3), rnorm(200, mean=40, sd=5))
category1 <- c(rep("A", 200), rep("B", 200), rep("C", 200), rep("D", 200))
undeuxtroisquatre <- c("1","2","3","4","5","6","7","8")
firstsecond <- c("first", "second", "third", "fourth")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  facet_wrap( ~ category3, ncol=2) +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##grid of clustered bar charts with CI
ID <- 1:800
values <- c(rnorm(200, mean=25, sd=5), rnorm(200, mean=30, sd=4), rnorm(200, mean=15, 3), rnorm(200, mean=40, sd=5))
category1 <- c(rep("A", 200), rep("B", 200), rep("C", 200), rep("D", 200))
undeuxtroisquatre <- c("1","2","3","4","5","6","7","8")
firstsecond <- c("first", "second", "third", "fourth")
category2 <- rep(undeuxtroisquatre, 100)
category3 <- rep(firstsecond, 200)
df <- data.frame(ID, category1, category2, category3, values)
ggplot(df, aes(category1, values, fill=category2)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +  
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  facet_wrap( ~ category3, ncol=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())



#comparison few periods, few categories
##simple bar chart
ID <- 1:600
values <- c(rnorm(150, mean=25, sd=5), rnorm(150, mean=30, sd=4), rnorm(150, mean=35, 3), rnorm(150, mean=40, sd=5))
year <- c(rep("2015", 150), rep("2016", 150), rep("2017", 150), rep("2018", 150))
df <- data.frame(ID, category, values)
ggplot(df, aes(year, values)) +
  geom_bar(stat="summary", fun.y="mean") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##simple bar chart with error bars
ID <- 1:600
values <- c(rnorm(150, mean=25, sd=5), rnorm(150, mean=30, sd=4), rnorm(150, mean=35, 3), rnorm(150, mean=40, sd=5))
year <- c(rep("2015", 150), rep("2016", 150), rep("2017", 150), rep("2018", 150))
df <- data.frame(ID, year, values)
ggplot(df, aes(year, values)) +
  geom_bar(stat="summary", fun.y="mean") +
  stat_summary(fun.data=mean_sdl, geom="errorbar", colour = "red", width=.3, size=1.5) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##clustered bar chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5))
year <- c(rep("2015", 100), rep("2016", 100), rep("2017", 100), rep("2018", 100))
undeux <- c("1","2")
category <- rep(undeux, 200)
df <- data.frame(ID, year, category, values)
ggplot(df, aes(year, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##clustered bar chart with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5))
year <- c(rep("2015", 100), rep("2016", 100), rep("2017", 100), rep("2018", 100))
undeux <- c("1","2")
category <- rep(undeux, 200)
df <- data.frame(ID, year, category, values)
ggplot(df, aes(year, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#comparison few periods, many categories
##clustered bar chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5))
year <- c(rep("2015", 100), rep("2016", 100), rep("2017", 100), rep("2018", 100))
unhuit <- c("1","2","3","4","5","6","7","8")
category <- rep(unhuit, 50)
df <- data.frame(ID, year, category, values)
ggplot(df, aes(year, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##clustered bar chart with CI
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5))
year <- c(rep("2015", 100), rep("2016", 100), rep("2017", 100), rep("2018", 100))
unhuit <- c("1","2","3","4","5","6","7","8")
category <- rep(unhuit, 50)
df <- data.frame(ID, year, category, values)
ggplot(df, aes(year, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  stat_summary(fun.data=mean_sdl, width=.3, position=position_dodge(0.90),geom="errorbar", size=1.5, color="#666666") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##line chart
ID <- 1:400
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=32, 3), rnorm(100, mean=40, sd=5))
year <- c(rep("2015", 100), rep("2016", 100), rep("2017", 100), rep("2018", 100))
unquatre <- c("1","2","3","4")
category <- rep(unquatre, 100)
df <- data.frame(ID, year, category, values)
ggplot(df, aes(x=year, y=values, group=category)) + 
  stat_summary(aes(color=category, linetype=category), fun.y=mean, size=1.5, position=position_dodge(.15), geom="line") +
  geom_point(aes(color=category), size = 3, stat="summary", fun.y=mean, position=position_dodge(.15)) +
  scale_color_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#comparison many periods, non-cyclic data
##clustered bar chart
ID <- 1:1200
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5), rnorm(100, mean=35, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=35, sd=5),rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=20, sd=5))
month <- rep(c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), each=100)
undeux <- c("1","2")
category <- rep(undeux, 600)
df <- data.frame(ID, month, category, values)
ggplot(df, aes(month, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  scale_x_discrete(limits=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##line chart
ID <- 1:1200
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5), rnorm(100, mean=35, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=35, sd=5),rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=20, sd=5))
month <- rep(c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), each=100)
undeux <- c("1","2")
category <- rep(undeux, 600)
df <- data.frame(ID, month, category, values)
ggplot(df, aes(x=month, y=values, group=category)) + 
  stat_summary(aes(color=category, linetype=category), fun.y=mean, size=1.5, position=position_dodge(.15), geom="line") +
  geom_point(aes(color=category), size = 3, stat="summary", fun.y=mean, position=position_dodge(.15)) +
  scale_x_discrete(limits=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#comparison many periods, cyclic data
##circular line chart
ID <- 1:1200
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5), rnorm(100, mean=35, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=35, sd=5),rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=20, sd=5))
month <- rep(c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), each=100)
undeux <- c("1","2")
category <- rep(undeux, 600)
df <- data.frame(ID, month, category, values)
ggplot(df, aes(x=month, y=values, group=category)) + 
  stat_summary(aes(color=category, linetype=category), fun.y=mean, size=1.5, position=position_dodge(.15), geom="line") +
  geom_point(aes(color=category), size = 3, stat="summary", fun.y=mean, position=position_dodge(.15)) +
  scale_x_discrete(limits=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")) +
  coord_polar() +
  ylim(0,55)+
  scale_color_viridis_d()
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank()) 

##circular bar chart
##clustered bar chart
ID <- 1:1200
values <- c(rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=40, sd=5), rnorm(100, mean=35, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=35, sd=5),rnorm(100, mean=25, sd=5), rnorm(100, mean=30, sd=4), rnorm(100, mean=35, 3), rnorm(100, mean=20, sd=5))
month <- rep(c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), each=100)
undeux <- c("1","2")
category <- rep(undeux, 600)
df <- data.frame(ID, month, category, values)
ggplot(df, aes(month, values, fill=category)) +
  stat_summary(fun.y=mean, geom="bar", position=position_dodge(width=0.90)) +
  scale_x_discrete(limits=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")) +
  ylim(-60,55) +
  coord_polar() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())



##################################################################################################

#RELATIONSHIP

#relationship  2-var
##scatter plot
ID <- 1:300
values1 <- c(rnorm(100, mean=50, sd=15), rnorm(100, mean=75, sd=15), rnorm(100, mean=100, sd=15))
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=30, sd=10),rnorm(100, mean=40, sd=10))
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_point(size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##scatter plot with loess curve fitting
ID <- 1:300
values1 <- c(rnorm(100, mean=50, sd=15), rnorm(100, mean=75, sd=15), rnorm(100, mean=100, sd=15))
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=30, sd=10),rnorm(100, mean=40, sd=10))
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_point(size=2) +
  geom_smooth() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##scatter plot with regression line
ID <- 1:300
values1 <- c(rnorm(100, mean=50, sd=15), rnorm(100, mean=75, sd=15), rnorm(100, mean=100, sd=15))
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=30, sd=10),rnorm(100, mean=40, sd=10))
df <- data.frame(ID, values1, values2)
ggplot(df, aes(values1, values2)) +
  geom_point(size=2) +
  geom_smooth(method='lm') +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#relationship  3-var
##scatter plot with color scale 
ID <- 1:300
values1 <- c(rnorm(100, mean=50, sd=15), rnorm(100, mean=75, sd=15), rnorm(100, mean=100, sd=15))
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=30, sd=10),rnorm(100, mean=40, sd=10))
values3 <- c(rnorm(100, mean=2, sd=1), rnorm(100, mean=3, sd=1),rnorm(100, mean=4, sd=1))
df <- data.frame(ID, values1, values2, values3)
ggplot(df, aes(values1, values2)) +
  geom_point(aes(color=values3), size=2) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##bubble plot
ID <- 1:300
values1 <- c(rnorm(100, mean=50, sd=15), rnorm(100, mean=75, sd=15), rnorm(100, mean=100, sd=15))
values2 <- c(rnorm(100, mean=20, sd=10), rnorm(100, mean=30, sd=10),rnorm(100, mean=40, sd=10))
values3 <- c(rnorm(100, mean=2, sd=1), rnorm(100, mean=5, sd=1),rnorm(100, mean=8, sd=1))
df <- data.frame(ID, values1, values2, values3)
ggplot(df, aes(values1, values2)) +
  geom_point(aes(size=values3), alpha=.3) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##################################################################################################

#PART OF A WHOLE
#static, simple
##pie chart
type <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
proportion <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
df <- data.frame(type, proportion)
ggplot(df, aes(x="", y=proportion, fill=type)) +
  geom_bar(stat = "identity") +
  scale_fill_manual(values = c("#40BFBF","#D1D075","#2A7E5D","#97C34B","#2A6D7E","#7DD4A8","#D5B081","#B6E7E0"  )) +
  coord_polar("y") + 
  theme_void()

##pie chart
type <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
proportion <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
df <- data.frame(type, proportion)
ggplot(df, aes(x="", y=proportion, fill=type)) +
  geom_bar(stat = "identity") +
  scale_fill_viridis_d() +
  coord_polar("y") + 
  theme_void()

##stacked bars
type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 3)
country <- c(rep("Norway", 8),rep("France", 8),rep("UK",8))
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
France <- c(36.0,	37.0,	9.0,	3.0,	6.0,	6.0,	2.0,	1.0)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
percentage <- c(Norway, France, UK)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
  geom_bar(width = 0.5, stat = "identity") +
  scale_fill_manual(values = c("#40BFBF","#D1D075","#2A7E5D","#97C34B","#2A6D7E","#7DD4A8","#D5B081","#B6E7E0"  )) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 3)
country <- c(rep("Norway", 8),rep("France", 8),rep("UK",8))
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
France <- c(36.0,	37.0,	9.0,	3.0,	6.0,	6.0,	2.0,	1.0)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
percentage <- c(Norway, France, UK)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
  geom_bar(width = 0.5, stat = "identity") +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

##ring plot
type <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
proportion <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
df <- data.frame(type, proportion)
ggplot(df, aes(x=2, y=proportion, fill=type)) +
  geom_bar(stat = "identity") +
  xlim(0.5, 2.5) +
  scale_fill_manual(values = c("#40BFBF","#D1D075","#2A7E5D","#97C34B","#2A6D7E","#7DD4A8","#D5B081","#B6E7E0"  )) +
  coord_polar("y") + 
  theme_void()

##ring plot
type <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
proportion <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
df <- data.frame(type, proportion)
ggplot(df, aes(x=2, y=proportion, fill=type)) +
  geom_bar(stat = "identity") +
  xlim(0.5, 2.5) +
  scale_fill_viridis_d() +
  coord_polar("y") + 
  theme_void()

##multiple Ring plot 
type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 3)
country <- c(rep("Norway", 8), rep("UK",8), rep("blank",8) )
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
blank <- c(0.0,	0.0,	0.0,	0.0,	0.0,	0.0,	0.0,	0.0)
percentage <- c(Norway, UK, blank)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
geom_bar(stat = "identity", width = .85) +
  scale_fill_manual(values = c("#40BFBF","#D1D075","#2A7E5D","#97C34B","#2A6D7E","#7DD4A8","#D5B081","#B6E7E0"  )) +
  coord_polar("y") +
  theme_void()
 
##multiple Ring plot 
type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 3)
country <- c(rep("Norway", 8), rep("UK",8), rep("blank",8) )
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
blank <- c(0.0,	0.0,	0.0,	0.0,	0.0,	0.0,	0.0,	0.0)
percentage <- c(Norway, UK, blank)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
  geom_bar(stat = "identity", width = .85) +
  scale_fill_viridis_d() +
  coord_polar("y") +
  theme_void()

##pie and ring plot 
type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 2)
country <- c(rep("Norway", 8), rep("UK",8))
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
percentage <- c(Norway, UK)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
  geom_bar(stat = "identity", width = .85) +
  scale_fill_manual(values = c("#40BFBF","#D1D075","#2A7E5D","#97C34B","#2A6D7E","#7DD4A8","#D5B081","#B6E7E0"  )) +
  coord_polar("y") +
  theme_void()

##pie and ring plot 
type <- rep(c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-"), 2)
country <- c(rep("Norway", 8), rep("UK",8))
Norway <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)
UK <- c(37.0,	31.0,	8.0,	3.0,	11.0,	7.0,	2.0,	1.0)
percentage <- c(Norway, UK)
df <- data.frame(type, country, percentage)
ggplot(df, aes(x=country, y=percentage, fill=type)) +
  geom_bar(stat = "identity", width = .85) +
  scale_fill_viridis_d()+
  coord_polar("y") +
  theme_void()

#static, subcomponents
##pie and ring plot 
country <- c(rep("Norway", 8))  
type <- rep(c("O","A","B","AB"), 2)
subtype <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
percentage <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)  
df <- data.frame(country, type, subtype, percentage)
ggplot( ) +
  geom_bar(data=df, aes(x=1, y=percentage, fill=type), stat="identity") +
  geom_bar(data=df, aes(x=2, y=percentage, fill=subtype), stat="sum") +
  geom_hline(yintercept =  c(0, 39, 47,51),
     colour="#451849", size=1.5) +
  scale_fill_manual(values = c("#2874A6", "#3498DB", "#85C1E9",
                               "#148F77","#1ABC9C","#76D7C4",
                               "#B7950B","#F1C40F","#F7DC6F",
                               "#922B21","#C0392B","#D98880"  )) +
  xlim(0, 2.5) +
  coord_polar("y") +
  theme_void()                     

##pie and ring plot 
country <- c(rep("Norway", 8))  
type <- rep(c("O","A","B","AB"), 2)
subtype <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
percentage <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)  
df <- data.frame(country, type, subtype, percentage)
ggplot( ) +
  geom_bar(data=df, aes(x=1, y=percentage, fill=type), stat="identity") +
  geom_bar(data=df, aes(x=2, y=percentage, fill=subtype), stat="sum") +
  geom_hline(yintercept =  c(0, 39, 47,51),
             colour="#451849", size=1.5) +
  scale_fill_manual(values = c("#2874A6", "#3498DB", "#85C1E9",
                               "#148F77","#1ABC9C","#76D7C4",
                               "#B7950B","#F1C40F","#F7DC6F",
                               "#922B21","#C0392B","#D98880"  )) +
  xlim(0, 2.5) +
  coord_polar("y") +
  theme_void()  
  
##bar plot with subcomponents  
country <- c(rep("Norway", 8))  
type <- rep(c("O","A","B","AB"), 2)
subtype <- c("O+", "A+", "B+", "AB+", "O-", "A-", "B-", "AB-")
percentage <- c(33.2,	41.6,	6.8,	3.4,	5.8,	7.4,	1.2,	0.6)  
df <- data.frame(country, type, subtype, percentage)
ggplot( ) +
  geom_bar(data=df, aes(x=1,  y=percentage, fill=type), width=.5, stat="identity") +
  geom_bar(data=subset(df, type == "B"), aes(x=2,  y=(percentage*100/8), fill=subtype), width=.5 , stat="sum") +
  geom_segment(data=df, aes(x=0.75,y=39, xend=1.25, yend=39), color="darkblue", size=1) +
  geom_segment(data=df, aes(x=0.75,y=47, xend=1.25, yend=47), color="darkblue", size=1) +
  geom_segment(data=df, aes(x=1.25,y=39, xend=1.75, yend=0), color="darkblue", size=1) +
  geom_segment(data=df, aes(x=1.25,y=47, xend=1.75, yend=100), color="darkblue", size=1) +
  geom_segment(data=df, aes(x=1.75,y=0, xend=2.25, yend=0), color="darkblue", size=1) +
  geom_segment(data=df, aes(x=1.75,y=100, xend=2.25, yend=100), color="darkblue", size=1) +
  scale_fill_manual(values = c("#3498DB", 
                               "#1ABC9C",
                               "#F1C40F","#F7DC6F",
                               "#C0392B","#D98880"  )) +
  xlim(0.5, 2.5) +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank()) +
  theme_void()




#changing over time, few periods, relative and absolute
#stacked bars
year <- rep(c("1988", "1998", "2008", "2018"), 2)
gender <- c(rep("male",4), rep("female",4)) 
absolute <- c(2076155,2185106,2359690,2668371,2122134,2232493,2377481,2627248)
percentage <- c(49.45,49.46,49.81,50.39,50.55,50.54,50.19,49.61)
df <- data.frame(year, gender, absolute, percentage)
ggplot(df, aes(x=year, y=absolute)) + 
  geom_bar(aes(fill=gender), stat="identity") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())
  

#changing over time, few periods, relative only
#stacked bars 100%
year <- rep(c("1988", "1998", "2008", "2018"), 10)
age <- rep(c("0-9 years","10-19 years", "20-29 years", "30-39 years", "40-49 years", "50-59 years", "60-69 years", "70-79 years", "80-89 years", "90 years or more"), each=4)
population <- c(522063.5,	607944.5,	595080.5,	619083.5,
                610809.5,	535235.5,	632107.5,	639091.5,
                652045.0,	629437.5,	589126.0,	713182.0,
              	621213.0,	664975.0,	682810.0,	712876.5,
	              529530.0,	616922.5,	681520.5,	731853.5,
              	383535.5,	511848.5,	605999.5,	686234.5,
                422845.5,	349618.5,	475742.0,	574534.5,
                316744.0,	329065.0,	286713.0,	410684.0,
                132696.5,	162373.5,	185147.0,	179545.5,
                 18005.0,  24043.5,  33965.5,  44830.0)
percentage <- c(12.40,	13.72,	12.48,	11.65,
                14.51,	12.08,	13.26,	12.03,
                15.49,	14.20,	12.36,	13.43,
                14.76,	15.01,	14.32,	13.42,
                12.58,	13.92,	14.29,  13.78,
                 9.11,	11.55,	12.71,	12.92,
                10.05,	7.89,  	9.98,	  10.82,
                 7.52,	7.43,	  6.01,  	 7.73,
                 3.15,	3.66,	  3.88,	   3.38,
                 0.43,	0.54,	  0.71,    0.84)
df <- data.frame(year, age, population, percentage)
ggplot(df, aes(x=year, y=percentage)) + 
  geom_bar(aes(fill=age), stat="identity") +
  scale_fill_viridis_d() +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#changing over time, many periods, relative and absolute
#stacked bars 

year <- c(2000,	2001,	2002,	2003,	2004,	2005,	2006,	2007,	2008,	2009,	2010,	2011,	2012,	2013,	2014,	2015,	2016,	2017)
gender <- rep(c("male", "female"), each=18)
students <-	c(74914,	76958,	83328,	84097,	85144,	84967,	83805,	81474,	83245,	87623,	90550,	94376,	98449,	103612,	103485,	107690,	110570,	113038,
              111088,	115939,	125365,	125673, 125857,	126297,	127424,	126789,	130938,	135297,	137197,	141464,	147123,	149705,	152103,	158738,	162657,	164599)
df <- data.frame(year, gender, students)
ggplot(df, aes(x=year, y=students)) + 
  geom_bar(aes(fill=gender), stat="identity") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#area 
year <- c(2000,	2001,	2002,	2003,	2004,	2005,	2006,	2007,	2008,	2009,	2010,	2011,	2012,	2013,	2014,	2015,	2016,	2017)
gender <- rep(c("male", "female"), each=18)
students <-	c(74914,	76958,	83328,	84097,	85144,	84967,	83805,	81474,	83245,	87623,	90550,	94376,	98449,	103612,	103485,	107690,	110570,	113038,
              111088,	115939,	125365,	125673, 125857,	126297,	127424,	126789,	130938,	135297,	137197,	141464,	147123,	149705,	152103,	158738,	162657,	164599)
df <- data.frame(year, gender, students)
ggplot(df, aes(x=year, y=students)) + 
  geom_area(aes(fill=gender), stat="identity") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())

#line
year <- c(2000,	2001,	2002,	2003,	2004,	2005,	2006,	2007,	2008,	2009,	2010,	2011,	2012,	2013,	2014,	2015,	2016,	2017)
gender <- rep(c("male", "female"), each=18)
students <-	c(74914,	76958,	83328,	84097,	85144,	84967,	83805,	81474,	83245,	87623,	90550,	94376,	98449,	103612,	103485,	107690,	110570,	113038,
              111088,	115939,	125365,	125673, 125857,	126297,	127424,	126789,	130938,	135297,	137197,	141464,	147123,	149705,	152103,	158738,	162657,	164599)
df <- data.frame(year, gender, students)
ggplot(df, aes(x=year, y=students)) + 
  geom_line(aes(color=gender), size=2) +
  ylim(0,175000)
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#changing over time, many periods, relative only
#area 100%
year <- c(2000,	2001,	2002,	2003,	2004,	2005,	2006,	2007,	2008,	2009,	2010,	2011,	2012,	2013,	2014,	2015,	2016,	2017)
gender <- rep(c("male", "female"), each=18)
students <-	c(74914,	76958,	83328,	84097,	85144,	84967,	83805,	81474,	83245,	87623,	90550,	94376,	98449,	103612,	103485,	107690,	110570,	113038,
              111088,	115939,	125365,	125673, 125857,	126297,	127424,	126789,	130938,	135297,	137197,	141464,	147123,	149705,	152103,	158738,	162657,	164599)
percentage <- c(40.28,	39.90,	39.93,	40.09,	40.35,	40.22,	39.67,	39.12,	38.87,	39.31,	39.76,	40.02,	40.09,	40.90,	40.49,	40.42,	40.47,	40.71,
                59.72,	60.10,	60.07,	59.91,	59.65,	59.78,	60.33,	60.88,	61.13,	60.69,	60.24,	59.98,	59.91,	59.10,	59.51,	59.58,	59.53,	59.29)
df <- data.frame(year, gender, students, percentage)
ggplot(df, aes(x=year, y=percentage)) + 
  geom_area(aes(fill=gender), stat="identity") +
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


##### NOT WORKING YET####


#area NEEDS continuous
year <- as.numeric(rep(c("1988", "1998", "2008", "2018"), 2))
gender <- c(rep("male",4), rep("female",4)) 
absolute <- c(2076155, 2185106, 2359690, 2668371, 2122134, 2232493, 2377481, 2627248)
percentage <- c(49.45, 49.46, 49.81, 50.39, 50.55, 50.54, 50.19, 49.61)
df <- data.frame(year, gender, absolute, percentage)
ggplot(df, aes(x=year, y=percentage, fill=gender)) + 
  geom_area() + 
  theme(
    plot.title = element_blank(),
    axis.title.x = element_blank(),
    axis.title.y = element_blank())


#changing over time, few periods, relative






year <- rep(c("1988", "1998", "2008", "2018"), 3)
citizenship <- c(rep("Sweden",4), rep("Denmark",4), rep("UK",4), rep("total",4)) 
absolute <- c(12037, 20629, 29886, 43963,
              17562, 18438, 20461, 22806, 
              12770, 10798, 12024, 16189,
              4198289, 4417599, 4737171, 5295619)
percentage <- c(0.29,	0.47,	0.63,	0.83, 
                0.42,	0.42,	0.43,	0.43,
                0.30,	0.24,	0.25,	0.31,
                100, 100, 100, 100)