M <-read.csv("C:/Users/jmtsi/Documents/today//FAOSTATmaize.csv")
YLD <- M[ which(M$Element == "Yield"), ]
YLD1617 <- YLD[YLD$Year > 2015,]
PRODIMP <- subset(M, subset = Element == "Production" | Element == "Import")
PRODIMPSouthAf <- subset(PRODIMP, subset = Area == "Southern Africa")
PROD <- subset(PRODIMP, subset = Element == "Production")
PROD17 <- PROD[PROD$Year > 2016,]
PRODAf <- subset(PROD, subset = Area == "Eastern Africa" | Area == "Middle Africa" | Area == "Northern Africa" | Area == "Southern Africa" | Area == "Western Africa")
PRODAf17 <- PRODAf[PRODAf$Year > 2016,]
PRODSouthAf <- subset(PROD, subset = Area == "Southern Africa")
MAf <- subset(M, subset = Area == "Eastern Africa" | Area == "Middle Africa" | Area == "Northern Africa" | Area == "Southern Africa" | Area == "Western Africa")
MSouthAf <- subset(M, subset = Area == "Southern Africa")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
mPRODIMP = group_by(PRODIMP, Area, Element)
mPRODIMP = summarise(mPRODIMP,
mValue = mean(Value))
library(ggplot2)
## Registered S3 methods overwritten by 'ggplot2':
## method from
## [.quosures rlang
## c.quosures rlang
## print.quosures rlang
#1. ONE CONTINUOUS VARIABLE------------------------------------------------------------------------------------------------------------------------------
#All ggplot2 plots begin with a call to ggplot(), supplying default data and aesthethic mappings, specified by aes().
#You then add layers, scales, coords and facets with +
ggplot(YLD1617, aes(Value))
ggplot(YLD1617, aes(Value)) + geom_density()
#Change the theme (grey by default, my personal favorite is bw)
ggplot(YLD1617, aes(Value)) + geom_density() + theme_classic()
ggplot(YLD1617, aes(Value)) + geom_density() + theme_minimal()
ggplot(YLD1617, aes(Value)) + geom_density() + theme_grey()
ggplot(YLD1617, aes(Value)) + geom_density() + theme_bw()
#Fill the density plot with a colour
ggplot(YLD1617, aes(Value)) + geom_density(fill = "red") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "blue") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "green") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "grey") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "grey35") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "springgreen") + theme_bw()
ggplot(YLD1617, aes(Value)) + geom_density(fill = "springgreen3") + theme_bw()
#http://sape.inf.usi.ch/quick-reference/ggplot2/colour
#Add axis legends and graph title
ggplot(YLD1617, aes(Value)) + geom_density(fill = "springgreen3") + theme_bw() +
ggtitle("A") + xlab("Yield (hg/ha)") + ylab("Density")
#Personalize the font
ggplot(YLD1617, aes(Value)) + geom_density(fill = "springgreen3") + theme_bw() +
ggtitle("A") + xlab("Yield (hg/ha)") + ylab("Density") +
theme(plot.title = element_text(hjust = 0, size=28, face="bold"),
axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Change the unit from hg/ha to t/ha
ggplot(YLD1617, aes(Value/10000)) + geom_density(fill = "springgreen3") + theme_bw() +
ggtitle("A") + xlab("Yield (t/ha)") + ylab("Density") +
theme(plot.title = element_text(hjust = 0, size=28, face="bold"),
axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#2. ONE CONTINUOUS VARIABLE AND TWO SUBSETS OF DATA---------------------------------------------------------------------------------------------------------
YLD1617$Year <- as.factor(YLD1617$Year)
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density() + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Change the colors manually
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density() + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Adding transparency (alpha) + thicker lines (size)
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density(alpha = 0.5, size = 1) + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Moving the position of the legend
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density(alpha = 0.5, size = 1) + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99))
#Removing the legend title
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density(alpha = 0.5, size = 1) + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99), legend.title = element_blank())
#Personalize the font of the legend
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density(alpha = 0.5, size = 1) + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=20, face="bold"), legend.title = element_blank())
#Increase the key size
ggplot(YLD1617, aes(x = Value/10000, fill = Year)) + geom_density(alpha = 0.5, size = 1) + theme_bw() +
xlab("Yield (t/ha)") + ylab("Density") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=20, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
#3. ONE DISCRETE VARIABLE AND ONE CONTINUOUS VARIABLE-------------------------------------------------------------------------------------------------------
#3.1. Example 1
ggplot(YLD1617, aes(Year, Value/10000)) + geom_boxplot(fill = "springgreen3") + theme_bw() +
xlab("Year") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#As a violin plot
ggplot(YLD1617, aes(Year, Value/10000)) + geom_violin(fill = "springgreen3") + theme_bw() +
xlab("Year") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#3.2. Example 2
ggplot(YLD, aes(Area, Value/10000)) + geom_boxplot(fill = "springgreen3") + theme_bw() +
xlab("Year") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Rotate and justify x axis labels
ggplot(YLD, aes(Area, Value/10000)) + geom_boxplot(fill = "springgreen3") + theme_bw() +
xlab("") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=20, face="bold"))
#As a violin plot
ggplot(YLD, aes(Area, Value/10000)) + geom_violin(fill = "springgreen3") + theme_bw() +
xlab("") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=20, face="bold"))
#4. ONE DISCRETE VARIABLE ONE CONTINUOUS VARIABLE AND TWO SUBSETS OF DATA-----------------------------------------------------------------------------------
#4.1. Boxplots
ggplot(PRODIMP, aes(Area, Value/1000000, fill = Element)) + geom_boxplot() + theme_bw() +
xlab("") + ylab("Yield (t/ha)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=20, face="bold"))
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
#Personalize colors and legend format
ggplot(PRODIMP, aes(Area, Value/1000000, fill = Element)) + geom_boxplot() + theme_bw() +
xlab("") + ylab("Maize grain (million tones)") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
#Space between the Y title and the Y axis, and naming the plot
ggplot(PRODIMP, aes(Area, Value/1000000, fill = Element)) + geom_boxplot() + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
#2 facets
ggplot(PRODIMP, aes(Area, Value/1000000, fill = Element)) + geom_boxplot() + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
facet_wrap(~ Element)
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
#Remove the legend, change the font of the strip
ggplot(PRODIMP, aes(Area, Value/1000000, fill = Element)) + geom_boxplot() + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.position="none", strip.text.x = element_text(size = 16)) +
facet_wrap(~ Element)
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
#4.1. Bar plot
ggplot(mPRODIMP, aes(Area, mValue/1000000, fill = Element)) + geom_bar(stat = "identity") + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 1 rows containing missing values (position_stack).
#Outline the bars
ggplot(mPRODIMP, aes(Area, mValue/1000000, fill = Element)) + geom_bar(stat = "identity", color ="black", size = 1) + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 1 rows containing missing values (position_stack).
#Dodge
ggplot(mPRODIMP, aes(Area, mValue/1000000, fill = Element)) + geom_bar(stat = "identity", color ="black", size = 1, position=position_dodge()) + theme_bw() +
xlab("") + ylab("Maize grain (million tones)\n") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=20, face="bold"),
axis.text.x = element_text(size=12, face="bold", angle = 90, hjust = 1),
axis.text.y = element_text(size=16, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
guides(fill=guide_legend(title=NULL))
## Warning: Removed 1 rows containing missing values (geom_bar).
#5. TWO CONTINUOUS VARIABLEs---------------------------------------------------------------------------------------------------------------------------------------
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) + theme_bw() +
xlab("Year") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"))
#Remove X axis title and increase scale (every 10 years)
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Add points
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) +
geom_point() + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Personalize the points
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) +
geom_point(colour = "springgreen3", fill = "springgreen3", size = 5) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Personalize points further
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) +
geom_point(shape = 21, colour = "black", fill = "springgreen3", stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Add regression line
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) +
geom_point(shape = 21, colour = "black", fill = "springgreen3", stroke = 1.5, size = 5) +
geom_smooth (method = "lm") + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Personalize the regression line
ggplot(PRODSouthAf, aes(Year, Value/1000000)) + geom_line(color = "springgreen3", size = 1) +
geom_point(shape = 21, colour = "black", fill = "springgreen3", stroke = 1.5, size = 5) +
geom_smooth (method = "lm", colour = "black", linetype = 2, fill = "springgreen3") + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Bring the regression line at the back (remember ggplot works with layers: their order is important!)
ggplot(PRODSouthAf, aes(Year, Value/1000000)) +
geom_smooth (method = "lm", colour = "black", linetype = 2, fill = "springgreen3") + theme_bw() +
geom_line(color = "springgreen3", size = 1) +
geom_point(shape = 21, colour = "black", fill = "springgreen3", stroke = 1.5, size = 5) +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#6. TWO CONTINUOUS VARIABLEs AND TWO DATA SUBSETS-------------------------------------------------------------------------------------------------------------------
#6.1. Line plot
ggplot(PRODIMPSouthAf, aes(Year, Value/1000000)) + geom_line(aes(color = Element), size = 1) +
geom_point(shape = 21, colour = "black", aes(fill = Element), stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production & import (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold")) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#Personalize colors and legend
ggplot(PRODIMPSouthAf, aes(Year, Value/1000000)) + geom_line(aes(color = Element), size = 1) +
geom_point(shape = 21, colour = "black", aes(fill = Element), stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production & import (million tones)") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
scale_color_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#6.2. Area plot
ggplot(PRODIMPSouthAf, aes(Year, Value/1000000)) + geom_area(aes(fill = Element), color = "black", size = 1) + theme_bw() +
xlab("") + ylab("Production and import (million tones)") +
scale_fill_manual(values=c("springgreen1", "springgreen3")) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
#7. TWO CONTINUOUS VARIABLE AND MORE THAN TWO DATA SUBSETS--------------------------------------------------------------------------------------------------------------
#7.1. Line plot
ggplot(PROD, aes(Year, Value/1000000)) + geom_line(aes(color = Area), size = 1) +
geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODSouthAf$Year), max(PRODSouthAf$Year), by = 10)))
## Warning: Removed 9 rows containing missing values (geom_path).
## Warning: Removed 20 rows containing missing values (geom_point).
#Move the legend
ggplot(PROD, aes(Year, Value/1000000)) + geom_line(aes(color = Area), size = 1) +
geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PROD$Year), max(PROD$Year), by = 10)))
## Warning: Removed 9 rows containing missing values (geom_path).
## Warning: Removed 20 rows containing missing values (geom_point).
#Personlize the palette of colors
mypal <- colorRampPalette( c("springgreen", "steelblue"))
ggplot(PROD, aes(Year, Value/1000000)) + geom_line(aes(color = Area), size = 1) +
geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
scale_fill_manual( values = mypal(21)) +
scale_color_manual( values = mypal(21)) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PROD$Year), max(PROD$Year), by = 10)))
## Warning: Removed 9 rows containing missing values (geom_path).
## Warning: Removed 20 rows containing missing values (geom_point).
#7.2. Area plot
ggplot(PROD, aes(Year, Value/1000000)) + geom_area(aes(fill = Area), color = "black", size = 1) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
scale_fill_manual(values = mypal(21)) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PROD$Year), max(PROD$Year), by = 10)))
## Warning: Removed 20 rows containing missing values (position_stack).
#Use of palettes provide by R is number of categories =< 13
ggplot(PRODAf, aes(Year, Value/1000000)) + geom_area(aes(fill = Area), color = "black", size = 1) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
scale_fill_brewer(palette = "Greens") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODAf$Year), max(PRODAf$Year), by = 10)))
#Try different palettes
#https://ggplot2.tidyverse.org/reference/scale_brewer.html
ggplot(PRODAf, aes(Year, Value/1000000)) + geom_area(aes(fill = Area), color = "black", size = 1) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
scale_fill_brewer(palette = "RdYlBu") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODAf$Year), max(PRODAf$Year), by = 10)))
#Colorblind friendly palettes
library(RColorBrewer)
display.brewer.all(colorblindFriendly = TRUE)
ggplot(PRODAf, aes(Year, Value/1000000)) + geom_area(aes(fill = Area), color = "black", size = 1) + theme_bw() +
xlab("") + ylab("Production (million tones)") +
scale_fill_brewer(palette = "BrBG") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.01, 0.99), legend.position = c(0.01, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank()) +
scale_x_continuous(breaks = round(seq(min(PRODAf$Year), max(PRODAf$Year), by = 10)))
#7.3. Scatter plot
PRODIMP2 <- subset(PRODIMP, select = -c(Domain.Code, Domain, Element.Code, Flag, Flag.Description))
library(tidyr)
PRODIMP_wide <- spread(PRODIMP2, Element, Value)
#http://www.cookbook-r.com/Manipulating_data/Converting_data_between_wide_and_long_format/
ggplot(PRODIMP_wide, aes(Production/1000000, Import/1000000)) + geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_manual( values = mypal(22)) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.title = element_blank())
## Warning: Removed 97 rows containing missing values (geom_point).
#Other example
PRODIMP_wide_Af <- subset(PRODIMP_wide, subset = Area == "Eastern Africa" | Area == "Middle Africa" | Area == "Northern Africa" | Area == "Southern Africa" | Area == "Western Africa")
ggplot(PRODIMP_wide_Af, aes(Production/1000000, Import/1000000)) + geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_brewer(palette = "BrBG") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 5 rows containing missing values (geom_point).
#Encircling ploints
library(ggalt)
## Registered S3 methods overwritten by 'ggalt':
## method from
## grid.draw.absoluteGrob ggplot2
## grobHeight.absoluteGrob ggplot2
## grobWidth.absoluteGrob ggplot2
## grobX.absoluteGrob ggplot2
## grobY.absoluteGrob ggplot2
ggplot(PRODIMP_wide_Af, aes(Production/1000000, Import/1000000)) + geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
geom_encircle(aes(fill = Area), alpha = 0.5) +
scale_fill_brewer(palette = "BrBG") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 5 rows containing missing values (geom_point).
## Warning: Removed 5 rows containing missing values (geom_encircle).
#Using elipses instead
ggplot(PRODIMP_wide_Af, aes(Production/1000000, Import/1000000)) +
stat_ellipse(geom = "polygon", alpha = 0.5, aes(fill = Area)) +
geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_brewer(palette = "Dark2") +
scale_y_continuous(breaks = round(seq(0, 20, by = 10),1)) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Warning: Removed 5 rows containing non-finite values (stat_ellipse).
## Warning: Removed 5 rows containing missing values (geom_point).
#Start the Y axis at zero
ggplot(PRODIMP_wide_Af, aes(Production/1000000, Import/1000000)) +
stat_ellipse(geom = "polygon", alpha = 0.5, aes(fill = Area)) +
geom_point(shape = 21, colour = "black", aes(fill = Area), stroke = 1.5, size = 5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_brewer(palette = "Dark2") +
scale_y_continuous(breaks = round(seq(0, 20, by = 10),1)) +
ylim(0, 17) +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_blank())
## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## Warning: Removed 5 rows containing non-finite values (stat_ellipse).
## Warning: Removed 5 rows containing missing values (geom_point).
#8. THREE CONTINUOUS VARIABLEs-------------------------------------------------------------------------------------------------------------------------------
MSouthAf2 <- subset(MSouthAf, select = -c(Domain.Code, Domain, Element.Code, Unit, Flag, Flag.Description))
library(tidyr)
MSouthAf_wide <- spread(MSouthAf2, Element, Value)
ggplot(MSouthAf_wide, aes(x = Production/1000000, y = Import/1000000, size = Yield)) + geom_point(shape = 21, colour = "black", aes(size = Yield), stroke = 1.5, fill = "springgreen") + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_brewer(palette = "BrBG") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.justification = c(0.99, 0.99), legend.position = c(0.99, 0.99),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_text(size=20, face="bold"))
## Warning: Removed 1 rows containing missing values (geom_point).
#9. THREE CONTINUOUS VARIABLEs AND ONE CATEGORICAL VARIABLE-------------------------------------------------------------------------------------------------------------------------------
MAf2 <- subset(MAf, select = -c(Domain.Code, Domain, Element.Code, Unit, Flag, Flag.Description))
library(tidyr)
MAf_wide <- spread(MAf2, Element, Value)
ggplot(MAf_wide, aes(x = Production/1000000, y = Import/1000000, size = Yield, fill = Area)) + geom_point(shape = 21, colour = "black", aes(size = Yield, fill = Area), stroke = 1.5) + theme_bw() +
xlab("Production (million tones)") + ylab("Import (million tones)") +
scale_fill_brewer(palette = "BrBG") +
theme(axis.title = element_text(size=24, face="bold"),
axis.text = element_text(size=20, face="bold"),
legend.text = element_text(size=16, face="bold"), legend.key.size = unit(2, 'lines'), legend.title = element_text(size=20, face="bold"))
## Warning: Removed 5 rows containing missing values (geom_point).
#.10 PIE CHARTS AND ALTERNATIVES--------------------------------------------------------------------------------------------------------------------------------------------------------------
#10.1. Pie chart
#Create a bar plot
ggplot(PRODAf17, aes(x="", y=Value, fill=Area)) + geom_bar(width = 1, stat = "identity", color = "black")
#Wrap it around
ggplot(PRODAf17, aes(x="", y=Value, fill=Area)) + geom_bar(width = 1, stat = "identity", color = "black")+
coord_polar("y", start=0)
#Personalize colors
ggplot(PRODAf17, aes(x="", y=Value, fill=Area)) + geom_bar(width = 1, stat = "identity", color = "black")+
coord_polar("y", start=0) + theme_minimal() +
scale_fill_brewer(palette = "Greens") +
theme(axis.title.x = element_blank(), axis.title.y = element_blank(),
panel.border = element_blank(), panel.grid=element_blank(),
axis.ticks = element_blank(),axis.text = element_blank(),
legend.text = element_text(size = 16), legend.key.size = unit(2, 'lines'),
legend.title = element_blank())
#Legend at the bottom and in 2 row
ggplot(PRODAf17, aes(x="", y=Value, fill=Area)) + geom_bar(width = 1, stat = "identity", color = "black")+
coord_polar("y", start=0) + theme_minimal() +
scale_fill_brewer(palette = "Greens") +
theme(axis.title.x = element_blank(), axis.title.y = element_blank(),
panel.border = element_blank(), panel.grid=element_blank(),
axis.ticks = element_blank(),axis.text = element_blank(),
legend.text = element_text(size = 16), legend.key.size = unit(2, 'lines'),
legend.title = element_blank(), legend.position="bottom") +
guides(fill = guide_legend(nrow = 2, byrow=TRUE))
#Other example
ggplot(PROD17, aes(x="", y=Value, fill=Area)) + geom_bar(width = 1, stat = "identity", color = "black")+
coord_polar("y", start=0) + theme_minimal() +
scale_fill_manual( values = mypal(22)) +
theme(axis.title.x = element_blank(), axis.title.y = element_blank(),
panel.border = element_blank(), panel.grid=element_blank(),
axis.ticks = element_blank(),axis.text = element_blank(),
legend.text = element_text(size = 10), legend.key.size = unit(1, 'lines'),
legend.title = element_blank(), legend.position="bottom") +
guides(fill = guide_legend(nrow = 4, byrow=TRUE))
#10.2. Tree map
library(treemap)
treemap(PROD17,
# data
index="Area",
vSize="Value",
type="index",
# Main
title="",
palette =mypal(22),
# Borders:
border.col=c("black"),
border.lwds=1,
# Labels
fontsize.labels=0.5,
fontcolor.labels="black",
fontface.labels=1,
bg.labels=c("transparent"),
align.labels=c("left", "top"),
overlap.labels=0.5,
inflate.labels=T # If true, labels are bigger when rectangle is bigger.
)
#10.3. Lollypop diagram
ggplot(PROD17, aes(x=Area, y=Value/1000000)) +
geom_segment( aes(x=Area, xend=Area, y=0, yend=Value/1000000), color="springgreen3", size=1) +
geom_point( color="springgreen4", size=10, alpha=0.5)
#With a few improvements
PROD17 %>%
arrange(Value) %>%
mutate(Area=factor(Area,Area)) %>%
ggplot( aes(x=Area, y=Value/1000000)) +
geom_segment( aes(x=Area, xend=Area, y=0, yend=Value/1000000), color="springgreen3", size=1) +
geom_point( color="springgreen4", size=10, alpha=0.5) +
theme_light() +
coord_flip() +
theme(
panel.grid.major.y = element_blank(),
panel.border = element_blank(),
axis.ticks.y = element_blank(),
axis.text.x = element_text(size=16),
axis.text.y = element_text(size=16),
axis.title.x = element_text(size=20),
axis.title.y = element_text(size=0)
) +
xlab("") +
ylab("\nProduction in 2017 (million tones)")
