Practice2

• Rename the legend in barplot using ggplot2

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 3.3.3

## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr

## Warning: package 'ggplot2' was built under R version 3.3.3

## Warning: package 'tibble' was built under R version 3.3.3

## Warning: package 'tidyr' was built under R version 3.3.3

## Warning: package 'readr' was built under R version 3.3.3

## Warning: package 'purrr' was built under R version 3.3.3

## Warning: package 'dplyr' was built under R version 3.3.3

## Conflicts with tidy packages ----------------------------------------------

## filter(): dplyr, stats
## lag():    dplyr, stats

p <- ggplot(diamonds,aes(x=cut,fill=cut)) +geom_bar()

#Rename legend, but this only works with bar (fill for bar)

p + scale_fill_discrete(name="Cut Type") + theme_bw() + ggtitle("Barplot")

Boxplot

p1<-ggplot(data=mpg,aes(x=manufacturer,y=hwy,fill=class)) 

# Add geom_boxplot and rename legend

p1<-p1 + geom_boxplot() + scale_fill_discrete(name="Class") 

# Change angle of xlab 

p1<-p1 + theme(axis.text.x = element_text(angle=30)) 

# Change to horizontal 

p1<-p1 + coord_flip() +theme_bw() 

# One may want to add jitter to see points

p1<-p1 + geom_jitter(aes(color=class),alpha=0.5,show.legend = F)

# legend.position can be changed

p1 + theme(legend.position = "bottom")

• Scatter plot

# Change numeric variable to factor in color() argument

p2<-ggplot(data=mtcars,aes(disp,y=hp,color=factor(gear,labels=c("Gear1","Gear2","Gear3"))))

p2<-p2 + geom_point() 

p2

# rename legend

p2 + labs(colour="Gear")  # we can rename shape="Something" if shape applied

# Add title 

p2 <-p2+ xlab("Disp") + ylab("HP") 

# Change text

p2 +theme(axis.text.x = element_text(size=2), plot.title = element_text(size=15,face="bold"))  + labs(title="Scatter plot\n")

• Section 2: Data summarisation with ggplot2

data_summary<-iris %>% dplyr::group_by(Species) %>% summarise(Min=min(Sepal.Length),Max=max(Sepal.Length),Mean=mean(Sepal.Length),SD=sd(Sepal.Length),n=n(),Missing_value=sum(is.na(Sepal.Length)), Q1=quantile(Sepal.Length,probs=0.25),Q3=quantile(Sepal.Length,probs=0.75),Median=median(Sepal.Length))


data_summary

## # A tibble: 3 × 10
##      Species   Min   Max  Mean        SD     n Missing_value    Q1    Q3
##       <fctr> <dbl> <dbl> <dbl>     <dbl> <int>         <int> <dbl> <dbl>
## 1     setosa   4.3   5.8 5.006 0.3524897    50             0 4.800   5.2
## 2 versicolor   4.9   7.0 5.936 0.5161711    50             0 5.600   6.3
## 3  virginica   4.9   7.9 6.588 0.6358796    50             0 6.225   6.9
## # ... with 1 more variables: Median <dbl>

Okay done!