Data Science - 2nd Session

> library(dplyr)
> library(ggplot2)
> library(statsr)
> data(nycflights)

//ggplot
> ggplot(data = nycflights, aes(x= dep_delay)) +geom_histogram()

//mean
> nycflights %>% summarise(mean_dd = mean(dep_delay))

//median
> nycflights %>% summarise(mean_dd = median(dep_delay))

//boxplot
> ggplot(data = nycflights, aes(x="",y= dep_delay)) +geom_boxplot()

//comparision between months
> ggplot(data = nycflights, aes(x=factor(month),y= dep_delay)) +geom_boxplot()

//mean of each month [piping]
> nycflights %>% group_by(month) %>% summarise(median_dd = mean(dep_delay)) %>% arrange(desc(median_dd))