DataCamp Tidyverse Training
Ming Si
July 03 2018
library(tidyverse)
# library(corrplot)
# library(DataExplorer)
#library(lubridate)
#library(pander)
#library(data.table)
#library(grid)
#library(gridExtra)
#library(mice)
#library(caret)1 Chapter 1
Data is contained in gapminder package
1.1 Filter Verb
1.2 Arrange Verb
1.3 Mutate
replace existing variable
add new variables
2 Chapter 2 Visualizing with ggplot
## Log scales
## Additional aesthetics
ggplot(gapminder_2007,aes(gdpPercap,lifeExp,
color = continent, size = pop))+
geom_point()+scale_x_log10()
3 Chaper 3 Summarise Verb
3.1 Group_by verb
gapminder %>% group_by(year) %>%
summarise(meanLifeExp = mean(lifeExp),totalPop = sum(as.numeric(pop)))gapminder %>% filter(year == 2007) %>%
group_by(continent) %>%
summarise(meanLifeExp = mean(lifeExp),totalPop = sum(as.numeric(pop)))gapminder %>%
group_by(year, continent) %>%
summarise(meanLifeExp = mean(lifeExp),totalPop = sum(as.numeric(pop)))3.2 Visualizing summerized data
by_year <- gapminder %>%
group_by(year) %>%
summarize(totalPop = sum(as.numeric(pop)),
meanLifeExp = mean(lifeExp))
by_year
make Y axis starts from 0
by_year_continent <- gapminder %>%
group_by(year, continent) %>%
summarize(totalPop = sum(as.numeric(pop)),
meanLifeExp = mean(lifeExp))
by_year_continent
4 Chapter 4 Line Plots and Others
by_continent <- gapminder %>%
filter(year == 2007) %>%
group_by(continent) %>%
summarize(meanLifeExp = mean(lifeExp))
by_continent
gapminder_1952 <- gapminder %>%
filter(year == 1952)
ggplot(gapminder_1952,aes(pop))+geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
gapminder_1952 <- gapminder %>%filter(year == 1952)
ggplot(gapminder_1952,aes(continent,gdpPercap))+geom_boxplot()+scale_y_log10()
ggplot(gapminder_1952, aes(x = continent, y = gdpPercap)) +
geom_boxplot() +
scale_y_log10()+
labs(title = "Comparing GDP per capita across continents")