w3-2

# Loading libraries
library(dplyr)
library(dslabs)
library(ggplot2)

data(heights)

tall_males <- heights$sex == "Male" & heights$height > 70

#summarise allows us to get summaty data - summaty statistics like mean, sd
s <- heights %>% filter(sex == "Female") %>% summarise(average = mean(height), standard_deviation = sd(height))

# Output
s$average

[1] 64.93942

s$standard_deviation

[1] 3.760656

# group_by(sex) tells R to treat the dataset as two separate groups — M and F
height_grp <- heights %>% group_by(sex) 

height_grp %>% summarize (avg = mean(height), stdev = sd(height))

# A tibble: 2 × 3
  sex      avg stdev
  <fct>  <dbl> <dbl>
1 Female  64.9  3.76
2 Male    69.3  3.61

# Arrange Function

#arrange() allows us to order entire tables.
data("murders")
murders %>% arrange(population) %>% head() #order by population

                 state abb        region population total
1              Wyoming  WY          West     563626     5
2 District of Columbia  DC         South     601723    99
3              Vermont  VT     Northeast     625741     2
4         North Dakota  ND North Central     672591     4
5               Alaska  AK          West     710231    19
6         South Dakota  SD North Central     814180     8

#desc() allows us to sort in descending order

data("murders")
murders %>% arrange(desc(total)) %>% head() #order by descending rate

         state abb        region population total
1   California  CA          West   37253956  1257
2        Texas  TX         South   25145561   805
3      Florida  FL         South   19687653   669
4     New York  NY     Northeast   19378102   517
5 Pennsylvania  PA     Northeast   12702379   457
6     Michigan  MI North Central    9883640   413

table(heights$sex)

Female   Male 
   238    812 

# Plotting

heights %>% ggplot(aes(sex, fill=sex)) + geom_bar() 

heights %>% count(sex) %>% mutate(proportion = n/sum(n)) #gives us the proportion

     sex   n proportion
1 Female 238  0.2266667
2   Male 812  0.7733333

#Add your own color choices for the different bars

#data(murders)

murders %>% ggplot(aes(region, fill= region)) + geom_bar() + scale_fill_manual(values=c("#FF0000", "#FFFFFF", "#D3D3D3", "#A9A9A9")) #red, white, lightgray, darkgray

# Boxplot

heights %>% ggplot(aes(sex,height,fill=sex)) + geom_boxplot() +scale_fill_manual(values=c("white","red")) 

murders %>% ggplot(aes(region,total, fill= region)) + geom_boxplot() + scale_fill_manual(values=c("red", "white", "lightgray", "darkgray"))