Week 3

Week 3

library(dslabs)
library(tidyverse)
library(ggplot2)
library(dplyr)

data(heights)
str(heights)

'data.frame':   1050 obs. of  2 variables:
 $ sex   : Factor w/ 2 levels "Female","Male": 2 2 2 2 2 1 1 1 1 2 ...
 $ height: num  75 70 68 74 61 65 66 62 66 67 ...

head(heights)

     sex height
1   Male     75
2   Male     70
3   Male     68
4   Male     74
5   Male     61
6 Female     65

Finding people who are male AND taller than 70 inches

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

   Mode   FALSE    TRUE 
logical     744     306 

Taking the average height and standard deviation of female.

s <- heights |>
  filter(sex=="Female") |>
  summarize(Average = mean(height), Standard_deviation = sd(height))
s

   Average Standard_deviation
1 64.93942           3.760656

Taking out mean and sd ofo both sex at once by grouping

height_grp <- heights |>
  group_by(sex)
height_grp |>
  summarise(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

height_grp

# A tibble: 1,050 × 2
# Groups:   sex [2]
   sex    height
   <fct>   <dbl>
 1 Male       75
 2 Male       70
 3 Male       68
 4 Male       74
 5 Male       61
 6 Female     65
 7 Female     66
 8 Female     62
 9 Female     66
10 Male       67
# ℹ 1,040 more rows

Arranging the data according to the population, lowest the first.

murders |> 
  arrange(population) |>
  head()

                 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

Arranging the data according to the population, Larger to small

murders |>
  arrange(desc(population)) |>
  head()

         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     Illinois  IL North Central   12830632   364
6 Pennsylvania  PA     Northeast   12702379   457

# Table and summary 
table(heights$sex)

Female   Male 
   238    812 

summary(heights$sex)

Female   Male 
   238    812 

table(murders$region)

    Northeast         South North Central          West 
            9            17            12            13 

summary(murders$region)

    Northeast         South North Central          West 
            9            17            12            13 

Creating a ggplot of male and female “sex”.

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

Counting and mutate and finding proportion.

heights |>
  count(sex) |>
  mutate(proportion = n/sum(n))

     sex   n proportion
1 Female 238  0.2266667
2   Male 812  0.7733333

Adding color to the boxplot by own choice.

ggplot(murders) +
  aes(region, fill = region) +
  geom_bar() +
  scale_fill_manual(values = c("blue", "white", "green", "red"))

Creating a boxplot and manually adding own colors.

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