Tidyverse Create Assignment Vignette

glimpse

Q: What are the variables and data types of the variables in my dataset?
A: Use dplyr’s glimpse function.

glimpse(heart_failure)

## Rows: 918
## Columns: 12
## $ Age            <dbl> 40, 49, 37, 48, 54, 39, 45, 54, 37, 48, 37, 58, 39, 49,~
## $ Sex            <chr> "M", "F", "M", "F", "M", "M", "F", "M", "M", "F", "F", ~
## $ ChestPainType  <chr> "ATA", "NAP", "ATA", "ASY", "NAP", "NAP", "ATA", "ATA",~
## $ RestingBP      <dbl> 140, 160, 130, 138, 150, 120, 130, 110, 140, 120, 130, ~
## $ Cholesterol    <dbl> 289, 180, 283, 214, 195, 339, 237, 208, 207, 284, 211, ~
## $ FastingBS      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0~
## $ RestingECG     <chr> "Normal", "Normal", "ST", "Normal", "Normal", "Normal",~
## $ MaxHR          <dbl> 172, 156, 98, 108, 122, 170, 170, 142, 130, 120, 142, 9~
## $ ExerciseAngina <chr> "N", "N", "N", "Y", "N", "N", "N", "N", "Y", "N", "N", ~
## $ Oldpeak        <dbl> 0.0, 1.0, 0.0, 1.5, 0.0, 0.0, 0.0, 0.0, 1.5, 0.0, 0.0, ~
## $ ST_Slope       <chr> "Up", "Flat", "Up", "Flat", "Up", "Up", "Up", "Up", "Fl~
## $ HeartDisease   <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1~

select

Q: I do not need all the columns, how do I select the columns that I only need for my analysis?
A: Use dplyr’s select function.

# select all columns except Oldpeak and ST_Slope
heart_failure_sub <- heart_failure %>% select(-c(Oldpeak, ST_Slope))
# select columns Age, Sex, RestingBP, and HeartDisease
heart_failure_sub1 <- heart_failure %>% select(Age, Sex, RestingBP, HeartDisease)
# select from columns Age to ExerciseAngina
heart_failure_sub2 <- heart_failure %>% select(Age:ExerciseAngina)

View the head of heart_failure_sub

head(heart_failure_sub)

## # A tibble: 6 x 10
##     Age Sex   ChestPainType RestingBP Cholesterol FastingBS RestingECG MaxHR
##   <dbl> <chr> <chr>             <dbl>       <dbl>     <dbl> <chr>      <dbl>
## 1    40 M     ATA                 140         289         0 Normal       172
## 2    49 F     NAP                 160         180         0 Normal       156
## 3    37 M     ATA                 130         283         0 ST            98
## 4    48 F     ASY                 138         214         0 Normal       108
## 5    54 M     NAP                 150         195         0 Normal       122
## 6    39 M     NAP                 120         339         0 Normal       170
## # ... with 2 more variables: ExerciseAngina <chr>, HeartDisease <dbl>

View the head of heart_failure_sub1

head(heart_failure_sub1)

## # A tibble: 6 x 4
##     Age Sex   RestingBP HeartDisease
##   <dbl> <chr>     <dbl>        <dbl>
## 1    40 M           140            0
## 2    49 F           160            1
## 3    37 M           130            0
## 4    48 F           138            1
## 5    54 M           150            0
## 6    39 M           120            0

View the head of heart_failure_sub2

head(heart_failure_sub2)

## # A tibble: 6 x 9
##     Age Sex   ChestPainType RestingBP Cholesterol FastingBS RestingECG MaxHR
##   <dbl> <chr> <chr>             <dbl>       <dbl>     <dbl> <chr>      <dbl>
## 1    40 M     ATA                 140         289         0 Normal       172
## 2    49 F     NAP                 160         180         0 Normal       156
## 3    37 M     ATA                 130         283         0 ST            98
## 4    48 F     ASY                 138         214         0 Normal       108
## 5    54 M     NAP                 150         195         0 Normal       122
## 6    39 M     NAP                 120         339         0 Normal       170
## # ... with 1 more variable: ExerciseAngina <chr>

filter

Q: I want only observations where Sex is M
A: Use dplyr’s filter function.

heart_failure_male <- heart_failure %>% filter(Sex == "M")
head(heart_failure_male)

## # A tibble: 6 x 12
##     Age Sex   ChestPainType RestingBP Cholesterol FastingBS RestingECG MaxHR
##   <dbl> <chr> <chr>             <dbl>       <dbl>     <dbl> <chr>      <dbl>
## 1    40 M     ATA                 140         289         0 Normal       172
## 2    37 M     ATA                 130         283         0 ST            98
## 3    54 M     NAP                 150         195         0 Normal       122
## 4    39 M     NAP                 120         339         0 Normal       170
## 5    54 M     ATA                 110         208         0 Normal       142
## 6    37 M     ASY                 140         207         0 Normal       130
## # ... with 4 more variables: ExerciseAngina <chr>, Oldpeak <dbl>,
## #   ST_Slope <chr>, HeartDisease <dbl>

Q: I want only observations where RestingECG is Normal
A: Use dplyr’s filter function.

heart_failure_disease <- heart_failure %>% filter(RestingECG == "Normal")
head(heart_failure_disease)

## # A tibble: 6 x 12
##     Age Sex   ChestPainType RestingBP Cholesterol FastingBS RestingECG MaxHR
##   <dbl> <chr> <chr>             <dbl>       <dbl>     <dbl> <chr>      <dbl>
## 1    40 M     ATA                 140         289         0 Normal       172
## 2    49 F     NAP                 160         180         0 Normal       156
## 3    48 F     ASY                 138         214         0 Normal       108
## 4    54 M     NAP                 150         195         0 Normal       122
## 5    39 M     NAP                 120         339         0 Normal       170
## 6    45 F     ATA                 130         237         0 Normal       170
## # ... with 4 more variables: ExerciseAngina <chr>, Oldpeak <dbl>,
## #   ST_Slope <chr>, HeartDisease <dbl>

Scatterplot

Q: I want to plot a scatter plot of RestingBP vs. Cholesterol
A: Use the ggplot function and the geom_point layer

ggplot(data = heart_failure, aes(x = Cholesterol, y = RestingBP)) + geom_point()

Add title, transparency, and theme

ggplot(data = heart_failure, aes(x = Cholesterol, y = RestingBP)) + geom_point(alpha = 0.5) + 
  labs(title = "RestingBP vs. Cholesterol") + theme_bw()

Barplot

Q: I want to plot a barchart of the count of Male and Female in the dataset
A: Use the ggplot function and the geom_bar layer

ggplot(data = heart_failure, aes(x = Gender)) + geom_bar(fill = "brown") + 
  labs(title = "Bar chart for count of Sex") + theme_bw()

Q: How do I flip co-ordinates?
A: Add the coord_flip layer

ggplot(data = heart_failure, aes(x = Gender)) + geom_bar(fill = "brown") + 
  labs(title = "Bar chart for count of Sex") + theme_bw() + coord_flip()