Module 6: Apply 5

Import data

data <- read_excel("../00_data/MyData.xlsx")
data

## # A tibble: 252 × 3
##        W Capacity Team     
##    <dbl>    <dbl> <chr>    
##  1     5    0.957 Cardinals
##  2     5    0.948 Cardinals
##  3     5    0.954 Cardinals
##  4     5    0.949 Cardinals
##  5     5    0.962 Cardinals
##  6     5    0.961 Cardinals
##  7     5    1.01  Cardinals
##  8     5    0.999 Cardinals
##  9     7    1.02  Falcons  
## 10     7    1.02  Falcons  
## # ℹ 242 more rows

Apply the following dplyr verbs to your data

Filter rows

filter(data, Capacity != 1)

## # A tibble: 239 × 3
##        W Capacity Team     
##    <dbl>    <dbl> <chr>    
##  1     5    0.957 Cardinals
##  2     5    0.948 Cardinals
##  3     5    0.954 Cardinals
##  4     5    0.949 Cardinals
##  5     5    0.962 Cardinals
##  6     5    0.961 Cardinals
##  7     5    1.01  Cardinals
##  8     5    0.999 Cardinals
##  9     7    1.02  Falcons  
## 10     7    1.02  Falcons  
## # ℹ 229 more rows

Arrange rows

arrange(data, desc(Capacity))

## # A tibble: 252 × 3
##        W Capacity Team    
##    <dbl>    <dbl> <chr>   
##  1     3     1.23 Redskins
##  2     3     1.21 Redskins
##  3     8     1.16 Cowboys 
##  4     8     1.14 Cowboys 
##  5     8     1.14 Cowboys 
##  6     8     1.13 Cowboys 
##  7     8     1.13 Cowboys 
##  8     8     1.13 Cowboys 
##  9     8     1.13 Cowboys 
## 10     8     1.13 Cowboys 
## # ℹ 242 more rows

Select columns

select(data, W, Capacity)

## # A tibble: 252 × 2
##        W Capacity
##    <dbl>    <dbl>
##  1     5    0.957
##  2     5    0.948
##  3     5    0.954
##  4     5    0.949
##  5     5    0.962
##  6     5    0.961
##  7     5    1.01 
##  8     5    0.999
##  9     7    1.02 
## 10     7    1.02 
## # ℹ 242 more rows

Add columns

data2 <- select(data,
                W,
                Capacity
)
mutate(data2, 
       WinRatio = W / 16
)

## # A tibble: 252 × 3
##        W Capacity WinRatio
##    <dbl>    <dbl>    <dbl>
##  1     5    0.957    0.312
##  2     5    0.948    0.312
##  3     5    0.954    0.312
##  4     5    0.949    0.312
##  5     5    0.962    0.312
##  6     5    0.961    0.312
##  7     5    1.01     0.312
##  8     5    0.999    0.312
##  9     7    1.02     0.438
## 10     7    1.02     0.438
## # ℹ 242 more rows

Summarize by groups

by_win <- group_by(data, W)
by_win <- summarise(by_win,
          Cap = mean(Capacity),
       
) 
ggplot(data = by_win, mapping = aes(x = W, y = Cap)) +
  geom_point() +
    geom_smooth(se = FALSE)