Module 6: Apply 5

Import data

# excel file
myData <- read_excel("../00_data/myData.xlsx")
myData

## # A tibble: 1,462 × 4
##       id  year shadow details                                                   
##    <dbl> <dbl> <chr>  <chr>                                                     
##  1     1  1886 NA     Groundhog Day first recognized in Punxsutawney by Weather…
##  2     1  1887 TRUE   First Official trek to Gobbler’s Knob. Saw Shadow.        
##  3     1  1888 TRUE   Saw Shadow.                                               
##  4     1  1889 NA     No Record.                                                
##  5     1  1890 FALSE  No Shadow.                                                
##  6     1  1891 NA     No Record.                                                
##  7     1  1892 NA     No Record.                                                
##  8     1  1893 NA     No Record.                                                
##  9     1  1894 NA     No Record.                                                
## 10     1  1895 NA     No Record.                                                
## # ℹ 1,452 more rows

Apply the following dplyr verbs to your data

Filter rows

filter(myData, id == 1)

## # A tibble: 138 × 4
##       id  year shadow details                                                   
##    <dbl> <dbl> <chr>  <chr>                                                     
##  1     1  1886 NA     Groundhog Day first recognized in Punxsutawney by Weather…
##  2     1  1887 TRUE   First Official trek to Gobbler’s Knob. Saw Shadow.        
##  3     1  1888 TRUE   Saw Shadow.                                               
##  4     1  1889 NA     No Record.                                                
##  5     1  1890 FALSE  No Shadow.                                                
##  6     1  1891 NA     No Record.                                                
##  7     1  1892 NA     No Record.                                                
##  8     1  1893 NA     No Record.                                                
##  9     1  1894 NA     No Record.                                                
## 10     1  1895 NA     No Record.                                                
## # ℹ 128 more rows

Arrange rows

arrange(myData, desc(year))

## # A tibble: 1,462 × 4
##       id  year shadow details                                                   
##    <dbl> <dbl> <chr>  <chr>                                                     
##  1     1  2023 TRUE   Shadow at 7:24 AM; 13º with clear skies. PA Governor Josh…
##  2     2  2023 FALSE  <NA>                                                      
##  3     3  2023 FALSE  No Shadow, Early Spring!                                  
##  4     4  2023 TRUE   <NA>                                                      
##  5     5  2023 FALSE  <NA>                                                      
##  6     6  2023 TRUE   <NA>                                                      
##  7     7  2023 FALSE  <NA>                                                      
##  8     8  2023 FALSE  <NA>                                                      
##  9     9  2023 TRUE   <NA>                                                      
## 10    10  2023 FALSE  <NA>                                                      
## # ℹ 1,452 more rows

Select columns

select(myData, year:shadow)

## # A tibble: 1,462 × 2
##     year shadow
##    <dbl> <chr> 
##  1  1886 NA    
##  2  1887 TRUE  
##  3  1888 TRUE  
##  4  1889 NA    
##  5  1890 FALSE 
##  6  1891 NA    
##  7  1892 NA    
##  8  1893 NA    
##  9  1894 NA    
## 10  1895 NA    
## # ℹ 1,452 more rows

Add columns

Summarize by groups