# Sort data with group_by
depthseries_data_grouped <- group_by(depthseries_data_select, core_id)
head(depthseries_data_grouped)

## # A tibble: 6 x 4
##   core_id depth_min depth_max organic_matter_density
##   <chr>       <int>     <int>                  <dbl>
## 1 BBRC_1          0         2                 0.0784
## 2 BBRC_1          4         6                 0.0943
## 3 BBRC_1          8        10                 0.108 
## 4 BBRC_1         12        14                 0.096 
## 5 BBRC_1         16        18                 0.0972
## 6 BBRC_1         20        22                 0.0944

tail(depthseries_data_grouped)

## # A tibble: 6 x 4
##   core_id depth_min depth_max organic_matter_density
##   <chr>       <int>     <int>                  <dbl>
## 1 GL              0         2                 0.0910
## 2 GL              8        10                 0.0174
## 3 HH              0         2                 0.0447
## 4 HH              8        10                 0.0344
## 5 HL              0         2                 0.0811
## 6 HL              8        10                 0.0177

It didn't seem like it did anything, did it? The rows are now arranged by core_id (BBRC_1,BBRC_2, NCBD_1, etc.), much in the same manner that they originally were. That's OK. the group_by operation isn't really useful on it's own, but can be very powerful when paired with other operations. Here's one: if you want to condense your data to one row according to one attribute, you can do so with the summarize() operation.

# What is the average organic matter density of all observations
depthseries_data_avg_organic_matter_density <- summarize(depthseries_data_select, # Define dataset
  organic_matter_density_avg = mean(organic_matter_density, # New column that has one entry, 
                                                            # the mean organic matter density
  na.rm = TRUE)) # Remove NA values before summarizing
depthseries_data_avg_organic_matter_density

## # A tibble: 1 x 1
##   organic_matter_density_avg
##                        <dbl>
## 1                     0.0679

This is the average organic matter density for all of our data. Now what if we wanted to calculate the average organic matter density for each core? Although group_by() and summarize() aren't that interesting by themselves, they are really effective when used in sequence:

# What is the average organic matter density of each core, for all cores
depthseries_data_avg_OMD_by_core <- depthseries_data_select %>%
  group_by(core_id) %>%
  summarize(organic_matter_density_avg = mean(organic_matter_density, na.rm = TRUE))
depthseries_data_avg_OMD_by_core

## # A tibble: 1,534 x 2
##    core_id                     organic_matter_density_avg
##    <chr>                                            <dbl>
##  1 AH                                              0.109 
##  2 AL                                              0.0930
##  3 Alley_Pond                                      0.0734
##  4 Altamaha_River_Site_7_Levee                   NaN     
##  5 Altamaha_River_Site_7_Plain                   NaN     
##  6 Altamaha_River_Site_8_Levee                   NaN     
##  7 Altamaha_River_Site_8_Plain                   NaN     
##  8 Altamaha_River_Site_9_Levee                   NaN     
##  9 Altamaha_River_Site_9_Plain                   NaN     
## 10 AND                                             0.0690
## # ... with 1,524 more rows

Using these two operations with the %>% notation, we were able to find the mean organic matter density for each of the cores in our dataset.

Last Page              Return to Top              Next Page