3_filter_data.yml

target_default: 3_filter_data

packages:
  - dplyr
  
include:
  - 2_process_data.yml
  
sources:
  - 3_filter_data/src/filter_data.R
  
targets:
  3_filter_data:
    depends:
      - field_blanks
      - duplicates
      - samples
      - pct_rec_surrogates
      - pct_rec_surrogates_5507
      - pct_rec_surrogates_5433
      - sediment_char
 
  field_blanks:
    command: filter_blanks(processed_sample)
    # this finds all sites with blanks, and returns blanks plus any samples 
    # or duplicates from the same site for comparison purposes
    
  duplicates:
    command: filter_duplicates(processed_sample)
    # this finds all sites where replicate samples were taken, and returns
    # all replicates plus samples from the same site for comparison purposes
    
  samples:
    command: filter_samples(processed_sample)
    # excludes blanks and duplicates to just return samples 
    
  pct_rec_surrogates:
    command: filter_surrogates(processed_sample)
    # % recoverives from Battelle were calculated on surrogates for every sample that was run (n = 71)
    # this filter provides the percent recoveries from the 4 surrogates in every sample
    
  pct_rec_surrogates_5507:
    command: filter_surrogates_5507(processed_5507)
    # % recoveries from schedule 5507 that was run in MKE for Austin's study.

    
  pct_rec_surrogates_5433:
    command: filter_surrogates_5433(processed_5433)
    # % recoveries from schedule 5433 that was run on split samples from GLRI sites.
    # this is all surrogates - not just PAH surrogates.
    
  sediment_char:
    command: filter_characteristics(samples)