7b_temp_merge.yml

target_default: 7b_temp_merge

packages:
  - scipiper
  - dplyr
  - feather
  - googledrive

sources:
  - 7b_temp_merge/src/merge_all_temp_dat.R
  - 7b_temp_merge/src/munge_source_ids.R

targets:

  7b_temp_merge:
    depends:
     - 7b_temp_merge/out/merged_temp_data_daily.feather.ind
     - 7b_temp_merge/out/temp_data_with_sources.feather.ind
     - 7b_temp_merge/out/source_metadata_for_release.csv.ind

  # -- get WQP, coop data and merge -- #
  # -- removes (coarsely defined) duplicates -- #
  # -- removes egregious outliers in Jan/Feb (>10 deg C) and July/Aug (surface, <10 deg C)
  # -- returns all times -- ##

  7b_temp_merge/out/merged_temp_data_alltimes.feather.ind:
    command: merge_temp_data(
      outind = target_name,
      wqp_ind = '7a_wqp_munge/out/temp_wqp_munged_linked.feather.ind',
      coop_ind = '7a_temp_coop_munge/out/all_coop_dat_linked.feather.ind')


  # -- resolve multiple unique obs per lake/date/depth -- ##
  7b_temp_merge/out/merged_temp_data_daily.feather.ind:
    command: reduce_temp_data(
      outind = target_name,
      inind = '7b_temp_merge/out/merged_temp_data_alltimes.feather.ind')

  # -- clean up data sources for data release -- #

  # create a version for daily temperature observations with new source
  # IDs for data release


  # download and indicate source metadata
  source_metadata_loc:
    command: as_id(I('1gX9ejUr18_w4mYTCORj0_ZuXdyqUhcZvpsV5G0Yu26U'))
    depends:
      - 6_temp_coop_fetch/log/6_temp_coop_fetch_tasks.ind

  7b_temp_merge/in/source_metadata.csv.ind:
    command: gd_download_and_indicate(
      source_metadata_loc,
      out_ind = target_name)

  # merge data with new source_ids

  7b_temp_merge/out/temp_data_with_sources.feather.ind:
    command: add_source_ids(
      datin_ind = '7b_temp_merge/out/merged_temp_data_daily.feather.ind',
      metadata_ind = '7b_temp_merge/in/source_metadata.csv.ind',
      datout_ind = target_name)

  # create a metadata file for data release
  7b_temp_merge/out/source_metadata_for_release.csv.ind:
    command: summarize_sources(
      datin_ind = '7b_temp_merge/out/temp_data_with_sources.feather.ind',
      metadata_ind = '7b_temp_merge/in/source_metadata.csv.ind',
      datout_ind = target_name)

  ## reservoir data - reduce to dailies
  ## leaving this seperate since 1) there are some oddities with depth data from reservoirs
  ## and 2) in eastern time zone, and above selects noon of central time
  ## not a huge but this lets us select noon local time

  7b_temp_merge/out/drb_daily_reservoir_temps.rds.ind:
    command: reduce_reservoir_data(target_name,
      drb_ind = '7a_nwis_munge/out/drb_reservoirs_temp_munged.rds.ind',
      nyc_dep_ind = '7a_nwis_munge/out/NYC_DEP_reservoir_temperature_data.rds.ind')