feat(qa): RG-K Fall 18 QA configuration and notes

bin/qtl-xtrain

@@ -7,67 +7,86 @@ unless ARGV.length == 2
   Verify that a directory of a train's skim files has the same list of
   run numbers as a directory of DST-file run directories.
 
-  USAGE: qtl xtrain [TRAIN_DIR] [DST_DIR]
+  USAGE: qtl xtrain [TRAIN_DIR(S)] [DST_DIR]
 
-  Both directories must be on /mss
+  Both directories must be on /mss or /cache; the /mss dir is checked
+  (even if the argument is /cache)
+
+  Use globs to specify multiple TRAIN_DIRS (surround in quotes)
   """
   exit 2
 end
-train_dir, dst_dir = ARGV
 
-# function to get a set of run numbers from one of the argument dirs
-def get_runnums(path, type)
-  runnums = Set.new
-  raise "#{type} dir `#{path}` is not on /mss" unless path.match? /^\/mss\//
-  raise "#{type} dir `#{path}` does not exist" unless Dir.exist? path
+train_dirs, dst_dir = ARGV
+num_failures = 0
 
-  # get list of files/directories within
-  files = []
-  case type
-  when :train
-    files = Dir.glob File.join(path, '*.hipo')
-  when :DST
-    files = Dir.glob File.join(path, '*/')
-  else
-    raise 'bad type'
-  end
-  raise "no #{type} files found in #{type} dir `#{path}`" if files.empty?
+# loop over train directories glob
+Dir.glob(train_dirs).select{|d|File.directory? d}.each do |train_dir|
+
+  # function to get a set of run numbers from one of the argument dirs
+  def get_runnums(path, type)
+    runnums = Set.new
+    path = path.sub /^\/cache\//, '/mss/' if path.match? /^\/cache\//
+    raise "#{type} dir `#{path}` does not exist" unless Dir.exist? path
 
-  # extract their run numbers
-  files.each do |file|
-    nums = File.basename(file).scan(/\d+/).map &:to_i
-    raise "failed to get run number from #{type} object `#{file}`" unless nums.length == 1
-    runnums << nums[0]
+    # get list of files/directories within
+    files = []
+    case type
+    when :train
+      files = Dir.glob File.join(path, '*.hipo')
+    when :DST
+      files = Dir.glob File.join(path, '*/')
+    else
+      raise 'bad type'
+    end
+    raise "no #{type} files found in #{type} dir `#{path}`" if files.empty?
+
+    # extract their run numbers
+    files.each do |file|
+      nums = File.basename(file).scan(/\d+/).map &:to_i
+      raise "failed to get run number from #{type} object `#{file}`" if nums.empty?
+      runnums << nums[-1]
+    end
+    raise "failed to get run numbers from #{type} dir `#{path}`" if runnums.empty?
+    runnums
   end
-  raise "failed to get run numbers from #{type} dir `#{path}`" if runnums.empty?
-  runnums
-end
 
-# get runnum lists
-train_runs = get_runnums train_dir, :train
-dst_runs   = get_runnums dst_dir,   :DST
-puts """----------------------------------------------------------------------------------
-train dir run list:
-#{train_runs}
-DST dir run list:
-#{dst_runs}
-----------------------------------------------------------------------------------"""
+  # get runnum lists
+  train_runs = get_runnums train_dir, :train
+  dst_runs   = get_runnums dst_dir,   :DST
+  puts """
+  ==================================================================================
+  train dir: #{train_dir}
+  run list: #{train_runs}
+  -----
+  DST dir: #{dst_dir}
+  run list: #{dst_runs}
+  =================================================================================="""
 
-# compare runnum sets
-only_in_trains = train_runs - dst_runs
-only_in_dsts   = dst_runs   - train_runs
+  # compare runnum sets
+  only_in_trains = train_runs - dst_runs
+  only_in_dsts   = dst_runs   - train_runs
 
-# return results
-code = 0
-unless only_in_trains.empty?
-  $stderr.puts "ERROR: there are runs with skim files, but no corresponding DST-file directories:"
-  $stderr.puts only_in_trains
-  code = 1
-end
-unless only_in_dsts.empty?
-  $stderr.puts "ERROR: there are runs with DST-file directories, but no corresponding skim files:"
-  $stderr.puts only_in_dsts
-  code = 1
+  # print results
+  $stdout.flush
+  $stderr.flush
+  code = 0
+  unless only_in_trains.empty?
+    $stderr.puts "ERROR: there are runs with skim files, but no corresponding DST-file directories:"
+    $stderr.puts only_in_trains
+    code = 1
+  end
+  unless only_in_dsts.empty?
+    $stderr.puts "ERROR: there are runs with DST-file directories, but no corresponding skim files:"
+    $stderr.puts only_in_dsts
+    code = 1
+  end
+
+  # handle exit code
+  if code == 0
+    puts "All good"
+  else
+    num_failures += 1
+  end
 end
-puts "All good" if code == 0
-exit code
+exit num_failures > 0 ? 1 : 0

qadb/cutdefs/rgk_fa18_6.5GeV.yaml

@@ -0,0 +1,12 @@
+OutlierFD:
+  IQR_cut_factor: 4.0
+OutlierFT:
+  IQR_cut_factor: 4.0
+LowLiveTime:
+  min_live_time: 0.9
+ChargeHigh:
+  IQR_cut_factor: 4.0
+PossiblyNoBeam:
+  max_num_events: 40000
+  max_num_electrons: 100
+  max_FC_charge: 20

qadb/cutdefs/rgk_fa18_7.5GeV.yaml

@@ -0,0 +1 @@
+rgk_fa18_6.5GeV.yaml

qadb/notes/rga_sp18.md

@@ -95,7 +95,7 @@ bin/qtl reheat -m rollover -c 13.3.0 -d rga_sp18_6.4GeV_inbending_lo_nSidis  -o
 for f in /cache/clas12/rg-a/production/recon/spring2018/6.42gev/torus+1/pass1/dst/train/nSidis/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge -s original; done
 
 # after reheat
-for f in ~/v/reheat/rga_sp18_6.4GeV_outbending_nSidis/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge -s original; done
+for f in ~/v/reheat/rga_sp18_6.4GeV_outbending_nSidis/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge -s reheated; done
 ```
 then see files in `test_charge/`.
 

qadb/notes/rgk_fa18.md

@@ -0,0 +1,71 @@
+# Run Group K, Fall 2018, Pass 2
+
+We will use SIDIS skims from two datasets: one for a 6.5 GeV beam, and another for a 7.5 GeV beam; we will keep them separate:
+- `rgk_fa18_6.5GeV`: from `/cache/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/train/skim1`
+- `rgk_fa18_7.5GeV`: from `/cache/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/train/skim1`
+
+Before anything, cross check the train and DST run lists:
+```bash
+bin/qtl xtrain /mss/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/train/skim1 /mss/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/recon
+bin/qtl xtrain /mss/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/train/skim1 /mss/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/recon
+```
+
+## Reheat
+
+> [!WARNING]
+> The FC charge from the Pass 2 data files is incorrect, since they were cooked with `recharge` set to `false`; therefore, we need to "reheat" the data.
+> See `rga_sp18.md` for some more details.
+
+1. make sure all data are on `/cache`; re-cache them if necessary:
+```bash
+qtl histogram --check-cache -d rgk_fa18_6.5GeV --flatdir --focus-physics /cache/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/train/skim1
+qtl histogram --check-cache -d rgk_fa18_7.5GeV --flatdir --focus-physics /cache/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/train/skim1
+```
+2. run reheat:
+```bash
+bin/qtl reheat -m rollover -c 13.3.0 rgk_fa18_6.5GeV -o /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_6.5GeV -i /cache/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/train/skim1
+bin/qtl reheat -m rollover -c 13.3.0 rgk_fa18_7.5GeV -o /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_7.5GeV -i /cache/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/train/skim1
+```
+3. check the results:
+```bash
+# before
+for f in /cache/clas12/rg-k/production/recon/fall2018/torus+1/6535MeV/pass2/v0/dst/train/skim1/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge_rgk_6.5GeV -s original; done
+for f in /cache/clas12/rg-k/production/recon/fall2018/torus+1/7546MeV/pass2/v0/dst/train/skim1/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge_rgk_7.5GeV -s original; done
+# after
+for f in /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_6.5GeV/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge_rgk_6.5GeV -s reheated; done
+for f in /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_7.5GeV/*.hipo; do bin/qtl xcharge -m charge -i $f -o test_charge_rgk_7.5GeV -s reheated; done
+```
+
+
+## Run monitoring
+
+> [!IMPORTANT]
+> Check any run-dependent settings in `qa-physics/monitorRead.groovy`, such as beam energy.
+
+```bash
+qtl histogram -d rgk_fa18_6.5GeV --flatdir --focus-physics /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_6.5GeV
+qtl histogram -d rgk_fa18_7.5GeV --flatdir --focus-physics /volatile/clas12/users/$LOGNAME/reheat/rgk_fa18_7.5GeV
+```
+
+## Double check that we have all the runs
+
+> [!IMPORTANT]
+> In case any runs disappeared from `/cache` while running monitoring or reheating, be sure to cross check the output runs with those from `/mss`
+
+## Make timelines
+
+> [!IMPORTANT]
+> Pass 2 run 5863 was mistakenly cooked into the 6.5 GeV, but it has beam energy 7.5 GeV. To make sure its QA
+> is performed in the correct epoch, move its `outfiles/` files to the correct output dataset directory:
+> ```bash
+> mv -v outfiles/rgk_fa18_6.5GeV/timeline_physics/5863 outfiles/rgk_fa18_7.5GeV/timeline_physics/
+> ```
+
+Make the timelines, separately for each of the 2 datasets:
+```bash
+bin/qtl physics -d rgk_fa18_6.5GeV -p rgk/pass2/qa/fa18_6.5GeV
+bin/qtl physics -d rgk_fa18_7.5GeV -p rgk/pass2/qa/fa18_7.5GeV
+```
+
+> [!WARNING]
+> You may not have permission to publish to this directory; if not, publish to another place and ask the chef to copy the files