Updated assessor docs

assess.py

@@ -185,14 +185,16 @@ def show_options(option: str, groupdir: str, operation: str, logger):
             os.system(f'ls {groupdir}/outs/')
         else:
             os.system(f'ls {groupdir}/errs/')
-    else:
+    elif option == 'labels':
         logger.info('Detecting labels from previous runs:')
         labels = glob.glob(f'{args.workdir}/groups/{args.groupID}/proj_codes*')
         for l in labels:
             pcode = l.split('/')[-1].replace("proj_codes_","").replace(".txt","")
             if pcode == '1':
                 pcode = 'main'
             logger.info(f'{format_str(pcode,20)} - {l}')
+    else:
+        logger.info(f'{option} not accepted - use "jobids" or "labels"')
 
 def cleanup(cleantype: str, groupdir: str, logger):
     """Remove older versions of project code files, error or output logs. Clear directories."""
@@ -343,7 +345,7 @@ def assess_main(args):
 
     parser.add_argument('-j','--jobid', dest='jobID', help='Identifier of job to inspect')
     parser.add_argument('-p','--phase', dest='phase', default='validate', help='Pipeline phase to inspect')
-    parser.add_argument('-s','--show-opts', dest='show_opts', help='Show options for jobids, repeat label')
+    parser.add_argument('-s','--show-opts', dest='show_opts', help='Show options for jobids, labels')
 
     parser.add_argument('-r','--repeat_label', dest='repeat_label', default=None, help='Save a selection of codes which failed on a given error - input a repeat id.')
     parser.add_argument('-i','--inspect', dest='inspect', help='Inspect error/output of a given type/label')

docs/source/assess-overview.rst

@@ -1,2 +1,43 @@
 Assessor Tool
-=============
+=============
+
+The assessor script ```assess.py``` is an all-purpose pipeline checking tool which can be used to assess:
+ - The current status of all datasets within a given group in the pipeline (which phase each dataset currently sits in)
+ - The errors/outputs associated with previous job runs.
+
+1. Overall Progress of the Pipeline
+--------------------------------
+
+To see the general status of the pipeline for a given group:
+::
+python assess.py <group> progress
+::
+
+An example use case is to write out all datasets that require scanning to a new label (repeat_label):
+::
+python assess.py <group> progress -p scan -r <label_for_scan_subgroup> -W
+::
+
+The last flag ```-W``` is required when writing an output file from this program, otherwise the program will dryrun and produce no files.
+
+2. Checking errors
+------------------
+Check what repeat labels are available already using
+::
+python assess.py <group> errors -s labels
+::
+
+Show what jobs have previously run
+::
+python assess.py <group> errors -s jobids
+::
+
+For showing all errors from a previous job run
+::
+python assess.py <group> errors -j <jobid>
+::
+
+For selecting a specific type of error to investigate (-i) and examine the full log for each example (-E)
+::
+python assess.py test errors -j <jobid> -i "type_of_error" -E
+::

requirements.txt

@@ -22,6 +22,7 @@ pandas==2.1.1
 python-dateutil==2.8.2
 pytz==2023.3.post1
 requests==2.31.0
+scipy==1.10.1
 six==1.16.0
 tzdata==2023.3
 ujson==5.8.0