def cmpcvr_by_one_tasklist(argsdict, tasklist_name):
""" This is the primary function to be run inside lambda for cmpcvr.
tasklist_name is like "{archive_root}_chunk_{chunk_idx}"
"""
# set s3 vs local mode -- this probably better done long before this point.
DB.set_DB_mode()
contests_dod = DB.load_data('styles', 'contests_dod.json')
if CVR.data_frame.empty:
CVR.load_cvrs_to_df(argsdict)
# marks/chunks/{archive_root}_chunk_{chunk_idx}.csv # individual marks chunks. These are kept for cmpcvr
if not DB.file_exists(file_name=tasklist_name+'.csv', dirname='marks', subdir="chunks"):
utils.sts(f"Logic Error: no marks df missing: {tasklist_name}")
traceback.print_stack()
sys.exit(1)
audit_df = DB.load_data(dirname='marks', subdir="chunks", name=tasklist_name, format='.csv')
#---------------------------------------
# primary call of this function performs chunk comparison
overvotes_results, disagreed_results, blank_results = compare_chunk_with_cvr(
argsdict=argsdict,
contests_dod=contests_dod,
cvr_df=CVR.data_frame,
audit_df=audit_df,
chunk_name=tasklist_name,
)
#---------------------------------------
"""
cmpcvr/chunks/disagreed_{archive_root}_chunk_{chunk_idx}.csv # individual cmpcvr disagreed chunks
cmpcvr/chunks/overvotes_{archive_root}_chunk_{chunk_idx}.csv # individual cmpcvr overvote chunks
"""
DB.save_data(data_item=disagreed_results,
dirname='cmpcvr', subdir='chunks',
name=f"disagreed-{tasklist_name}.csv")
DB.save_data(data_item=disagreed_results,
dirname='cmpcvr', subdir='chunks',
name=f"overvotes-{tasklist_name}.csv")
DB.save_data(data_item=blank_results,
dirname='cmpcvr', subdir='chunks',
name=f"blanks-{tasklist_name}.csv")
def is_dirname_chunk_built(dirname, group_name, chunk_idx: int, s3flag=None):
file_name = create_dirname_chunk_filename(dirname, group_name, chunk_idx)
return DB.file_exists(file_name, dirname, subdir='chunks', s3flag=s3flag)
