args.add_argument('-p', '--prob-function', help='Candidate probability/matching function', required=True)
args.add_argument('-n', '--num-iters', help='Number of iterations to est. error', default=100, type=int)
args.add_argument('-w', '--weights', help='Model parameters (as comma-separated string)', type=allow_negatives)
args.add_argument('-r', '--ranking', help='Which ranking to use', default='pi_rescaled')
args.add_argument('-v', '--validation', help='Years to hold out', default='')
args = args.parse_args()
return args
if __name__=="__main__":
args = interface()
inst = parse_institution_records(open(args.inst_file, 'rU'))
candidate_pools, job_pools, job_ranks, year_range = load_assistant_prof_pools(open(args.fac_file),
school_info=inst,
ranking='pi_rescaled',
year_start=1970,
year_stop=2012,
year_step=1)
if args.validation: # if specified years are to be evaluated
hold_out = [int(year) for year in args.validation.split(',')]
testing_candidates, testing_jobs, testing_job_ranks = [], [], []
for i, year in enumerate(year_range):
if year in hold_out:
testing_candidates.append(candidate_pools[i])
testing_jobs.append(job_pools[i])
testing_job_ranks.append(job_ranks[i])
# Overwrite originals
candidate_pools, job_pools, job_ranks = testing_candidates, testing_jobs, testing_job_ranks
model = SigmoidModel(prob_function=args.prob_function)
def interface():
args = argparse.ArgumentParser()
args.add_argument('-f', '--fac-file', help='Faculty file', required=True)
args.add_argument('-i', '--inst-file', help='Institutions file', required=True)
args.add_argument('-s', '--orders-file', help='Input (pickle) file', required=True)
args = args.parse_args()
return args
if __name__=="__main__":
args = interface()
inst = parse_institution_records(open(args.inst_file, 'rU'))
candidate_pools, job_pools, job_ranks, year_range = load_assistant_prof_pools(open(args.fac_file),
school_info=inst,
ranking='pi_rescaled',
year_start=1970,
year_stop=2012,
year_step=1)
hiring_orders, hiring_probs = load_hiring_order_set(args.orders_file)
if len(hiring_orders) != len(job_pools):
raise ValueError('Incorrect number of pools!')
for i, pool in enumerate(job_pools):
pool_size = len(pool)
if len(pool) != len(hiring_orders[i][0]):
raise ValueError('Incorrect pool size')
if np.sum(hiring_orders[i][0]) != np.sum(np.arange(pool_size)):
raise ValueError('Ordering doesnt seem legit')