def test_uni_parse(self):
X = get_test_universities()
institutions = parse_institution_records(X)
self.assertEqual(institutions['Yale University']['Region'],
'Northeast')
self.assertEqual(institutions['Princeton University']['NRC95'], 6)
self.assertEqual(institutions['Carnegie Mellon University']['USN2010'],
1)
self.assertEqual(institutions['Harvard University']['pi'], 6.12)
self.assertEqual(institutions['Harvard University']['pi_inv'],
1. / 6.12)
self.assertEqual(institutions['Stanford University']['pi_rescaled'],
1.)
self.assertEqual(institutions['MIT']['u'], 3)
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('-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])
DBLP_FILE = "DBLP_%s_file_0.html"
def interface():
args = argparse.ArgumentParser()
args.add_argument("-i", "--inst-file", help="Institution profiles")
args.add_argument("-f", "--faculty-file", help="Faculty profiles")
args.add_argument("-g", "--gs-dir", help="Directory of GS profiles")
args.add_argument("-d", "--dblp-dir", help="Directory of DBLP profiles")
args = args.parse_args()
return args
if __name__ == "__main__":
args = interface()
inst = institution_parser.parse_institution_records(open(args.inst_file, "rU"))
faculty = load_assistant_profs(open(args.faculty_file, "rU"), inst)
# gs_prefix = os.path.join(args.gs_dir, 'GSP_')
dblp_prefix = os.path.join(args.dblp_dir, "DBLP_")
for f in faculty:
# Check for each profile, download if missing
"""
if 'gs' in f:
gs_file = os.path.join(args.gs_dir, GS_FILE % f['gs'])
if not os.path.isfile(gs_file):
print 'GS -> ', f['facultyName']
download_all_gs_pages(f['gs'], gs_prefix)
"""
if "dblp" in f:
from faculty_hiring.parse.institution_parser import parse_institution_records
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]):
name = line.split(':', 1)[-1].strip()
if name == next_name:
output.write('# dblp_n : %d\n' % num_papers[next_ind])
output.write('# dblp_n_2011 : %d\n' %
num_papers_2011[next_ind])
next_ind += 1
if next_ind < max_ind:
next_name = names[next_ind]
else:
done = True
if not done:
print 'WARNING: failed to link all z-scores!'
output.close()
if __name__ == "__main__":
args = interface()
inst = institution_parser.parse_institution_records(open(args.inst_file))
faculty = load_assistant_profs(open(args.faculty_file, 'rU'), inst)
load.load_all_publications(faculty, args.dblp_dir, gs_dir=None)
dists, tots = get_paper_counts_by_topic(faculty)
means, stds = get_topic_means_stds(dists, tots)
print means
print stds
set_zscores(faculty, means, stds)
#add_zscores_to_file(faculty, args.faculty_file, args.output_file)
add_counts_to_file(faculty, args.faculty_file, args.output_file)
GS_DIR = '/Users/samfway/Documents/Work/ClausetLab/Projects/research_env/data/gs_profiles_042617/'
BS_FACULTY_FILE = os.path.join(DATA_DIR, 'faculty_bs_CURRENT.txt')
CS_FACULTY_FILE = os.path.join(DATA_DIR, 'faculty_cs_CURRENT.txt')
HS_FACULTY_FILE = os.path.join(DATA_DIR, 'faculty_hs_CURRENT.txt')
BS_INST_FILE = os.path.join(DATA_DIR, 'inst_bs_CURRENT.txt')
CS_INST_FILE = os.path.join(DATA_DIR, 'inst_cs_CURRENT.txt')
HS_INST_FILE = os.path.join(DATA_DIR, 'inst_hs_CURRENT.txt')
# Colors
ACCENT_COLOR_1 = np.array([176., 116., 232.]) / 255.
# Load the standard set of files
# Business
bs_inst = institution_parser.parse_institution_records(open(
BS_INST_FILE, 'rU'))
all_bs_faculty = [
person for person in faculty_parser.parse_faculty_records(
open(BS_FACULTY_FILE, 'rU'), school_info=bs_inst, ranking='pi')
]
bs_faculty = load.load_assistant_profs(open(BS_FACULTY_FILE, 'rU'),
school_info=bs_inst,
ranking='pi',
year_start=1970,
year_stop=2012)
# bs_faculty_df = convert_faculty_list_to_df(bs_faculty)
# Computer Science
cs_inst = institution_parser.parse_institution_records(open(
CS_INST_FILE, 'rU'))
all_cs_faculty = [
