stats.py

#!/usr/bin/env python

import re
import fileinput

stats = {}
totals = {}

for line in fileinput.input():
    line = line.strip()
    m = re.match('^"(\d{4})-.+organizations/(.+)>$', line)
    if not m:
        print "uhoh: %s" % line
        continue
    year, inst = m.groups()

    s = stats.get(year, {})
    s[inst] = s.get(inst, 0) + 1
    stats[year] = s
    totals[inst] = totals.get(inst, 0) + 1

years = stats.keys()
years.sort()

institutions = totals.keys()
institutions.sort(lambda a, b: cmp(totals[b], totals[a]))

print "year\t", "\t".join(institutions)
for year in years:
    print year,
    for inst in institutions:
        print "\t", stats[year].get(inst, 0),
    print