def check_bishophill():
f = os.path.join('results','676.csv')
for items in read_results_file(f):
print '\t'.join(map(str, items))
data = process_results_file(f)
print calc_race_times(data)
def list_clubs():
folder = 'results'
clubs = set()
for f in os.listdir(folder):
fpath = os.path.join(folder, f)
for _, club, _, _ in read_results_file(fpath):
clubs.add(normalise_club1(club))
print '\n'.join(sorted(clubs))
def print_all_clubs():
clubs = set()
result_folder = 'results'
for f in os.listdir(result_folder):
fpath = os.path.join(result_folder, f)
for name, club, category, time in read_results_file(fpath):
clubs.add(club)
print '\n'.join(sorted(clubs))
def process(self):
"""
Munges a results csv file and returns usable data
Returns:
Dict[str, int]: mapping of runner name -> finish time (in seconds)
"""
runners = {}
for name, club, category, time in read_results_file(self._f):
runners[name] = time
if not runners:
raise EmptyResultSet
return runners
def find_ambiguous_names():
runner_clubs = defaultdict(set)
result_folder = 'results'
fname = 'result_to_race_index.dat'
result_to_race, _ = read_result_to_race_index(fname)
for race_id in result_to_race:
f = os.path.join(result_folder, race_id + '.csv')
if not os.path.exists(f):
continue
for name, club, category, time in read_results_file(f):
runner_clubs[name].add(club)
ordered_names = sorted(runner_clubs.iteritems(),
reverse=True,
key=lambda x: len(x[1]))
lines = []
for name, clubs in ordered_names[0:10]:
lines.append('%s\t%s' % (name, ', '.join(clubs)))
print '\n'.join(lines)