def print_statistics(self, methods):
single_queries = Query(self.collection_path).get_queries_of_length(1)
queries = {ele['num']:ele['title'] for ele in single_queries}
cs = CollectionStats(self.collection_path)
performance = Performances(self.collection_path)
res = performance.gen_optimal_performances_queries(methods, queries.keys())
avdl = cs.get_avdl()
total_terms = cs.get_total_terms()
collection_freq = []
for qid in queries:
idx = 0
ctf = cs.get_term_collection_occur(queries[qid])
idf = cs.get_term_logidf1(queries[qid])
collection_freq.append( ctf*1.0/total_terms )
print avdl
print np.mean(collection_freq)
for ele in res:
label = ele[0]
p = ele[1]
para = float(ele[2].split(':')[1])
print label
if 'okapi' in label:
print 'b:', para, 'beta:', 1.2*para/avdl, 'c2:', 1.2*(1-para)
if 'pivoted' in label:
print 's:', para, 'beta:', para/avdl, 'c2:', 1-para
def print_best_performances(self, methods=[]):
single_queries = Query(self.collection_path).get_queries_of_length(1)
queries = {ele['num']:ele['title'] for ele in single_queries}
cs = CollectionStats(self.collection_path)
performance = Performances(self.collection_path)
res = performance.gen_optimal_performances_queries(methods, queries.keys())
print res
def gen_output_performances_batch():
all_paras = []
with open('collections.json') as cf:
for c in json.load(cf):
collection_name = c['collection']
this_output_root = os.path.join(output_root, collection_name)
if not os.path.exists(this_output_root):
os.makedirs(this_output_root)
index_path = os.path.join(
index_root, 'lucene-index.' + collection_name + '.cnt.1')
all_paras.extend(
Performances(index_path).gen_output_performances_paras(
this_output_root))
#print all_paras
gen_batch_framework(all_paras, output_performances_atom)
def print_optimal_performances(metrics=['map']):
# with open('g.json') as f:
# methods = [m['name'] for m in json.load(f)['methods']]
# if os.path.exists('microblog_funcs.json'):
# with open('microblog_funcs.json') as f:
# methods.extend([m['name'] for m in json.load(f)['methods']])
with open('collections.json') as cf:
for c in json.load(cf):
collection_name = c['collection']
this_output_root = os.path.join(output_root, collection_name)
index_path = os.path.join(
index_root, 'lucene-index.' + collection_name + '.cnt.1')
print
print collection_name
print '=' * 30
Performances(index_path).print_optimal_performance(
this_output_root, metrics)
def output_performances_atom(para):
index_path = para[0]
output_fn = para[1]
input_fns = para[2:]
Performances(index_path).output_performances(output_fn, input_fns)
