def compare_algs_tfidf_simhashtfidf(self):
token_length = 1
test_set = self.generate_random_triples()
ds = DocSim(self.document_set)
sh = SimHashTfIdf(self.document_set)
total = float(len(test_set))
correct = 0.
for t1, t2, t3 in test_set:
dsim1 = ds.similarity(t1, t2)
dsim2 = ds.similarity(t1, t3)
ssim1 = sh.similarity(t1, t2)
ssim2 = sh.similarity(t1, t3)
if ((abs(dsim1 - 0) < 0.000001 and abs(dsim2 - 0) < 0.000001)):
total -= 1.
continue
db = dsim1 < dsim2
sb = ssim1 < ssim2
if db == sb:
correct += 1.
# print len(test_set)
# print total
return correct / total
def benchmark_memory_tfidf(self, iterations):
ds = DocSim(self.document_set)
for i in range(iterations):
title1 = self.select_random_document()
title2 = self.select_random_document()
sim = ds.similarity(title1, title2)
return resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1000
def benchmark_tfidf(self, iterations):
t0 = time.clock()
ds = DocSim(self.document_set)
for i in range(iterations):
title1 = self.select_random_document()
title2 = self.select_random_document()
sim = ds.similarity(title1, title2)
t1 = time.clock()
span = t1 - t0
return span