def benchmark_ground_truth(threshold, index_data, query_data):
times = []
results = []
for q in query_data.sets:
start = time.clock()
result = []
for key, a in zip(index_data.keys, index_data.sets):
j = _compute_jaccard(q, a)
if j >= threshold:
result.append([key, j])
duration = time.clock() - start
results.append(sorted(result, key=lambda x : x[1], reverse=True))
times.append(duration)
return times, results
def benchmark_linearscan(num_perm, threshold, index_data, query_data):
times = []
results = []
for qs, q in zip(query_data.sets, query_data.minhashes[num_perm]):
start = time.clock()
result = []
for key, m in zip(index_data.keys, index_data.minhashes[num_perm]):
j = q.jaccard(m)
if j >= threshold:
result.append(key)
duration = time.clock() - start
times.append(duration)
results.append(sorted([[key, _compute_jaccard(qs, index_data.sets[key])]
for key in result],
key=lambda x : x[1], reverse=True))
return times, results
def benchmark_lsh(num_perm, threshold, index_data, query_data):
print("Building LSH index")
lsh = MinHashLSH(threshold, num_perm)
for key, minhash in zip(index_data.keys, index_data.minhashes[num_perm]):
lsh.insert(key, minhash)
print("Querying")
times = []
results = []
for qs, minhash in zip(query_data.sets, query_data.minhashes[num_perm]):
start = time.clock()
result = lsh.query(minhash)
duration = time.clock() - start
times.append(duration)
results.append(sorted([[key, _compute_jaccard(qs, index_data.sets[key])]
for key in result],
key=lambda x : x[1], reverse=True))
return times, results
def benchmark_lsh(num_perm, threshold, index_data, query_data):
print("Building LSH index")
lsh = MinHashLSH(threshold, num_perm)
for key, minhash in z:xip(index_data.keys, index_data.minhashes[num_perm]):
lsh.insert(key, minhash)
print("Querying")
times = []
results = []
for qs, minhash in zip(query_data.sets, query_data.minhashes[num_perm]):
start = time.clock()
result = lsh.query(minhash)
duration = time.clock() - start
times.append(duration)
results.append(sorted([[key, _compute_jaccard(qs, index_data.sets[key])]
for key in result],
key=lambda x : x[1], reverse=True))
return times, results
def benchmark_linearscan(num_perm, threshold, index_data, query_data):
times = []
results = []
for qs, q in zip(query_data.sets, query_data.minhashes[num_perm]):
start = time.clock()
result = []
for key, m in zip(index_data.keys, index_data.minhashes[num_perm]):
j = q.jaccard(m)
if j >= threshold:
result.append(key)