def generate_condition(self):
if self.role == Condition.UseNative:
return RandomData.random_choice(self.UseNative_Roles)
elif self.role == Condition.UseData:
return RandomData.random_choice(self.UseData_Roles)
else:
raise Exception("role error")
def test_kd_tree(n, D, n_test, alphas):
"""
Tests the query time and distance for a random data set and test set
@param n: int - the number of points of the dataset
@param D: int - the dimension of the data points
@param n_test: int - the number of points to test
@param alphas: [float] - a set of alphas to test
@return [TestResult] array of objects of class TestResult, which has the average time and distance for a single query
"""
documents = RandomData.random_dataset(n, D)
test_documents = RandomData.random_dataset(n_test, D)
rand_tree = KDTree(D)
for i, document in documents.iteritems():
key = [document.get(idx) for idx in xrange(0, D)]
rand_tree.insert(key, i)
print "Finished making random tree."
times = []
for alpha in alphas:
print "Running for alpha", alpha
start_time = time.clock()
cum_dist = 0.0
print "Setting up test documents or whatever this is.."
for i, test_document in test_documents.iteritems():
key = [test_document.get(idx) for idx in xrange(0, D)]
doc_id = rand_tree.nearest(key, alpha)
cum_dist += EvalUtil.distance(test_document, documents[doc_id])
print "Finished."
duration = time.clock() - start_time
times.append(
TestResult("KDTree", n, D, alpha, duration / n_test,
cum_dist / n_test))
return times
def test_lsh(n, D, n_test, alphas):
"""
Tests the query time and distance for a random data set and test set
@param n: int - the number of points of the dataset
@param D: int - the dimension of the data points
@param n_test: int - the number of points to test
@param alphas: [float] - a set of alphas to test
@return [TestResult] array of objects of class TestResult, which has the average time and distance for a single query
"""
documents = RandomData.random_dataset(n, D)
test_documents = RandomData.random_dataset(n_test, D)
times = []
for m in ms:
lsh = LocalitySensitiveHash(documents, D, m)
print "Finished making locally sensitive hash."
print "Running for", m, "projections..."
start_time = time.clock()
cum_dist = 0.0
print "Running for the test documents..."
for i, test_document in test_documents.iteritems():
key = [test_document.get(idx) for idx in xrange(0, D)]
doc = lsh.nearest_neighbor(test_document, 3)
doc_id = doc.doc_id
cum_dist += EvalUtil.distance(test_document, documents[doc_id])
print "Finished."
duration = time.clock() - start_time
times.append(
TestResult("LSH", n, D, m, duration / n_test, cum_dist / n_test))
return times
def choice():
return RandomData.random_choice(ConditionConnection.Kinds)
def index_value(index=None, *args):
if index is None:
index = RandomData.random_choice(range(len(args)))
ans = args[index]
return '%s里第%s个内容' % ('、'.join(map(str, args)), index + 1), ans
def __init__(self, role):
self.UseNative_Roles = [
("今年年份", RandomData.current_year()),
("本月月份", RandomData.current_month()),
("今天几号", RandomData.current_day()),
("今天周几[1-7]", RandomData.current_weekday()),
("北京奥运那年", "2008"),
Calc.index_value(
None, *[RandomData.get_letter_digit() for i in range(4)]),
]
self.UseData_Roles = [
Calc.sum(*[RandomData.get_int() for i in range(4)]),
Calc.get_even(*[RandomData.get_int() for i in range(4)]),
Calc.get_odd(*[RandomData.get_int() for i in range(4)]),
Calc.max(*[RandomData.get_int() for i in range(4)]),
Calc.min(*[RandomData.get_int() for i in range(4)]),
]
if role == self.Any:
role = RandomData.random_choice([self.UseData, self.UseNative])
self.role = role