def bench_float(m1=200, m2=200, rseed=0):
print 79 * '_'
print " real valued distance metrics"
print
np.random.seed(rseed)
X1 = np.random.random((m1, DTEST))
X2 = np.random.random((m2, DTEST))
for (metric, argdict) in METRIC_DICT.iteritems():
keys = argdict.keys()
for vals in itertools.product(*argdict.values()):
kwargs = dict(zip(keys, vals))
print metric, param_info(kwargs)
t0 = time()
try:
dist_metric = DistanceMetric(metric, **kwargs)
Yc1 = dist_metric.cdist(X1, X2)
except Exception as inst:
print " >>>>>>>>>> error in pyDistances cdist:"
print " ", inst
t1 = time()
try:
Yc2 = cdist(X1, X2, metric, **kwargs)
except Exception as inst:
print " >>>>>>>>>> error in scipy cdist:"
print " ", inst
t2 = time()
try:
dist_metric = DistanceMetric(metric, **kwargs)
Yp1 = dist_metric.pdist(X1)
except Exception as inst:
print " >>>>>>>>>> error in pyDistances pdist:"
print " ", inst
t3 = time()
try:
Yp2 = pdist(X1, metric, **kwargs)
except Exception as inst:
print " >>>>>>>>>> error in scipy pdist:"
print " ", inst
t4 = time()
if not np.allclose(Yc1, Yc2):
print " >>>>>>>>>> FAIL: cdist results don't match"
if not np.allclose(Yp1, Yp2):
print " >>>>>>>>>> FAIL: pdist results don't match"
print " - pyDistances: c: %.4f sec p: %.4f sec" % (t1 - t0,
t3 - t2)
print " - scipy: c: %.4f sec p: %.4f sec" % (t2 - t1,
t4 - t3)
print ''
def bench_float(m1=200, m2=200, rseed=0):
print 79 * '_'
print " real valued distance metrics"
print
np.random.seed(rseed)
X1 = np.random.random((m1, DTEST))
X2 = np.random.random((m2, DTEST))
for (metric, argdict) in METRIC_DICT.iteritems():
keys = argdict.keys()
for vals in itertools.product(*argdict.values()):
kwargs = dict(zip(keys, vals))
print metric, param_info(kwargs)
t0 = time()
try:
dist_metric = DistanceMetric(metric, **kwargs)
Yc1 = dist_metric.cdist(X1, X2)
except Exception as inst:
print " >>>>>>>>>> error in pyDistances cdist:"
print " ", inst
t1 = time()
try:
Yc2 = cdist(X1, X2, metric, **kwargs)
except Exception as inst:
print " >>>>>>>>>> error in scipy cdist:"
print " ", inst
t2 = time()
try:
dist_metric = DistanceMetric(metric, **kwargs)
Yp1 = dist_metric.pdist(X1)
except Exception as inst:
print " >>>>>>>>>> error in pyDistances pdist:"
print " ", inst
t3 = time()
try:
Yp2 = pdist(X1, metric, **kwargs)
except Exception as inst:
print " >>>>>>>>>> error in scipy pdist:"
print " ", inst
t4 = time()
if not np.allclose(Yc1, Yc2):
print " >>>>>>>>>> FAIL: cdist results don't match"
if not np.allclose(Yp1, Yp2):
print " >>>>>>>>>> FAIL: pdist results don't match"
print " - pyDistances: c: %.4f sec p: %.4f sec" % (t1 - t0,
t3 - t2)
print " - scipy: c: %.4f sec p: %.4f sec" % (t2 - t1,
t4 - t3)
print ''
def _check_metrics_bool(self, k, metric, kwargs):
bt = BallTree(self.Xbool, metric=metric, **kwargs)
dist_bt, ind_bt = bt.query(self.Ybool, k=k)
dm = DistanceMetric(metric=metric, **kwargs)
D = dm.cdist(self.Ybool, self.Xbool)
ind_dm = np.argsort(D, 1)[:, :k]
dist_dm = D[np.arange(self.Ybool.shape[0])[:, None], ind_dm]
# we don't check the indices here because there are very often
# ties for nearest neighbors, which cause the test to fail.
# Distances will be correct in either case.
assert_array_almost_equal(dist_bt, dist_dm)
def _check_metrics_bool(self, k, metric, kwargs):
bt = BallTree(self.Xbool, metric=metric, **kwargs)
dist_bt, ind_bt = bt.query(self.Ybool, k=k)
dm = DistanceMetric(metric=metric, **kwargs)
D = dm.cdist(self.Ybool, self.Xbool)
ind_dm = np.argsort(D, 1)[:, :k]
dist_dm = D[np.arange(self.Ybool.shape[0])[:, None], ind_dm]
# we don't check the indices here because there are very often
# ties for nearest neighbors, which cause the test to fail.
# Distances will be correct in either case.
assert_array_almost_equal(dist_bt, dist_dm)
def test_query_radius_indices(self, n_queries=20):
# center the data
X = 2 * self.X - 1
dm = DistanceMetric()
D = dm.cdist(X[:n_queries], X)
r = np.mean(D)
bt = BallTree(X)
ind = bt.query_radius(X[:n_queries], r, return_distance=False)
ind2 = np.zeros(D.shape) + np.arange(D.shape[1])
ind = np.concatenate(map(np.sort, ind))
ind2 = ind2[D <= r]
assert_array_almost_equal(ind, ind2)
def test_query_radius_indices(self, n_queries=20):
# center the data
X = 2 * self.X - 1
dm = DistanceMetric()
D = dm.cdist(X[:n_queries], X)
r = np.mean(D)
bt = BallTree(X)
ind = bt.query_radius(X[:n_queries], r, return_distance=False)
ind2 = np.zeros(D.shape) + np.arange(D.shape[1])
ind = np.concatenate(map(np.sort, ind))
ind2 = ind2[D <= r]
assert_array_almost_equal(ind, ind2)
def test_query_radius_distance(self):
# center the data
X = 2 * self.X - 1
# choose a query point near the origin
query_pt = 0.01 * X[:1]
eps = 1E-15 # roundoff error can cause test to fail
bt = BallTree(X, leaf_size=5)
# compute reference distances
dm = DistanceMetric()
dist_true = dm.cdist(query_pt, X)[0]
dist_true.sort()
for r in np.linspace(dist_true[0], dist_true[-1], 10):
yield (self._check_query_radius_distance,
X, bt, query_pt, dist_true, r, eps)
def test_query_radius_distance(self):
# center the data
X = 2 * self.X - 1
# choose a query point near the origin
query_pt = 0.01 * X[:1]
eps = 1E-15 # roundoff error can cause test to fail
bt = BallTree(X, leaf_size=5)
# compute reference distances
dm = DistanceMetric()
dist_true = dm.cdist(query_pt, X)[0]
dist_true.sort()
for r in np.linspace(dist_true[0], dist_true[-1], 10):
yield (self._check_query_radius_distance, X, bt, query_pt,
dist_true, r, eps)
