def test_sample_training():
X_train, X_test = _get_mnist_data()
for no_trees, expected_precision in ((1, 0.05),
(5, 0.3),
(10, 0.5),
(50, 0.9)):
tree = RPForest(leaf_size=10, no_trees=no_trees)
# Fit on quarter of data
X_sample = X_train[:X_train.shape[0] / 4]
tree.fit(X_sample)
# Clear and index everything
tree.clear()
for i, x in enumerate(X_train):
tree.index(i, x)
tree._X = X_train
precision = 0.0
X_train /= np.linalg.norm(X_train, axis=1)[:, np.newaxis]
for x_test in X_test:
true_nns = np.argsort(-np.dot(X_train, x_test))[:10]
nns = tree.query(x_test, 10)[:10]
precision += len(set(nns) & set(true_nns)) / 10.0
precision /= X_test.shape[0]
assert precision >= expected_precision
def test_sample_training():
X_train, X_test = _get_mnist_data()
for no_trees, expected_precision in ((1, 0.05), (5, 0.3), (10, 0.5),
(50, 0.9)):
tree = RPForest(leaf_size=10, no_trees=no_trees)
# Fit on quarter of data
X_sample = X_train[:X_train.shape[0] / 4]
tree.fit(X_sample)
# Clear and index everything
tree.clear()
for i, x in enumerate(X_train):
tree.index(i, x)
tree._X = X_train
precision = 0.0
X_train /= np.linalg.norm(X_train, axis=1)[:, np.newaxis]
for x_test in X_test:
true_nns = np.argsort(-np.dot(X_train, x_test))[:10]
nns = tree.query(x_test, 10)[:10]
precision += len(set(nns) & set(true_nns)) / 10.0
precision /= X_test.shape[0]
assert precision >= expected_precision
def test_clear():
X_train, X_test = _get_mnist_data()
tree = RPForest(leaf_size=10, no_trees=10)
tree.fit(X_train)
for leaf_code, leaf_indices in tree.get_leaf_nodes():
assert leaf_indices
tree.clear()
for leaf_code, leaf_indices in tree.get_leaf_nodes():
assert not leaf_indices
def test_clear():
X_train, X_test = _get_mnist_data()
tree = RPForest(leaf_size=10, no_trees=10)
tree.fit(X_train)
for leaf_code, leaf_indices in tree.get_leaf_nodes():
assert leaf_indices
tree.clear()
for leaf_code, leaf_indices in tree.get_leaf_nodes():
assert not leaf_indices
## RPFOREST TEST
from rpforest import RPForest
leaf_size = 5
n_trees = 20
name = 'RPForest(leaf_size=%d, n_trees=%d)' % (leaf_size, n_trees)
model = RPForest(leaf_size=leaf_size, no_trees=n_trees)
#fitting
features = features.copy(order='C') #something related to Cython error
model.fit(features)
model.clear()
#indexing
for i, x in enumerate(features):
t = Timer()
with t:
model.index(dict_feat[i], x.tolist())
#querying
for i in range(features.shape[0]):
t = Timer()
with t:
results = model.get_candidates(features[i])
print 'queried', dict_feat[i], 'results', results