def test_sa_to_nd(self):
dtype = np.dtype({'names': map('f{}'.format, xrange(3)),
'formats': [float] * 3})
sa = np.array([(-1.0, 2.0, -1.0), (0.0, -1.0, 2.0)], dtype=dtype)
control = np.array([[-1.0, 2.0, -1.0], [0.0, -1.0, 2.0]],
dtype=float)
result = utils.cast_np_sa_to_nd(sa)
self.assertTrue(np.array_equal(result, control))
def test_sa_to_nd(self):
dtype = np.dtype({
'names': map('f{}'.format, xrange(3)),
'formats': [float] * 3
})
sa = np.array([(-1.0, 2.0, -1.0), (0.0, -1.0, 2.0)], dtype=dtype)
control = np.array([[-1.0, 2.0, -1.0], [0.0, -1.0, 2.0]], dtype=float)
result = utils.cast_np_sa_to_nd(sa)
self.assertTrue(np.array_equal(result, control))
def __init__(
self,
M,
y,
clfs=[{'clf': RandomForestClassifier}],
subsets=[{'subset': SubsetNoSubset}],
cvs=[{'cv': NoCV}],
trials=None):
if utils.is_sa(M):
self.col_names = M.dtype.names
self.M = utils.cast_np_sa_to_nd(M)
else: # assuming an nd_array
self.M = M
self.col_names = ['f{}'.format(i) for i in xrange(M.shape[1])]
self.y = y
self.clfs = clfs
self.subsets = subsets
self.cvs = cvs
self.trials = trials
def test_get_top_features(self):
M, labels = uft.generate_test_matrix(1000, 15, random_state=0)
M = utils.cast_np_sa_to_nd(M)
M_train, M_test, labels_train, labels_test = train_test_split(
M, labels)
clf = RandomForestClassifier(random_state=0)
clf.fit(M_train, labels_train)
res = comm.get_top_features(clf, M, verbose=False)
ctrl = utils.convert_to_sa([('f5', 0.0773838526068),
('f13', 0.0769596713039),
('f8', 0.0751584839431),
('f6', 0.0730815879102),
('f11', 0.0684456133071),
('f9', 0.0666747414603),
('f10', 0.0659621889608),
('f7', 0.0657988099065),
('f2', 0.0634000069218),
('f0', 0.0632912268319)],
col_names=('feat_name', 'score'))
self.assertTrue(uft.array_equal(ctrl, res))
def test_get_top_features(self):
M, labels = uft.generate_test_matrix(1000, 15, random_state=0)
M = utils.cast_np_sa_to_nd(M)
M_train, M_test, labels_train, labels_test = train_test_split(
M,
labels)
clf = RandomForestClassifier(random_state=0)
clf.fit(M_train, labels_train)
res = comm.get_top_features(clf, M, verbose=False)
ctrl = utils.convert_to_sa(
[('f5', 0.0773838526068),
('f13', 0.0769596713039),
('f8', 0.0751584839431),
('f6', 0.0730815879102),
('f11', 0.0684456133071),
('f9', 0.0666747414603),
('f10', 0.0659621889608),
('f7', 0.0657988099065),
('f2', 0.0634000069218),
('f0', 0.0632912268319)],
col_names=('feat_name', 'score'))
self.assertTrue(uft.array_equal(ctrl, res))