def top_features():
models = get_models(current_user.id)
model_id = int(request.args.get('model_id', '0'))
model = models[model_id]
n = int(request.args.get('n', '10'))
top_features = get_top_features(model['clf'],
col_names=model['feature_names'],
n=n)
ret = [{'feature': feat, 'score': score} for feat, score in top_features]
return jsonify(data=ret)
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)
ctrl_feat_importances = clf.feature_importances_
ctrl_col_names = ['f{}'.format(i) for i in xrange(15)]
ctrl_feat_ranks = np.argsort(ctrl_feat_importances)[::-1][:10]
ctrl = utils.convert_to_sa(
zip(ctrl_col_names, ctrl_feat_importances),
col_names=('feat_name', 'score'))[ctrl_feat_ranks]
res = dsp.get_top_features(clf, M, verbose=False)
self.assertTrue(uft.array_equal(ctrl, res))
res = dsp.get_top_features(clf, col_names=['f{}'.format(i) for i in xrange(15)], verbose=False)
self.assertTrue(uft.array_equal(ctrl, res))
def top_features():
models = get_models(current_user.id)
model_id = int(request.args.get('model_id', '0'))
model = models[model_id]
n = int(request.args.get('n', '10'))
top_features = get_top_features(
model['clf'],
col_names=model['feature_names'],
n=n)
ret = [{'feature': feat, 'score': score} for feat, score in
top_features]
return jsonify(data=ret)
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 = dsp.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))
res = dsp.get_top_features(clf, col_names=['f{}'.format(i) for i in xrange(15)], verbose=False)
self.assertTrue(uft.array_equal(ctrl, res))
