def train(args): if args.verbosity == 0: logging.basicConfig(level=logging.WARNING) elif args.verbosity == 1: logging.basicConfig(level=logging.INFO) else: logging.basicConfig(level=logging.DEBUG) assert args.role in ['leader', 'follower', 'local'], \ "role must be leader, follower, or local" assert args.mode in ['train', 'test', 'eval'], \ "mode must be train, test, or eval" if args.data_path.endswith('.csv'): with open(args.data_path, 'rb') as fin: data = np.loadtxt(fin, delimiter=',') if args.mode == 'train' or args.mode == 'test': if args.role == 'leader' or args.role == 'local': X = data[:, :-1] y = data[:, -1] else: X = data y = None else: # eval X = data y = None else: raise ValueError("Unsupported data type %s" % args.data_path) if args.role != 'local': bridge = Bridge(args.role, int(args.local_addr.split(':')[1]), args.peer_addr, args.application_id, 0) else: bridge = None booster = BoostingTreeEnsamble(bridge, learning_rate=args.learning_rate, max_iters=args.max_iters, max_depth=args.max_depth, l2_regularization=args.l2_regularization, max_bins=args.max_bins, num_parallel=args.num_parallel) if args.load_model_path: booster.load_saved_model(args.load_model_path) if args.mode == 'train': booster.fit(X, y, args.checkpoint_path) elif args.mode == 'test': pred = booster.batch_predict(X) acc = sum((pred > 0.5) == y) / len(y) logging.info("Test accuracy: %f", acc) else: pred = booster.batch_predict(X) for i in pred: print(i) if args.export_path: booster.save_model(args.export_path)
def local_test_boosting_tree_helper(self, X, y): booster = BoostingTreeEnsamble(None, max_iters=5, max_depth=3, num_parallel=2) booster.fit(X, y) pred = booster.batch_predict(X) return pred
def follower_test_boosting_tree_helper(self, X, cat_X): bridge = fl.trainer.bridge.Bridge('follower', 50052, 'localhost:50051', streaming_mode=False) booster = BoostingTreeEnsamble(bridge, max_iters=3, max_depth=2) booster.fit(X, None, cat_features=cat_X) pred = booster.batch_predict(X, cat_features=cat_X) bridge.terminate()
def local_test_boosting_tree_helper(self, X, y, cat_X): booster = BoostingTreeEnsamble(None, max_iters=3, max_depth=2, num_parallel=2) train_pred = booster.fit(X, y, cat_features=cat_X) pred = booster.batch_predict(X, cat_features=cat_X) np.testing.assert_almost_equal(train_pred, pred) return pred
def follower_test_boosting_tree_helper(self, X, cat_X): bridge = fl.trainer.bridge.Bridge('follower', 50052, 'localhost:50051', streaming_mode=True) booster = BoostingTreeEnsamble(bridge, max_iters=3, max_depth=2) booster.fit(X, None, cat_features=cat_X) pred = booster.batch_predict(X, cat_features=cat_X, get_raw_score=True) bridge.terminate() np.testing.assert_almost_equal(pred, 0)
def leader_test_boosting_tree_helper(self, X, y): bridge = fl.trainer.bridge.Bridge('leader', 50051, 'localhost:50052', streaming_mode=False) booster = BoostingTreeEnsamble(bridge, max_iters=5, max_depth=3) booster.fit(X, y) pred = booster.batch_predict(X) bridge.terminate() return pred
def leader_test_boosting_tree_helper(self, X, y, cat_X): bridge = fl.trainer.bridge.Bridge('leader', 50051, 'localhost:50052', streaming_mode=False) booster = BoostingTreeEnsamble(bridge, max_iters=3, max_depth=2) train_pred = booster.fit(X, y, cat_features=cat_X) pred = booster.batch_predict(X, cat_features=cat_X) np.testing.assert_almost_equal(train_pred, pred) bridge.terminate() return pred
def test_boosting_tree_local(self): data = load_iris() X = data.data mask = np.random.choice(a=[False, True], size=X.shape, p=[0.5, 0.5]) X[mask] = float('nan') y = np.minimum(data.target, 1) booster = BoostingTreeEnsamble(None, max_iters=5, max_depth=3, num_parallel=2) booster.fit(X, y) pred = booster.batch_predict(X) self.assertGreater(sum((pred > 0.5) == y) / len(y), 0.94)