init_orca_context(cluster_mode=args.cluster_mode,
cores=args.cores,
memory=args.memory,
num_nodes=num_nodes,
init_ray_on_spark=True)
tsdata_train, tsdata_valid, tsdata_test = get_nyc_taxi_tsdataset(
args.datadir)
auto_lstm = AutoLSTM(input_feature_num=1,
output_target_num=1,
past_seq_len=14,
optimizer='Adam',
loss=torch.nn.MSELoss(),
metric="mse",
hidden_dim=hp.grid_search([32, 64]),
layer_num=hp.randint(1, 3),
lr=hp.choice([0.001, 0.003, 0.01]),
dropout=hp.uniform(0.1, 0.2),
logs_dir="/tmp/auto_lstm",
cpus_per_trial=args.cpus_per_trial,
name="auto_lstm")
auto_lstm.fit(
data=get_data_creator(tsdata_train),
epochs=args.epoch,
batch_size=hp.choice([32, 64]),
validation_data=get_data_creator(tsdata_valid),
n_sampling=args.n_sampling,
)
best_model = auto_lstm.get_best_model()
best_config = auto_lstm.get_best_config()
parser.add_argument('--epochs', type=int, default=1,
help="Max number of epochs to train in each trial.")
args = parser.parse_args()
num_nodes = 1 if args.cluster_mode == "local" else args.num_workers
init_orca_context(cluster_mode=args.cluster_mode, cores=args.cores,
memory=args.memory, num_nodes=num_nodes, init_ray_on_spark=True)
tsdata_train, tsdata_valid, tsdata_test = get_tsdata()
auto_lstm = AutoLSTM(input_feature_num=1,
output_target_num=1,
past_seq_len=20,
hidden_dim=hp.grid_search([32, 64]),
layer_num=hp.randint(1, 3),
lr=hp.choice([0.01, 0.03, 0.1]),
dropout=hp.uniform(0.1, 0.2),
optimizer='Adam',
loss=torch.nn.MSELoss(),
metric="mse")
x_train, y_train = tsdata_train.roll(lookback=20, horizon=1).to_numpy()
x_val, y_val = tsdata_test.roll(lookback=20, horizon=1).to_numpy()
x_test, y_test = tsdata_test.roll(lookback=20, horizon=1).to_numpy()
auto_lstm.fit(data=(x_train, y_train),
epochs=args.epochs,
validation_data=(x_val, y_val))
yhat = auto_lstm.predict(x_test)
unscale_y_test = tsdata_test.unscale_numpy(y_test)