update basicts

GestaltCogTeam · Aug 31, 2024 · b6f3d80 · b6f3d80
1 parent fd15e52
commit b6f3d80
Show file tree

Hide file tree

Showing 104 changed files with 5,614 additions and 404 deletions.
diff --git a/baselines/AGCRN/run.sh b/baselines/AGCRN/run.sh
diff --git a/baselines/Autoformer/PEMS04_LTSF.py b/baselines/Autoformer/PEMS04_LTSF.py
@@ -0,0 +1,156 @@
+import os
+import sys
+from easydict import EasyDict
+sys.path.append(os.path.abspath(__file__ + '/../../..'))
+
+from basicts.metrics import masked_mae, masked_mape, masked_rmse
+from basicts.data import TimeSeriesForecastingDataset
+from basicts.runners import SimpleTimeSeriesForecastingRunner
+from basicts.scaler import ZScoreScaler
+from basicts.utils import get_regular_settings
+
+from .arch import Autoformer
+
+############################## Hot Parameters ##############################
+# Dataset & Metrics configuration
+DATA_NAME = 'PEMS04'  # Dataset name
+regular_settings = get_regular_settings(DATA_NAME)
+# INPUT_LEN = regular_settings['INPUT_LEN']  # Length of input sequence
+# OUTPUT_LEN = regular_settings['OUTPUT_LEN']  # Length of output sequence
+INPUT_LEN = 720 # LTSF
+OUTPUT_LEN = 336 # LTSF
+TRAIN_VAL_TEST_RATIO = regular_settings['TRAIN_VAL_TEST_RATIO']  # Train/Validation/Test split ratios
+NORM_EACH_CHANNEL = regular_settings['NORM_EACH_CHANNEL'] # Whether to normalize each channel of the data
+RESCALE = regular_settings['RESCALE'] # Whether to rescale the data
+NULL_VAL = regular_settings['NULL_VAL'] # Null value in the data
+# Model architecture and parameters
+MODEL_ARCH = Autoformer
+NUM_NODES = 307
+MODEL_PARAM = {
+    "seq_len": INPUT_LEN,
+    "label_len": INPUT_LEN/2,       # start token length used in decoder
+    "pred_len": OUTPUT_LEN,         # prediction sequence length
+    "moving_avg": 65,                           # window size of moving average. This is a CRUCIAL hyper-parameter.
+    "output_attention": False,
+    "enc_in": NUM_NODES,                        # num nodes
+    "dec_in": NUM_NODES,
+    "c_out": NUM_NODES,
+    "d_model": 512,
+    "embed": "timeF",                           # [timeF, fixed, learned]
+    "dropout": 0.05,
+    "factor": 6,                                # attn factor
+    "n_heads": 8,
+    "d_ff": 2048,
+    "activation": "gelu",
+    "e_layers": 2,                              # num of encoder layers
+    "d_layers": 1,                              # num of decoder layers
+    "num_time_features": 2,                     # number of used time features
+    "time_of_day_size": 288,
+    "day_of_week_size": 7,
+    }
+NUM_EPOCHS = 100
+
+############################## General Configuration ##############################
+CFG = EasyDict()
+# General settings
+CFG.DESCRIPTION = 'An Example Config'
+CFG.GPU_NUM = 1 # Number of GPUs to use (0 for CPU mode)
+# Runner
+CFG.RUNNER = SimpleTimeSeriesForecastingRunner
+
+############################## Dataset Configuration ##############################
+CFG.DATASET = EasyDict()
+# Dataset settings
+CFG.DATASET.NAME = DATA_NAME
+CFG.DATASET.TYPE = TimeSeriesForecastingDataset
+CFG.DATASET.PARAM = EasyDict({
+    'dataset_name': DATA_NAME,
+    'train_val_test_ratio': TRAIN_VAL_TEST_RATIO,
+    'input_len': INPUT_LEN,
+    'output_len': OUTPUT_LEN,
+    # 'mode' is automatically set by the runner
+})
+
+############################## Scaler Configuration ##############################
+CFG.SCALER = EasyDict()
+# Scaler settings
+CFG.SCALER.TYPE = ZScoreScaler # Scaler class
+CFG.SCALER.PARAM = EasyDict({
+    'dataset_name': DATA_NAME,
+    'train_ratio': TRAIN_VAL_TEST_RATIO[0],
+    'norm_each_channel': NORM_EACH_CHANNEL,
+    'rescale': RESCALE,
+})
+
+############################## Model Configuration ##############################
+CFG.MODEL = EasyDict()
+# Model settings
+CFG.MODEL.NAME = MODEL_ARCH.__name__
+CFG.MODEL.ARCH = MODEL_ARCH
+CFG.MODEL.PARAM = MODEL_PARAM
+CFG.MODEL.FORWARD_FEATURES = [0, 1, 2]
+CFG.MODEL.TARGET_FEATURES = [0]
+
+############################## Metrics Configuration ##############################
+
+CFG.METRICS = EasyDict()
+# Metrics settings
+CFG.METRICS.FUNCS = EasyDict({
+                                'MAE': masked_mae,
+                                'MAPE': masked_mape,
+                                'RMSE': masked_rmse
+                            })
+CFG.METRICS.TARGET = 'MAE'
+CFG.METRICS.NULL_VAL = NULL_VAL
+
+############################## Training Configuration ##############################
+CFG.TRAIN = EasyDict()
+CFG.TRAIN.NUM_EPOCHS = NUM_EPOCHS
+CFG.TRAIN.CKPT_SAVE_DIR = os.path.join(
+    'checkpoints',
+    MODEL_ARCH.__name__,
+    '_'.join([DATA_NAME, str(CFG.TRAIN.NUM_EPOCHS), str(INPUT_LEN), str(OUTPUT_LEN)])
+)
+CFG.TRAIN.LOSS = masked_mae
+# Optimizer settings
+CFG.TRAIN.OPTIM = EasyDict()
+CFG.TRAIN.OPTIM.TYPE = "Adam"
+CFG.TRAIN.OPTIM.PARAM = {
+    "lr": 0.0005,
+    "weight_decay": 0.0005,
+}
+# Learning rate scheduler settings
+CFG.TRAIN.LR_SCHEDULER = EasyDict()
+CFG.TRAIN.LR_SCHEDULER.TYPE = "MultiStepLR"
+CFG.TRAIN.LR_SCHEDULER.PARAM = {
+    "milestones": [1, 25, 50],
+    "gamma": 0.5
+}
+CFG.TRAIN.CLIP_GRAD_PARAM = {
+    'max_norm': 5.0
+}
+# Train data loader settings
+CFG.TRAIN.DATA = EasyDict()
+CFG.TRAIN.DATA.BATCH_SIZE = 64
+CFG.TRAIN.DATA.SHUFFLE = True
+
+############################## Validation Configuration ##############################
+CFG.VAL = EasyDict()
+CFG.VAL.INTERVAL = 1
+CFG.VAL.DATA = EasyDict()
+CFG.VAL.DATA.BATCH_SIZE = 64
+
+############################## Test Configuration ##############################
+CFG.TEST = EasyDict()
+CFG.TEST.INTERVAL = 1
+CFG.TEST.DATA = EasyDict()
+CFG.TEST.DATA.BATCH_SIZE = 64
+
+############################## Evaluation Configuration ##############################
+
+CFG.EVAL = EasyDict()
+
+# Evaluation parameters
+CFG.EVAL.HORIZONS = [12, 24, 48, 96, 192, 288, 336]
+CFG.EVAL.USE_GPU = True # Whether to use GPU for evaluation. Default: True
+CFG.TRAIN.EARLY_STOPPING_PATIENCE = 10 #  stopping patience. Default: None. If not specified, the  stopping will not be used.
diff --git a/baselines/Autoformer/PEMS08_LTSF.py b/baselines/Autoformer/PEMS08_LTSF.py
@@ -0,0 +1,156 @@
+import os
+import sys
+from easydict import EasyDict
+sys.path.append(os.path.abspath(__file__ + '/../../..'))
+
+from basicts.metrics import masked_mae, masked_mape, masked_rmse
+from basicts.data import TimeSeriesForecastingDataset
+from basicts.runners import SimpleTimeSeriesForecastingRunner
+from basicts.scaler import ZScoreScaler
+from basicts.utils import get_regular_settings
+
+from .arch import Autoformer
+
+############################## Hot Parameters ##############################
+# Dataset & Metrics configuration
+DATA_NAME = 'PEMS08'  # Dataset name
+regular_settings = get_regular_settings(DATA_NAME)
+# INPUT_LEN = regular_settings['INPUT_LEN']  # Length of input sequence
+# OUTPUT_LEN = regular_settings['OUTPUT_LEN']  # Length of output sequence
+INPUT_LEN = 336 # LTSF
+OUTPUT_LEN = 336 # LTSF
+TRAIN_VAL_TEST_RATIO = regular_settings['TRAIN_VAL_TEST_RATIO']  # Train/Validation/Test split ratios
+NORM_EACH_CHANNEL = regular_settings['NORM_EACH_CHANNEL'] # Whether to normalize each channel of the data
+RESCALE = regular_settings['RESCALE'] # Whether to rescale the data
+NULL_VAL = regular_settings['NULL_VAL'] # Null value in the data
+# Model architecture and parameters
+MODEL_ARCH = Autoformer
+NUM_NODES = 170
+MODEL_PARAM = {
+    "seq_len": INPUT_LEN,
+    "label_len": INPUT_LEN/2,       # start token length used in decoder
+    "pred_len": OUTPUT_LEN,         # prediction sequence length
+    "moving_avg": 65,                           # window size of moving average. This is a CRUCIAL hyper-parameter.
+    "output_attention": False,
+    "enc_in": NUM_NODES,                        # num nodes
+    "dec_in": NUM_NODES,
+    "c_out": NUM_NODES,
+    "d_model": 512,
+    "embed": "timeF",                           # [timeF, fixed, learned]
+    "dropout": 0.05,
+    "factor": 6,                                # attn factor
+    "n_heads": 8,
+    "d_ff": 2048,
+    "activation": "gelu",
+    "e_layers": 2,                              # num of encoder layers
+    "d_layers": 1,                              # num of decoder layers
+    "num_time_features": 2,                     # number of used time features
+    "time_of_day_size": 288,
+    "day_of_week_size": 7,
+    }
+NUM_EPOCHS = 100
+
+############################## General Configuration ##############################
+CFG = EasyDict()
+# General settings
+CFG.DESCRIPTION = 'An Example Config'
+CFG.GPU_NUM = 1 # Number of GPUs to use (0 for CPU mode)
+# Runner
+CFG.RUNNER = SimpleTimeSeriesForecastingRunner
+
+############################## Dataset Configuration ##############################
+CFG.DATASET = EasyDict()
+# Dataset settings
+CFG.DATASET.NAME = DATA_NAME
+CFG.DATASET.TYPE = TimeSeriesForecastingDataset
+CFG.DATASET.PARAM = EasyDict({
+    'dataset_name': DATA_NAME,
+    'train_val_test_ratio': TRAIN_VAL_TEST_RATIO,
+    'input_len': INPUT_LEN,
+    'output_len': OUTPUT_LEN,
+    # 'mode' is automatically set by the runner
+})
+
+############################## Scaler Configuration ##############################
+CFG.SCALER = EasyDict()
+# Scaler settings
+CFG.SCALER.TYPE = ZScoreScaler # Scaler class
+CFG.SCALER.PARAM = EasyDict({
+    'dataset_name': DATA_NAME,
+    'train_ratio': TRAIN_VAL_TEST_RATIO[0],
+    'norm_each_channel': NORM_EACH_CHANNEL,
+    'rescale': RESCALE,
+})
+
+############################## Model Configuration ##############################
+CFG.MODEL = EasyDict()
+# Model settings
+CFG.MODEL.NAME = MODEL_ARCH.__name__
+CFG.MODEL.ARCH = MODEL_ARCH
+CFG.MODEL.PARAM = MODEL_PARAM
+CFG.MODEL.FORWARD_FEATURES = [0, 1, 2]
+CFG.MODEL.TARGET_FEATURES = [0]
+
+############################## Metrics Configuration ##############################
+
+CFG.METRICS = EasyDict()
+# Metrics settings
+CFG.METRICS.FUNCS = EasyDict({
+                                'MAE': masked_mae,
+                                'MAPE': masked_mape,
+                                'RMSE': masked_rmse
+                            })
+CFG.METRICS.TARGET = 'MAE'
+CFG.METRICS.NULL_VAL = NULL_VAL
+
+############################## Training Configuration ##############################
+CFG.TRAIN = EasyDict()
+CFG.TRAIN.NUM_EPOCHS = NUM_EPOCHS
+CFG.TRAIN.CKPT_SAVE_DIR = os.path.join(
+    'checkpoints',
+    MODEL_ARCH.__name__,
+    '_'.join([DATA_NAME, str(CFG.TRAIN.NUM_EPOCHS), str(INPUT_LEN), str(OUTPUT_LEN)])
+)
+CFG.TRAIN.LOSS = masked_mae
+# Optimizer settings
+CFG.TRAIN.OPTIM = EasyDict()
+CFG.TRAIN.OPTIM.TYPE = "Adam"
+CFG.TRAIN.OPTIM.PARAM = {
+    "lr": 0.0005,
+    "weight_decay": 0.0005,
+}
+# Learning rate scheduler settings
+CFG.TRAIN.LR_SCHEDULER = EasyDict()
+CFG.TRAIN.LR_SCHEDULER.TYPE = "MultiStepLR"
+CFG.TRAIN.LR_SCHEDULER.PARAM = {
+    "milestones": [1, 25, 50],
+    "gamma": 0.5
+}
+CFG.TRAIN.CLIP_GRAD_PARAM = {
+    'max_norm': 5.0
+}
+# Train data loader settings
+CFG.TRAIN.DATA = EasyDict()
+CFG.TRAIN.DATA.BATCH_SIZE = 64
+CFG.TRAIN.DATA.SHUFFLE = True
+
+############################## Validation Configuration ##############################
+CFG.VAL = EasyDict()
+CFG.VAL.INTERVAL = 1
+CFG.VAL.DATA = EasyDict()
+CFG.VAL.DATA.BATCH_SIZE = 64
+
+############################## Test Configuration ##############################
+CFG.TEST = EasyDict()
+CFG.TEST.INTERVAL = 1
+CFG.TEST.DATA = EasyDict()
+CFG.TEST.DATA.BATCH_SIZE = 64
+
+############################## Evaluation Configuration ##############################
+
+CFG.EVAL = EasyDict()
+
+# Evaluation parameters
+CFG.EVAL.HORIZONS = [12, 24, 48, 96, 192, 288, 336]
+CFG.EVAL.USE_GPU = True # Whether to use GPU for evaluation. Default: True
+CFG.TRAIN.EARLY_STOPPING_PATIENCE = 10 #  stopping patience. Default: None. If not specified, the  stopping will not be used.
diff --git a/baselines/Autoformer/run.sh b/baselines/Autoformer/run.sh