Source code for pypots.imputation.transformer.model

The implementation of Transformer for the partially-observed time-series imputation task.


# Created by Wenjie Du <>
# License: BSD-3-Clause

from typing import Union, Optional

import numpy as np
import torch
from import DataLoader

from .core import _Transformer
from .data import DatasetForTransformer
from ..base import BaseNNImputer
from import BaseDataset
from import key_in_data_set
from ...optim.adam import Adam
from ...optim.base import Optimizer
from ...utils.logging import logger

[docs] class Transformer(BaseNNImputer): """The PyTorch implementation of the Transformer model. Transformer is originally proposed by Vaswani et al. in :cite:`vaswani2017Transformer`, and gets re-implemented as a time-series imputation model by Du et al. in :cite:`du2023SAITS`. Here you should refer to :cite:`du2023SAITS` for details about this Transformer imputation model. Parameters ---------- n_steps : The number of time steps in the time-series data sample. n_features : The number of features in the time-series data sample. n_layers : The number of layers in the 1st and 2nd DMSA blocks in the SAITS model. d_model : The dimension of the model's backbone. It is the input dimension of the multi-head self-attention layers. n_heads : The number of heads in the multi-head self-attention mechanism. ``d_model`` must be divisible by ``n_heads``, and the result should be equal to ``d_k``. d_k : The dimension of the `keys` (K) and the `queries` (Q) in the DMSA mechanism. ``d_k`` should be the result of ``d_model`` divided by ``n_heads``. Although ``d_k`` can be directly calculated with given ``d_model`` and ``n_heads``, we want it be explicitly given together with ``d_v`` by users to ensure users be aware of them and to avoid any potential mistakes. d_v : The dimension of the `values` (V) in the DMSA mechanism. d_ffn : The dimension of the layer in the Feed-Forward Networks (FFN). dropout : The dropout rate for all fully-connected layers in the model. attn_dropout : The dropout rate for the attention mechanism. ORT_weight : The weight for the ORT loss. MIT_weight : The weight for the MIT loss. batch_size : The batch size for training and evaluating the model. epochs : The number of epochs for training the model. patience : The patience for the early-stopping mechanism. Given a positive integer, the training process will be stopped when the model does not perform better after that number of epochs. Leaving it default as None will disable the early-stopping. optimizer : The optimizer for model training. If not given, will use a default Adam optimizer. num_workers : The number of subprocesses to use for data loading. `0` means data loading will be in the main process, i.e. there won't be subprocesses. device : The device for the model to run on. It can be a string, a :class:`torch.device` object, or a list of them. If not given, will try to use CUDA devices first (will use the default CUDA device if there are multiple), then CPUs, considering CUDA and CPU are so far the main devices for people to train ML models. If given a list of devices, e.g. ['cuda:0', 'cuda:1'], or [torch.device('cuda:0'), torch.device('cuda:1')] , the model will be parallely trained on the multiple devices (so far only support parallel training on CUDA devices). Other devices like Google TPU and Apple Silicon accelerator MPS may be added in the future. saving_path : The path for automatically saving model checkpoints and tensorboard files (i.e. loss values recorded during training into a tensorboard file). Will not save if not given. model_saving_strategy : The strategy to save model checkpoints. It has to be one of [None, "best", "better", "all"]. No model will be saved when it is set as None. The "best" strategy will only automatically save the best model after the training finished. The "better" strategy will automatically save the model during training whenever the model performs better than in previous epochs. The "all" strategy will save every model after each epoch training. """ def __init__( self, n_steps: int, n_features: int, n_layers: int, d_model: int, n_heads: int, d_k: int, d_v: int, d_ffn: int, dropout: float = 0, attn_dropout: float = 0, ORT_weight: int = 1, MIT_weight: int = 1, batch_size: int = 32, epochs: int = 100, patience: Optional[int] = None, optimizer: Optional[Optimizer] = Adam(), num_workers: int = 0, device: Optional[Union[str, torch.device, list]] = None, saving_path: str = None, model_saving_strategy: Optional[str] = "best", ): super().__init__( batch_size, epochs, patience, num_workers, device, saving_path, model_saving_strategy, ) if d_model != n_heads * d_k: logger.warning( "‼️ d_model must = n_heads * d_k, it should be divisible by n_heads " f"and the result should be equal to d_k, but got d_model={d_model}, n_heads={n_heads}, d_k={d_k}" ) d_model = n_heads * d_k logger.warning( f"⚠️ d_model is reset to {d_model} = n_heads ({n_heads}) * d_k ({d_k})" ) self.n_steps = n_steps self.n_features = n_features # model hype-parameters self.n_layers = n_layers self.d_model = d_model self.d_ffn = d_ffn self.n_heads = n_heads self.d_k = d_k self.d_v = d_v self.dropout = dropout self.attn_dropout = attn_dropout self.ORT_weight = ORT_weight self.MIT_weight = MIT_weight # set up the model self.model = _Transformer( self.n_steps, self.n_features, self.n_layers, self.d_model, self.n_heads, self.d_k, self.d_v, self.d_ffn, self.dropout, self.attn_dropout, self.ORT_weight, self.MIT_weight, ) self._send_model_to_given_device() self._print_model_size() # set up the optimizer self.optimizer = optimizer self.optimizer.init_optimizer(self.model.parameters()) def _assemble_input_for_training(self, data: list) -> dict: ( indices, X, missing_mask, X_ori, indicating_mask, ) = self._send_data_to_given_device(data) inputs = { "X": X, "missing_mask": missing_mask, "X_ori": X_ori, "indicating_mask": indicating_mask, } return inputs def _assemble_input_for_validating(self, data: list) -> dict: return self._assemble_input_for_training(data) def _assemble_input_for_testing(self, data: list) -> dict: indices, X, missing_mask = self._send_data_to_given_device(data) inputs = { "X": X, "missing_mask": missing_mask, } return inputs
[docs] def fit( self, train_set: Union[dict, str], val_set: Optional[Union[dict, str]] = None, file_type: str = "hdf5", ) -> None: # Step 1: wrap the input data with classes Dataset and DataLoader training_set = DatasetForTransformer( train_set, return_X_ori=False, return_y=False, file_type=file_type ) training_loader = DataLoader( training_set, batch_size=self.batch_size, shuffle=True, num_workers=self.num_workers, ) val_loader = None if val_set is not None: if not key_in_data_set("X_ori", val_set): raise ValueError("val_set must contain 'X_ori' for model validation.") val_set = DatasetForTransformer( val_set, return_X_ori=True, return_y=False, file_type=file_type ) val_loader = DataLoader( val_set, batch_size=self.batch_size, shuffle=False, num_workers=self.num_workers, ) # Step 2: train the model and freeze it self._train_model(training_loader, val_loader) self.model.load_state_dict(self.best_model_dict) self.model.eval() # set the model as eval status to freeze it. # Step 3: save the model if necessary self._auto_save_model_if_necessary(confirm_saving=True)
[docs] def predict( self, test_set: Union[dict, str], file_type: str = "hdf5", ) -> dict: self.model.eval() # set the model as eval status to freeze it. test_set = BaseDataset( test_set, return_X_ori=False, return_X_pred=False, return_y=False, file_type=file_type, ) test_loader = DataLoader( test_set, batch_size=self.batch_size, shuffle=False, num_workers=self.num_workers, ) imputation_collector = [] with torch.no_grad(): for idx, data in enumerate(test_loader): inputs = self._assemble_input_for_testing(data) results = self.model.forward(inputs, training=False) imputed_data = results["imputed_data"] imputation_collector.append(imputed_data) imputation = result_dict = { "imputation": imputation, } return result_dict
[docs] def impute( self, test_set: Union[dict, str], file_type: str = "hdf5", ) -> np.ndarray: """Impute missing values in the given data with the trained model. Parameters ---------- test_set : The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps), n_features], or a path string locating a data file, e.g. h5 file. file_type : The type of the given file if X is a path string. Returns ------- array-like, shape [n_samples, sequence length (n_steps), n_features], Imputed data. """ result_dict = self.predict(test_set, file_type=file_type) return result_dict["imputation"]