diff --git a/pypots/imputation/__init__.py b/pypots/imputation/__init__.py index 4620eb4c..b6cc4c3f 100644 --- a/pypots/imputation/__init__.py +++ b/pypots/imputation/__init__.py @@ -14,6 +14,7 @@ from .transformer import Transformer from .itransformer import iTransformer from .nonstationary_transformer import NonstationaryTransformer +from .pyraformer import Pyraformer from .timesnet import TimesNet from .etsformer import ETSformer from .fedformer import FEDformer @@ -47,6 +48,7 @@ "Informer", "Autoformer", "NonstationaryTransformer", + "Pyraformer", "BRITS", "MRNN", "GPVAE", diff --git a/pypots/imputation/nonstationary_transformer/model.py b/pypots/imputation/nonstationary_transformer/model.py index 1e5f11f2..9786ccd7 100644 --- a/pypots/imputation/nonstationary_transformer/model.py +++ b/pypots/imputation/nonstationary_transformer/model.py @@ -24,7 +24,7 @@ class NonstationaryTransformer(BaseNNImputer): """The PyTorch implementation of the Nonstationary-Transformer model. - NonstationaryTransformer is originally proposed by Wu et al. in :cite:`liu2022nonstationary`. + NonstationaryTransformer is originally proposed by Liu et al. in :cite:`liu2022nonstationary`. Parameters ---------- diff --git a/pypots/imputation/pyraformer/__init__.py b/pypots/imputation/pyraformer/__init__.py new file mode 100644 index 00000000..56a3bcac --- /dev/null +++ b/pypots/imputation/pyraformer/__init__.py @@ -0,0 +1,24 @@ +""" +The package of the partially-observed time-series imputation model Pyraformer. + +Refer to the paper +`Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu, and Schahram Dustdar. +"Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting". +International Conference on Learning Representations. 2022. +`_ + +Notes +----- +This implementation is inspired by the official one https://github.com/ant-research/Pyraformer + +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + + +from .model import Pyraformer + +__all__ = [ + "Pyraformer", +] diff --git a/pypots/imputation/pyraformer/core.py b/pypots/imputation/pyraformer/core.py new file mode 100644 index 00000000..3087d90a --- /dev/null +++ b/pypots/imputation/pyraformer/core.py @@ -0,0 +1,86 @@ +""" +The core wrapper assembles the submodules of Pyraformer imputation model +and takes over the forward progress of the algorithm. +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + +import torch.nn as nn + +from ...nn.modules.pyraformer import PyraformerEncoder +from ...nn.modules.saits import SaitsLoss, SaitsEmbedding + + +class _Pyraformer(nn.Module): + def __init__( + self, + n_steps: int, + n_features: int, + n_layers: int, + d_model: int, + n_heads: int, + d_ffn: int, + dropout: float, + attn_dropout: float, + window_size: list, + inner_size: int, + ORT_weight: float = 1, + MIT_weight: float = 1, + ): + super().__init__() + + self.saits_embedding = SaitsEmbedding( + n_features * 2, + d_model, + with_pos=False, + dropout=dropout, + ) + self.encoder = PyraformerEncoder( + n_steps, + n_layers, + d_model, + n_heads, + d_ffn, + dropout, + attn_dropout, + window_size, + inner_size, + ) + + # for the imputation task, the output dim is the same as input dim + self.output_projection = nn.Linear((len(window_size) + 1) * d_model, n_features) + self.saits_loss_func = SaitsLoss(ORT_weight, MIT_weight) + + def forward(self, inputs: dict, training: bool = True) -> dict: + X, missing_mask = inputs["X"], inputs["missing_mask"] + + # WDU: the original Pyraformer paper isn't proposed for imputation task. Hence the model doesn't take + # the missing mask into account, which means, in the process, the model doesn't know which part of + # the input data is missing, and this may hurt the model's imputation performance. Therefore, I apply the + # SAITS embedding method to project the concatenation of features and masks into a hidden space, as well as + # the output layers to project back from the hidden space to the original space. + enc_out = self.saits_embedding(X, missing_mask) + + # Pyraformer encoder processing + enc_out, attns = self.encoder(enc_out) + # project back the original data space + reconstruction = self.output_projection(enc_out) + + imputed_data = missing_mask * X + (1 - missing_mask) * reconstruction + results = { + "imputed_data": imputed_data, + } + + # if in training mode, return results with losses + if training: + X_ori, indicating_mask = inputs["X_ori"], inputs["indicating_mask"] + loss, ORT_loss, MIT_loss = self.saits_loss_func( + reconstruction, X_ori, missing_mask, indicating_mask + ) + results["ORT_loss"] = ORT_loss + results["MIT_loss"] = MIT_loss + # `loss` is always the item for backward propagating to update the model + results["loss"] = loss + + return results diff --git a/pypots/imputation/pyraformer/data.py b/pypots/imputation/pyraformer/data.py new file mode 100644 index 00000000..0ed0b31b --- /dev/null +++ b/pypots/imputation/pyraformer/data.py @@ -0,0 +1,24 @@ +""" +Dataset class for Pyraformer. +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + +from typing import Union + +from ..saits.data import DatasetForSAITS + + +class DatasetForPyraformer(DatasetForSAITS): + """Actually Pyraformer uses the same data strategy as SAITS, needs MIT for training.""" + + def __init__( + self, + data: Union[dict, str], + return_X_ori: bool, + return_y: bool, + file_type: str = "hdf5", + rate: float = 0.2, + ): + super().__init__(data, return_X_ori, return_y, file_type, rate) diff --git a/pypots/imputation/pyraformer/model.py b/pypots/imputation/pyraformer/model.py new file mode 100644 index 00000000..757e96f3 --- /dev/null +++ b/pypots/imputation/pyraformer/model.py @@ -0,0 +1,326 @@ +""" +The implementation of Pyraformer 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 torch.utils.data import DataLoader + +from .core import _Pyraformer +from .data import DatasetForPyraformer +from ..base import BaseNNImputer +from ...data.checking import key_in_data_set +from ...data.dataset import BaseDataset +from ...optim.adam import Adam +from ...optim.base import Optimizer + + +class Pyraformer(BaseNNImputer): + """The PyTorch implementation of the Pyraformer model. + Pyraformer is originally proposed by Liu et al. in :cite:`liu2022pyraformer`. + + 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 Pyraformer model. + + d_model : + The dimension of the model. + + n_heads : + The number of heads in each layer of Pyraformer. + + d_ffn : + The dimension of the feed-forward network. + + window_size : + The downsample window size in pyramidal attention. + + inner_size : + The size of neighbour attention + + dropout : + The dropout rate for the model. + + attn_dropout : + The dropout rate for the attention mechanism. + + ORT_weight : + The weight for the ORT loss, the same as SAITS. + + MIT_weight : + The weight for the MIT loss, the same as SAITS. + + 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_ffn: int, + window_size: list, + inner_size: int, + dropout: float = 0, + attn_dropout: float = 0, + ORT_weight: float = 1, + MIT_weight: float = 1, + batch_size: int = 32, + epochs: int = 100, + patience: 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, + ) + + self.n_steps = n_steps + self.n_features = n_features + # model hype-parameters + self.n_heads = n_heads + self.n_layers = n_layers + self.d_model = d_model + self.d_ffn = d_ffn + self.dropout = dropout + self.attn_dropout = attn_dropout + self.window_size = window_size + self.inner_size = inner_size + self.ORT_weight = ORT_weight + self.MIT_weight = MIT_weight + + # set up the model + self.model = _Pyraformer( + self.n_steps, + self.n_features, + self.n_layers, + self.d_model, + self.n_heads, + self.d_ffn, + self.dropout, + self.attn_dropout, + self.window_size, + self.inner_size, + 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 + + 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 = DatasetForPyraformer( + 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 = DatasetForPyraformer( + 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) + + def predict( + self, + test_set: Union[dict, str], + file_type: str = "hdf5", + ) -> dict: + """Make predictions for the input data with the trained model. + + Parameters + ---------- + test_set : dict or str + The dataset for model validating, should be a dictionary including keys as 'X', + or a path string locating a data file supported by PyPOTS (e.g. h5 file). + If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features], + which is time-series data for validating, can contain missing values, and y should be array-like of shape + [n_samples], which is classification labels of X. + If it is a path string, the path should point to a data file, e.g. a h5 file, which contains + key-value pairs like a dict, and it has to include keys as 'X' and 'y'. + + file_type : + The type of the given file if test_set is a path string. + + Returns + ------- + file_type : + The dictionary containing the clustering results and latent variables if necessary. + + """ + # Step 1: wrap the input data with classes Dataset and DataLoader + 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 = [] + + # Step 2: process the data with the model + 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) + imputation_collector.append(results["imputed_data"]) + + # Step 3: output collection and return + imputation = torch.cat(imputation_collector).cpu().detach().numpy() + result_dict = { + "imputation": imputation, + } + return result_dict + + 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"] diff --git a/pypots/imputation/transformer/model.py b/pypots/imputation/transformer/model.py index 76d04fac..d7d59097 100644 --- a/pypots/imputation/transformer/model.py +++ b/pypots/imputation/transformer/model.py @@ -63,7 +63,7 @@ class Transformer(BaseNNImputer): The dropout rate for all fully-connected layers in the model. attn_dropout : - The dropout rate for DMSA. + The dropout rate for the attention mechanism. ORT_weight : The weight for the ORT loss. diff --git a/pypots/nn/modules/pyraformer/__init__.py b/pypots/nn/modules/pyraformer/__init__.py new file mode 100644 index 00000000..f20b9cc9 --- /dev/null +++ b/pypots/nn/modules/pyraformer/__init__.py @@ -0,0 +1,24 @@ +""" +The package including the modules of Pyraformer. + +Refer to the paper +`Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu, and Schahram Dustdar. +"Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting". +International Conference on Learning Representations. 2022. +`_ + +Notes +----- +This implementation is inspired by the official one https://github.com/ant-research/Pyraformer + +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + + +from .autoencoder import PyraformerEncoder + +__all__ = [ + "PyraformerEncoder", +] diff --git a/pypots/nn/modules/pyraformer/autoencoder.py b/pypots/nn/modules/pyraformer/autoencoder.py new file mode 100644 index 00000000..df2d455a --- /dev/null +++ b/pypots/nn/modules/pyraformer/autoencoder.py @@ -0,0 +1,73 @@ +""" + +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + +from typing import Optional, Tuple, Union + +import torch +import torch.nn as nn + +from .layers import get_mask, refer_points, Bottleneck_Construct +from ..transformer.attention import ScaledDotProductAttention +from ..transformer.layers import TransformerEncoderLayer + + +class PyraformerEncoder(nn.Module): + def __init__( + self, + n_steps: int, + n_layers: int, + d_model: int, + n_heads: int, + d_ffn: int, + dropout: float, + attn_dropout: float, + window_size: list, + inner_size: int, + ): + super().__init__() + + d_bottleneck = d_model // 4 + d_k = d_v = d_model // n_heads + + self.mask, self.all_size = get_mask(n_steps, window_size, inner_size) + self.indexes = refer_points(self.all_size, window_size) + self.layer_stack = nn.ModuleList( + [ + TransformerEncoderLayer( + ScaledDotProductAttention(d_k**0.5, attn_dropout), + d_model, + n_heads, + d_k, + d_v, + d_ffn, + dropout=dropout, + ) + for _ in range(n_layers) + ] + ) # in the official code, they only use the naive pyramid attention + self.conv_layers = Bottleneck_Construct(d_model, window_size, d_bottleneck) + + def forward( + self, + x: torch.Tensor, + src_mask: Optional[torch.Tensor] = None, + ) -> Union[torch.Tensor, Tuple[torch.Tensor, list]]: + + mask = self.mask.repeat(len(x), 1, 1).to(x.device) + x = self.conv_layers(x) + + attn_weights_collector = [] + for layer in self.layer_stack: + x, attn_weights = layer(x, mask) + attn_weights_collector.append(attn_weights) + + indexes = self.indexes.repeat(x.size(0), 1, 1, x.size(2)).to(x.device) + indexes = indexes.view(x.size(0), -1, x.size(2)) + all_enc = torch.gather(x, 1, indexes) + enc_output = all_enc.view(x.size(0), self.all_size[0], -1) + + return enc_output, attn_weights_collector diff --git a/pypots/nn/modules/pyraformer/layers.py b/pypots/nn/modules/pyraformer/layers.py new file mode 100644 index 00000000..0fc61e90 --- /dev/null +++ b/pypots/nn/modules/pyraformer/layers.py @@ -0,0 +1,130 @@ +""" + +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + +import math + +import torch +import torch.fft +import torch.nn as nn + + +def get_mask(input_size, window_size, inner_size): + """Get the attention mask of PAM-Naive""" + # Get the size of all layers + all_size = [input_size] + for i in range(len(window_size)): + layer_size = math.floor(all_size[i] / window_size[i]) + all_size.append(layer_size) + + seq_length = sum(all_size) + mask = torch.zeros(seq_length, seq_length) + + # get intra-scale mask + inner_window = inner_size // 2 + for layer_idx in range(len(all_size)): + start = sum(all_size[:layer_idx]) + for i in range(start, start + all_size[layer_idx]): + left_side = max(i - inner_window, start) + right_side = min(i + inner_window + 1, start + all_size[layer_idx]) + mask[i, left_side:right_side] = 1 + + # get inter-scale mask + for layer_idx in range(1, len(all_size)): + start = sum(all_size[:layer_idx]) + for i in range(start, start + all_size[layer_idx]): + left_side = (start - all_size[layer_idx - 1]) + (i - start) * window_size[ + layer_idx - 1 + ] + if i == (start + all_size[layer_idx] - 1): + right_side = start + else: + right_side = (start - all_size[layer_idx - 1]) + ( + i - start + 1 + ) * window_size[layer_idx - 1] + mask[i, left_side:right_side] = 1 + mask[left_side:right_side, i] = 1 + + mask = (1 - mask).bool() + + return mask, all_size + + +def refer_points(all_sizes, window_size): + """Gather features from PAM's pyramid sequences""" + input_size = all_sizes[0] + indexes = torch.zeros(input_size, len(all_sizes)) + + for i in range(input_size): + indexes[i][0] = i + former_index = i + for j in range(1, len(all_sizes)): + start = sum(all_sizes[:j]) + inner_layer_idx = former_index - (start - all_sizes[j - 1]) + former_index = start + min( + inner_layer_idx // window_size[j - 1], all_sizes[j] - 1 + ) + indexes[i][j] = former_index + + indexes = indexes.unsqueeze(0).unsqueeze(3) + + return indexes.long() + + +class ConvLayer(nn.Module): + def __init__(self, c_in, window_size): + super().__init__() + self.downConv = nn.Conv1d( + in_channels=c_in, + out_channels=c_in, + kernel_size=window_size, + stride=window_size, + ) + self.norm = nn.BatchNorm1d(c_in) + self.activation = nn.ELU() + + def forward(self, x): + x = self.downConv(x) + x = self.norm(x) + x = self.activation(x) + return x + + +class Bottleneck_Construct(nn.Module): + """Bottleneck convolution CSCM""" + + def __init__(self, d_model, window_size, d_inner): + super().__init__() + if not isinstance(window_size, list): + self.conv_layers = nn.ModuleList( + [ + ConvLayer(d_inner, window_size), + ConvLayer(d_inner, window_size), + ConvLayer(d_inner, window_size), + ] + ) + else: + self.conv_layers = [] + for i in range(len(window_size)): + self.conv_layers.append(ConvLayer(d_inner, window_size[i])) + self.conv_layers = nn.ModuleList(self.conv_layers) + self.up = nn.Linear(d_inner, d_model) + self.down = nn.Linear(d_model, d_inner) + self.norm = nn.LayerNorm(d_model) + + def forward(self, enc_input): + temp_input = self.down(enc_input).permute(0, 2, 1) + all_inputs = [] + for i in range(len(self.conv_layers)): + temp_input = self.conv_layers[i](temp_input) + all_inputs.append(temp_input) + + all_inputs = torch.cat(all_inputs, dim=2).transpose(1, 2) + all_inputs = self.up(all_inputs) + all_inputs = torch.cat([enc_input, all_inputs], dim=1) + + all_inputs = self.norm(all_inputs) + return all_inputs diff --git a/tests/imputation/pyraformer.py b/tests/imputation/pyraformer.py new file mode 100644 index 00000000..64629647 --- /dev/null +++ b/tests/imputation/pyraformer.py @@ -0,0 +1,131 @@ +""" +Test cases for Pyraformer imputation model. +""" + +# Created by Wenjie Du +# License: BSD-3-Clause + + +import os.path +import unittest + +import numpy as np +import pytest + +from pypots.imputation import Pyraformer +from pypots.optim import Adam +from pypots.utils.logging import logger +from pypots.utils.metrics import calc_mse +from tests.global_test_config import ( + DATA, + EPOCHS, + DEVICE, + TRAIN_SET, + VAL_SET, + TEST_SET, + GENERAL_H5_TRAIN_SET_PATH, + GENERAL_H5_VAL_SET_PATH, + GENERAL_H5_TEST_SET_PATH, + RESULT_SAVING_DIR_FOR_IMPUTATION, + check_tb_and_model_checkpoints_existence, +) + + +class TestPyraformer(unittest.TestCase): + logger.info("Running tests for an imputation model Pyraformer...") + + # set the log and model saving path + saving_path = os.path.join(RESULT_SAVING_DIR_FOR_IMPUTATION, "Pyraformer") + model_save_name = "saved_pyraformer_model.pypots" + + # initialize an Adam optimizer + optimizer = Adam(lr=0.001, weight_decay=1e-5) + + # initialize a Pyraformer model + pyraformer = Pyraformer( + DATA["n_steps"], + DATA["n_features"], + n_layers=2, + d_model=32, + n_heads=2, + d_ffn=32, + window_size=[2, 2], + inner_size=3, + dropout=0, + attn_dropout=0, + epochs=EPOCHS, + saving_path=saving_path, + optimizer=optimizer, + device=DEVICE, + ) + + @pytest.mark.xdist_group(name="imputation-pyraformer") + def test_0_fit(self): + self.pyraformer.fit(TRAIN_SET, VAL_SET) + + @pytest.mark.xdist_group(name="imputation-pyraformer") + def test_1_impute(self): + imputation_results = self.pyraformer.predict(TEST_SET) + assert not np.isnan( + imputation_results["imputation"] + ).any(), "Output still has missing values after running impute()." + + test_MSE = calc_mse( + imputation_results["imputation"], + DATA["test_X_ori"], + DATA["test_X_indicating_mask"], + ) + logger.info(f"Pyraformer test_MSE: {test_MSE}") + + @pytest.mark.xdist_group(name="imputation-pyraformer") + def test_2_parameters(self): + assert hasattr(self.pyraformer, "model") and self.pyraformer.model is not None + + assert ( + hasattr(self.pyraformer, "optimizer") + and self.pyraformer.optimizer is not None + ) + + assert hasattr(self.pyraformer, "best_loss") + self.assertNotEqual(self.pyraformer.best_loss, float("inf")) + + assert ( + hasattr(self.pyraformer, "best_model_dict") + and self.pyraformer.best_model_dict is not None + ) + + @pytest.mark.xdist_group(name="imputation-pyraformer") + def test_3_saving_path(self): + # whether the root saving dir exists, which should be created by save_log_into_tb_file + assert os.path.exists( + self.saving_path + ), f"file {self.saving_path} does not exist" + + # check if the tensorboard file and model checkpoints exist + check_tb_and_model_checkpoints_existence(self.pyraformer) + + # save the trained model into file, and check if the path exists + saved_model_path = os.path.join(self.saving_path, self.model_save_name) + self.pyraformer.save(saved_model_path) + + # test loading the saved model, not necessary, but need to test + self.pyraformer.load(saved_model_path) + + @pytest.mark.xdist_group(name="imputation-pyraformer") + def test_4_lazy_loading(self): + self.pyraformer.fit(GENERAL_H5_TRAIN_SET_PATH, GENERAL_H5_VAL_SET_PATH) + imputation_results = self.pyraformer.predict(GENERAL_H5_TEST_SET_PATH) + assert not np.isnan( + imputation_results["imputation"] + ).any(), "Output still has missing values after running impute()." + + test_MSE = calc_mse( + imputation_results["imputation"], + DATA["test_X_ori"], + DATA["test_X_indicating_mask"], + ) + logger.info(f"Lazy-loading Pyraformer test_MSE: {test_MSE}") + + +if __name__ == "__main__": + unittest.main()