Merge branch dev into branch (refactor)random_walk

.pre-commit-config.yaml

@@ -1,23 +1,26 @@
 repos:
     # hooks for checking files
     -   repo: https://github.com/pre-commit/pre-commit-hooks
-        rev: v4.4.0
+        rev: v4.6.0
         hooks:
             -   id: trailing-whitespace
             -   id: end-of-file-fixer
             -   id: check-yaml
 
     # hooks for linting code
     -   repo: https://github.com/psf/black
-        rev: 22.10.0
+        rev: 24.8.0
         hooks:
             -   id: black
+                args: [
+                    --line-length=120, # refer to pyproject.toml
+                ]
 
     -   repo: https://github.com/PyCQA/flake8
-        rev: 6.0.0
+        rev: 7.1.1
         hooks:
             -   id: flake8
                 args: [
                     --max-line-length=120, # refer to pyproject.toml
-                    --extend-ignore=E203, # why ignore E203? Refer to https://github.com/PyCQA/pycodestyle/issues/373
+                    --extend-ignore=E203,E231
                 ]

docs/conf.py

@@ -108,8 +108,7 @@
     html_context["READTHEDOCS"] = True
 
 html_favicon = (
-    "https://raw.githubusercontent.com/"
-    "PyPOTS/pypots.github.io/main/static/figs/pypots_logos/PyPOTS/logo_FFBG.svg"
+    "https://raw.githubusercontent.com/PyPOTS/pypots.github.io/main/static/figs/pypots_logos/PyPOTS/logo_FFBG.svg"
 )
 
 html_sidebars = {

docs/index.rst

@@ -133,10 +133,16 @@ The paper references are all listed at the bottom of this readme file.
 +----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
 | Type           | Algorithm                                                 | IMPU | FORE | CLAS | CLUS | ANOD | Year - Venue          |
 +================+===========================================================+======+======+======+======+======+=======================+
-| Neural Net     | ImputeFormer      :cite:`nie2024imputeformer`             |  ✅  |      |      |      |      | ``2024 - KDD``        |
+| Neural Net     | TEFN🧑‍🔧           :cite:`zhan2024tefn`                  |  ✅  |      |      |      |      | ``2024 - arXiv``      |
++----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
+| Neural Net     | TimeMixer      :cite:`wang2024timemixer`                  |  ✅  |      |      |      |      | ``2024 - ICLR``       |
 +----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
 | Neural Net     | iTransformer🧑‍🔧 :cite:`liu2024itransformer`             |  ✅  |      |      |      |      | ``2024 - ICLR``       |
 +----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
+| Neural Net     | ModernTCN :cite:`luo2024moderntcn`                        |  ✅  |      |      |      |      | ``2024 - ICLR``       |
++----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
+| Neural Net     | ImputeFormer      :cite:`nie2024imputeformer`             |  ✅  |      |      |      |      | ``2024 - KDD``        |
++----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
 | Neural Net     | SAITS :cite:`du2023SAITS`                                 |  ✅  |      |      |      |      | ``2023 - ESWA``       |
 +----------------+-----------------------------------------------------------+------+------+------+------+------+-----------------------+
 | Neural Net     | FreTS🧑‍🔧 :cite:`yi2023frets`                            |  ✅  |      |      |      |      | ``2023 - NeurIPS``    |
@@ -333,7 +339,7 @@ By committing your code, you'll
    `pypots/imputation/template <https://github.com/WenjieDu/PyPOTS/tree/main/pypots/imputation/template>`_) to quickly start;
 2. become one of `PyPOTS contributors <https://github.com/WenjieDu/PyPOTS/graphs/contributors>`_ and
    be listed as a volunteer developer `on the PyPOTS website <https://pypots.com/about/#volunteer-developers>`_;
-3. get mentioned in our `release notes <https://github.com/WenjieDu/PyPOTS/releases>`_;
+3. get mentioned in PyPOTS `release notes <https://github.com/WenjieDu/PyPOTS/releases>`_;
 
 You can also contribute to PyPOTS by simply staring🌟 this repo to help more people notice it.
 Your star is your recognition to PyPOTS, and it matters!

docs/pypots.imputation.rst

@@ -19,6 +19,24 @@ pypots.imputation.transformer
    :show-inheritance:
    :inherited-members:
 
+pypots.imputation.timemixer
+------------------------------------
+
+.. automodule:: pypots.imputation.timemixer
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :inherited-members:
+
+pypots.imputation.moderntcn
+------------------------------------
+
+.. automodule:: pypots.imputation.moderntcn
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :inherited-members:
+
 pypots.imputation.imputeformer
 ------------------------------------
 

docs/references.bib

@@ -763,3 +763,10 @@ @article{bai2018tcn
 journal={arXiv preprint arXiv:1803.01271},
 year={2018}
 }
+
+@article{zhan2024tefn,
+  title={Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting},
+  author={Zhan, Tianxiang and He, Yuanpeng and Li, Zhen and Deng, Yong},
+  journal={arXiv preprint arXiv:2405.06419},
+  year={2024}
+}

pypots/base.py

@@ -106,9 +106,7 @@ def _setup_device(self, device: Union[None, str, torch.device, list]) -> None:
                 self.device = device
             elif isinstance(device, list):
                 if len(device) == 0:
-                    raise ValueError(
-                        "The list of devices should have at least 1 device, but got 0."
-                    )
+                    raise ValueError("The list of devices should have at least 1 device, but got 0.")
                 elif len(device) == 1:
                     return self._setup_device(device[0])
                 # parallely training on multiple CUDA devices
@@ -179,18 +177,14 @@ def _setup_path(self, saving_path) -> None:
             logger.info(f"Model files will be saved to {self.saving_path}")
             logger.info(f"Tensorboard file will be saved to {tb_saving_path}")
         else:
-            logger.warning(
-                "‼️ saving_path not given. Model files and tensorboard file will not be saved."
-            )
+            logger.warning("‼️ saving_path not given. Model files and tensorboard file will not be saved.")
 
     def _send_model_to_given_device(self) -> None:
         if isinstance(self.device, list):
             # parallely training on multiple devices
             self.model = torch.nn.DataParallel(self.model, device_ids=self.device)
             self.model = self.model.cuda()
-            logger.info(
-                f"Model has been allocated to the given multiple devices: {self.device}"
-            )
+            logger.info(f"Model has been allocated to the given multiple devices: {self.device}")
         else:
             self.model = self.model.to(self.device)
 
@@ -291,9 +285,7 @@ def save(
 
         if os.path.exists(saving_path):
             if overwrite:
-                logger.warning(
-                    f"‼️ File {saving_path} exists. Argument `overwrite` is True. Overwriting now..."
-                )
+                logger.warning(f"‼️ File {saving_path} exists. Argument `overwrite` is True. Overwriting now...")
             else:
                 logger.error(
                     f"❌ File {saving_path} exists. Saving operation aborted. "
@@ -309,9 +301,7 @@ def save(
                 torch.save(self.model, saving_path)
             logger.info(f"Saved the model to {saving_path}")
         except Exception as e:
-            raise RuntimeError(
-                f'Failed to save the model to "{saving_path}" because of the below error! \n{e}'
-            )
+            raise RuntimeError(f'Failed to save the model to "{saving_path}" because of the below error! \n{e}')
 
     def load(self, path: str) -> None:
         """Load the saved model from a disk file.
@@ -519,9 +509,7 @@ def __init__(
 
     def _print_model_size(self) -> None:
         """Print the number of trainable parameters in the initialized NN model."""
-        self.num_params = sum(
-            p.numel() for p in self.model.parameters() if p.requires_grad
-        )
+        self.num_params = sum(p.numel() for p in self.model.parameters() if p.requires_grad)
         logger.info(
             f"{self.__class__.__name__} initialized with the given hyperparameters, "
             f"the number of trainable parameters: {self.num_params:,}"

pypots/classification/base.py

@@ -313,9 +313,7 @@ def _train_model(
                         for idx, data in enumerate(val_loader):
                             inputs = self._assemble_input_for_validating(data)
                             results = self.model.forward(inputs)
-                            epoch_val_loss_collector.append(
-                                results["loss"].sum().item()
-                            )
+                            epoch_val_loss_collector.append(results["loss"].sum().item())
 
                     mean_val_loss = np.mean(epoch_val_loss_collector)
 
@@ -333,15 +331,11 @@ def _train_model(
                     )
                     mean_loss = mean_val_loss
                 else:
-                    logger.info(
-                        f"Epoch {epoch:03d} - training loss: {mean_train_loss:.4f}"
-                    )
+                    logger.info(f"Epoch {epoch:03d} - training loss: {mean_train_loss:.4f}")
                     mean_loss = mean_train_loss
 
                 if np.isnan(mean_loss):
-                    logger.warning(
-                        f"‼️ Attention: got NaN loss in Epoch {epoch}. This may lead to unexpected errors."
-                    )
+                    logger.warning(f"‼️ Attention: got NaN loss in Epoch {epoch}. This may lead to unexpected errors.")
 
                 if mean_loss < self.best_loss:
                     self.best_epoch = epoch
@@ -363,9 +357,7 @@ def _train_model(
                         nni.report_final_result(self.best_loss)
 
                 if self.patience == 0:
-                    logger.info(
-                        "Exceeded the training patience. Terminating the training procedure..."
-                    )
+                    logger.info("Exceeded the training patience. Terminating the training procedure...")
                     break
 
         except KeyboardInterrupt:  # if keyboard interrupt, only warning
@@ -386,9 +378,7 @@ def _train_model(
         if np.isnan(self.best_loss):
             raise ValueError("Something is wrong. best_loss is Nan after training.")
 
-        logger.info(
-            f"Finished training. The best model is from epoch#{self.best_epoch}."
-        )
+        logger.info(f"Finished training. The best model is from epoch#{self.best_epoch}.")
 
     @abstractmethod
     def fit(

pypots/classification/grud/core.py

@@ -58,19 +58,15 @@ def forward(self, inputs: dict, training: bool = True) -> dict:
         empirical_mean = inputs["empirical_mean"]
         X_filledLOCF = inputs["X_filledLOCF"]
 
-        _, hidden_state = self.model(
-            X, missing_mask, deltas, empirical_mean, X_filledLOCF
-        )
+        _, hidden_state = self.model(X, missing_mask, deltas, empirical_mean, X_filledLOCF)
 
         logits = self.classifier(hidden_state)
         classification_pred = torch.softmax(logits, dim=1)
         results = {"classification_pred": classification_pred}
 
         # if in training mode, return results with losses
         if training:
-            classification_loss = F.nll_loss(
-                torch.log(classification_pred), inputs["label"]
-            )
+            classification_loss = F.nll_loss(torch.log(classification_pred), inputs["label"])
             results["loss"] = classification_loss
 
         return results

pypots/classification/grud/data.py

@@ -60,9 +60,9 @@ def __init__(
             self.X_filledLOCF = locf_torch(self.X)
             self.X = torch.nan_to_num(self.X)
             self.deltas = _parse_delta_torch(self.missing_mask)
-            self.empirical_mean = torch.sum(
-                self.missing_mask * self.X, dim=[0, 1]
-            ) / torch.sum(self.missing_mask, dim=[0, 1])
+            self.empirical_mean = torch.sum(self.missing_mask * self.X, dim=[0, 1]) / torch.sum(
+                self.missing_mask, dim=[0, 1]
+            )
             # fill nan with 0, in case some features have no observations
             self.empirical_mean = torch.nan_to_num(self.empirical_mean, 0)
 
@@ -134,9 +134,7 @@ def _fetch_data_from_file(self, idx: int) -> Iterable:
         X_filledLOCF = locf_torch(X.unsqueeze(dim=0)).squeeze()
         X = torch.nan_to_num(X)
         deltas = _parse_delta_torch(missing_mask)
-        empirical_mean = torch.sum(missing_mask * X, dim=[0]) / torch.sum(
-            missing_mask, dim=[0]
-        )
+        empirical_mean = torch.sum(missing_mask * X, dim=[0]) / torch.sum(missing_mask, dim=[0])
 
         sample = [
             torch.tensor(idx),

pypots/classification/raindrop/core.py

@@ -3,7 +3,6 @@
 and takes over the forward progress of the algorithm.
 """
 
-
 # Created by Wenjie Du <[email protected]>
 # License: BSD-3-Clause
 
@@ -84,21 +83,13 @@ def forward(self, inputs, training=True):
         lengths2 = lengths.unsqueeze(1).to(device)
         mask2 = mask.permute(1, 0).unsqueeze(2).long()
         if self.sensor_wise_mask:
-            output = torch.zeros(
-                [batch_size, self.n_features, self.d_ob + 16], device=device
-            )
+            output = torch.zeros([batch_size, self.n_features, self.d_ob + 16], device=device)
             extended_missing_mask = missing_mask.view(-1, batch_size, self.n_features)
             for se in range(self.n_features):
-                representation = representation.view(
-                    -1, batch_size, self.n_features, (self.d_ob + 16)
-                )
+                representation = representation.view(-1, batch_size, self.n_features, (self.d_ob + 16))
                 out = representation[:, :, se, :]
-                l_ = torch.sum(extended_missing_mask[:, :, se], dim=0).unsqueeze(
-                    1
-                )  # length
-                out_sensor = torch.sum(
-                    out * (1 - extended_missing_mask[:, :, se].unsqueeze(-1)), dim=0
-                ) / (l_ + 1)
+                l_ = torch.sum(extended_missing_mask[:, :, se], dim=0).unsqueeze(1)  # length
+                out_sensor = torch.sum(out * (1 - extended_missing_mask[:, :, se].unsqueeze(-1)), dim=0) / (l_ + 1)
                 output[:, se, :] = out_sensor
             output = output.view([-1, self.n_features * (self.d_ob + 16)])
         elif self.aggregation == "mean":
@@ -116,9 +107,7 @@ def forward(self, inputs, training=True):
 
         # if in training mode, return results with losses
         if training:
-            classification_loss = F.nll_loss(
-                torch.log(classification_pred), inputs["label"]
-            )
+            classification_loss = F.nll_loss(torch.log(classification_pred), inputs["label"])
             results["loss"] = classification_loss
 
         return results

pypots/classification/raindrop/model.py

@@ -3,7 +3,6 @@
 
 """
 
-
 # Created by Wenjie Du <[email protected]>
 # License: BSD-3-Clause
 

pypots/cli/dev.py

@@ -131,10 +131,9 @@ def checkup(self):
             )
 
         if self._cleanup:
-            assert not self._run_tests and not self._lint_code, (
-                "Argument `--cleanup` should be used alone. "
-                "Try `pypots-cli dev --cleanup`"
-            )
+            assert (
+                not self._run_tests and not self._lint_code
+            ), "Argument `--cleanup` should be used alone. Try `pypots-cli dev --cleanup`"
 
     def run(self):
         """Execute the given command."""
@@ -149,14 +148,8 @@ def run(self):
             elif self._build:
                 self.execute_command("python -m build")
             elif self._run_tests:
-                pytest_command = (
-                    f"pytest -k {self._k}" if self._k is not None else "pytest"
-                )
-                command_to_run_test = (
-                    f"coverage run -m {pytest_command}"
-                    if self._show_coverage
-                    else pytest_command
-                )
+                pytest_command = f"pytest -k {self._k}" if self._k is not None else "pytest"
+                command_to_run_test = f"coverage run -m {pytest_command}" if self._show_coverage else pytest_command
                 self.execute_command(command_to_run_test)
                 if self._show_coverage and os.path.exists(".coverage"):
                     self.execute_command("coverage report -m")