pypots/clustering/base.py
"""
The base classes for PyPOTS clustering models.
"""
# Created by Wenjie Du <wenjay.du@gmail.com>
# License: BSD-3-Clause
import os
from abc import abstractmethod
from typing import Union, Optional
import numpy as np
import torch
from torch.utils.data import DataLoader
from ..base import BaseModel, BaseNNModel
from ..utils.logging import logger
try:
import nni
except ImportError:
pass
class BaseClusterer(BaseModel):
"""Abstract class for all clustering models.
Parameters
----------
n_clusters :
The number of clusters in the clustering task.
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.
verbose :
Whether to print out the training logs during the training process.
"""
def __init__(
self,
n_clusters: int,
device: Optional[Union[str, torch.device, list]] = None,
saving_path: str = None,
model_saving_strategy: Optional[str] = "best",
verbose: bool = True,
):
super().__init__(
device,
saving_path,
model_saving_strategy,
verbose,
)
self.n_clusters = n_clusters
@abstractmethod
def fit(
self,
train_set: Union[dict, str],
val_set: Union[dict, str] = None,
file_type: str = "hdf5",
) -> None:
"""Train the cluster.
Parameters
----------
train_set :
The dataset for model training, should be a dictionary including the key 'X',
or a path string locating a data 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 training, can contain missing values.
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 the key 'X'.
val_set :
The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
or a path string locating a data 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 train_set and val_set are path strings.
"""
raise NotImplementedError
@abstractmethod
def predict(
self,
test_set: Union[dict, str],
file_type: str = "hdf5",
) -> dict:
raise NotImplementedError
@abstractmethod
def cluster(
self,
test_set: Union[dict, str],
file_type: str = "hdf5",
) -> np.ndarray:
"""Cluster the input 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,
Clustering results.
"""
raise NotImplementedError
class BaseNNClusterer(BaseNNModel):
"""The abstract class for all neural-network clustering models in PyPOTS.
Parameters
----------
n_clusters :
The number of clusters in the clustering task.
batch_size :
Size of the batch input into the model for one step.
epochs :
Training epochs, i.e. the maximum rounds of the model to be trained with.
patience :
Number of epochs the training procedure will keep if loss doesn't decrease.
Once exceeding the number, the training will stop.
Must be smaller than or equal to the value of ``epochs``.
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.
verbose :
Whether to print out the training logs during the training process.
Notes
-----
Optimizers are necessary for training deep-learning neural networks, but we don't put a parameter ``optimizer``
here because some models (e.g. GANs) need more than one optimizer (e.g. one for generator, one for discriminator),
and ``optimizer`` is ambiguous for them. Therefore, we leave optimizers as parameters for concrete model
implementations, and you can pass any number of optimizers to your model when implementing it,
:class:`pypots.clustering.crli.CRLI` for example.
"""
def __init__(
self,
n_clusters: int,
batch_size: int,
epochs: int,
patience: Optional[int] = None,
num_workers: int = 0,
device: Optional[Union[str, torch.device, list]] = None,
saving_path: str = None,
model_saving_strategy: Optional[str] = "best",
verbose: bool = True,
):
super().__init__(
batch_size,
epochs,
patience,
num_workers,
device,
saving_path,
model_saving_strategy,
verbose,
)
self.n_clusters = n_clusters
@abstractmethod
def _assemble_input_for_training(self, data: list) -> dict:
"""Assemble the given data into a dictionary for training input.
Parameters
----------
data :
Input data from dataloader, should be list.
Returns
-------
dict,
A python dictionary contains the input data for model training.
"""
raise NotImplementedError
@abstractmethod
def _assemble_input_for_validating(self, data: list) -> dict:
"""Assemble the given data into a dictionary for validating input.
Parameters
----------
data :
Data output from dataloader, should be list.
Returns
-------
dict,
A python dictionary contains the input data for model validating.
"""
raise NotImplementedError
@abstractmethod
def _assemble_input_for_testing(self, data: list) -> dict:
"""Assemble the given data into a dictionary for testing input.
Notes
-----
The processing functions of train/val/test stages are separated for the situation that the input of
the three stages are different, and this situation usually happens when the Dataset/Dataloader classes
used in the train/val/test stages are not the same, e.g. the training data and validating data in a
classification task contains labels, but the testing data (from the production environment) generally
doesn't have labels.
Parameters
----------
data :
Data output from dataloader, should be list.
Returns
-------
dict,
A python dictionary contains the input data for model testing.
"""
raise NotImplementedError
def _train_model(
self,
training_loader: DataLoader,
val_loader: DataLoader = None,
) -> None:
"""
Parameters
----------
training_loader
val_loader
Notes
-----
The training procedures of NN clustering models are very different from each other. For example, VaDER needs
pretraining while CRLI doesn't, VaDER only needs one optimizer while CRLI needs two for its generator and
discriminator separately. So far, I'd suggest to implement function _train_model() for each model individually.
"""
# each training starts from the very beginning, so reset the loss and model dict here
self.best_loss = float("inf")
self.best_model_dict = None
try:
for epoch in range(1, self.epochs + 1):
self.model.train()
epoch_train_loss_collector = []
for idx, data in enumerate(training_loader):
inputs = self._assemble_input_for_training(data)
self.optimizer.zero_grad()
results = self.model.forward(inputs)
results["loss"].sum().backward()
self.optimizer.step()
epoch_train_loss_collector.append(results["loss"].sum().item())
# mean training loss of the current epoch
mean_train_loss = np.mean(epoch_train_loss_collector)
if val_loader is not None:
self.model.eval()
epoch_val_loss_collector = []
with torch.no_grad():
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())
mean_val_loss = np.mean(epoch_val_loss_collector)
logger.info(
f"Epoch {epoch:03d} - "
f"training loss: {mean_train_loss:.4f}, "
f"validation loss: {mean_val_loss:.4f}"
)
mean_loss = mean_val_loss
else:
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.")
if mean_loss < self.best_loss:
self.best_epoch = epoch
self.best_loss = mean_loss
self.best_model_dict = self.model.state_dict()
self.patience = self.original_patience
else:
self.patience -= 1
if os.getenv("enable_tuning", False):
nni.report_intermediate_result(mean_loss)
if epoch == self.epochs - 1 or self.patience == 0:
nni.report_final_result(self.best_loss)
if self.patience == 0:
logger.info("Exceeded the training patience. Terminating the training procedure...")
break
except KeyboardInterrupt: # if keyboard interrupt, only warning
logger.warning("‼️ Training got interrupted by the user. Exist now ...")
except Exception as e: # other kind of exception follows below processing
logger.error(f"❌ Exception: {e}")
if self.best_model_dict is None: # if no best model, raise error
raise RuntimeError(
"Training got interrupted. Model was not trained. Please investigate the error printed above."
)
else:
RuntimeWarning(
"Training got interrupted. Please investigate the error printed above.\n"
"Model got trained and will load the best checkpoint so far for testing.\n"
"If you don't want it, please try fit() again."
)
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}.")
@abstractmethod
def fit(
self,
train_set: Union[dict, str],
val_set: Union[dict, str] = None,
file_type: str = "hdf5",
) -> None:
"""Train the cluster.
Parameters
----------
train_set :
The dataset for model training, should be a dictionary including the key 'X',
or a path string locating a data 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 training, can contain missing values.
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 the key 'X'.
val_set :
The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
or a path string locating a data 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 train_set and val_set are path strings.
"""
raise NotImplementedError
@abstractmethod
def predict(
self,
test_set: Union[dict, str],
file_type: str = "hdf5",
) -> dict:
raise NotImplementedError
@abstractmethod
def cluster(
self,
test_set: Union[dict, str],
file_type: str = "hdf5",
) -> np.ndarray:
"""Cluster the input 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,
Clustering results.
"""
raise NotImplementedError