get number of parameters in model

Loads the optimizer state. Parameters ---------- state_dict : Optimizer state. It should be an object returned fr

Automatically save the current model into a file if in need. Parameters ---------- confirm_saving : One more cond

Initialize the torch optimizer wrapped by this class. Parameters ---------- params : An iterable of ``torch.Tenso

Print the number of trainable parameters in the initialized NN model.

Train the classifier on the given data. Parameters ---------- train_set : The dataset for model training, should

Check if the key is in the given dataset. The dataset could be a path to an HDF5 file or a Python dictionary. Parameters ---------- k

Scale and encode values. Args: name (str): name of variable values (Union[pd.Series, torch.Tensor, np.ndarra

Open the file handle for reading data from the file. Notes ----- This function can also help confirm if the given file and fi

Generate the time-gap matrix (i.e. the delta metrix) from the missing mask. Please refer to :cite:`che2018GRUD` for its math definition. Para

Returns the state of the optimizer as a dict. Returns ------- state_dict : The state dict of the optimizer, which

Saving training logs into the tensorboard file specified by the given path `tb_file_saving_path`. Parameters ---------- step

Check if 2D tensor contains NAs or inifinite values. Args: names (Union[str, List[str]]): name(s) of column(s) (used for error messa

Initialize the scheduler. This method should be called in :class:`pypots.optim.base.Optimizer.init_optimizer()` to initialize the scheduler to

Calculate the Mean Square Error between ``predictions`` and ``targets``. ``masks`` can be used for filtering. For values==0 in ``masks``, valu

Turn the given data into the specified data type.

Sets the gradients of all optimized ``torch.Tensor`` to zero. Parameters ---------- set_to_none : Instead of sett

Generate names for lagged variables Args: name (str): name of variable to lag Returns: Dict[str, in

Get parameters that can be used with :py:meth:`~from_parameters` to create a new dataset with the same scalers. Returns:

Performs a single optimization step (parameter update). Parameters ---------- closure : A closure that reevaluate

Concatenate tensor along ``dim=0`` and add nans along ``dim=1`` if necessary. Allows concatenation of tensors where ``dim=1`` are not equal.

Get transformer for variable. Args: name (str): variable name group_id (bool, optional): If the passed name

Load dataset from disk Args: fname (str): filename to load from Returns: TimeSeriesDataSet

Run inference / prediction. Args: dataloader: dataloader, dataframe or dataset mode: one of "prediction", "q

Save the model with current parameters to a disk file. A ``.pypots`` extension will be appended to the filename if it does not already have o

calculate single sample's delta. The sample's shape is [n_steps, n_features].

Create the given directory if it doesn't exist. Parameters ---------- path : The path for check. is_dir : Whether th

Run at epoch end for training or validation. Can be overriden in models.

Extract the given path's parent directory. Parameters ---------- path : The path for extracting. Returns ------- par

Create model from dataset, i.e. save dataset parameters in model This function should be called as ``super().from_dataset()`` in a d

Generate dataset with different underlying data but same variable encoders and scalers, etc. Args: parameters (Dict[str,

get modes on frequency domain: 'random' means sampling randomly; 'else' means sampling the lowest modes;

Save dataset to disk Args: fname (str): filename to save to

Run for each train/val step. Args: x (Dict[str, torch.Tensor]): x as passed to the network by the dataloader

Get dataloader from dataset. The Args: train (bool, optional): if dataloader is used for training or prediction

Convert output to prediction using the loss metric. Args: out (Dict[str, Any]): output of network where "prediction" has

This module is an encoder with 1d-convolutional network and multivariate Normal posterior used by GP-VAE with proposed banded covariance matri

Concatenate multiple batches of output dictionary. Args: output (List[Dict[str, List[Union[List[torch.Tensor], torch.Tensor, bool, i

Calculate the Root Mean Square Error between ``predictions`` and ``targets``. ``masks`` can be used for filtering. For values==0 in ``masks``,

Calculate length of decoder. Args: time_last (Union[int, pd.Series, np.ndarray]): last time index of the sequence

Create the log used in the training and validation step. Args: x (Dict[str, torch.Tensor]): x as passed to the network b

add time dimension to static context

interpret output of model Args: out: output as produced by ``forward()`` reduction: "none" for no averaging

Load the saved model from a disk file. Parameters ---------- path : The local path to a disk file saving the trai

Plot prediction of prediction vs actuals Args: x: network input out: network output idx: index o

Reset values used to override sample features.