Load a YAML file. Args: path (str): Path to the YAML file. subsection (str): Subsection to be considered (i.e. general, mode

Detect the last index of the file containing the target value. Args: target (int): Target index. cumulative_lengths (list): L

Identical to the XLM create_sinusoidal_embeddings except features are not interleaved. The cos features are in the 2nd half of the ve

Compute the pairwise mutual information between the columns of a dataframe. Parameters ---------- df : pandas.Dataframe The

Create and save a YAML file containing the hyperparameters as part of an experiment. Args: experiment_id (str): ID of the experiment.

Create folders recursively. Args: path (str): Tree of folders to be created. Returns: None.

Split the data into training, validation and test sets based on the training, validation and test ratios. Args: dataset (str): The c

Given the cliques, separators and adjacency matrix of a TMFG, extract the b-cliques of size 2 (edges), 3 (triangles) and 4 (tetrahedra). Par

Get the best levels (bid and ask) prices and the corresponding discretized labels. Args: dataset (str): Name of the dataset to be use

Compute the homological structures to be used in the HCNN building process. Parameters ---------- general_hyperparameters : Dict[str

Compute the average similarity matrix for a list of similarity matrices. Parameters ---------- sm_list : List[pandas.DataFrame]

Parser for input arguments. Returns: The parsed arguments.

Save all the days used in the training, validation and test sets. Args: experiment_id (str): ID of the experiment. general_hy

Save the general/model hyperparameters in the Weights & Biases dashboard. Args: wandb_logger (any): Wandb logger. general_hyp

Find the directory path for saving results associated with a given `model_id`. This function constructs a directory path within the 'loggers/

`input_ids_shape` is expected to be [bsz x seqlen].

Generate a unique experiment identifier based on the input `name` and the current timestamp in the format "YYYY-MM-DD_HH_MM_SS". Create a dir

Log experimental results in a YAML file associated with the given `model_id`. If the file already exists, it appends new data to it; otherwis

Function to pre-process LOBSTER data. The data must be stored in the input_path directory as 'daily message LOB' and 'orderbook' files. The

Compute the TMFG for volumes of a given orderbook file. Parameters ---------- file : str The path to the file to compute the

Read and retrieve data from a log file associated with the given `model_id`. :param model_id: Model identifier, (str). :param header: He