Skip to main content

vame.analysis.segment_behavior

Variational Animal Motion Embedding 0.1 Toolbox © K. Luxem & P. Bauer, Department of Cellular Neuroscience Leibniz Institute for Neurobiology, Magdeburg, Germany

https://github.com/LINCellularNeuroscience/VAME Licensed under GNU General Public License v3.0

load_data​

def load_data(PROJECT_PATH: str, file: str, data: str) -> np.ndarray

Load data for the given file.

Arguments:

  • PROJECT_PATH str - Path to the project directory.
  • file str - Name of the file.
  • data str - Data to load.

Returns:

  • np.ndarray - Loaded data.

kmeans_clustering​

def kmeans_clustering(context: np.ndarray, n_clusters: int) -> np.ndarray

Perform k-Means clustering.

Arguments:

  • context np.ndarray - Input data for clustering.
  • n_clusters int - Number of clusters.

Returns:

  • np.ndarray - Cluster labels.

gmm_clustering​

def gmm_clustering(context: np.ndarray, n_components: int) -> np.ndarray

Perform Gaussian Mixture Model (GMM) clustering.

Arguments:

  • context np.ndarray - Input data for clustering.
  • n_components int - Number of components.

Returns:

  • np.ndarray - Cluster labels.

behavior_segmentation​

def behavior_segmentation(config: str,
                          model_name: str = None,
                          cluster_method: str = 'kmeans',
                          n_cluster: List[int] = [30]) -> None

Perform behavior segmentation.

Arguments:

  • config str - Path to the configuration file.
  • model_name str, optional - Name of the model. Defaults to None.
  • cluster_method str, optional - Clustering method. Defaults to 'kmeans'.
  • n_cluster List[int], optional - List of number of clusters. Defaults to [30].

Returns:

  • None - Save data to the results directory.

temporal_quant​

def temporal_quant(cfg: dict, model_name: str, files: List[str],
                   use_gpu: bool) -> Tuple

Quantify the temporal latent space.

Arguments:

  • cfg dict - Configuration dictionary.
  • model_name str - Name of the model.
  • files List[str] - List of file names.
  • use_gpu bool - Whether to use GPU.

Returns:

  • Tuple - Tuple of latent space array and logger.

cluster_latent_space​

def cluster_latent_space(cfg: dict, files: List[str], z_data: np.ndarray,
                         z_logger: List[int], cluster_method: str,
                         n_cluster: List[int], model_name: str) -> None

Cluster the latent space.

Arguments:

  • cfg dict - Configuration dictionary.
  • files List[str] - List of file names.
  • z_data np.ndarray - Latent space data.
  • z_logger List[int] - Logger for the latent space.
  • cluster_method str - Clustering method.
  • n_cluster List[int] - List of number of clusters.
  • model_name str - Name of the model.

Returns:

None -> Save data to the results directory.