fetch_dataset_paths#

movement.sample_data.fetch_dataset_paths(filename, with_video=False)[source]#

Get paths to sample dataset and any associated frames or videos.

The data are downloaded from the movement data repository to the user’s local machine upon first use and are stored in a local cache directory. The function returns the paths to the downloaded files.

Parameters:

filename (str) – Name of the sample data file to fetch.
with_video (bool, optional) – Whether to download the associated video file (if available). If set to False, the “video” entry in the returned dictionary will be None. Defaults to False.

Returns:

paths – Dictionary mapping file types to their respective paths. The possible file types are: “poses” or “bboxes” (depending on tracking type), “frame”, “video”. A None value for “frame” or “video” indicates that the file is either not available or not requested (if with_video=False).

Return type:

dict

Examples

Fetch a sample dataset and get the paths to the file containing the predicted poses, as well as the associated frame and video files:

>>> from movement.sample_data import fetch_dataset_paths
>>> paths = fetch_dataset_paths(
...     "DLC_single-mouse_EPM.predictions.h5", with_video=True
... )
>>> poses_path = paths["poses"]
>>> frame_path = paths["frame"]
>>> video_path = paths["video"]

If the sample dataset contains bounding boxes instead of poses, use paths["bboxes"] instead of paths["poses"]:

>>> paths = fetch_dataset_paths("VIA_multiple-crabs_5-frames_labels.csv")
>>> bboxes_path = paths["bboxes"]