Keypoint MoSeq
Motion Sequencing (MoSeq) is an unsupervised machine learning method for animal behavior analysis. Given behavioral recordings, MoSeq learns a set of stereotyped movement patterns and when they occur over time. This package provides tools for fitting a MoSeq model to keypoint tracking data and analyzing the results.
Advanced topics
Developer API
- Model fitting
- Visualization
crop_image()plot_scree()plot_pcs()plot_syllable_frequencies()plot_duration_distribution()plot_kappa_scan()plot_progress()write_video_clip()grid_movie()get_grid_movie_window_size()generate_grid_movies()get_limits()plot_trajectories()generate_trajectory_plots()overlay_keypoints_on_image()overlay_keypoints_on_video()add_3D_pose_to_plotly_fig()plot_similarity_dendrogram()matplotlib_colormap_to_plotly()initialize_3D_plot()add_3D_pose_to_fig()plot_pcs_3D()plot_trajectories_3D()plot_poses_3D()hierarchical_clustering_order()plot_confusion_matrix()plot_eml_scores()plot_pose()
- Input/Output
- Utilities
np_io()print_dims_to_explain_variance()list_files_with_exts()find_matching_videos()pad_along_axis()filter_angle()get_centroids_headings()filter_centroids_headings()get_syllable_instances()get_edges()reindex_by_bodyparts()get_instance_trajectories()sample_instances()interpolate_along_axis()interpolate_keypoints()filtered_derivative()permute_cyclic()check_nan_proportions()format_data()get_typical_trajectories()syllable_similarity()downsample_timepoints()check_video_paths()
- Error Calibration