deepof.utils

Functions and general utilities for the deepof package.

Functions

align_trajectories(data[, mode, run_numba])	Remove rotational variance on the trajectories.
angle(bpart_array)	Return a numpy.ndarray with the angles between the provided instances.
binary_moving_median_numba(time_series, lag)	will applay a moving median like filter on a binary signal, i.e. if a window of size lag has more 1s than 0s set the frame to 1 for that window, set it to 0 otherwise.
bp2polar(tab)	Return the DataFrame in polar coordinates.
bpart_distance(dataframe)	Return a pandas.DataFrame with the scaled distances between all pairs of body parts.
cluster_transition_matrix(cluster_sequence, ...)	Compute the transition matrix between clusters and the autocorrelation in the sequence.
compute_animal_presence_mask(quality[, ...])	Compute a mask of the animal presence in the video.
compute_areas(polygon_xy_stack)	Compute polygon areas for the provided stack of sets of data point-xy coordinates.
compute_areas_numba(polygon_xy_stack)	Compute polygon areas for the provided stack of sets of data point-xy coordinates.
compute_dist(pair_array)	Return a pandas.DataFrame with the scaled distances between a pair of body parts.
connect_mouse([animal_ids, ...])	Create a nx.Graph object with the connectivity of the bodyparts in the DLC topview model for a single mouse.
count_events(binary_behavior[, ...])	Counts the number of continuous blocks of 1s in a binary behavior vector in different ways
count_transitions(tab_dict, exp_conditions)	Count transitions between successive behaviors for all experiments in tab_dict.
edges_to_weighted_adj(adj, edges)	Convert an edge feature matrix to a weighted adjacency matrix.
enforce_skeleton_constraints_numba(data, ...)	Adjusts the positions of body parts in each frame to ensure that the distances between connected parts adhere to predefined skeleton constraints within a specified tolerance.
enumerate_all_bridges(G)	Enumerate all 3-node connected sequences in the given graph.
extend_behaviors_numba(behaviors[, delta_T, ...])	Takes a booelan array of behavior detections and extends each behavior detection by delta_T.
extract_windows(to_window, window_size, ...)	Apply the rupture method independently to each experiment, and concatenate into a single dataset at the end.
filter_animal_id_in_table(table[, ...])	Filter a DataFrame to keep only those columns related to the selected id.
filter_columns(columns, selected_id[, ...])	Given a set of TableDict columns, returns those that correspond to a given animal, specified in selected_id.
filter_short_bouts(cluster_assignments, ...)	Filter out cluster assignment bouts shorter than min_bout_duration.
filter_short_true_segments(array, min_length)	Filters out sahort "True" sections from boolean array "array"
filter_short_true_segments_numba(array, ...)	Filters out sahort "True" sections from boolean array "array"
full_outlier_mask(experiment, likelihood, ...)	Iterate over all body parts of experiment, and outputs a dataframe where all x, y positions are replaced by a boolean mask, where True indicates an outlier.
get_behavior_mask_and_confidence(tab, ...)	Generates a boolean mask and a confidence dataframe for given behaviors.
get_point_polygon_distance(points, polygon)	Calculates array of distances between 2D points and a polygon (roi)
get_point_polygon_distance_numba(points, poly_xy)
get_total_Frames(video_paths)	Get the number of all frames in all videos listed in the input dictionary
gmm_compute(x, n_components, cv_type)	Fit a Gaussian Mixture Model to the provided data and returns evaluation metrics.
gmm_model_selection(x, n_components_range, ...)	Run GMM clustering model selection on the specified X dataframe.
in_field_of_view(mouse_pts, fov_angle_deg, roi)	mouse_pts: (N, 3, 2) or (3, 2), order [left_ear, nose, right_ear] Returns float array of shape (N,): 1.0 -> ROI intersects FOV 0.0 -> ROI does not intersect FOV np.nan -> cannot be calculated (invalid/degenerate geometry or non-finite points) Apex of FOV triangle is midpoint between ears.
in_field_of_view_numba(mouse_pts, ...[, eps])	Numba version of in_field_of_view (no plotting, no shapely).
infer_column_types(df)	Identify coord, speed, distance, and angle columns from a pose table.
infer_scalar_cols(df)
iterative_imputation(project, tab_dict, lik_dict)	Perform iterative imputation on occluded body parts.
kleinberg(offsets[, s, gamma, n, T, k])	Apply Kleinberg's algorithm (described in 'Bursty and Hierarchical Structure in Streams').
kleinberg_core_numba(gaps, s, gamma, n, T, k)	Computation intensive core part of Kleinberg's algorithm (described in 'Bursty and Hierarchical Structure in Streams').
load_precompiled_model(path, download_path, ...)	Loads model for automatic arena segmentation
load_table(tab, table_path, table_format[, ...])	Loads a table into a structured pandas data frame.
mask_outliers(time_series, likelihood, ...)	Return a mask over the bivariate trajectory of a body part, identifying as True all detected outliers.
mouse_in_roi(tab, aid, in_roi_criterion, ...)	Checks if a given animal for a given table is in a given roi by given criterion.
moving_average(time_series[, lag])	Fast implementation of a moving average function.
multi_step_paired_smoothing(behavior_in[, ...])	This filtering approach will first gradually merge together very close behavioral instances (how close is regulated by min_length), then filter out remaining short instances.
point_in_polygon(points, polygon)	Check if a set of points is inside a polygon.
point_in_polygon_numba(points, polygon)	This function was generated by Perplexity.ai Check if a set of points is inside a polygon.
polygon_area_numba(vertices)	Calculate the area of a single polygon given its vertices.
remove_outliers(experiment, likelihood, ...)	Mark all outliers in experiment and replaces them using a uni-variate linear interpolation approach.
rename_track_bps(loaded_tab, ...)	Renames all body parts in the provided dataframe.
rolling_speed(dframe[, frame_rate, window, ...])	Return the average speed over n frames in millimeters per second.
rolling_window(a, window_size, window_step)	Return a 3D numpy.array with a sliding-window extra dimension.
rotate(p, angles[, origin])	Return a 2D numpy.ndarray with the initial values rotated by angles radians.
rotate_all_numba(data, angles)	Rotates Return a 2D numpy.ndarray with the initial values rotated by angles radians.
rotate_numba(p, angles[, origin])	Return a 2D numpy.ndarray with the initial values rotated by angles radians.
row_nanargmax(arr)	argmax per row, ignoring NaNs.
rts_smoother_numba(measurements, F, H, Q, R)	Implements the Rauch-Tung-Striebel (RTS) smoother for state estimation.
scale_table(df[, scale, animal_ids, ...])
set_missing_animals(coordinates, tab_dict, ...)	Set the coordinates of the missing animals to NaN.
signed_angle(bpart_array)	Return a numpy.ndarray with the signed angles between the provided instances.
smooth_boolean_array(a[, scale, sigma, ...])	LEGACY FILTER FOR BEHAVIORAL ANALYSIS.
smooth_mult_trajectory(series[, alpha, w_length])	Return a smoothed a trajectory using a Savitzky-Golay 1D filter.
str2bool(v)	Return the passed string as a boolean.
tab2polar(cartesian_df)	Return a pandas.DataFrame in which all the coordinates are polar.
validate_parameter(param_name, param_value, ...)	A generic helper to validate a single parameter against a list of valid options.

Classes

KeyErrorMessage
MouseTrackingImputer([n_iterations, ...])	A class for imputing and processing mouse tracking data.