utils.py 38.6 KB
Newer Older
lucas_miranda's avatar
lucas_miranda committed
1
# @author lucasmiranda42
2
3
4
5

import cv2
import matplotlib.pyplot as plt
import multiprocessing
6
import networkx as nx
7
import numpy as np
lucas_miranda's avatar
lucas_miranda committed
8
import os
9
import pandas as pd
10
import regex as re
11
import seaborn as sns
12
from copy import deepcopy
13
from itertools import combinations, product
14
15
from joblib import Parallel, delayed
from scipy import spatial
16
from scipy import stats
17
from sklearn import mixture
18
19
from tqdm import tqdm
from typing import Tuple, Any, List, Union
20
21


22
# QUALITY CONTROL AND PREPROCESSING #
23

24

lucas_miranda's avatar
lucas_miranda committed
25
26
27
28
29
30
31
32
33
34
def likelihood_qc(dframe: pd.DataFrame, threshold: float = 0.9) -> np.array:
    """Returns a DataFrame filtered dataframe, keeping only the rows entirely above the threshold.

        Parameters:
            - dframe (pandas.DataFrame): DeepLabCut output, with positions over time and associated likelihhod
            - threshold (float): minimum acceptable confidence

        Returns:
            - filt_mask (np.array): mask on the rows of dframe"""

35
36
    Likes = np.array([dframe[i]["likelihood"] for i in list(dframe.columns.levels[0])])
    Likes = np.nan_to_num(Likes, nan=1.0)
lucas_miranda's avatar
lucas_miranda committed
37
38
39
    filt_mask = np.all(Likes > threshold, axis=0)

    return filt_mask
40
41


42
43
44
45
46
47
48
49
50
def bp2polar(tab: pd.DataFrame) -> pd.DataFrame:
    """Returns the DataFrame in polar coordinates.

        Parameters:
            - tab (pandas.DataFrame):Table with cartesian coordinates

        Returns:
            - polar (pandas.DataFrame): Equivalent to input, but with values in polar coordinates"""

51
52
53
54
55
56
57
    tab_ = np.array(tab)
    complex_ = tab_[:, 0] + 1j * tab_[:, 1]
    polar = pd.DataFrame(np.array([abs(complex_), np.angle(complex_)]).T)
    polar.rename(columns={0: "rho", 1: "phi"}, inplace=True)
    return polar


58
59
60
61
62
63
64
65
66
def tab2polar(cartesian_df: pd.DataFrame) -> pd.DataFrame:
    """Returns a pandas.DataFrame in which all the coordinates are polar.

        Parameters:
            - cartesian_df (pandas.DataFrame):DataFrame containing tables with cartesian coordinates

        Returns:
            - result (pandas.DataFrame): Equivalent to input, but with values in polar coordinates"""

67
    result = []
68
69
    for df in list(cartesian_df.columns.levels[0]):
        result.append(bp2polar(cartesian_df[df]))
70
71
    result = pd.concat(result, axis=1)
    idx = pd.MultiIndex.from_product(
72
73
        [list(cartesian_df.columns.levels[0]), ["rho", "phi"]],
        names=["bodyparts", "coords"],
74
75
76
77
78
    )
    result.columns = idx
    return result


79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
def compute_dist(
    pair_array: np.array, arena_abs: int = 1, arena_rel: int = 1
) -> pd.DataFrame:
    """Returns a pandas.DataFrame with the scaled distances between a pair of body parts.

        Parameters:
            - pair_array (numpy.array): np.array of shape N * 4 containing X,y positions
            over time for a given pair of body parts
            - arena_abs (int): diameter of the real arena in cm
            - arena_rel (int): diameter of the captured arena in pixels

        Returns:
            - result (pd.DataFrame): pandas.DataFrame with the
            absolute distances between a pair of body parts"""

lucas_miranda's avatar
lucas_miranda committed
94
95
    lim = 2 if pair_array.shape[1] == 4 else 1
    a, b = pair_array[:, :lim], pair_array[:, lim:]
96
    ab = a - b
lucas_miranda's avatar
lucas_miranda committed
97

98
    dist = np.sqrt(np.einsum("...i,...i", ab, ab))
99
100
101
    return pd.DataFrame(dist * arena_abs / arena_rel)


102
103
104
105
106
107
108
109
110
111
def bpart_distance(
    dataframe: pd.DataFrame, arena_abs: int = 1, arena_rel: int = 1
) -> pd.DataFrame:
    """Returns a pandas.DataFrame with the scaled distances between all pairs of body parts.

        Parameters:
            - dataframe (pandas.DataFrame): pd.DataFrame of shape N*(2*bp) containing X,y positions
        over time for a given set of bp body parts
            - arena_abs (int): diameter of the real arena in cm
            - arena_rel (int): diameter of the captured arena in pixels
112

113
114
115
116
117
        Returns:
            - result (pd.DataFrame): pandas.DataFrame with the
            absolute distances between all pairs of body parts"""

    indexes = combinations(dataframe.columns.levels[0], 2)
118
119
120
121
122
123
124
    dists = []
    for idx in indexes:
        dist = compute_dist(np.array(dataframe.loc[:, list(idx)]), arena_abs, arena_rel)
        dist.columns = [idx]
        dists.append(dist)

    return pd.concat(dists, axis=1)
125
126


127
128
129
130
131
132
133
def angle(a: np.array, b: np.array, c: np.array) -> np.array:
    """Returns a numpy.array with the angles between the provided instances.

        Parameters:
            - a (2D np.array): positions over time for a bodypart
            - b (2D np.array): positions over time for a bodypart
            - c (2D np.array): positions over time for a bodypart
lucas_miranda's avatar
lucas_miranda committed
134

135
136
137
        Returns:
            - ang (1D np.array): angles between the three-point-instances"""

lucas_miranda's avatar
lucas_miranda committed
138
139
140
    ba = a - b
    bc = c - b

141
    cosine_angle = np.einsum("...i,...i", ba, bc) / (
lucas_miranda's avatar
lucas_miranda committed
142
143
        np.linalg.norm(ba, axis=1) * np.linalg.norm(bc, axis=1)
    )
144
145
146
147
148
149
150
    ang = np.arccos(cosine_angle)

    return ang


def angle_trio(bpart_array: np.array) -> np.array:
    """Returns a numpy.array with all three possible angles between the provided instances.
lucas_miranda's avatar
lucas_miranda committed
151

152
153
        Parameters:
            - bpart_array (2D numpy.array): positions over time for a bodypart
lucas_miranda's avatar
lucas_miranda committed
154

155
156
        Returns:
            - ang_trio (2D numpy.array): all-three angles between the three-point-instances"""
lucas_miranda's avatar
lucas_miranda committed
157

158
159
    a, b, c = bpart_array
    ang_trio = np.array([angle(a, b, c), angle(a, c, b), angle(b, a, c)])
lucas_miranda's avatar
lucas_miranda committed
160

161
    return ang_trio
lucas_miranda's avatar
lucas_miranda committed
162
163


164
165
166
167
def rotate(
    p: np.array, angles: np.array, origin: np.array = np.array([0, 0])
) -> np.array:
    """Returns a numpy.array with the initial values rotated by angles radians
lucas_miranda's avatar
lucas_miranda committed
168

169
170
171
172
173
174
175
        Parameters:
            - p (2D numpy.array): array containing positions of bodyparts over time
            - angles (2D numpy.array): set of angles (in radians) to rotate p with
            - origin (2D numpy.array): rotation axis (zero vector by default)

        Returns:
            - rotated (2D numpy.array): rotated positions over time"""
lucas_miranda's avatar
lucas_miranda committed
176

177
178
179
180
181
    R = np.array([[np.cos(angles), -np.sin(angles)], [np.sin(angles), np.cos(angles)]])

    o = np.atleast_2d(origin)
    p = np.atleast_2d(p)

182
183
184
185
    rotated = np.squeeze((R @ (p.T - o.T) + o.T).T)

    return rotated

186

187
188
189
def align_trajectories(data: np.array, mode: str = "all") -> np.array:
    """Returns a numpy.array with the positions rotated in a way that the center (0 vector)
    and the body part in the first column of data are aligned with the y axis.
190

191
192
193
194
195
        Parameters:
            - data (3D numpy.array): array containing positions of body parts over time, where
            shape is N (sliding window instances) * m (sliding window size) * l (features)
            - mode (string): specifies if *all* instances of each sliding window get
            aligned, or only the *center*
196

197
198
        Returns:
            - aligned_trajs (2D np.array): aligned positions over time"""
199

200
    angles = np.zeros(data.shape[0])
201
    data = deepcopy(data)
202
    dshape = data.shape
203

204
205
206
207
    if mode == "center":
        center_time = (data.shape[1] - 1) // 2
        angles = np.arctan2(data[:, center_time, 0], data[:, center_time, 1])
    elif mode == "all":
lucas_miranda's avatar
lucas_miranda committed
208
        data = data.reshape(-1, dshape[-1], order="C")
209
        angles = np.arctan2(data[:, 0], data[:, 1])
lucas_miranda's avatar
lucas_miranda committed
210
211
212
    elif mode == "none":
        data = data.reshape(-1, dshape[-1], order="C")
        angles = np.zeros(data.shape[0])
213
214
215
216
217

    aligned_trajs = np.zeros(data.shape)

    for frame in range(data.shape[0]):
        aligned_trajs[frame] = rotate(
lucas_miranda's avatar
lucas_miranda committed
218
219
            data[frame].reshape([-1, 2], order="C"), angles[frame],
        ).reshape(data.shape[1:], order="C")
220

lucas_miranda's avatar
lucas_miranda committed
221
222
    if mode == "all" or mode == "none":
        aligned_trajs = aligned_trajs.reshape(dshape, order="C")
223

224
225
226
    return aligned_trajs


227
228
229
230
231
232
233
234
235
def smooth_boolean_array(a: np.array) -> np.array:
    """Returns a boolean array in which isolated appearances of a feature are smoothened

        Parameters:
            - a (1D numpy.array): boolean instances

        Returns:
            - a (1D numpy.array): smoothened boolean instances"""

236
237
238
239
240
241
    for i in range(1, len(a) - 1):
        if a[i - 1] == a[i + 1]:
            a[i] = a[i - 1]
    return a == 1


242
243
244
def rolling_window(a: np.array, window_size: int, window_step: int) -> np.array:
    """Returns a 3D numpy.array with a sliding-window extra dimension

245
246
        Parameters:
            - a (2D np.array): N (instances) * m (features) shape
247

248
249
250
        Returns:
            - rolled_a (3D np.array):
            N (sliding window instances) * l (sliding window size) * m (features)"""
251

252
253
    shape = (a.shape[0] - window_size + 1, window_size) + a.shape[1:]
    strides = (a.strides[0],) + a.strides
254
255
    rolled_a = np.lib.stride_tricks.as_strided(
        a, shape=shape, strides=strides, writeable=True
256
    )[::window_step]
257
    return rolled_a
258

259

260
261
262
def smooth_mult_trajectory(series: np.array, alpha: float = 0.15) -> np.array:
    """Returns a smooths a trajectory using exponentially weighted averages

263
264
        Parameters:
            - series (numpy.array): 1D trajectory array with N (instances) - alpha (float): 0 <= alpha <= 1;
265
266
            indicates the inverse weight assigned to previous observations. Higher (alpha~1) indicates less smoothing;
            lower indicates more (alpha~0)
267
268
269

        Returns:
            - smoothed_series (np.array): smoothed version of the input, with equal shape"""
270
271
272
273
274

    result = [series[0]]
    for n in range(len(series)):
        result.append(alpha * series[n] + (1 - alpha) * result[n - 1])

275
276
277
    smoothed_series = np.array(result)

    return smoothed_series
278

lucas_miranda's avatar
lucas_miranda committed
279
280

# BEHAVIOUR RECOGNITION FUNCTIONS #
281
282


283
284
285
286
def close_single_contact(
    pos_dframe: pd.DataFrame, left: str, right: str, tol: float
) -> np.array:
    """Returns a boolean array that's True if the specified body parts are closer than tol.
287

288
289
290
291
292
293
        Parameters:
            - pos_dframe (pandas.DataFrame): DLC output as pandas.DataFrame; only applicable
            to two-animal experiments.
            - left (string): First member of the potential contact
            - right (string): Second member of the potential contact
            - tol (float)
294

295
296
297
        Returns:
            - contact_array (np.array): True if the distance between the two specified points
            is less than tol, False otherwise"""
298

299
    close_contact = np.linalg.norm(pos_dframe[left] - pos_dframe[right], axis=1) < tol
300

301
    return close_contact
302
303


304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
def close_double_contact(
    pos_dframe: pd.DataFrame,
    left1: str,
    left2: str,
    right1: str,
    right2: str,
    tol: float,
    rev: bool = False,
) -> np.array:
    """Returns a boolean array that's True if the specified body parts are closer than tol.

        Parameters:
            - pos_dframe (pandas.DataFrame): DLC output as pandas.DataFrame; only applicable
            to two-animal experiments.
            - left1 (string): First contact point of animal 1
            - left2 (string): Second contact point of animal 1
            - right1 (string): First contact point of animal 2
            - right2 (string): Second contact point of animal 2
            - tol (float)

        Returns:
            - double_contact (np.array): True if the distance between the two specified points
            is less than tol, False otherwise"""

    if rev:
        double_contact = (
            np.linalg.norm(pos_dframe[right1] - pos_dframe[left2], axis=1) < tol
        ) & (np.linalg.norm(pos_dframe[right2] - pos_dframe[left1], axis=1) < tol)

    else:
        double_contact = (
            np.linalg.norm(pos_dframe[right1] - pos_dframe[left1], axis=1) < tol
        ) & (np.linalg.norm(pos_dframe[right2] - pos_dframe[left2], axis=1) < tol)

    return double_contact
339
340
341


def recognize_arena(
lucas_miranda's avatar
lucas_miranda committed
342
343
344
345
346
347
348
349
350
    videos: list,
    vid_index: int,
    path: str = ".",
    recoglimit: int = 1,
    arena_type: str = "circular",
) -> np.array:
    """Returns numpy.array with information about the arena recognised from the first frames
    of the video. WARNING: estimates won't be reliable if the camera moves along the video.

351
352
353
354
355
356
        Parameters:
            - videos (list): relative paths of the videos to analise
            - vid_index (int): element of videos to use
            - path (string): full path of the directory where the videos are
            - recoglimit (int): number of frames to use for position estimates
            - arena_type (string): arena type; must be one of ['circular']
lucas_miranda's avatar
lucas_miranda committed
357

358
359
        Returns:
            - arena (np.array): 1D-array containing information about the arena.
lucas_miranda's avatar
lucas_miranda committed
360
            "circular" (3-element-array) -> x-y position of the center and the radius"""
lucas_miranda's avatar
lucas_miranda committed
361
362

    cap = cv2.VideoCapture(os.path.join(path, videos[vid_index]))
363
364

    # Loop over the first frames in the video to get resolution and center of the arena
lucas_miranda's avatar
lucas_miranda committed
365
    arena, fnum, h, w = False, 0, None, None
366
367
368
369
370
371
372
373
374
375
376
377

    while cap.isOpened() and fnum < recoglimit:
        ret, frame = cap.read()
        # if frame is read correctly ret is True
        if not ret:
            print("Can't receive frame (stream end?). Exiting ...")
            break

        if arena_type == "circular":

            # Detect arena and extract positions
            arena = circular_arena_recognition(frame)[0]
lucas_miranda's avatar
lucas_miranda committed
378
            if h is not None and w is not None:
379
380
381
382
383
384
385
                h, w = frame.shape[0], frame.shape[1]

        fnum += 1

    return arena


386
387
def circular_arena_recognition(frame: np.array) -> np.array:
    """Returns x,y position of the center and the radius of the recognised arena
lucas_miranda's avatar
lucas_miranda committed
388

389
        Parameters:
390
            - frame (np.array): numpy.array representing an individual frame of a video
391

392
393
394
        Returns:
            - circles (np.array): 3-element-array containing x,y positions of the center
            of the arena, and a third value indicating the radius"""
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420

    # Convert image to greyscale, threshold it, blur it and detect the biggest best fitting circle
    # using the Hough algorithm
    gray_image = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    ret, thresh = cv2.threshold(gray_image, 50, 255, 0)
    frame = cv2.medianBlur(thresh, 9)
    circle = cv2.HoughCircles(
        frame,
        cv2.HOUGH_GRADIENT,
        1,
        300,
        param1=50,
        param2=10,
        minRadius=0,
        maxRadius=0,
    )

    circles = []

    if circle is not None:
        circle = np.uint16(np.around(circle[0]))
        circles.append(circle)

    return circles[0]


421
422
423
424
def climb_wall(
    arena_type: str, arena: np.array, pos_dict: pd.DataFrame, tol: float, nose: str
) -> np.array:
    """Returns True if the specified mouse is climbing the wall
lucas_miranda's avatar
lucas_miranda committed
425

426
427
428
429
430
431
432
433
434
435
436
437
438
        Parameters:
            - arena_type (str): arena type; must be one of ['circular']
            - arena (np.array): contains arena location and shape details
            - pos_dict (table_dict): position over time for all videos in a project
            - tol (float): minimum tolerance to report a hit
            - nose (str): indicates the name of the body part representing the nose of
            the selected animal

        Returns:
            - climbing (np.array): boolean array. True if selected animal
            is climbing the walls of the arena"""

    nose = pos_dict[nose]
439

440
441
442
443
444
445
    if arena_type == "circular":
        center = np.array(arena[:2])
        climbing = np.linalg.norm(nose - center, axis=1) > (arena[2] + tol)

    else:
        raise NotImplementedError("Supported values for arena_type are ['circular']")
446

447
    return climbing
448
449


lucas_miranda's avatar
lucas_miranda committed
450
451
452
453
def rolling_speed(
    dframe: pd.DatetimeIndex, window: int = 10, rounds: int = 10, deriv: int = 1
) -> pd.DataFrame:
    """Returns the average speed over n frames in pixels per frame
lucas_miranda's avatar
lucas_miranda committed
454

lucas_miranda's avatar
lucas_miranda committed
455
456
457
458
459
460
        Parameters:
            - dframe (pandas.DataFrame): position over time dataframe
            - pause (int):  frame-length of the averaging window
            - rounds (int): float rounding decimals
            - deriv (int): position derivative order; 1 for speed,
            2 for acceleration, 3 for jerk, etc
lucas_miranda's avatar
lucas_miranda committed
461

lucas_miranda's avatar
lucas_miranda committed
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
        Returns:
            - speeds (pd.DataFrame): containing 2D speeds for each body part
            in the original data or their consequent derivatives"""

    original_shape = dframe.shape
    body_parts = dframe.columns.levels[0]
    speeds = pd.DataFrame

    for der in range(deriv):
        distances = np.concatenate(
            [
                np.array(dframe).reshape([-1, (2 if der == 0 else 1)], order="F"),
                np.array(dframe.shift()).reshape(
                    [-1, (2 if der == 0 else 1)], order="F"
                ),
            ],
            axis=1,
        )
lucas_miranda's avatar
lucas_miranda committed
480

lucas_miranda's avatar
lucas_miranda committed
481
482
483
484
485
486
487
        distances = np.array(compute_dist(distances))
        distances = distances.reshape(
            [original_shape[0], original_shape[1] // 2], order="F"
        )
        distances = pd.DataFrame(distances, index=dframe.index)
        speeds = np.round(distances.rolling(window).mean(), rounds)
        speeds[np.isnan(speeds)] = 0.0
lucas_miranda's avatar
lucas_miranda committed
488

lucas_miranda's avatar
lucas_miranda committed
489
        dframe = speeds
lucas_miranda's avatar
lucas_miranda committed
490

lucas_miranda's avatar
lucas_miranda committed
491
    speeds.columns = body_parts
492
493
494
495

    return speeds


lucas_miranda's avatar
lucas_miranda committed
496
497
498
def huddle(pos_dframe: pd.DataFrame, tol_forward: float, tol_spine: float) -> np.array:
    """Returns true when the mouse is huddling using simple rules. (!!!) Designed to
    work with deepof's default DLC mice models; not guaranteed to work otherwise.
499

lucas_miranda's avatar
lucas_miranda committed
500
501
502
503
504
505
        Parameters:
            - pos_dframe (pandas.DataFrame):
            - tol_forward (float): Maximum tolerated distance between ears and
            forward limbs
            - tol_rear (float): Maximum tolerated average distance between spine
            body parts
lucas_miranda's avatar
lucas_miranda committed
506

lucas_miranda's avatar
lucas_miranda committed
507
508
509
510
511
512
513
514
515
516
        Returns:
            hudd (np.array): True if the animal is huddling, False otherwise
        """

    forward = (
        np.linalg.norm(pos_dframe["Left_ear"] - pos_dframe["Left_fhip"], axis=1)
        < tol_forward
    ) & (
        np.linalg.norm(pos_dframe["Right_ear"] - pos_dframe["Right_fhip"], axis=1)
        < tol_forward
517
518
    )

lucas_miranda's avatar
lucas_miranda committed
519
520
521
522
523
524
525
526
527
528
529
530
531
532
    spine = ["Spine1", "Center", "Spine2", "Tail_base"]
    spine_dists = []
    for comb in range(2):
        spine_dists.append(
            np.linalg.norm(
                pos_dframe[spine[comb]] - pos_dframe[spine[comb + 1]], axis=1
            )
        )
    spine = np.mean(spine_dists) < tol_spine

    hudd = forward & spine

    return hudd

533

lucas_miranda's avatar
lucas_miranda committed
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
def following_path(
    distance_dframe: pd.DataFrame,
    position_dframe: pd.DataFrame,
    follower: str,
    followed: str,
    frames: int = 20,
    tol: float = 0,
) -> np.array:
    """For multi animal videos only. Returns True if 'follower' is closer than tol to the path that
    followed has walked over the last specified number of frames

        Parameters:
            - distance_dframe (pandas.DataFrame): distances between bodyparts; generated by the preprocess module
            - position_dframe (pandas.DataFrame): position of bodyparts; generated by the preprocess module
            - follower (str) identifier for the animal who's following
            - followed (str) identifier for the animal who's followed
            - frames (int) frames in which to track whether the process consistently occurs,
            - tol (float) Maximum distance for which True is returned

        Returns:
            - follow (np.array): boolean sequence, True if conditions are fulfilled, False otherwise"""
555
556

    # Check that follower is close enough to the path that followed has passed though in the last frames
lucas_miranda's avatar
lucas_miranda committed
557
558
559
    shift_dict = {
        i: position_dframe[followed + "_Tail_base"].shift(i) for i in range(frames)
    }
560
561
    dist_df = pd.DataFrame(
        {
lucas_miranda's avatar
lucas_miranda committed
562
563
564
            i: np.linalg.norm(
                position_dframe[follower + "_Nose"] - shift_dict[i], axis=1
            )
565
566
567
568
569
570
            for i in range(frames)
        }
    )

    # Check that the animals are oriented follower's nose -> followed's tail
    right_orient1 = (
lucas_miranda's avatar
lucas_miranda committed
571
572
573
574
        distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distance_dframe[
            tuple(sorted([follower + "_Tail_base", followed + "_Tail_base"]))
        ]
575
576
577
    )

    right_orient2 = (
lucas_miranda's avatar
lucas_miranda committed
578
579
        distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Nose"]))]
580
581
    )

lucas_miranda's avatar
lucas_miranda committed
582
583
    follow = np.all(
        np.array([(dist_df.min(axis=1) < tol), right_orient1, right_orient2]), axis=0,
584
585
    )

lucas_miranda's avatar
lucas_miranda committed
586
587
    return follow

588

lucas_miranda's avatar
lucas_miranda committed
589
def single_behaviour_analysis(
590
591
592
593
594
595
596
597
    behaviour_name: str,
    treatment_dict: dict,
    behavioural_dict: dict,
    plot: int = 0,
    stat_tests: bool = True,
    save: str = None,
    ylim: float = None,
) -> list:
598
    """Given the name of the behaviour, a dictionary with the names of the groups to compare, and a dictionary
599
600
601
602
603
604
605
606
607
608
609
610
611
612
       with the actual tags, outputs a box plot and a series of significance tests amongst the groups

        Parameters:
            - behaviour_name (str): name of the behavioural trait to analize
            - treatment_dict (dict): dictionary containing video names as keys and experimental conditions as values
            - behavioural_dict (dict): tagged dictionary containing video names as keys and annotations as values
            - plot (int): Silent if 0; otherwise, indicates the dpi of the figure to plot
            - stat_tests (bool): performs FDR corrected Mann-U non-parametric tests among all groups if True
            - save (str): Saves the produced figure to the specified file
            - ylim (float): y-limit for the boxplot. Ignored if plot == False

        Returns:
            - beh_dict (dict): dictionary containing experimental conditions as keys and video names as values
            - stat_dict (dict): dictionary containing condition pairs as keys and stat results as values"""
613
614
615
616
617
618
619
620
621
622

    beh_dict = {condition: [] for condition in treatment_dict.keys()}

    for condition in beh_dict.keys():
        for ind in treatment_dict[condition]:
            beh_dict[condition].append(
                np.sum(behavioural_dict[ind][behaviour_name])
                / len(behavioural_dict[ind][behaviour_name])
            )

623
    return_list = [beh_dict]
624

625
    if plot > 0:
626

627
        fig, ax = plt.subplots(dpi=plot)
628

629
630
631
632
633
634
635
636
637
        sns.boxplot(
            list(beh_dict.keys()), list(beh_dict.values()), orient="vertical", ax=ax
        )

        ax.set_title("{} across groups".format(behaviour_name))
        ax.set_ylabel("Proportion of frames")

        if ylim is not None:
            ax.set_ylim(ylim)
638

639
        if save is not None:
640
641
            plt.savefig(save)

642
        return_list.append(ax)
643

644
645
    if stat_tests:
        stat_dict = {}
646
        for i in combinations(treatment_dict.keys(), 2):
647
648
649
650
651
652
653
654
655
656
657
            # Solves issue with automatically generated examples
            if (
                beh_dict[i[0]] == beh_dict[i[1]]
                or np.var(beh_dict[i[0]]) == 0
                or np.var(beh_dict[i[1]]) == 0
            ):
                stat_dict[i] = "Identical sources. Couldn't run"
            else:
                stat_dict[i] = stats.mannwhitneyu(
                    beh_dict[i[0]], beh_dict[i[1]], alternative="two-sided"
                )
658
        return_list.append(stat_dict)
659

660
    return return_list
661
662


663
# MAIN BEHAVIOUR TAGGING FUNCTION #
664

665
666

def tag_video(
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
    Tracks,
    Videos,
    Track_dict,
    Distance_dict,
    Like_QC_dict,
    vid_index,
    show=False,
    save=False,
    fps=25.0,
    speedpause=50,
    framelimit=np.inf,
    recoglimit=1,
    path="./",
    classifiers={},
):
    """Outputs a dataframe with the motives registered per frame. If mp4==True, outputs a video in mp4 format"""

    vid_name = re.findall("(.*?)_", Tracks[vid_index])[0]

    cap = cv2.VideoCapture(path + Videos[vid_index])
    dframe = Track_dict[vid_name]
    h, w = None, None
    bspeed, wspeed = None, None

    # Disctionary with motives per frame
    tagdict = {
        func: np.zeros(dframe.shape[0])
        for func in [
            "nose2nose",
            "bnose2tail",
            "wnose2tail",
            "sidebyside",
            "sidereside",
            "bclimbwall",
            "wclimbwall",
            "bspeed",
            "wspeed",
            "bhuddle",
            "whuddle",
            "bfollowing",
            "wfollowing",
        ]
    }

    # Keep track of the frame number, to align with the tracking data
    fnum = 0
lucas_miranda's avatar
lucas_miranda committed
713
    if save:
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
        writer = None

    # Loop over the first frames in the video to get resolution and center of the arena
    while cap.isOpened() and fnum < recoglimit:
        ret, frame = cap.read()
        # if frame is read correctly ret is True
        if not ret:
            print("Can't receive frame (stream end?). Exiting ...")
            break

        # Detect arena and extract positions
        arena = circular_arena_recognition(frame)[0]
        if h == None and w == None:
            h, w = frame.shape[0], frame.shape[1]

        fnum += 1

    # Define behaviours that can be computed on the fly from the distance matrix
    tagdict["nose2nose"] = smooth_boolean_array(
        Distance_dict[vid_name][("B_Nose", "W_Nose")] < 15
    )
    tagdict["bnose2tail"] = smooth_boolean_array(
        Distance_dict[vid_name][("B_Nose", "W_Tail_base")] < 15
    )
    tagdict["wnose2tail"] = smooth_boolean_array(
        Distance_dict[vid_name][("B_Tail_base", "W_Nose")] < 15
    )
    tagdict["sidebyside"] = smooth_boolean_array(
        (Distance_dict[vid_name][("B_Nose", "W_Nose")] < 40)
        & (Distance_dict[vid_name][("B_Tail_base", "W_Tail_base")] < 40)
    )
    tagdict["sidereside"] = smooth_boolean_array(
        (Distance_dict[vid_name][("B_Nose", "W_Tail_base")] < 40)
        & (Distance_dict[vid_name][("B_Tail_base", "W_Nose")] < 40)
    )

    B_mouse_X = np.array(
        Distance_dict[vid_name][
            [j for j in Distance_dict[vid_name].keys() if "B_" in j[0] and "B_" in j[1]]
        ]
    )
    W_mouse_X = np.array(
        Distance_dict[vid_name][
            [j for j in Distance_dict[vid_name].keys() if "W_" in j[0] and "W_" in j[1]]
        ]
    )

    tagdict["bhuddle"] = smooth_boolean_array(classifiers["huddle"].predict(B_mouse_X))
    tagdict["whuddle"] = smooth_boolean_array(classifiers["huddle"].predict(W_mouse_X))

    tagdict["bclimbwall"] = smooth_boolean_array(
        pd.Series(
            (
                spatial.distance.cdist(
                    np.array(dframe["B_Nose"]), np.array([arena[:2]])
                )
                > (w / 200 + arena[2])
            ).reshape(dframe.shape[0]),
            index=dframe.index,
        )
    )
    tagdict["wclimbwall"] = smooth_boolean_array(
        pd.Series(
            (
                spatial.distance.cdist(
                    np.array(dframe["W_Nose"]), np.array([arena[:2]])
                )
                > (w / 200 + arena[2])
            ).reshape(dframe.shape[0]),
            index=dframe.index,
        )
    )
    tagdict["bfollowing"] = smooth_boolean_array(
        following_path(
            Distance_dict[vid_name],
            dframe,
            follower="B",
            followed="W",
            frames=20,
            tol=20,
        )
    )
    tagdict["wfollowing"] = smooth_boolean_array(
        following_path(
            Distance_dict[vid_name],
            dframe,
            follower="W",
            followed="B",
            frames=20,
            tol=20,
        )
    )

    # Compute speed on a rolling window
lucas_miranda's avatar
lucas_miranda committed
808
809
    tagdict["bspeed"] = rolling_speed(dframe["B_Center"], window=speedpause)
    tagdict["wspeed"] = rolling_speed(dframe["W_Center"], window=speedpause)
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936

    if any([show, save]):
        # Loop over the frames in the video
        pbar = tqdm(total=min(dframe.shape[0] - recoglimit, framelimit))
        while cap.isOpened() and fnum < framelimit:

            ret, frame = cap.read()
            # if frame is read correctly ret is True
            if not ret:
                print("Can't receive frame (stream end?). Exiting ...")
                break

            font = cv2.FONT_HERSHEY_COMPLEX_SMALL

            if Like_QC_dict[vid_name][fnum]:

                # Extract positions
                pos_dict = {
                    i: np.array([dframe[i]["x"][fnum], dframe[i]["y"][fnum]])
                    for i in dframe.columns.levels[0]
                    if i != "Like_QC"
                }

                if h == None and w == None:
                    h, w = frame.shape[0], frame.shape[1]

                # Label positions
                downleft = (int(w * 0.3 / 10), int(h / 1.05))
                downright = (int(w * 6.5 / 10), int(h / 1.05))
                upleft = (int(w * 0.3 / 10), int(h / 20))
                upright = (int(w * 6.3 / 10), int(h / 20))

                # Display all annotations in the output video
                if tagdict["nose2nose"][fnum] and not tagdict["sidebyside"][fnum]:
                    cv2.putText(
                        frame,
                        "Nose-Nose",
                        (downleft if bspeed > wspeed else downright),
                        font,
                        1,
                        (255, 255, 255),
                        2,
                    )
                if tagdict["bnose2tail"][fnum] and not tagdict["sidereside"][fnum]:
                    cv2.putText(
                        frame, "Nose-Tail", downleft, font, 1, (255, 255, 255), 2
                    )
                if tagdict["wnose2tail"][fnum] and not tagdict["sidereside"][fnum]:
                    cv2.putText(
                        frame, "Nose-Tail", downright, font, 1, (255, 255, 255), 2
                    )
                if tagdict["sidebyside"][fnum]:
                    cv2.putText(
                        frame,
                        "Side-side",
                        (downleft if bspeed > wspeed else downright),
                        font,
                        1,
                        (255, 255, 255),
                        2,
                    )
                if tagdict["sidereside"][fnum]:
                    cv2.putText(
                        frame,
                        "Side-Rside",
                        (downleft if bspeed > wspeed else downright),
                        font,
                        1,
                        (255, 255, 255),
                        2,
                    )
                if tagdict["bclimbwall"][fnum]:
                    cv2.putText(
                        frame, "Climbing", downleft, font, 1, (255, 255, 255), 2
                    )
                if tagdict["wclimbwall"][fnum]:
                    cv2.putText(
                        frame, "Climbing", downright, font, 1, (255, 255, 255), 2
                    )
                if tagdict["bhuddle"][fnum] and not tagdict["bclimbwall"][fnum]:
                    cv2.putText(frame, "huddle", downleft, font, 1, (255, 255, 255), 2)
                if tagdict["whuddle"][fnum] and not tagdict["wclimbwall"][fnum]:
                    cv2.putText(frame, "huddle", downright, font, 1, (255, 255, 255), 2)
                if tagdict["bfollowing"][fnum] and not tagdict["bclimbwall"][fnum]:
                    cv2.putText(
                        frame,
                        "*f",
                        (int(w * 0.3 / 10), int(h / 10)),
                        font,
                        1,
                        ((150, 150, 255) if wspeed > bspeed else (150, 255, 150)),
                        2,
                    )
                if tagdict["wfollowing"][fnum] and not tagdict["wclimbwall"][fnum]:
                    cv2.putText(
                        frame,
                        "*f",
                        (int(w * 6.3 / 10), int(h / 10)),
                        font,
                        1,
                        ((150, 150, 255) if wspeed < bspeed else (150, 255, 150)),
                        2,
                    )

                if (bspeed == None and wspeed == None) or fnum % speedpause == 0:
                    bspeed = tagdict["bspeed"][fnum]
                    wspeed = tagdict["wspeed"][fnum]

                cv2.putText(
                    frame,
                    "W: " + str(np.round(wspeed, 2)) + " mmpf",
                    (upright[0] - 20, upright[1]),
                    font,
                    1,
                    ((150, 150, 255) if wspeed < bspeed else (150, 255, 150)),
                    2,
                )
                cv2.putText(
                    frame,
                    "B: " + str(np.round(bspeed, 2)) + " mmpf",
                    upleft,
                    font,
                    1,
                    ((150, 150, 255) if bspeed < wspeed else (150, 255, 150)),
                    2,
                )

lucas_miranda's avatar
lucas_miranda committed
937
                if show:
938
939
                    cv2.imshow("frame", frame)

lucas_miranda's avatar
lucas_miranda committed
940
                if save:
941

lucas_miranda's avatar
lucas_miranda committed
942
                    if writer is None:
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
                        # Define the codec and create VideoWriter object.The output is stored in 'outpy.avi' file.
                        # Define the FPS. Also frame size is passed.
                        writer = cv2.VideoWriter()
                        writer.open(
                            re.findall("(.*?)_", Tracks[vid_index])[0] + "_tagged.avi",
                            cv2.VideoWriter_fourcc(*"MJPG"),
                            fps,
                            (frame.shape[1], frame.shape[0]),
                            True,
                        )
                    writer.write(frame)

            if cv2.waitKey(1) == ord("q"):
                break

            pbar.update(1)
            fnum += 1

    cap.release()
    cv2.destroyAllWindows()

    tagdf = pd.DataFrame(tagdict)

    return tagdf, arena


969
970
971
972
973
974
975
976
977
978
979
980
def max_behaviour(
    behaviour_dframe: pd.DataFrame, window_size: int = 10, stepped: bool = False
) -> np.array:
    """Returns the most frequent behaviour in a window of window_size frames

        Parameters:
                - behaviour_dframe (pd.DataFrame): boolean matrix containing occurrence
                of tagged behaviours per frame in the video
                - window_size (int): size of the window to use when computing
                the maximum behaviour per time slot
                - stepped (bool): sliding windows don't overlap if True. False by default

981
982
983
        Returns:
            - max_array (np.array): string array with the most common behaviour per instance
            of the sliding window"""
984
985
986
987
988
989
990

    speeds = [col for col in behaviour_dframe.columns if "speed" in col.lower()]

    behaviour_dframe = behaviour_dframe.drop(speeds, axis=1).astype("float")
    win_array = behaviour_dframe.rolling(window_size, center=True).sum()
    if stepped:
        win_array = win_array[::window_size]
991
992
    max_array = win_array[1:].idxmax(axis=1)

993
994
995
996
    return np.array(max_array)


# MACHINE LEARNING FUNCTIONS #
997
998


999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
def gmm_compute(x: np.array, n_components: int, cv_type: str) -> list:
    """Fits a Gaussian Mixture Model to the provided data and returns evaluation metrics.

        Parameters:
            - x (numpy.array): data matrix to train the model
            - n_components (int): number of Gaussian components to use
            - cv_type (str): covariance matrix type to use.
            Must be one of "spherical", "tied", "diag", "full"

        Returns:
            - gmm_eval (list): model and associated BIC for downstream selection
    """

1012
1013
1014
1015
1016
1017
1018
    gmm = mixture.GaussianMixture(
        n_components=n_components,
        covariance_type=cv_type,
        max_iter=100000,
        init_params="kmeans",
    )
    gmm.fit(x)
1019
1020
1021
1022
1023
    gmm_eval = [gmm, gmm.bic(x)]
    return gmm_eval


def gmm_model_selection(
1024
    x: pd.DataFrame,
1025
1026
1027
1028
1029
1030
1031
1032
    n_components_range: range,
    part_size: int,
    n_runs: int = 100,
    n_cores: int = False,
    cv_types: Tuple = ("spherical", "tied", "diag", "full"),
) -> Tuple[List[list], List[np.ndarray], Union[int, Any]]:
    """Runs GMM clustering model selection on the specified X dataframe, outputs the bic distribution per model,
       a vector with the median BICs and an object with the overall best model
1033

1034
        Parameters:
1035
            - x (pandas.DataFrame): data matrix to train the models
1036
1037
1038
1039
1040
            - n_components_range (range): generator with numbers of components to evaluate
            - n_runs (int): number of bootstraps for each model
            - part_size (int): size of bootstrap samples for each model
            - n_cores (int): number of cores to use for computation
            - cv_types (tuple): Covariance Matrices to try. All four available by default
1041

1042
1043
1044
1045
1046
1047
1048
        Returns:
            - bic (list): All recorded BIC values for all attempted parameter combinations
            (useful for plotting)
            - m_bic(list): All minimum BIC values recorded throughout the process
            (useful for plottinh)
            - best_bic_gmm (sklearn.GMM): unfitted version of the best found model
    """
1049
1050
1051
1052
1053
1054
1055
1056

    # Set the default of n_cores to the most efficient value
    if not n_cores:
        n_cores = min(multiprocessing.cpu_count(), n_runs)

    bic = []
    m_bic = []
    lowest_bic = np.inf
1057
    best_bic_gmm = 0
1058
1059
1060
1061
1062
1063
1064
1065

    pbar = tqdm(total=len(cv_types) * len(n_components_range))

    for cv_type in cv_types:

        for n_components in n_components_range:

            res = Parallel(n_jobs=n_cores, prefer="threads")(
1066
1067
1068
1069
                delayed(gmm_compute)(
                    x.sample(part_size, replace=True), n_components, cv_type
                )
                for _ in range(n_runs)
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
            )
            bic.append([i[1] for i in res])

            pbar.update(1)
            m_bic.append(np.median([i[1] for i in res]))
            if m_bic[-1] < lowest_bic:
                lowest_bic = m_bic[-1]
                best_bic_gmm = res[0][0]

    return bic, m_bic, best_bic_gmm

1081
1082

# RESULT ANALYSIS FUNCTIONS #
1083
1084
1085


def cluster_transition_matrix(
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
    cluster_sequence: np.array,
    nclusts: int,
    autocorrelation: bool = True,
    return_graph: bool = False,
) -> Tuple[Union[nx.Graph, Any], np.ndarray]:
    """Computes the transition matrix between clusters and the autocorrelation in the sequence.

        Parameters:
            - cluster_sequence (numpy.array):
            - nclusts (int):
            - autocorrelation (bool):
            - return_graph (bool):

        Returns:
            - trans_normed (numpy.array / networkx.Graph:
            - autocorr (numpy.array):
1102
1103
1104
    """

    # Stores all possible transitions between clusters
1105
1106
1107
    clusters = [str(i) for i in range(nclusts)]
    cluster_sequence = cluster_sequence.astype(str)

1108
1109
1110
1111
1112
1113
1114
    trans = {t: 0 for t in product(clusters, clusters)}
    k = len(clusters)

    # Stores the cluster sequence as a string
    transtr = "".join(list(cluster_sequence))

    # Assigns to each transition the number of times it occurs in the sequence
1115
    for t in trans.keys():
1116
1117
1118
        trans[t] = len(re.findall("".join(t), transtr, overlapped=True))

    # Normalizes the counts to add up to 1 for each departing cluster
1119
1120
    trans_normed = np.zeros([k, k]) + 1e-5
    for t in trans.keys():
1121
        trans_normed[int(t[0]), int(t[1])] = np.round(
1122
1123
1124
            trans[t]
            / (sum({i: j for i, j in trans.items() if i[0] == t[0]}.values()) + 1e-5),
            3,
1125
1126
1127
1128
1129
1130
1131
1132
        )

    # If specified, returns the transition matrix as an nx.Graph object
    if return_graph:
        trans_normed = nx.Graph(trans_normed)

    if autocorrelation:
        cluster_sequence = list(map(int, cluster_sequence))
1133
1134
        autocorr = np.corrcoef(cluster_sequence[:-1], cluster_sequence[1:])
        return trans_normed, autocorr
1135
1136
1137

    return trans_normed

1138

1139
1140
# TODO:
#    - Add sequence plot to single_behaviour_analysis (show how the condition varies across a specified time window)