utils.py 34.9 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
12
import scipy
import seaborn as sns
13
from copy import deepcopy
14
from itertools import cycle, combinations, product
15
16
17
18
19
20
from joblib import Parallel, delayed
from scipy import spatial
from sklearn import mixture
from tqdm import tqdm_notebook as tqdm


21
# QUALITY CONTROL AND PREPROCESSING #
22

23

lucas_miranda's avatar
lucas_miranda committed
24
25
26
27
28
29
30
31
32
33
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"""

34
35
    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
36
37
38
    filt_mask = np.all(Likes > threshold, axis=0)

    return filt_mask
39
40


41
42
43
44
45
46
47
48
49
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"""

50
51
52
53
54
55
56
    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


57
58
59
60
61
62
63
64
65
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"""

66
    result = []
67
68
    for df in list(cartesian_df.columns.levels[0]):
        result.append(bp2polar(cartesian_df[df]))
69
70
    result = pd.concat(result, axis=1)
    idx = pd.MultiIndex.from_product(
71
72
        [list(cartesian_df.columns.levels[0]), ["rho", "phi"]],
        names=["bodyparts", "coords"],
73
74
75
76
77
    )
    result.columns = idx
    return result


78
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"""

    a, b = pair_array[:, :2], pair_array[:, 2:]
94
    ab = a - b
95
    dist = np.sqrt(np.einsum("...i,...i", ab, ab))
96
97
98
    return pd.DataFrame(dist * arena_abs / arena_rel)


99
100
101
102
103
104
105
106
107
108
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
109

110
111
112
113
114
        Returns:
            - result (pd.DataFrame): pandas.DataFrame with the
            absolute distances between all pairs of body parts"""

    indexes = combinations(dataframe.columns.levels[0], 2)
115
116
117
118
119
120
121
    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)
122
123


124
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
        Returns:
            - ang (1D np.array): angles between the three-point-instances"""

lucas_miranda's avatar
lucas_miranda committed
134
135
136
    ba = a - b
    bc = c - b

137
    cosine_angle = np.einsum("...i,...i", ba, bc) / (
lucas_miranda's avatar
lucas_miranda committed
138
139
        np.linalg.norm(ba, axis=1) * np.linalg.norm(bc, axis=1)
    )
140
141
142
143
144
145
146
    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
147

148
149
        Parameters:
            - bpart_array (2D numpy.array): positions over time for a bodypart
lucas_miranda's avatar
lucas_miranda committed
150

151
152
153
154
        Returns:
            - ang_trio (2D numpy.array): all-three angles between the three-point-instances"""
    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
155

156
    return ang_trio
lucas_miranda's avatar
lucas_miranda committed
157
158


159
160
161
162
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
163

164
165
166
167
168
169
170
        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"""
171
172
173
174
175
    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)

176
177
178
179
    rotated = np.squeeze((R @ (p.T - o.T) + o.T).T)

    return rotated

180

181
182
183
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.
184

185
186
187
188
189
        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*
190

191
192
        Returns:
            - aligned_trajs (2D np.array): aligned positions over time"""
193

194
    angles = np.zeros(data.shape[0])
195
    data = deepcopy(data)
196
    dshape = data.shape
197

198
199
200
201
202
203
    if mode == "center":
        center_time = (data.shape[1] - 1) // 2
        angles = np.arctan2(data[:, center_time, 0], data[:, center_time, 1])
    elif mode == "all":
        data = data.reshape(-1, dshape[-1])
        angles = np.arctan2(data[:, 0], data[:, 1])
204
205
206
207
208

    aligned_trajs = np.zeros(data.shape)

    for frame in range(data.shape[0]):
        aligned_trajs[frame] = rotate(
209
            data[frame].reshape([-1, 2]), angles[frame],
210
211
        ).reshape(data.shape[1:])

212
213
214
    if mode == "all":
        aligned_trajs = aligned_trajs.reshape(dshape)

215
216
217
    return aligned_trajs


218
219
220
221
222
223
224
225
226
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"""

227
228
229
230
231
232
    for i in range(1, len(a) - 1):
        if a[i - 1] == a[i + 1]:
            a[i] = a[i - 1]
    return a == 1


233
234
235
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

236
237
        Parameters:
            - a (2D np.array): N (instances) * m (features) shape
238

239
240
241
        Returns:
            - rolled_a (3D np.array):
            N (sliding window instances) * l (sliding window size) * m (features)"""
242

243
244
    shape = (a.shape[0] - window_size + 1, window_size) + a.shape[1:]
    strides = (a.strides[0],) + a.strides
245
246
    rolled_a = np.lib.stride_tricks.as_strided(
        a, shape=shape, strides=strides, writeable=True
247
    )[::window_step]
248
    return rolled_a
249

250

251
252
253
def smooth_mult_trajectory(series: np.array, alpha: float = 0.15) -> np.array:
    """Returns a smooths a trajectory using exponentially weighted averages

254
255
        Parameters:
            - series (numpy.array): 1D trajectory array with N (instances) - alpha (float): 0 <= alpha <= 1;
256
257
            indicates the inverse weight assigned to previous observations. Higher (alpha~1) indicates less smoothing;
            lower indicates more (alpha~0)
258
259
260

        Returns:
            - smoothed_series (np.array): smoothed version of the input, with equal shape"""
261
262
263
264
265

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

266
267
268
    smoothed_series = np.array(result)

    return smoothed_series
269

lucas_miranda's avatar
lucas_miranda committed
270
271

# BEHAVIOUR RECOGNITION FUNCTIONS #
272
273


274
275
276
277
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.
278

279
280
281
282
283
284
        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)
285

286
287
288
        Returns:
            - contact_array (np.array): True if the distance between the two specified points
            is less than tol, False otherwise"""
289

290
    close_contact = np.linalg.norm(pos_dframe[left] - pos_dframe[right], axis=1) < tol
291

292
    return close_contact
293
294


295
296
297
298
299
300
301
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
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
330
331
332


def recognize_arena(
lucas_miranda's avatar
lucas_miranda committed
333
334
335
336
337
338
339
340
341
    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.

342
343
344
345
346
347
        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
348

349
350
351
        Returns:
            - arena (np.array): 1D-array containing information about the arena.
                "circular" (3-element-array) -> x-y position of the center and the radius"""
lucas_miranda's avatar
lucas_miranda committed
352
353

    cap = cv2.VideoCapture(os.path.join(path, videos[vid_index]))
354
355

    # Loop over the first frames in the video to get resolution and center of the arena
lucas_miranda's avatar
lucas_miranda committed
356
    arena, fnum, h, w = False, 0, None, None
357
358
359
360
361
362
363
364
365
366
367
368

    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
369
            if h is not None and w is not None:
370
371
372
373
374
375
376
                h, w = frame.shape[0], frame.shape[1]

        fnum += 1

    return arena


377
378
379
def circular_arena_recognition(frame: np.array) -> np.array:
    """Returns x,y position of the center and the radius of the recognised arena
        Parameters:
380
            - frame (np.array): numpy.array representing an individual frame of a video
381

382
383
384
        Returns:
            - circles (np.array): 3-element-array containing x,y positions of the center
            of the arena, and a third value indicating the radius"""
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410

    # 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]


411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
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
        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]
428

429
430
431
432
433
434
    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']")
435

436
    return climbing
437
438


lucas_miranda's avatar
lucas_miranda committed
439
def rolling_speed(dframe, typ, pause=10, rounds=5, order=1):
440
441
    """Returns the average speed over 10 frames in pixels per frame"""

lucas_miranda's avatar
lucas_miranda committed
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
    s = dframe.shape[0]

    if typ == "coords":
        bp = dframe.shape[1] / 2 if order == 1 else dframe.shape[1]
        d = 2 if order == 1 else 1

    else:
        bp = dframe.shape[1]
        d = 1

    distances = np.linalg.norm(
        np.array(dframe).reshape(s, int(bp), d)
        - np.array(dframe.shift()).reshape(s, int(bp), d),
        axis=2,
    )

    distances = pd.DataFrame(distances, index=dframe.index)
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
    speeds = np.round(distances.rolling(pause).mean(), rounds)
    speeds[np.isnan(speeds)] = 0.0

    return speeds


def huddle(pos_dict, fnum, tol, tol2, mouse="B"):
    """Returns true when the specified mouse is huddling"""

    return (
        np.linalg.norm(pos_dict[mouse + "_Left_ear"] - pos_dict[mouse + "_Left_flank"])
        < tol
        and np.linalg.norm(
            pos_dict[mouse + "_Right_ear"] - pos_dict[mouse + "_Right_flank"]
        )
        < tol
        and np.linalg.norm(pos_dict[mouse + "_Center"] - pos_dict[mouse + "_Tail_base"])
        < tol2
    )


def following_path(distancedf, dframe, follower="B", followed="W", frames=20, tol=0):
    """Returns true if follower is closer than tol to the path that followed has walked over
    the last specified number of frames"""

    # Check that follower is close enough to the path that followed has passed though in the last frames
    shift_dict = {i: dframe[followed + "_Tail_base"].shift(i) for i in range(frames)}
    dist_df = pd.DataFrame(
        {
            i: np.linalg.norm(dframe[follower + "_Nose"] - shift_dict[i], axis=1)
            for i in range(frames)
        }
    )

    # Check that the animals are oriented follower's nose -> followed's tail
    right_orient1 = (
        distancedf[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distancedf[tuple(sorted([follower + "_Tail_base", followed + "_Tail_base"]))]
    )

    right_orient2 = (
        distancedf[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distancedf[tuple(sorted([follower + "_Nose", followed + "_Nose"]))]
    )

    return pd.Series(
        np.all(
            np.array([(dist_df.min(axis=1) < tol), right_orient1, right_orient2]),
            axis=0,
        ),
        index=dframe.index,
    )


def Single_behaviour_analysis(
    behaviour_name,
    treatment_dict,
    behavioural_dict,
    plot=False,
    stats=False,
    save=False,
    ylim=False,
):
    """Given the name of the behaviour, a dictionary with the names of the groups to compare, and a dictionary
       with the actual taggings, outputs a box plot and a series of significance tests amongst the groups"""

    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])
            )

lucas_miranda's avatar
lucas_miranda committed
534
    if plot:
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
        sns.boxplot(list(beh_dict.keys()), list(beh_dict.values()), orient="vertical")

        plt.title("{} across groups".format(behaviour_name))
        plt.ylabel("Proportion of frames")

        if ylim != False:
            plt.ylim(*ylim)

        plt.tight_layout()
        plt.savefig("Exploration_heatmaps.pdf")

        if save != False:
            plt.savefig(save)

        plt.show()

lucas_miranda's avatar
lucas_miranda committed
551
    if stats:
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
        for i in combinations(treatment_dict.keys(), 2):
            print(i)
            print(scipy.stats.mannwhitneyu(beh_dict[i[0]], beh_dict[i[1]]))

    return beh_dict

    ##### MAIN BEHAVIOUR TAGGING FUNCTION #####


def Tag_video(
    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
608
    if save:
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
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
713
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
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
        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
    tagdict["bspeed"] = rolling_speed(dframe["B_Center"], pause=speedpause)
    tagdict["wspeed"] = rolling_speed(dframe["W_Center"], pause=speedpause)

    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
832
                if show:
833
834
                    cv2.imshow("frame", frame)

lucas_miranda's avatar
lucas_miranda committed
835
                if save:
836

lucas_miranda's avatar
lucas_miranda committed
837
                    if writer is None:
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
                        # 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


def max_behaviour(array, window_size=50):
    """Returns the most frequent behaviour in a window of window_size frames"""
    array = array.drop(["bspeed", "wspeed"], axis=1).astype("float")
    win_array = array.rolling(window_size, center=True).sum()[::50]
    max_array = win_array[1:].idxmax(axis=1)
    return list(max_array)

    ##### MACHINE LEARNING FUNCTIONS #####


def gmm_compute(x, n_components, cv_type):
    gmm = mixture.GaussianMixture(
        n_components=n_components,
        covariance_type=cv_type,
        max_iter=100000,
        init_params="kmeans",
    )
    gmm.fit(x)
    return [gmm, gmm.bic(x)]


def GMM_Model_Selection(
    X,
    n_components_range,
    n_runs=100,
    part_size=10000,
    n_cores=False,
    cv_types=["spherical", "tied", "diag", "full"],
):
    """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"""

    # 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

    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")(
                delayed(gmm_compute)(X.sample(part_size), n_components, cv_type)
                for i in range(n_runs)
            )
            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

924
925
926
927
    ##### RESULT ANALYSIS FUNCTIONS #####


def cluster_transition_matrix(
928
    cluster_sequence, nclusts, autocorrelation=True, return_graph=False
929
930
931
932
933
934
):
    """
    Computes the transition matrix between clusters and the autocorrelation in the sequence.
    """

    # Stores all possible transitions between clusters
935
936
937
    clusters = [str(i) for i in range(nclusts)]
    cluster_sequence = cluster_sequence.astype(str)

938
939
940
941
942
943
944
    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
945
    for t in trans.keys():
946
947
948
        trans[t] = len(re.findall("".join(t), transtr, overlapped=True))

    # Normalizes the counts to add up to 1 for each departing cluster
949
950
    trans_normed = np.zeros([k, k]) + 1e-5
    for t in trans.keys():
951
        trans_normed[int(t[0]), int(t[1])] = np.round(
952
953
954
            trans[t]
            / (sum({i: j for i, j in trans.items() if i[0] == t[0]}.values()) + 1e-5),
            3,
955
956
957
958
959
960
961
962
963
964
965
966
        )

    # 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))
        return trans_normed, np.corrcoef(cluster_sequence[:-1], cluster_sequence[1:])

    return trans_normed

967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
    ##### PLOTTING FUNCTIONS #####


def plot_speed(Behaviour_dict, Treatments):
    """Plots a histogram with the speed of the specified mouse.
       Treatments is expected to be a list of lists with mice keys per treatment"""

    fig, [ax1, ax2] = plt.subplots(1, 2, figsize=(20, 10))

    for Treatment, Mice_list in Treatments.items():
        hist = pd.concat([Behaviour_dict[mouse] for mouse in Mice_list])
        sns.kdeplot(hist["bspeed"], shade=True, label=Treatment, ax=ax1)
        sns.kdeplot(hist["wspeed"], shade=True, label=Treatment, ax=ax2)

    ax1.set_xlim(0, 7)
    ax2.set_xlim(0, 7)
    ax1.set_title("Average speed density for black mouse")
    ax2.set_title("Average speed density for white mouse")
    plt.xlabel("Average speed")
    plt.ylabel("Density")
    plt.show()


def plot_heatmap(dframe, bodyparts, xlim, ylim, save=False):
    """Returns a heatmap of the movement of a specific bodypart in the arena.
       If more than one bodypart is passed, it returns one subplot for each"""

    fig, ax = plt.subplots(1, len(bodyparts), sharex=True, sharey=True)

    for i, bpart in enumerate(bodyparts):
        heatmap = dframe[bpart]
        if len(bodyparts) > 1:
            sns.kdeplot(heatmap.x, heatmap.y, cmap="jet", shade=True, alpha=1, ax=ax[i])
        else:
            sns.kdeplot(heatmap.x, heatmap.y, cmap="jet", shade=True, alpha=1, ax=ax)
            ax = np.array([ax])

    [x.set_xlim(xlim) for x in ax]
    [x.set_ylim(ylim) for x in ax]
    [x.set_title(bp) for x, bp in zip(ax, bodyparts)]

    if save != False:
        plt.savefig(save)

    plt.show()


def model_comparison_plot(
    bic,
    m_bic,
    best_bic_gmm,
    n_components_range,
    cov_plot,
    save,
    cv_types=["spherical", "tied", "diag", "full"],
):
    """Plots model comparison statistics over all tests"""

    m_bic = np.array(m_bic)
    color_iter = cycle(["navy", "turquoise", "cornflowerblue", "darkorange"])
    clf = best_bic_gmm
    bars = []

    # Plot the BIC scores
    plt.figure(figsize=(12, 8))
    spl = plt.subplot(2, 1, 1)
    covplot = np.repeat(cv_types, len(m_bic) / 4)

    for i, (cv_type, color) in enumerate(zip(cv_types, color_iter)):
        xpos = np.array(n_components_range) + 0.2 * (i - 2)
        bars.append(
            spl.bar(
                xpos,
                m_bic[i * len(n_components_range) : (i + 1) * len(n_components_range)],
                color=color,
                width=0.2,
            )
        )

    spl.set_xticks(n_components_range)
    plt.title("BIC score per model")
    xpos = (
        np.mod(m_bic.argmin(), len(n_components_range))
        + 0.5
        + 0.2 * np.floor(m_bic.argmin() / len(n_components_range))
    )
    spl.text(xpos, m_bic.min() * 0.97 + 0.1 * m_bic.max(), "*", fontsize=14)
    spl.legend([b[0] for b in bars], cv_types)
    spl.set_ylabel("BIC value")

    spl2 = plt.subplot(2, 1, 2, sharex=spl)
    spl2.boxplot(list(np.array(bic)[covplot == cov_plot]), positions=n_components_range)
    spl2.set_xlabel("Number of components")
    spl2.set_ylabel("BIC value")

    plt.tight_layout()

    if save:
        plt.savefig(save)

    plt.show()