utils.py 32.4 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
8
9
10
import numpy as np
import pandas as pd
import pickle
import pims
11
import regex as re
12
13
import scipy
import seaborn as sns
14
from copy import deepcopy
15
from itertools import cycle, combinations, product
16
from joblib import Parallel, delayed
lucas_miranda's avatar
lucas_miranda committed
17
from numba import jit
18
19
20
21
22
from scipy import spatial
from sklearn import mixture
from tqdm import tqdm_notebook as tqdm


23
# QUALITY CONTROL AND PREPROCESSING #
24

25
26

def likelihood_qc(dframe, threshold=0.9):
27
28
29
30
31
32
    """Returns only rows where all lilelihoods are above a specified threshold"""
    Likes = np.array([dframe[i]["likelihood"] for i in list(dframe.columns.levels[0])])
    Likes = np.nan_to_num(Likes, nan=1.0)
    return np.all(Likes > threshold, axis=0)


33
34
35
36
37
38
39
40
41
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"""

42
43
44
45
46
47
48
    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


49
50
51
52
53
54
55
56
57
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"""

58
    result = []
59
60
    for df in list(cartesian_df.columns.levels[0]):
        result.append(bp2polar(cartesian_df[df]))
61
62
    result = pd.concat(result, axis=1)
    idx = pd.MultiIndex.from_product(
63
64
        [list(cartesian_df.columns.levels[0]), ["rho", "phi"]],
        names=["bodyparts", "coords"],
65
66
67
68
69
    )
    result.columns = idx
    return result


70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
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:]
86
    ab = a - b
87
    dist = np.sqrt(np.einsum("...i,...i", ab, ab))
88
89
90
    return pd.DataFrame(dist * arena_abs / arena_rel)


91
92
93
94
95
96
97
98
99
100
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
101

102
103
104
105
106
        Returns:
            - result (pd.DataFrame): pandas.DataFrame with the
            absolute distances between all pairs of body parts"""

    indexes = combinations(dataframe.columns.levels[0], 2)
107
108
109
110
111
112
113
    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)
114
115


116
117
118
119
120
121
122
123
124
125
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
126
127
128
    ba = a - b
    bc = c - b

129
    cosine_angle = np.einsum("...i,...i", ba, bc) / (
lucas_miranda's avatar
lucas_miranda committed
130
131
        np.linalg.norm(ba, axis=1) * np.linalg.norm(bc, axis=1)
    )
132
133
134
135
136
137
138
    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
139

140
141
        Parameters:
            - bpart_array (2D numpy.array): positions over time for a bodypart
lucas_miranda's avatar
lucas_miranda committed
142

143
144
145
146
        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
147

148
    return ang_trio
lucas_miranda's avatar
lucas_miranda committed
149
150


151
152
153
154
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
155

156
157
158
159
160
161
162
        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"""
163
164
165
166
167
    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)

168
169
170
171
    rotated = np.squeeze((R @ (p.T - o.T) + o.T).T)

    return rotated

172

173
174
175
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.
176

177
178
179
180
181
        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*
182

183
184
        Returns:
            - aligned_trajs (2D np.array): aligned positions over time"""
185

186
    angles = np.zeros(data.shape[0])
187
    data = deepcopy(data)
188
    dshape = data.shape
189

190
191
192
193
194
195
    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])
196
197
198
199
200

    aligned_trajs = np.zeros(data.shape)

    for frame in range(data.shape[0]):
        aligned_trajs[frame] = rotate(
201
            data[frame].reshape([-1, 2]), angles[frame],
202
203
        ).reshape(data.shape[1:])

204
205
206
    if mode == "all":
        aligned_trajs = aligned_trajs.reshape(dshape)

207
208
209
    return aligned_trajs


210
211
212
213
214
215
216
217
218
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"""

219
220
221
222
223
224
    for i in range(1, len(a) - 1):
        if a[i - 1] == a[i + 1]:
            a[i] = a[i - 1]
    return a == 1


225
226
227
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

228
229
        Parameters:
            - a (2D np.array): N (instances) * m (features) shape
230

231
232
233
        Returns:
            - rolled_a (3D np.array):
            N (sliding window instances) * l (sliding window size) * m (features)"""
234

235
236
    shape = (a.shape[0] - window_size + 1, window_size) + a.shape[1:]
    strides = (a.strides[0],) + a.strides
237
238
    rolled_a = np.lib.stride_tricks.as_strided(
        a, shape=shape, strides=strides, writeable=True
239
    )[::window_step]
240
    return rolled_a
241

242
243

@jit
244
245
246
247
248
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

        Parameters:
            - series (np.array): 2D trajectory array with N (instances) * m (features)
            - alpha (float): 0 <= alpha <= 1; indicates the weight assigned to the current observation.
            higher (alpha~1) indicates less smoothing; lower indicates more (alpha~0)

        Returns:
            - smoothed_series (np.array): smoothed version of the input, with equal shape"""
254
255
256
257
258

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

259
260
261
    smoothed_series = np.array(result)

    return smoothed_series
262

263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
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
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
    ##### IMAGE/VIDEO PROCESSING FUNCTIONS #####


def index_frames(video_list, sample=False, index=0, pkl=False):
    """Pickles a 4D numpy array per video in video list, for easy random access afterwards"""

    pbar = tqdm(total=len(video_list))

    for i, vid in enumerate(video_list):

        v = np.array(pims.PyAVReaderIndexed(vid))

        if sample:
            v = v[np.random.choice(v.shape[0], sample)]

        if type(index) != int:
            v = v[index]

        if pkl:
            with open(pkl, "wb") as f:
                pickle.dump(v, f, protocol=4)

        pbar.update(1)

    return True

    ##### BEHAVIOUR RECOGNITION FUNCTIONS #####


# Nose to Nose contact
def nose_to_nose(pos_dict, fnum, tol):
    """Takes DLC dataframe as input. Returns True when distances of both noses are closer to tolerance"""

    return np.linalg.norm(pos_dict["B_Nose"] - pos_dict["W_Nose"]) < tol


# Black nose to white tail contact
def nose_to_tail(pos_dict, fnum, tol, mouse1="B", mouse2="W"):
    """Takes DLC dataframe as input. Returns True when the distance of nose1 and tail2 are closer to tolerance"""

    return (
        np.linalg.norm(pos_dict[mouse1 + "_Nose"] - pos_dict[mouse2 + "_Tail_base"])
        < tol
    )


# Side by side (noses and tails close)
def side_by_side(pos_dict, fnum, tol, rev=False):
    """Takes DLC dataframe as input. Returns True when mice are side by side"""
    w_nose = pos_dict["W_Nose"]
    b_nose = pos_dict["B_Nose"]
    w_tail = pos_dict["W_Tail_base"]
    b_tail = pos_dict["B_Tail_base"]

    if rev:
        return (
            np.linalg.norm(w_nose - b_tail) < tol
            and np.linalg.norm(w_tail - b_nose) < tol
        )

    else:
        return (
            np.linalg.norm(w_nose - b_nose) < tol
            and np.linalg.norm(w_tail - b_tail) < tol
        )


def recognize_arena(
    Videos, vid_index, path=".", recoglimit=1, arena_type="circular",
):
    cap = cv2.VideoCapture(path + Videos[vid_index])

    # Loop over the first frames in the video to get resolution and center of the arena
    fnum, h, w = 0, None, None

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

        fnum += 1

    return arena


def circular_arena_recognition(frame):
    """Returns x,y position of the center and the radius of the recognised arena"""

    # 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]


def climb_wall(arena, pos_dict, fnum, tol, mouse):
    """Returns True if the specified mouse is climbing the wall"""

    nose = pos_dict[mouse + "_Nose"]
    center = np.array(arena[:2])

    return np.linalg.norm(nose - center) > arena[2] + tol


lucas_miranda's avatar
lucas_miranda committed
394
def rolling_speed(dframe, typ, pause=10, rounds=5, order=1):
395
396
    """Returns the average speed over 10 frames in pixels per frame"""

lucas_miranda's avatar
lucas_miranda committed
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
    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)
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
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
    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
489
    if plot:
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
        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
506
    if stats:
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
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
        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
563
    if save:
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
608
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
        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
787
                if show:
788
789
                    cv2.imshow("frame", frame)

lucas_miranda's avatar
lucas_miranda committed
790
                if save:
791

lucas_miranda's avatar
lucas_miranda committed
792
                    if writer is None:
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
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
                        # 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

879
880
881
882
    ##### RESULT ANALYSIS FUNCTIONS #####


def cluster_transition_matrix(
883
    cluster_sequence, nclusts, autocorrelation=True, return_graph=False
884
885
886
887
888
889
):
    """
    Computes the transition matrix between clusters and the autocorrelation in the sequence.
    """

    # Stores all possible transitions between clusters
890
891
892
    clusters = [str(i) for i in range(nclusts)]
    cluster_sequence = cluster_sequence.astype(str)

893
894
895
896
897
898
899
    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
900
    for t in trans.keys():
901
902
903
        trans[t] = len(re.findall("".join(t), transtr, overlapped=True))

    # Normalizes the counts to add up to 1 for each departing cluster
904
905
    trans_normed = np.zeros([k, k]) + 1e-5
    for t in trans.keys():
906
        trans_normed[int(t[0]), int(t[1])] = np.round(
907
908
909
            trans[t]
            / (sum({i: j for i, j in trans.items() if i[0] == t[0]}.values()) + 1e-5),
            3,
910
911
912
913
914
915
916
917
918
919
920
921
        )

    # 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

922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
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
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
    ##### 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()