utils.py 42.1 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
from tqdm import tqdm
19
20
21
22
23
from typing import Tuple, Any, List, Union, Dict, NewType

# DEFINE CUSTOM ANNOTATED TYPES #


24
Coordinates = NewType("Coordinates", Any)
25
26


27
# QUALITY CONTROL AND PREPROCESSING #
28

29

lucas_miranda's avatar
lucas_miranda committed
30
31
32
33
34
35
36
37
38
39
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"""

40
41
    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
42
43
44
    filt_mask = np.all(Likes > threshold, axis=0)

    return filt_mask
45
46


47
48
49
50
51
52
53
54
55
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"""

56
57
58
59
60
61
62
    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


63
64
65
66
67
68
69
70
71
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"""

72
    result = []
73
74
    for df in list(cartesian_df.columns.levels[0]):
        result.append(bp2polar(cartesian_df[df]))
75
76
    result = pd.concat(result, axis=1)
    idx = pd.MultiIndex.from_product(
77
78
        [list(cartesian_df.columns.levels[0]), ["rho", "phi"]],
        names=["bodyparts", "coords"],
79
80
81
82
83
    )
    result.columns = idx
    return result


84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
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
99
100
    lim = 2 if pair_array.shape[1] == 4 else 1
    a, b = pair_array[:, :lim], pair_array[:, lim:]
101
    ab = a - b
lucas_miranda's avatar
lucas_miranda committed
102

103
    dist = np.sqrt(np.einsum("...i,...i", ab, ab))
104
105
106
    return pd.DataFrame(dist * arena_abs / arena_rel)


107
108
109
110
111
112
113
114
115
116
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
117

118
119
120
121
122
        Returns:
            - result (pd.DataFrame): pandas.DataFrame with the
            absolute distances between all pairs of body parts"""

    indexes = combinations(dataframe.columns.levels[0], 2)
123
124
125
126
127
128
129
    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)
130
131


132
133
134
135
136
137
138
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
139

140
141
142
        Returns:
            - ang (1D np.array): angles between the three-point-instances"""

lucas_miranda's avatar
lucas_miranda committed
143
144
145
    ba = a - b
    bc = c - b

146
    cosine_angle = np.einsum("...i,...i", ba, bc) / (
lucas_miranda's avatar
lucas_miranda committed
147
148
        np.linalg.norm(ba, axis=1) * np.linalg.norm(bc, axis=1)
    )
149
150
151
152
153
154
155
    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
156

157
158
        Parameters:
            - bpart_array (2D numpy.array): positions over time for a bodypart
lucas_miranda's avatar
lucas_miranda committed
159

160
161
        Returns:
            - ang_trio (2D numpy.array): all-three angles between the three-point-instances"""
lucas_miranda's avatar
lucas_miranda committed
162

163
164
    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
165

166
    return ang_trio
lucas_miranda's avatar
lucas_miranda committed
167
168


169
170
171
172
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
173

174
175
176
177
178
179
180
        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
181

182
183
184
185
186
    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)

187
188
189
190
    rotated = np.squeeze((R @ (p.T - o.T) + o.T).T)

    return rotated

191

192
193
194
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.
195

196
197
198
199
200
        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*
201

202
203
        Returns:
            - aligned_trajs (2D np.array): aligned positions over time"""
204

205
    angles = np.zeros(data.shape[0])
206
    data = deepcopy(data)
207
    dshape = data.shape
208

209
210
211
212
    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
213
        data = data.reshape(-1, dshape[-1], order="C")
214
        angles = np.arctan2(data[:, 0], data[:, 1])
lucas_miranda's avatar
lucas_miranda committed
215
216
217
    elif mode == "none":
        data = data.reshape(-1, dshape[-1], order="C")
        angles = np.zeros(data.shape[0])
218
219
220
221
222

    aligned_trajs = np.zeros(data.shape)

    for frame in range(data.shape[0]):
        aligned_trajs[frame] = rotate(
lucas_miranda's avatar
lucas_miranda committed
223
224
            data[frame].reshape([-1, 2], order="C"), angles[frame],
        ).reshape(data.shape[1:], order="C")
225

lucas_miranda's avatar
lucas_miranda committed
226
227
    if mode == "all" or mode == "none":
        aligned_trajs = aligned_trajs.reshape(dshape, order="C")
228

229
230
231
    return aligned_trajs


232
233
234
235
236
237
238
239
240
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"""

241
242
243
244
245
246
    for i in range(1, len(a) - 1):
        if a[i - 1] == a[i + 1]:
            a[i] = a[i - 1]
    return a == 1


247
248
249
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

250
251
        Parameters:
            - a (2D np.array): N (instances) * m (features) shape
252

253
254
255
        Returns:
            - rolled_a (3D np.array):
            N (sliding window instances) * l (sliding window size) * m (features)"""
256

257
258
    shape = (a.shape[0] - window_size + 1, window_size) + a.shape[1:]
    strides = (a.strides[0],) + a.strides
259
260
    rolled_a = np.lib.stride_tricks.as_strided(
        a, shape=shape, strides=strides, writeable=True
261
    )[::window_step]
262
    return rolled_a
263

264

265
266
267
def smooth_mult_trajectory(series: np.array, alpha: float = 0.15) -> np.array:
    """Returns a smooths a trajectory using exponentially weighted averages

268
269
        Parameters:
            - series (numpy.array): 1D trajectory array with N (instances) - alpha (float): 0 <= alpha <= 1;
270
271
            indicates the inverse weight assigned to previous observations. Higher (alpha~1) indicates less smoothing;
            lower indicates more (alpha~0)
272
273
274

        Returns:
            - smoothed_series (np.array): smoothed version of the input, with equal shape"""
275
276
277
278
279

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

280
281
282
    smoothed_series = np.array(result)

    return smoothed_series
283

lucas_miranda's avatar
lucas_miranda committed
284
285

# BEHAVIOUR RECOGNITION FUNCTIONS #
286
287


288
def close_single_contact(
289
290
291
292
293
294
    pos_dframe: pd.DataFrame,
    left: str,
    right: str,
    tol: float,
    arena_abs: int,
    arena_rel: int,
295
296
) -> np.array:
    """Returns a boolean array that's True if the specified body parts are closer than tol.
297

298
299
300
301
302
        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
303
304
305
            - tol (float): maximum distance for which a contact is reported
            - arena_abs (int): length in mm of the diameter of the real arena
            - arena_rel (int): length in pixels of the diameter of the arena in the video
306

307
308
309
        Returns:
            - contact_array (np.array): True if the distance between the two specified points
            is less than tol, False otherwise"""
310

311
312
313
    close_contact = (
        np.linalg.norm(pos_dframe[left] - pos_dframe[right], axis=1) * arena_abs
    ) / arena_rel < tol
314

315
    return close_contact
316
317


318
319
320
321
322
323
324
def close_double_contact(
    pos_dframe: pd.DataFrame,
    left1: str,
    left2: str,
    right1: str,
    right2: str,
    tol: float,
325
326
    arena_abs: int,
    arena_rel: int,
327
328
329
330
331
332
333
334
335
336
337
    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
338
339
340
341
            - tol (float): maximum distance for which a contact is reported
            - arena_abs (int): length in mm of the diameter of the real arena
            - arena_rel (int): length in pixels of the diameter of the arena in the video
            - rev (bool): reverses the default behaviour (nose2tail contact for both mice)
342
343
344
345
346
347
348

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

    if rev:
        double_contact = (
349
350
351
352
353
354
355
356
            (np.linalg.norm(pos_dframe[right1] - pos_dframe[left2], axis=1) * arena_abs)
            / arena_rel
            < tol
        ) & (
            (np.linalg.norm(pos_dframe[right2] - pos_dframe[left1], axis=1) * arena_abs)
            / arena_rel
            < tol
        )
357
358
359

    else:
        double_contact = (
360
361
362
363
364
365
366
367
            (np.linalg.norm(pos_dframe[right1] - pos_dframe[left1], axis=1) * arena_abs)
            / arena_rel
            < tol
        ) & (
            (np.linalg.norm(pos_dframe[right2] - pos_dframe[left2], axis=1) * arena_abs)
            / arena_rel
            < tol
        )
368
369

    return double_contact
370
371
372


def recognize_arena(
lucas_miranda's avatar
lucas_miranda committed
373
374
375
376
377
    videos: list,
    vid_index: int,
    path: str = ".",
    recoglimit: int = 1,
    arena_type: str = "circular",
378
) -> Tuple[np.array, int, int]:
lucas_miranda's avatar
lucas_miranda committed
379
380
381
    """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.

382
383
384
385
386
387
        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
388

389
390
        Returns:
            - arena (np.array): 1D-array containing information about the arena.
391
392
393
            "circular" (3-element-array) -> x-y position of the center and the radius
            - h (int): height of the video in pixels
            - w (int): width of the video in pixels"""
lucas_miranda's avatar
lucas_miranda committed
394
395

    cap = cv2.VideoCapture(os.path.join(path, videos[vid_index]))
396
397

    # Loop over the first frames in the video to get resolution and center of the arena
lucas_miranda's avatar
lucas_miranda committed
398
    arena, fnum, h, w = False, 0, None, None
399
400
401
402
403
404
405
406
407
408
409
410

    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]
411
            if h is None and w is None:
412
413
414
415
                h, w = frame.shape[0], frame.shape[1]

        fnum += 1

416
    return arena, h, w
417
418


419
420
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
421

422
        Parameters:
423
            - frame (np.array): numpy.array representing an individual frame of a video
424

425
426
427
        Returns:
            - circles (np.array): 3-element-array containing x,y positions of the center
            of the arena, and a third value indicating the radius"""
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

    # 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]


454
455
456
457
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
458

459
460
461
462
463
464
465
466
467
468
469
470
471
        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]
472

473
474
475
476
477
478
    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']")
479

480
    return climbing
481
482


lucas_miranda's avatar
lucas_miranda committed
483
484
485
486
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
487

lucas_miranda's avatar
lucas_miranda committed
488
489
490
491
492
493
        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
494

lucas_miranda's avatar
lucas_miranda committed
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
        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
513

lucas_miranda's avatar
lucas_miranda committed
514
515
516
517
518
519
520
        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
521

lucas_miranda's avatar
lucas_miranda committed
522
        dframe = speeds
lucas_miranda's avatar
lucas_miranda committed
523

lucas_miranda's avatar
lucas_miranda committed
524
    speeds.columns = body_parts
525
526
527
528

    return speeds


529
def huddle(
530
531
532
533
534
535
    pos_dframe: pd.DataFrame,
    speed_dframe: pd.DataFrame,
    tol_forward: float,
    tol_spine: float,
    tol_speed: float,
    animal_id: str = "",
536
) -> np.array:
lucas_miranda's avatar
lucas_miranda committed
537
538
    """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.
539

lucas_miranda's avatar
lucas_miranda committed
540
        Parameters:
541
542
            - pos_dframe (pandas.DataFrame): position of body parts over time
            - speed_dframe (pandas.DataFrame): speed of body parts over time
lucas_miranda's avatar
lucas_miranda committed
543
544
545
546
            - tol_forward (float): Maximum tolerated distance between ears and
            forward limbs
            - tol_rear (float): Maximum tolerated average distance between spine
            body parts
547
            - tol_speed (float): Maximum tolerated speed for the center of the mouse
lucas_miranda's avatar
lucas_miranda committed
548

lucas_miranda's avatar
lucas_miranda committed
549
550
551
552
        Returns:
            hudd (np.array): True if the animal is huddling, False otherwise
        """

553
554
555
    if animal_id != "":
        animal_id += "_"

lucas_miranda's avatar
lucas_miranda committed
556
    forward = (
557
558
559
560
        np.linalg.norm(
            pos_dframe[animal_id + "Left_ear"] - pos_dframe[animal_id + "Left_fhip"],
            axis=1,
        )
lucas_miranda's avatar
lucas_miranda committed
561
562
        < tol_forward
    ) & (
563
564
565
566
        np.linalg.norm(
            pos_dframe[animal_id + "Right_ear"] - pos_dframe[animal_id + "Right_fhip"],
            axis=1,
        )
lucas_miranda's avatar
lucas_miranda committed
567
        < tol_forward
568
569
    )

570
571
572
573
574
575
    spine = [
        animal_id + "Spine_1",
        animal_id + "Center",
        animal_id + "Spine_2",
        animal_id + "Tail_base",
    ]
lucas_miranda's avatar
lucas_miranda committed
576
577
578
579
580
581
582
583
    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
584
585
    speed = speed_dframe[animal_id + "Center"] < tol_speed
    hudd = forward & spine & speed
lucas_miranda's avatar
lucas_miranda committed
586
587
588

    return hudd

589

lucas_miranda's avatar
lucas_miranda committed
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
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"""
611
612

    # 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
613
614
615
    shift_dict = {
        i: position_dframe[followed + "_Tail_base"].shift(i) for i in range(frames)
    }
616
617
    dist_df = pd.DataFrame(
        {
lucas_miranda's avatar
lucas_miranda committed
618
619
620
            i: np.linalg.norm(
                position_dframe[follower + "_Nose"] - shift_dict[i], axis=1
            )
621
622
623
624
625
626
            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
627
628
629
630
        distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distance_dframe[
            tuple(sorted([follower + "_Tail_base", followed + "_Tail_base"]))
        ]
631
632
633
    )

    right_orient2 = (
lucas_miranda's avatar
lucas_miranda committed
634
635
        distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Tail_base"]))]
        < distance_dframe[tuple(sorted([follower + "_Nose", followed + "_Nose"]))]
636
637
    )

lucas_miranda's avatar
lucas_miranda committed
638
639
    follow = np.all(
        np.array([(dist_df.min(axis=1) < tol), right_orient1, right_orient2]), axis=0,
640
641
    )

lucas_miranda's avatar
lucas_miranda committed
642
643
    return follow

644

lucas_miranda's avatar
lucas_miranda committed
645
def single_behaviour_analysis(
646
647
648
649
650
651
652
653
    behaviour_name: str,
    treatment_dict: dict,
    behavioural_dict: dict,
    plot: int = 0,
    stat_tests: bool = True,
    save: str = None,
    ylim: float = None,
) -> list:
654
    """Given the name of the behaviour, a dictionary with the names of the groups to compare, and a dictionary
655
656
657
658
659
660
661
662
663
664
665
666
667
668
       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"""
669
670
671
672
673
674
675
676
677
678

    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])
            )

679
    return_list = [beh_dict]
680

681
    if plot > 0:
682

683
        fig, ax = plt.subplots(dpi=plot)
684

685
686
687
688
689
690
691
692
693
        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)
694

695
        if save is not None:
696
697
            plt.savefig(save)

698
        return_list.append(ax)
699

700
701
    if stat_tests:
        stat_dict = {}
702
        for i in combinations(treatment_dict.keys(), 2):
703
704
705
706
707
708
709
710
711
712
713
            # 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"
                )
714
        return_list.append(stat_dict)
715

716
    return return_list
717
718


719
720
721
722
723
724
725
726
727
728
729
730
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

731
732
733
        Returns:
            - max_array (np.array): string array with the most common behaviour per instance
            of the sliding window"""
734
735
736
737
738
739
740

    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]
741
742
    max_array = win_array[1:].idxmax(axis=1)

743
744
745
746
    return np.array(max_array)


# MACHINE LEARNING FUNCTIONS #
747
748


749
750
751
752
753
754
755
756
757
758
759
760
761
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
    """

762
763
764
765
766
767
768
    gmm = mixture.GaussianMixture(
        n_components=n_components,
        covariance_type=cv_type,
        max_iter=100000,
        init_params="kmeans",
    )
    gmm.fit(x)
769
770
771
772
773
    gmm_eval = [gmm, gmm.bic(x)]
    return gmm_eval


def gmm_model_selection(
774
    x: pd.DataFrame,
775
776
777
778
779
780
781
782
    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
783

784
        Parameters:
785
            - x (pandas.DataFrame): data matrix to train the models
786
787
788
789
790
            - 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
791

792
793
794
795
796
797
798
        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
    """
799
800
801
802
803
804
805
806

    # 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
807
    best_bic_gmm = 0
808
809
810
811
812
813
814
815

    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")(
816
817
818
819
                delayed(gmm_compute)(
                    x.sample(part_size, replace=True), n_components, cv_type
                )
                for _ in range(n_runs)
820
821
822
823
824
825
826
827
828
829
830
            )
            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

831
832

# RESULT ANALYSIS FUNCTIONS #
833
834
835


def cluster_transition_matrix(
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
    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):
852
853
854
    """

    # Stores all possible transitions between clusters
855
856
857
    clusters = [str(i) for i in range(nclusts)]
    cluster_sequence = cluster_sequence.astype(str)

858
859
860
861
862
863
864
    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
865
    for t in trans.keys():
866
867
868
        trans[t] = len(re.findall("".join(t), transtr, overlapped=True))

    # Normalizes the counts to add up to 1 for each departing cluster
869
870
    trans_normed = np.zeros([k, k]) + 1e-5
    for t in trans.keys():
871
        trans_normed[int(t[0]), int(t[1])] = np.round(
872
873
874
            trans[t]
            / (sum({i: j for i, j in trans.items() if i[0] == t[0]}.values()) + 1e-5),
            3,
875
876
877
878
879
880
881
882
        )

    # 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))
883
884
        autocorr = np.corrcoef(cluster_sequence[:-1], cluster_sequence[1:])
        return trans_normed, autocorr
885
886
887

    return trans_normed

888

889
890
891
892
893
894
# MAIN BEHAVIOUR TAGGING FUNCTION #


def rule_based_tagging(
    tracks: List,
    videos: List,
895
    coordinates: Coordinates,
896
897
898
899
900
901
902
903
904
905
906
907
    vid_index: int,
    arena_abs: int,
    animal_ids: List = None,
    show: bool = False,
    save: bool = False,
    fps: float = 25.0,
    speed_pause: int = 50,
    frame_limit: float = np.inf,
    recog_limit: int = 1,
    path: str = os.path.join("./"),
    arena_type: str = "circular",
    classifiers: Dict = None,
908
909
910
911
912
913
914
    close_contact_tol: int = 15,
    side_contact_tol: int = 15,
    follow_frames: int = 20,
    follow_tol: int = 20,
    huddle_forward: int = 15,
    huddle_spine: int = 10,
    huddle_speed: int = 5,
915
916
) -> pd.DataFrame:
    """Outputs a dataframe with the motives registered per frame."""
917
918
919

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

920
    coords = coordinates.get_coords()[vid_name]
921
    speeds = coordinates.get_coords(speed=1)[vid_name]
922
923
924
    arena, h, w = recognize_arena(videos, vid_index, path, recog_limit, arena_type)

    # Dictionary with motives per frame
925
    tag_dict = {}
926
927
928
929
930

    if animal_ids:
        # Define behaviours that can be computed on the fly from the distance matrix
        tag_dict["nose2nose"] = smooth_boolean_array(
            close_single_contact(
931
                coords,
932
933
                animal_ids[0] + "_Nose",
                animal_ids[1] + "_Nose",
934
                close_contact_tol,
935
936
937
938
939
940
                arena_abs,
                arena[2],
            )
        )
        tag_dict[animal_ids[0] + "_nose2tail"] = smooth_boolean_array(
            close_single_contact(
941
                coords,
942
943
                animal_ids[0] + "_Nose",
                animal_ids[1] + "_Tail_base",
944
                close_contact_tol,
945
946
947
948
949
950
                arena_abs,
                arena[2],
            )
        )
        tag_dict[animal_ids[1] + "_nose2tail"] = smooth_boolean_array(
            close_single_contact(
951
                coords,
952
953
                animal_ids[1] + "_Nose",
                animal_ids[0] + "_Tail_base",
954
                close_contact_tol,
955
956
957
958
959
960
                arena_abs,
                arena[2],
            )
        )
        tag_dict["sidebyside"] = smooth_boolean_array(
            close_double_contact(
961
                coords,
962
963
964
965
                animal_ids[0] + "_Nose",
                animal_ids[0] + "_Tail_base",
                animal_ids[1] + "_Nose",
                animal_ids[1] + "_Tail_base",
966
                side_contact_tol,
967
968
969
970
971
972
973
                rev=False,
                arena_abs=arena_abs,
                arena_rel=arena[2],
            )
        )
        tag_dict["sidereside"] = smooth_boolean_array(
            close_double_contact(
974
                coords,
975
976
977
978
                animal_ids[0] + "_Nose",
                animal_ids[0] + "_Tail_base",
                animal_ids[1] + "_Nose",
                animal_ids[1] + "_Tail_base",
979
                side_contact_tol,
980
981
982
983
984
985
986
987
                rev=True,
                arena_abs=arena_abs,
                arena_rel=arena[2],
            )
        )
        for _id in animal_ids:
            tag_dict[_id + "_following"] = smooth_boolean_array(
                following_path(
988
989
                    coords[vid_name],
                    coords,
990
991
                    follower=_id,
                    followed=[i for i in animal_ids if i != _id][0],
992
993
                    frames=follow_frames,
                    tol=follow_tol,
994
995
                )
            )
996
            tag_dict[_id + "_climbing"] = smooth_boolean_array(
997
998
999
                pd.Series(
                    (
                        spatial.distance.cdist(
1000
                            np.array(coords[_id + "_Nose"]), np.array([arena[:2]])
1001
1002
                        )
                        > (w / 200 + arena[2])
1003
1004
                    ).reshape(coords.shape[0]),
                    index=coords.index,
1005
                ).astype(bool)
1006
            )
1007
            tag_dict[_id + "_speed"] = speeds[_id + "_speed"]
1008
1009

    else:
1010
        tag_dict["climbing"] = smooth_boolean_array(
1011
1012
1013
            pd.Series(
                (
                    spatial.distance.cdist(
1014
                        np.array(coords["Nose"]), np.array([arena[:2]])
1015
1016
                    )
                    > (w / 200 + arena[2])
1017
1018
                ).reshape(coords.shape[0]),
                index=coords.index,
1019
            ).astype(bool)
1020
        )
1021
        tag_dict["speed"] = speeds["Center"]
1022

1023
    if classifiers and "huddle" in classifiers:
1024
1025
        mouse_X = {
            _id: np.array(
1026
                coords[vid_name][
1027
1028
                    [
                        j
1029
                        for j in coords[vid_name].keys()
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
                        if (len(j) == 2 and _id in j[0] and _id in j[1])
                    ]
                ]
            )
            for _id in animal_ids
        }
        for _id in animal_ids:
            tag_dict[_id + "_huddle"] = smooth_boolean_array(
                classifiers["huddle"].predict(mouse_X[_id])
            )
    else:
        try:
            for _id in animal_ids:
                tag_dict[_id + "_huddle"] = smooth_boolean_array(
1044
                    huddle(coords, speeds, huddle_forward, huddle_spine, huddle_speed)
1045
1046
                )
        except TypeError:
1047
1048
1049
            tag_dict["huddle"] = smooth_boolean_array(
                huddle(coords, speeds, huddle_forward, huddle_spine, huddle_speed)
            )
1050
1051
1052

    # if any([show, save]):
    #     cap = cv2.VideoCapture(path + videos[vid_index])
1053
1054
1055
1056
1057
1058
    #
    #     # Keep track of the frame number, to align with the tracking data
    #     fnum = 0
    #     if save:
    #         writer = None
    #
1059
    #     # Loop over the frames in the video
1060
    #     pbar = tqdm(total=min(coords.shape[0] - recog_limit, frame_limit))
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
    #     while cap.isOpened() and fnum < frame_limit:
    #
    #         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 = {
1075
1076
    #                 i: np.array([coords[i]["x"][fnum], coords[i]["y"][fnum]])
    #                 for i in coords.columns.levels[0]
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
    #                 if i != "Like_QC"
    #             }
    #
    #             if h is None and w is 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 tag_dict["nose2nose"][fnum] and not tag_dict["sidebyside"][fnum]:
    #                 cv2.putText(
    #                     frame,
    #                     "Nose-Nose",
    #                     (downleft if bspeed > wspeed else downright),
    #                     font,
    #                     1,
    #                     (255, 255, 255),
    #                     2,
    #                 )
    #             if tag_dict["bnose2tail"][fnum] and not tag_dict["sidereside"][fnum]:
    #                 cv2.putText(
    #                     frame, "Nose-Tail", downleft, font, 1, (255, 255, 255), 2
    #                 )
    #             if tag_dict["wnose2tail"][fnum] and not tag_dict["sidereside"][fnum]:
    #                 cv2.putText(
    #                     frame, "Nose-Tail", downright, font, 1, (255, 255, 255), 2
    #                 )
    #             if tag_dict["sidebyside"][fnum]:
    #                 cv2.putText(
    #                     frame,
    #                     "Side-side",
    #                     (downleft if bspeed > wspeed else downright),
    #                     font,
    #                     1,
    #                     (255, 255, 255),
    #                     2,
    #                 )
    #             if tag_dict["sidereside"][fnum]:
    #                 cv2.putText(
    #                     frame,
    #                     "Side-Rside",
    #                     (downleft if bspeed > wspeed else downright),
    #                     font,
    #                     1,
    #                     (255, 255, 255),
    #                     2,
    #                 )
    #             if tag_dict["bclimbwall"][fnum]:
    #                 cv2.putText(
    #                     frame, "Climbing", downleft, font, 1, (255, 255, 255), 2
    #                 )
    #             if tag_dict["wclimbwall"][fnum]:
    #                 cv2.putText(
    #                     frame, "Climbing", downright, font, 1, (255, 255, 255), 2
    #                 )
    #             if tag_dict["bhuddle"][fnum] and not tag_dict["bclimbwall"][fnum]:
    #                 cv2.putText(frame, "huddle", downleft, font, 1, (255, 255, 255), 2)
    #             if tag_dict["whuddle"][fnum] and not tag_dict["wclimbwall"][fnum]:
    #                 cv2.putText(frame, "huddle", downright, font, 1, (255, 255, 255), 2)
    #             if tag_dict["bfollowing"][fnum] and not tag_dict["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 tag_dict["wfollowing"][fnum] and not tag_dict["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 % speed_pause == 0:
    #                 bspeed = tag_dict["bspeed"][fnum]
    #                 wspeed = tag_dict["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,
    #             )
    #
    #             if show:
    #                 cv2.imshow("frame", frame)
    #
    #             if save:
    #
    #                 if writer is None:
    #                     # 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
1207
    #
1208
1209
1210
    # cap.release()
    # cv2.destroyAllWindows()

1211
    tag_df = pd.DataFrame(tag_dict)
1212

1213
    return tag_df
1214
1215


1216
1217
# TODO:
#    - Add sequence plot to single_behaviour_analysis (show how the condition varies across a specified time window)
1218
1219
1220
#    - Add digging to rule_based_tagging
#    - Add center to rule_based_tagging
#    - Check for features requested by Joeri
1221
1222
1223
1224

#    - Check speed. Avoid recomputing unnecessarily
#    - Pass thresholds as parameters of the function. Provide defaults (we should tune them in the future)
#    - Check if attributes I'm asking for (eg arena) are already stored in Table_dict metadata