test_utils.py 23 KB
Newer Older
1
2
3
# @author lucasmiranda42

from hypothesis import given
4
from hypothesis import HealthCheck
lucas_miranda's avatar
lucas_miranda committed
5
from hypothesis import settings
6
7
8
9
from hypothesis import strategies as st
from hypothesis.extra.numpy import arrays
from hypothesis.extra.pandas import range_indexes, columns, data_frames
from scipy.spatial import distance
lucas_miranda's avatar
lucas_miranda committed
10
from deepof.utils import *
11
12
import deepof.preprocess
import pytest
13
import string
14

15

lucas_miranda's avatar
lucas_miranda committed
16
17
18
19
20
21
# AUXILIARY FUNCTIONS #


def autocorr(x, t=1):
    return np.round(np.corrcoef(np.array([x[:-t], x[t:]]))[0, 1], 5)

22

23
24
25
# QUALITY CONTROL AND PREPROCESSING #


lucas_miranda's avatar
lucas_miranda committed
26
@settings(deadline=None)
lucas_miranda's avatar
lucas_miranda committed
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
@given(
    mult=st.integers(min_value=1, max_value=10),
    dframe=data_frames(
        index=range_indexes(min_size=1),
        columns=columns(["X", "y", "likelihood"], dtype=float),
        rows=st.tuples(
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
            st.floats(
                min_value=0.01, max_value=1.0, allow_nan=False, allow_infinity=False
            ),
        ),
    ),
    threshold=st.data(),
)
def test_likelihood_qc(mult, dframe, threshold):
    thresh1 = threshold.draw(st.floats(min_value=0.1, max_value=1.0, allow_nan=False))
    thresh2 = threshold.draw(
        st.floats(min_value=thresh1, max_value=1.0, allow_nan=False)
    )

    dframe = pd.concat([dframe] * mult, axis=0)
    idx = pd.MultiIndex.from_product(
        [list(dframe.columns[: len(dframe.columns) // 3]), ["X", "y", "likelihood"]],
        names=["bodyparts", "coords"],
    )
    dframe.columns = idx

    filt1 = likelihood_qc(dframe, thresh1)
    filt2 = likelihood_qc(dframe, thresh2)

    assert np.sum(filt1) <= dframe.shape[0]
    assert np.sum(filt2) <= dframe.shape[0]
    assert np.sum(filt1) >= np.sum(filt2)


lucas_miranda's avatar
lucas_miranda committed
67
@settings(deadline=None)
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
@given(
    tab=data_frames(
        index=range_indexes(min_size=1),
        columns=columns(["X", "y"], dtype=float),
        rows=st.tuples(
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
        ),
    )
)
def test_bp2polar(tab):
    polar = bp2polar(tab)
    assert np.allclose(polar["rho"], np.sqrt(tab["X"] ** 2 + tab["y"] ** 2))
    assert np.allclose(polar["phi"], np.arctan2(tab["y"], tab["X"]))


lucas_miranda's avatar
lucas_miranda committed
88
@settings(deadline=None)
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
@given(
    mult=st.integers(min_value=1, max_value=10),
    cartdf=data_frames(
        index=range_indexes(min_size=1),
        columns=columns(["X", "y"], dtype=float),
        rows=st.tuples(
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
            st.floats(
                min_value=0, max_value=1000, allow_nan=False, allow_infinity=False
            ),
        ),
    ),
)
def test_tab2polar(mult, cartdf):
    cart_df = pd.concat([cartdf] * mult, axis=0)
    idx = pd.MultiIndex.from_product(
        [list(cart_df.columns[: len(cart_df.columns) // 2]), ["X", "y"]],
        names=["bodyparts", "coords"],
    )
    cart_df.columns = idx

    assert cart_df.shape == tab2polar(cart_df).shape


lucas_miranda's avatar
lucas_miranda committed
115
@settings(deadline=None)
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
@given(
    pair_array=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=1, max_value=1000),
            st.integers(min_value=4, max_value=4),
        ),
        elements=st.floats(min_value=-1000, max_value=1000, allow_nan=False),
    ),
    arena_abs=st.integers(min_value=1, max_value=1000),
    arena_rel=st.integers(min_value=1, max_value=1000),
)
def test_compute_dist(pair_array, arena_abs, arena_rel):
    assert np.allclose(
        compute_dist(pair_array, arena_abs, arena_rel),
        pd.DataFrame(distance.cdist(pair_array[:, :2], pair_array[:, 2:]).diagonal())
        * arena_abs
        / arena_rel,
    )


lucas_miranda's avatar
lucas_miranda committed
137
@settings(deadline=None)
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
@given(
    cordarray=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=1, max_value=100),
            st.integers(min_value=2, max_value=5).map(lambda x: 4 * x),
        ),
        elements=st.floats(
            min_value=-1000, max_value=1000, allow_nan=False, allow_infinity=False
        ),
    ),
)
def test_bpart_distance(cordarray):
    cord_df = pd.DataFrame(cordarray)
    idx = pd.MultiIndex.from_product(
        [list(cord_df.columns[: len(cord_df.columns) // 2]), ["X", "y"]],
        names=["bodyparts", "coords"],
    )
    cord_df.columns = idx

    bpart = bpart_distance(cord_df)

    assert bpart.shape[0] == cord_df.shape[0]
    assert bpart.shape[1] == len(list(combinations(range(cord_df.shape[1] // 2), 2)))


lucas_miranda's avatar
lucas_miranda committed
164
@settings(deadline=None)
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
@given(
    abc=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=3, max_value=3),
            st.integers(min_value=5, max_value=100),
            st.integers(min_value=2, max_value=2),
        ),
        elements=st.floats(
            min_value=1, max_value=10, allow_nan=False, allow_infinity=False
        ).map(lambda x: x + np.random.uniform(0, 10)),
    ),
)
def test_angle(abc):
    a, b, c = abc

    angles = []
    for i, j, k in zip(a, b, c):
        ang = np.arccos(
            (np.dot(i - j, k - j) / (np.linalg.norm(i - j) * np.linalg.norm(k - j)))
        )
        angles.append(ang)

    print(angle(a, b, c), np.array(angles))

    assert np.allclose(angle(a, b, c), np.array(angles))


lucas_miranda's avatar
lucas_miranda committed
193
@settings(deadline=None)
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
@given(
    array=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=3, max_value=3),
            st.integers(min_value=5, max_value=100),
            st.integers(min_value=2, max_value=2),
        ),
        elements=st.floats(
            min_value=1, max_value=10, allow_nan=False, allow_infinity=False
        ).map(lambda x: x + np.random.uniform(0, 10)),
    )
)
def test_angle_trio(array):
    assert len(angle_trio(array)) == 3


lucas_miranda's avatar
lucas_miranda committed
211
@settings(deadline=None)
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
@given(
    p=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=2, max_value=100),
            st.integers(min_value=2, max_value=2),
        ),
        elements=st.floats(
            min_value=1, max_value=10, allow_nan=False, allow_infinity=False
        ),
    )
)
def test_rotate(p):
    assert np.allclose(rotate(p, 2 * np.pi), p)
    assert np.allclose(rotate(p, np.pi), -p)
lucas_miranda's avatar
lucas_miranda committed
227
    assert np.allclose(rotate(p, 0), p)
228
229


lucas_miranda's avatar
lucas_miranda committed
230
@settings(deadline=None)
231
232
233
234
235
236
237
238
239
240
241
@given(
    data=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=1, max_value=100),
            st.integers(min_value=3, max_value=100),
            st.integers(min_value=1, max_value=10).map(lambda x: 2 * x),
        ),
        elements=st.floats(
            min_value=1, max_value=10, allow_nan=False, allow_infinity=False
        ),
242
    ),
lucas_miranda's avatar
lucas_miranda committed
243
    mode_idx=st.integers(min_value=0, max_value=2),
244
)
245
def test_align_trajectories(data, mode_idx):
lucas_miranda's avatar
lucas_miranda committed
246
    mode = ["center", "all", "none"][mode_idx]
247
248
249
250
251
252
    aligned = align_trajectories(data, mode)
    assert aligned.shape == data.shape
    if mode == "center":
        assert np.allclose(aligned[:, (data.shape[1] - 1) // 2, 0], 0)
    elif mode == "all":
        assert np.allclose(aligned[:, :, 0], 0)
lucas_miranda's avatar
lucas_miranda committed
253
254
    elif mode == "none":
        assert np.allclose(aligned, data)
255
256


lucas_miranda's avatar
lucas_miranda committed
257
@settings(deadline=None)
258
259
260
@given(a=arrays(dtype=bool, shape=st.tuples(st.integers(min_value=3, max_value=1000))))
def test_smooth_boolean_array(a):
    smooth = smooth_boolean_array(a)
lucas_miranda's avatar
lucas_miranda committed
261
262
263
264

    def trans(x):
        return sum([i + 1 != i for i in range(x.shape[0] - 1)])

265
266
267
    assert trans(a) >= trans(smooth)


lucas_miranda's avatar
lucas_miranda committed
268
@settings(deadline=None)
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
@given(
    a=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=1000, max_value=10000),
            st.integers(min_value=1, max_value=10).map(lambda x: 2 * x),
        ),
        elements=st.floats(
            min_value=1, max_value=10, allow_nan=False, allow_infinity=False
        ),
    ),
    window=st.data(),
)
def test_rolling_window(a, window):
    window_step = window.draw(st.integers(min_value=1, max_value=10))
    window_size = window.draw(
        st.integers(min_value=1, max_value=10).map(lambda x: x * window_step)
    )

    rolled_shape = rolling_window(a, window_size, window_step).shape

290
    assert len(rolled_shape) == len(a.shape) + 1
291
    assert rolled_shape[1] == window_size
lucas_miranda's avatar
lucas_miranda committed
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


@settings(deadline=None)
@given(
    alpha=st.data(),
    series=arrays(
        dtype=float,
        shape=st.tuples(st.integers(min_value=10, max_value=1000),),
        elements=st.floats(
            min_value=1.0, max_value=1.0, allow_nan=False, allow_infinity=False
        ),
    ),
)
def test_smooth_mult_trajectory(alpha, series):
    alpha1 = alpha.draw(
        st.floats(min_value=0.1, max_value=1.0, allow_nan=False, allow_infinity=False)
    )
    alpha2 = alpha.draw(
        st.floats(
            min_value=alpha1, max_value=1.0, allow_nan=False, allow_infinity=False
        )
    )

    series *= +np.random.normal(0, 1, len(series))

    smoothed1 = smooth_mult_trajectory(series, alpha1)
    smoothed2 = smooth_mult_trajectory(series, alpha2)

    assert autocorr(smoothed1) >= autocorr(series)
    assert autocorr(smoothed2) >= autocorr(series)
    assert autocorr(smoothed2) <= autocorr(smoothed1)
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339


# BEHAVIOUR RECOGNITION FUNCTIONS #


@settings(deadline=None)
@given(
    pos_dframe=data_frames(
        index=range_indexes(min_size=5),
        columns=columns(["X1", "y1", "X2", "y2"], dtype=float),
        rows=st.tuples(
            st.floats(min_value=1, max_value=10, allow_nan=False, allow_infinity=False),
            st.floats(min_value=1, max_value=10, allow_nan=False, allow_infinity=False),
            st.floats(min_value=1, max_value=10, allow_nan=False, allow_infinity=False),
            st.floats(min_value=1, max_value=10, allow_nan=False, allow_infinity=False),
        ),
    ),
340
    tol=st.floats(min_value=0.01, max_value=4.98),
341
342
343
344
345
346
347
)
def test_close_single_contact(pos_dframe, tol):

    idx = pd.MultiIndex.from_product(
        [["bpart1", "bpart2"], ["X", "y"]], names=["bodyparts", "coords"],
    )
    pos_dframe.columns = idx
348
    close_contact = close_single_contact(pos_dframe, "bpart1", "bpart2", tol, 1, 1)
349
350
    assert close_contact.dtype == bool
    assert np.array(close_contact).shape[0] <= pos_dframe.shape[0]
351
352
353
354
355
356
357
358


@settings(deadline=None)
@given(
    pos_dframe=data_frames(
        index=range_indexes(min_size=5),
        columns=columns(["X1", "y1", "X2", "y2", "X3", "y3", "X4", "y4"], dtype=float),
        rows=st.tuples(
lucas_miranda's avatar
lucas_miranda committed
359
360
361
362
363
364
365
366
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
367
368
369
370
371
372
373
374
375
376
377
378
379
        ),
    ),
    tol=st.floats(min_value=0.01, max_value=4.98),
    rev=st.booleans(),
)
def test_close_double_contact(pos_dframe, tol, rev):

    idx = pd.MultiIndex.from_product(
        [["bpart1", "bpart2", "bpart3", "bpart4"], ["X", "y"]],
        names=["bodyparts", "coords"],
    )
    pos_dframe.columns = idx
    close_contact = close_double_contact(
380
        pos_dframe, "bpart1", "bpart2", "bpart3", "bpart4", tol, 1, 1, rev
381
382
383
    )
    assert close_contact.dtype == bool
    assert np.array(close_contact).shape[0] <= pos_dframe.shape[0]
lucas_miranda's avatar
lucas_miranda committed
384
385


386
@settings(deadline=None)
387
388
@given(indexes=st.data())
def test_recognize_arena_and_subfunctions(indexes):
lucas_miranda's avatar
lucas_miranda committed
389

390
    path = os.path.join(".", "tests", "test_examples", "Videos")
lucas_miranda's avatar
lucas_miranda committed
391
392
393
394
395
    videos = [i for i in os.listdir(path) if i.endswith("mp4")]

    vid_index = indexes.draw(st.integers(min_value=0, max_value=len(videos) - 1))
    recoglimit = indexes.draw(st.integers(min_value=1, max_value=10))

396
    assert recognize_arena(videos, vid_index, path, recoglimit, "")[0] == 0
397
    assert len(recognize_arena(videos, vid_index, path, recoglimit, "circular")) == 3
398
399
400
401
402
403
404
    assert len(recognize_arena(videos, vid_index, path, recoglimit, "circular")[0]) == 3
    assert (
        type(recognize_arena(videos, vid_index, path, recoglimit, "circular")[1]) == int
    )
    assert (
        type(recognize_arena(videos, vid_index, path, recoglimit, "circular")[2]) == int
    )
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420


@settings(deadline=None)
@given(
    arena=st.lists(
        min_size=3, max_size=3, elements=st.integers(min_value=300, max_value=500)
    ),
    tol=st.data(),
)
def test_climb_wall(arena, tol):

    tol1 = tol.draw(st.floats(min_value=0.001, max_value=10))
    tol2 = tol.draw(st.floats(min_value=tol1, max_value=10))

    prun = (
        deepof.preprocess.project(
421
            path=os.path.join(".", "tests", "test_examples"),
422
            arena="circular",
423
            arena_dims=[arena[2]],
424
425
426
427
            angles=False,
            video_format=".mp4",
            table_format=".h5",
        )
428
        .run(verbose=True)
429
430
431
432
433
434
435
436
437
438
439
440
        .get_coords()
    )

    climb1 = climb_wall("circular", arena, prun["test"], tol1, nose="Nose")
    climb2 = climb_wall("circular", arena, prun["test"], tol2, nose="Nose")

    assert climb1.dtype == bool
    assert climb2.dtype == bool
    assert np.sum(climb1) >= np.sum(climb2)

    with pytest.raises(NotImplementedError):
        climb_wall("", arena, prun["test"], tol1, nose="Nose")
lucas_miranda's avatar
lucas_miranda committed
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


@settings(deadline=None)
@given(
    dframe=data_frames(
        index=range_indexes(min_size=50),
        columns=columns(["X1", "y1", "X2", "y2"], dtype=float),
        rows=st.tuples(
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
            st.floats(min_value=1, max_value=10),
        ),
    ),
    sampler=st.data(),
)
def test_rolling_speed(dframe, sampler):

    dframe *= np.random.uniform(0, 1, dframe.shape)

    order1 = sampler.draw(st.integers(min_value=1, max_value=3))
    order2 = sampler.draw(st.integers(min_value=order1, max_value=3))

    idx = pd.MultiIndex.from_product(
        [["bpart1", "bpart2"], ["X", "y"]], names=["bodyparts", "coords"],
    )
    dframe.columns = idx

    speeds1 = rolling_speed(dframe, 5, 10, order1)
    speeds2 = rolling_speed(dframe, 5, 10, order2)

    assert speeds1.shape[0] == dframe.shape[0]
    assert speeds1.shape[1] == dframe.shape[1] // 2
    assert np.all(np.std(speeds1) >= np.std(speeds2))
lucas_miranda's avatar
lucas_miranda committed
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


@settings(deadline=None)
@given(
    pos_dframe=data_frames(
        index=range_indexes(min_size=5),
        columns=columns(
            [
                "X1",
                "y1",
                "X2",
                "y2",
                "X3",
                "y3",
                "X4",
                "y4",
                "X5",
                "y5",
                "X6",
                "y6",
                "X7",
                "y7",
                "X8",
                "y8",
            ],
            dtype=float,
            elements=st.floats(min_value=-20, max_value=20),
        ),
    ),
    tol_forward=st.floats(min_value=0.01, max_value=4.98),
    tol_spine=st.floats(min_value=0.01, max_value=4.98),
506
    tol_speed=st.floats(min_value=0.01, max_value=4.98),
507
    animal_id=st.text(min_size=0, max_size=15, alphabet=string.ascii_lowercase),
lucas_miranda's avatar
lucas_miranda committed
508
)
509
510
511
512
513
def test_huddle(pos_dframe, tol_forward, tol_spine, tol_speed, animal_id):

    _id = animal_id
    if animal_id != "":
        _id += "_"
lucas_miranda's avatar
lucas_miranda committed
514
515
516
517

    idx = pd.MultiIndex.from_product(
        [
            [
518
519
520
521
522
523
524
525
                _id + "Left_ear",
                _id + "Right_ear",
                _id + "Left_fhip",
                _id + "Right_fhip",
                _id + "Spine_1",
                _id + "Center",
                _id + "Spine_2",
                _id + "Tail_base",
lucas_miranda's avatar
lucas_miranda committed
526
527
528
529
530
531
            ],
            ["X", "y"],
        ],
        names=["bodyparts", "coords"],
    )
    pos_dframe.columns = idx
532
533
534
535
536
537
538
539
    hudd = huddle(
        pos_dframe,
        pos_dframe.xs("X", level="coords", axis=1, drop_level=True),
        tol_forward,
        tol_spine,
        tol_speed,
        animal_id,
    )
lucas_miranda's avatar
lucas_miranda committed
540
541
542
543

    assert hudd.dtype == bool
    assert np.array(hudd).shape[0] == pos_dframe.shape[0]
    assert np.sum(np.array(hudd)) <= pos_dframe.shape[0]
lucas_miranda's avatar
lucas_miranda committed
544
545
546
547
548
549
550


@settings(deadline=None)
@given(
    distance_dframe=data_frames(
        index=range_indexes(min_size=20, max_size=20),
        columns=columns(
551
            ["d1", "d2", "d3", "d4"],
lucas_miranda's avatar
lucas_miranda committed
552
553
554
555
556
557
558
            dtype=float,
            elements=st.floats(min_value=-20, max_value=20),
        ),
    ),
    position_dframe=data_frames(
        index=range_indexes(min_size=20, max_size=20),
        columns=columns(
559
            ["X1", "y1", "X2", "y2", "X3", "y3", "X4", "y4"],
lucas_miranda's avatar
lucas_miranda committed
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
            dtype=float,
            elements=st.floats(min_value=-20, max_value=20),
        ),
    ),
    frames=st.integers(min_value=1, max_value=20),
    tol=st.floats(min_value=0.01, max_value=4.98),
)
def test_following_path(distance_dframe, position_dframe, frames, tol):

    bparts = [
        "A_Nose",
        "B_Nose",
        "A_Tail_base",
        "B_Tail_base",
    ]

    pos_idx = pd.MultiIndex.from_product(
577
        [bparts, ["X", "y"]], names=["bodyparts", "coords"],
lucas_miranda's avatar
lucas_miranda committed
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
    )

    position_dframe.columns = pos_idx
    distance_dframe.columns = [c for c in combinations(bparts, 2) if c[0][0] != c[1][0]]

    follow = following_path(
        distance_dframe,
        position_dframe,
        follower="A",
        followed="B",
        frames=frames,
        tol=tol,
    )

    assert follow.dtype == bool
    assert len(follow) == position_dframe.shape[0]
    assert len(follow) == distance_dframe.shape[0]
    assert np.sum(follow) <= position_dframe.shape[0]
    assert np.sum(follow) <= distance_dframe.shape[0]
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


@settings(
    deadline=None, suppress_health_check=[HealthCheck.too_slow],
)
@given(sampler=st.data())
def test_single_behaviour_analysis(sampler):
    behaviours = sampler.draw(
        st.lists(min_size=2, elements=st.text(min_size=5), unique=True)
    )
    treatments = sampler.draw(
        st.lists(min_size=2, max_size=4, elements=st.text(min_size=5), unique=True)
    )

    behavioural_dict = sampler.draw(
        st.dictionaries(
            min_size=2,
            keys=st.text(min_size=5),
            values=data_frames(
                index=range_indexes(min_size=50, max_size=50),
                columns=columns(behaviours, dtype=bool),
            ),
        )
    )

    ind_dict = {vid: np.random.choice(treatments) for vid in behavioural_dict.keys()}
    treatment_dict = {treat: [] for treat in set(ind_dict.values())}
    for vid, treat in ind_dict.items():
        treatment_dict[treat].append(vid)

    ylim = sampler.draw(st.floats(min_value=0, max_value=10))
    stat_tests = sampler.draw(st.booleans())

    out = single_behaviour_analysis(
        behaviours[0],
        treatment_dict,
        behavioural_dict,
        plot=0,
        stat_tests=stat_tests,
        save=None,
        ylim=ylim,
    )

    assert len(out) == 1 if stat_tests == 0 else len(out) == 2
    assert type(out[0]) == dict
    if stat_tests:
        assert type(out[0]) == dict
644
645
646
647
648
649
650
651
652
653
654
655
656


@settings(
    deadline=None, suppress_health_check=[HealthCheck.too_slow],
)
@given(
    behaviour_dframe=data_frames(
        index=range_indexes(min_size=100, max_size=1000),
        columns=columns(
            ["d1", "d2", "d3", "d4", "speed1"], dtype=bool, elements=st.booleans(),
        ),
    ),
    window_size=st.data(),
657
    stepped=st.booleans(),
658
)
659
def test_max_behaviour(behaviour_dframe, window_size, stepped):
660
661
662
    wsize1 = window_size.draw(st.integers(min_value=5, max_value=50))
    wsize2 = window_size.draw(st.integers(min_value=wsize1, max_value=50))

663
664
    maxbe1 = max_behaviour(behaviour_dframe, wsize1, stepped)
    maxbe2 = max_behaviour(behaviour_dframe, wsize2, stepped)
665
666
667

    assert type(maxbe1) == np.ndarray
    assert type(maxbe2) == np.ndarray
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
    if not stepped:
        assert type(maxbe1[wsize1 // 2 + 1]) == str
        assert type(maxbe1[wsize2 // 2 + 1]) == str
        assert maxbe1[wsize1 // 2 + 1] in behaviour_dframe.columns
        assert maxbe2[wsize2 // 2 + 1] in behaviour_dframe.columns
        assert len(maxbe1) >= len(maxbe2)


@settings(
    deadline=None, suppress_health_check=[HealthCheck.too_slow],
)
@given(
    x=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=10, max_value=1000),
            st.integers(min_value=10, max_value=1000),
        ),
        elements=st.floats(min_value=1.0, max_value=1.0,),
    ).map(lambda x: x * np.random.uniform(0, 2, x.shape)),
    n_components=st.integers(min_value=1, max_value=10),
    cv_type=st.integers(min_value=0, max_value=3),
)
def test_gmm_compute(x, n_components, cv_type):
    cv_type = ["spherical", "tied", "diag", "full"][cv_type]
    assert len(gmm_compute(x, n_components, cv_type)) == 2


@settings(
    deadline=None, suppress_health_check=[HealthCheck.too_slow],
)
@given(
    x=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=10, max_value=1000),
            st.integers(min_value=10, max_value=1000),
        ),
        elements=st.floats(min_value=1.0, max_value=1.0,),
    ).map(lambda x: x * np.random.uniform(0, 2, x.shape)),
    sampler=st.data(),
)
def test_gmm_model_selection(x, sampler):
    n_component_range = range(1, sampler.draw(st.integers(min_value=2, max_value=5)))
    part_size = sampler.draw(
        st.integers(min_value=x.shape[0] // 2, max_value=x.shape[0] * 2)
    )
    assert (
        len(
            gmm_model_selection(pd.DataFrame(x), n_component_range, part_size, n_runs=1)
        )
        == 3
    )
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


@settings(deadline=None)
@given(sampler=st.data(), autocorrelation=st.booleans(), return_graph=st.booleans())
def test_cluster_transition_matrix(sampler, autocorrelation, return_graph):

    nclusts = sampler.draw(st.integers(min_value=1, max_value=10))
    cluster_sequence = sampler.draw(
        arrays(
            dtype=int,
            shape=st.tuples(st.integers(min_value=10, max_value=1000)),
            elements=st.integers(min_value=1, max_value=nclusts),
        ).filter(lambda x: len(set(x)) != 1)
    )

    trans = cluster_transition_matrix(
        cluster_sequence, nclusts, autocorrelation, return_graph
    )

    if autocorrelation:
        assert len(trans) == 2

        if return_graph:
            assert type(trans[0]) == nx.Graph
        else:
            assert type(trans[0]) == np.ndarray

        assert type(trans[1]) == np.ndarray

    else:
        if return_graph:
            assert type(trans) == nx.Graph
        else:
            assert type(trans) == np.ndarray
755
756


757
def test_rule_based_tagging():
758
759
760
761
762
763
764
765

    prun = deepof.preprocess.project(
        path=os.path.join(".", "tests", "test_examples"),
        arena="circular",
        arena_dims=[380],
        angles=False,
        video_format=".mp4",
        table_format=".h5",
766
    ).run(verbose=True)
767
768
769
770
771
772
773

    hardcoded_tags = rule_based_tagging(
        list([i + "_" for i in prun.get_coords().keys()]),
        ["test_video_circular_arena.mp4"],
        prun,
        vid_index=0,
        path=os.path.join(".", "tests", "test_examples", "Videos"),
774
775
        save=True,
        frame_limit=100,
776
777
778
    )

    assert type(hardcoded_tags) == pd.DataFrame
779
    assert hardcoded_tags.shape[1] == 3