test_utils.py 19 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

lucas_miranda's avatar
lucas_miranda committed
14
15
16
17
18
19
# AUXILIARY FUNCTIONS #


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

20

21
22
23
# QUALITY CONTROL AND PREPROCESSING #


lucas_miranda's avatar
lucas_miranda committed
24
@settings(deadline=None)
lucas_miranda's avatar
lucas_miranda committed
25
26
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
@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
65
@settings(deadline=None)
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
@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
86
@settings(deadline=None)
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
@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
113
@settings(deadline=None)
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
@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
135
@settings(deadline=None)
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
@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
162
@settings(deadline=None)
163
164
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
@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
191
@settings(deadline=None)
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
@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
209
@settings(deadline=None)
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
@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
225
    assert np.allclose(rotate(p, 0), p)
226
227


lucas_miranda's avatar
lucas_miranda committed
228
@settings(deadline=None)
229
230
231
232
233
234
235
236
237
238
239
@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
        ),
240
    ),
lucas_miranda's avatar
lucas_miranda committed
241
    mode_idx=st.integers(min_value=0, max_value=2),
242
)
243
def test_align_trajectories(data, mode_idx):
lucas_miranda's avatar
lucas_miranda committed
244
    mode = ["center", "all", "none"][mode_idx]
245
246
247
248
249
250
    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
251
252
    elif mode == "none":
        assert np.allclose(aligned, data)
253
254


lucas_miranda's avatar
lucas_miranda committed
255
@settings(deadline=None)
256
257
258
@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
259
260
261
262

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

263
264
265
    assert trans(a) >= trans(smooth)


lucas_miranda's avatar
lucas_miranda committed
266
@settings(deadline=None)
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
@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

288
    assert len(rolled_shape) == len(a.shape) + 1
289
    assert rolled_shape[1] == window_size
lucas_miranda's avatar
lucas_miranda committed
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


@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)
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337


# 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),
        ),
    ),
338
    tol=st.floats(min_value=0.01, max_value=4.98),
339
340
341
342
343
344
345
346
347
348
)
def test_close_single_contact(pos_dframe, tol):

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


@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
357
358
359
360
361
362
363
364
            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),
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
        ),
    ),
    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(
        pos_dframe, "bpart1", "bpart2", "bpart3", "bpart4", tol, rev
    )
    assert close_contact.dtype == bool
    assert np.array(close_contact).shape[0] <= pos_dframe.shape[0]
lucas_miranda's avatar
lucas_miranda committed
382
383


384
@settings(deadline=None)
385
386
@given(indexes=st.data())
def test_recognize_arena_and_subfunctions(indexes):
lucas_miranda's avatar
lucas_miranda committed
387

388
    path = "./tests/test_examples/Videos/"
lucas_miranda's avatar
lucas_miranda committed
389
390
391
392
393
    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))

394
    assert recognize_arena(videos, vid_index, path, recoglimit, "") == 0
395
    assert len(recognize_arena(videos, vid_index, path, recoglimit, "circular")) == 3
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431


@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(
            path="./tests/test_examples",
            arena="circular",
            arena_dims=[arena[0]],
            angles=False,
            video_format=".mp4",
            table_format=".h5",
        )
        .run(verbose=False)
        .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
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


@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
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521


@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),
)
def test_huddle(pos_dframe, tol_forward, tol_spine):

    idx = pd.MultiIndex.from_product(
        [
            [
                "Left_ear",
                "Right_ear",
                "Left_fhip",
                "Right_fhip",
                "Spine1",
                "Center",
                "Spine2",
                "Tail_base",
            ],
            ["X", "y"],
        ],
        names=["bodyparts", "coords"],
    )
    pos_dframe.columns = idx
    hudd = huddle(pos_dframe, tol_forward, tol_spine)

    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
522
523
524
525
526
527
528


@settings(deadline=None)
@given(
    distance_dframe=data_frames(
        index=range_indexes(min_size=20, max_size=20),
        columns=columns(
529
            ["d1", "d2", "d3", "d4"],
lucas_miranda's avatar
lucas_miranda committed
530
531
532
533
534
535
536
            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(
537
            ["X1", "y1", "X2", "y2", "X3", "y3", "X4", "y4"],
lucas_miranda's avatar
lucas_miranda committed
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
            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(
555
        [bparts, ["X", "y"]], names=["bodyparts", "coords"],
lucas_miranda's avatar
lucas_miranda committed
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
    )

    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]
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


@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
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


@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(),
)
def test_max_behaviour(behaviour_dframe, window_size):
    wsize1 = window_size.draw(st.integers(min_value=5, max_value=50))
    wsize2 = window_size.draw(st.integers(min_value=wsize1, max_value=50))

    maxbe1 = max_behaviour(behaviour_dframe, wsize1)
    maxbe2 = max_behaviour(behaviour_dframe, wsize2)

    assert type(maxbe1) == np.ndarray
    assert type(maxbe2) == np.ndarray
    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)