test_utils.py 14.2 KB
Newer Older
1
# @author lucasmiranda42
2
3
4
5
6
7
8
9
# encoding: utf-8
# module deepof

"""

Testing module for deepof.utils

"""
10
11

from hypothesis import given
12
from hypothesis import HealthCheck
lucas_miranda's avatar
lucas_miranda committed
13
from hypothesis import settings
14
15
16
17
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
18
from deepof.utils import *
19

20

lucas_miranda's avatar
lucas_miranda committed
21
22
23
24
# AUXILIARY FUNCTIONS #


def autocorr(x, t=1):
lucas_miranda's avatar
lucas_miranda committed
25
    """Computes autocorrelation of the given array with a lag of t"""
lucas_miranda's avatar
lucas_miranda committed
26
27
    return np.round(np.corrcoef(np.array([x[:-t], x[t:]]))[0, 1], 5)

28

29
30
31
# QUALITY CONTROL AND PREPROCESSING #


32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
@settings(deadline=None)
@given(
    v=st.one_of(
        st.just("yes"),
        st.just("true"),
        st.just("t"),
        st.just("y"),
        st.just("1"),
        st.just("no"),
        st.just("false"),
        st.just("f"),
        st.just("n"),
        st.just("0"),
    )
)
def test_str2bool(v):
    assert type(str2bool(v)) == bool


lucas_miranda's avatar
lucas_miranda committed
51
@settings(deadline=None)
lucas_miranda's avatar
lucas_miranda committed
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
@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
92
@settings(deadline=None)
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
@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
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
135
136
137
138
139
@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
140
@settings(deadline=None)
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
@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
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
@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
189
@settings(deadline=None)
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
@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
218
@settings(deadline=None)
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
@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
236
@settings(deadline=None)
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
@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
252
    assert np.allclose(rotate(p, 0), p)
253
254


lucas_miranda's avatar
lucas_miranda committed
255
@settings(deadline=None)
256
257
258
259
260
261
262
263
264
265
266
@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
        ),
267
    ),
lucas_miranda's avatar
lucas_miranda committed
268
    mode_idx=st.integers(min_value=0, max_value=2),
269
)
270
def test_align_trajectories(data, mode_idx):
lucas_miranda's avatar
lucas_miranda committed
271
    mode = ["center", "all", "none"][mode_idx]
272
273
274
275
276
277
    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
278
279
    elif mode == "none":
        assert np.allclose(aligned, data)
280
281


lucas_miranda's avatar
lucas_miranda committed
282
@settings(deadline=None)
283
284
285
@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
286
287

    def trans(x):
lucas_miranda's avatar
lucas_miranda committed
288
        """In situ function for computing boolean transitions"""
lucas_miranda's avatar
lucas_miranda committed
289
290
        return sum([i + 1 != i for i in range(x.shape[0] - 1)])

291
292
293
    assert trans(a) >= trans(smooth)


lucas_miranda's avatar
lucas_miranda committed
294
@settings(deadline=None)
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
@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

316
    assert len(rolled_shape) == len(a.shape) + 1
317
    assert rolled_shape[1] == window_size
lucas_miranda's avatar
lucas_miranda committed
318
319
320
321
322
323
324


@settings(deadline=None)
@given(
    alpha=st.data(),
    series=arrays(
        dtype=float,
325
326
327
        shape=st.tuples(
            st.integers(min_value=10, max_value=1000),
        ),
lucas_miranda's avatar
lucas_miranda committed
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
        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)
351
352


353
354
355
356
def test_interpolate_outliers():
    pass


357
@settings(deadline=None)
358
359
@given(indexes=st.data())
def test_recognize_arena_and_subfunctions(indexes):
lucas_miranda's avatar
lucas_miranda committed
360

361
    path = os.path.join(".", "tests", "test_examples", "test_single_topview", "Videos")
lucas_miranda's avatar
lucas_miranda committed
362
363
364
365
366
    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))

367
    assert recognize_arena(videos, vid_index, path, recoglimit, "")[0] == 0
368
    assert len(recognize_arena(videos, vid_index, path, recoglimit, "circular")) == 3
369
370
371
372
373
374
375
    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
    )
376
377


lucas_miranda's avatar
lucas_miranda committed
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
@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(
400
401
        [["bpart1", "bpart2"], ["X", "y"]],
        names=["bodyparts", "coords"],
lucas_miranda's avatar
lucas_miranda committed
402
403
404
405
406
407
408
409
410
    )
    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
411
412


413
@settings(
414
415
    deadline=None,
    suppress_health_check=[HealthCheck.too_slow],
416
417
418
419
420
421
422
423
)
@given(
    x=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=10, max_value=1000),
            st.integers(min_value=10, max_value=1000),
        ),
424
425
426
427
        elements=st.floats(
            min_value=1.0,
            max_value=1.0,
        ),
428
429
430
431
432
433
434
435
436
437
    ).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(
438
439
    deadline=None,
    suppress_health_check=[HealthCheck.too_slow],
440
441
442
443
444
445
446
447
)
@given(
    x=arrays(
        dtype=float,
        shape=st.tuples(
            st.integers(min_value=10, max_value=1000),
            st.integers(min_value=10, max_value=1000),
        ),
448
449
450
451
        elements=st.floats(
            min_value=1.0,
            max_value=1.0,
        ),
452
453
454
455
456
457
458
459
460
461
462
463
464
465
    ).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
    )
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


@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