def test_fextractor():
filename = os.path.join(get_test_data_path(), "iMotions_Test_v6.txt")
df = read_facet(filename)
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
dat = dat[[
"Joy",
"Anger",
"Surprise",
"Fear",
"Contempt",
"Disgust",
"Sadness",
"Confusion",
"Frustration",
"Neutral",
"Positive",
"Negative",
]]
# Test Fextractor class
extractor = Fextractor()
dat = dat.interpolate() # interpolate data to get rid of NAs
f = 0.5
num_cyc = 3 # for wavelet extraction
# Test each extraction method
extractor.mean(fex_object=dat)
extractor.max(fex_object=dat)
extractor.min(fex_object=dat)
# boft needs a groupby function.
extractor.multi_wavelet(fex_object=dat)
extractor.wavelet(fex_object=dat, freq=f, num_cyc=num_cyc)
# Test ValueError
with pytest.raises(ValueError):
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
mode="BadValue")
# Test Fextracor merge method
newdat = extractor.merge(out_format="long")
assert newdat["sessions"].nunique() == 52
assert isinstance(newdat, DataFrame)
assert len(extractor.merge(out_format="long")) == 7488
assert len(extractor.merge(out_format="wide")) == 52
# Test summary method
extractor = Fextractor()
dat2 = dat.loc[:, ["Positive", "Negative"]].interpolate()
extractor.summary(fex_object=dat2, min=True, max=True, mean=True)
# [Pos, Neg] * [mean, max, min] + ['sessions']
assert extractor.merge(out_format="wide").shape[1] == dat2.shape[1] * 3 + 1
# Test wavelet extraction
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=False)
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True)
wavelet = extractor.extracted_features[0] # ignore_sessions = False
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
wavelet = extractor.extracted_features[1] # ignore_sessions = True
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
assert np.array_equal(wavelet.sessions, dat.sessions)
for i in ["filtered", "phase", "magnitude", "power"]:
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True,
mode=i)
wavelet = extractor.extracted_features[0]
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
# Test multi wavelet
dat2 = dat.loc[:, ["Positive", "Negative"]].interpolate()
n_bank = 4
extractor = Fextractor()
extractor.multi_wavelet(
fex_object=dat2,
min_freq=0.1,
max_freq=2,
bank=n_bank,
mode="power",
ignore_sessions=False,
)
out = extractor.extracted_features[0]
assert n_bank * dat2.shape[1] == out.shape[1]
assert len(out) == len(dat2)
assert np.array_equal(out.sessions, dat2.sessions)
assert out.sampling_freq == dat2.sampling_freq
# Test Bag Of Temporal Features Extraction
filename = os.path.join(get_test_data_path(), "iMotions_Test_v6.txt")
facet = Fex(filename=filename, sampling_freq=30, detector="FACET")
facet = facet.read_file()
facet_filled = facet.fillna(0)
facet_filled = facet_filled[[
"Joy",
"Anger",
"Surprise",
"Fear",
"Contempt",
"Disgust",
"Sadness",
"Confusion",
"Frustration",
"Neutral",
"Positive",
"Negative",
]]
# assert isinstance(facet_filled,Facet)
extractor = Fextractor()
extractor.boft(facet_filled)
assert isinstance(extractor.extracted_features[0], DataFrame)
filters, histograms = 8, 12
assert (extractor.extracted_features[0].shape[1] ==
facet_filled.columns.shape[0] * filters * histograms)
def test_fex():
with pytest.raises(Exception):
fex = Fex().read_feat()
with pytest.raises(Exception):
fex = Fex().read_facet()
with pytest.raises(Exception):
fex = Fex().read_openface()
with pytest.raises(Exception):
fex = Fex().read_affectiva()
# For iMotions-FACET data files
# test reading iMotions file < version 6
filename = os.path.join(get_test_data_path(), "iMotions_Test_v5.txt")
dat = Fex(read_facet(filename), sampling_freq=30)
# test reading iMotions file > version 6
filename = os.path.join(get_test_data_path(), "iMotions_Test_v6.txt")
df = read_facet(filename)
# Test slicing functions.
assert df.aus().shape == (519, 20)
assert df.emotions().shape == (519, 12)
assert df.facebox().shape == (519, 4)
assert df.time().shape[-1] == 4
assert df.design().shape[-1] == 4
# Test metadata propagation to sliced series
assert df.iloc[0].aus().shape == (20, )
assert df.iloc[0].emotions().shape == (12, )
assert df.iloc[0].facebox().shape == (4, )
assert df.iloc[0].time().shape == (4, )
assert df.iloc[0].design().shape == (4, )
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
dat = dat[[
"Joy",
"Anger",
"Surprise",
"Fear",
"Contempt",
"Disgust",
"Sadness",
"Confusion",
"Frustration",
"Neutral",
"Positive",
"Negative",
]]
# Test Session ValueError
with pytest.raises(ValueError):
Fex(df, sampling_freq=30, sessions=sessions[:10])
# Test KeyError
with pytest.raises(KeyError):
Fex(read_facet(filename, features=["NotHere"]), sampling_freq=30)
# Test length
assert len(dat) == 519
# Test sessions generator
assert len(np.unique(dat.sessions)) == len([x for x in dat.itersessions()])
# Test metadata propagation
assert dat[["Joy"]].sampling_freq == dat.sampling_freq
assert dat.iloc[:, 0].sampling_freq == dat.sampling_freq
assert dat.iloc[0, :].sampling_freq == dat.sampling_freq
assert dat.loc[[0], :].sampling_freq == dat.sampling_freq
assert dat.loc[:, ["Joy"]].sampling_freq == dat.sampling_freq
# assert dat.loc[0].sampling_freq == dat.sampling_freq # DOES NOT WORK YET
# Test Downsample
assert len(dat.downsample(target=10)) == 52
# Test upsample
assert len(dat.upsample(target=60, target_type="hz")) == (len(dat) - 1) * 2
# Test interpolation
assert (dat.interpolate(method="linear").isnull().sum()["Positive"] <
dat.isnull().sum()["Positive"])
dat = dat.interpolate(method="linear")
# Test distance
d = dat[["Positive"]].distance()
assert isinstance(d, Adjacency)
assert d.square_shape()[0] == len(dat)
# Test Copy
assert isinstance(dat.copy(), Fex)
assert dat.copy().sampling_freq == dat.sampling_freq
# Test rectification
rectified = df.rectification()
assert (df[df.au_columns].isna().sum()[0] <
rectified[rectified.au_columns].isna().sum()[0])
# Test pspi
assert len(df.calc_pspi()) == len(df)
# Test baseline
assert isinstance(dat.baseline(baseline="median"), Fex)
assert isinstance(dat.baseline(baseline="mean"), Fex)
assert isinstance(dat.baseline(baseline="begin"), Fex)
assert isinstance(dat.baseline(baseline=dat.mean()), Fex)
assert isinstance(dat.baseline(baseline="median", ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline="mean", ignore_sessions=True), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline="median", normalize="pct"), Fex)
assert isinstance(dat.baseline(baseline="mean", normalize="pct"), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), normalize="pct"), Fex)
assert isinstance(
dat.baseline(baseline="median", ignore_sessions=True, normalize="pct"),
Fex)
assert isinstance(
dat.baseline(baseline="mean", ignore_sessions=True, normalize="pct"),
Fex)
assert isinstance(
dat.baseline(baseline=dat.mean(),
ignore_sessions=True,
normalize="pct"), Fex)
# Test ValueError
with pytest.raises(ValueError):
dat.baseline(baseline="BadValue")
# Test summary
dat2 = dat.loc[:, ["Positive", "Negative"]].interpolate()
out = dat2.extract_summary(min=True, max=True, mean=True)
assert len(out) == len(np.unique(dat2.sessions))
assert np.array_equal(out.sessions, np.unique(dat2.sessions))
assert out.sampling_freq == dat2.sampling_freq
assert dat2.shape[1] * 3 == out.shape[1]
out = dat2.extract_summary(min=True,
max=True,
mean=True,
ignore_sessions=True)
assert len(out) == 1
assert dat2.shape[1] * 3 == out.shape[1]
# Check if file is missing columns
data_bad = dat.iloc[:, 0:10]
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Check if file has too many columns
data_bad = dat.copy()
data_bad["Test"] = 0
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Test clean
assert isinstance(dat.clean(), Fex)
assert dat.clean().columns is dat.columns
assert dat.clean().sampling_freq == dat.sampling_freq
# Test Decompose
n_components = 3
stats = dat.decompose(algorithm="pca", axis=1, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
stats = dat.decompose(algorithm="ica", axis=1, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm="nnmf",
axis=1,
n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
stats = dat.decompose(algorithm="fa", axis=1, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
stats = dat.decompose(algorithm="pca", axis=0, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
stats = dat.decompose(algorithm="ica", axis=0, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm="nnmf",
axis=0,
n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
stats = dat.decompose(algorithm="fa", axis=0, n_components=n_components)
assert n_components == stats["components"].shape[1]
assert n_components == stats["weights"].shape[1]
def test1(self):
with self.assertRaises(KeyError):
Fex(read_facet(filename, features=['NotHere']),
sampling_freq=30)
print(type(detections)) display(detections.head()) All functionalities of the `Fex` class will be available when you load an OpenFace file using `read_openface`. For example, you can quickly grab the facial landmark columns using `landmarks()` or the aus using `aus()` detections.landmark().head() detections.aus().head() ## Loading FACET iMotions data Loading a FACET file as a Fex class is also simple using `read_facet`. from feat.utils import read_facet facet = os.path.join(get_test_data_path(), "iMotions_Test_v6.txt") detections = read_facet(facet) print(type(detections)) display(detections.head()) You can take advantage of the Fex functionalties such as grabbing the emotions detections.emotions().head() You can also extract features from the data. For example, to extract bags of temporal features from this video, you would simply set the sampling frequency and run `extract_boft`. detections.sampling_freq = 30 detections.emotions().dropna().extract_boft() ## Loading Affectiva API file You can also load an affectiva file processed through the [Affectiva Javascript SDK](https://blog.affectiva.com/javascript-emotion-sdk-for-youtube-facebook-and-twitch-api) available [here](http://jinhyuncheong.com/affectiva-app/affectiva_emotion_detector_photo.html)
def test_fex(tmpdir):
# For iMotions-FACET data files
# test reading iMotions file < version 6
dat = Fex(read_facet(join(get_test_data_path(), 'iMotions_Test_v2.txt')),
sampling_freq=30)
# test reading iMotions file > version 6
filename = join(get_test_data_path(), 'iMotions_Test.txt')
df = read_facet(filename)
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
# Test KeyError
class MyTestCase(unittest.TestCase):
def test1(self):
with self.assertRaises(KeyError):
Fex(read_facet(filename, features=['NotHere']),
sampling_freq=30)
# Test length
assert len(dat) == 519
# Test Info
assert isinstance(dat.info(), str)
# Test sessions generator
assert len(np.unique(dat.sessions)) == len([x for x in dat.itersessions()])
# Test metadata propagation
assert dat['Joy'].sampling_freq == dat.sampling_freq
assert dat.iloc[:, 0].sampling_freq == dat.sampling_freq
# Test Downsample
assert len(dat.downsample(target=10)) == 52
# Test upsample
assert len(dat.upsample(target=60, target_type='hz')) == (len(dat) - 1) * 2
# Test interpolation
assert np.sum(dat.interpolate(method='linear').isnull().sum() == 0) == len(
dat.columns)
dat = dat.interpolate(method='linear')
# Test distance
d = dat.distance()
assert isinstance(d, Adjacency)
assert d.square_shape()[0] == len(dat)
# Test Copy
assert isinstance(dat.copy(), Fex)
assert dat.copy().sampling_freq == dat.sampling_freq
# Test baseline
assert isinstance(dat.baseline(baseline='median'), Fex)
assert isinstance(dat.baseline(baseline='mean'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean()), Fex)
assert isinstance(dat.baseline(baseline='median', ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='mean', ignore_sessions=True), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='median', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline='mean', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), normalize='pct'), Fex)
assert isinstance(
dat.baseline(baseline='median', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline='mean', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline=dat.mean(),
ignore_sessions=True,
normalize='pct'), Fex)
# Test facet subclass
facet = Facet(filename=filename, sampling_freq=30)
facet.read_file()
assert len(facet) == 519
# Test PSPI calculation
assert len(facet.calc_pspi()) == len(facet)
# Test Fextractor class
extractor = Fextractor()
dat = dat.interpolate() # interpolate data to get rid of NAs
f = .5
num_cyc = 3 # for wavelet extraction
# Test each extraction method
extractor.mean(fex_object=dat)
extractor.max(fex_object=dat)
extractor.min(fex_object=dat)
#extractor.boft(fex_object=dat, min_freq=.01, max_freq=.20, bank=1)
extractor.multi_wavelet(fex_object=dat)
extractor.wavelet(fex_object=dat, freq=f, num_cyc=num_cyc)
# Test Fextracor merge method
newdat = extractor.merge(out_format='long')
assert newdat['sessions'].nunique() == 52
assert isinstance(newdat, DataFrame)
assert len(extractor.merge(out_format='long')) == 24960
assert len(extractor.merge(out_format='wide')) == 52
# Test wavelet extraction
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=False)
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True)
wavelet = extractor.extracted_features[0] # ignore_sessions = False
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
wavelet = extractor.extracted_features[1] # ignore_sessions = True
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
assert np.array_equal(wavelet.sessions, dat.sessions)
for i in ['filtered', 'phase', 'magnitude', 'power']:
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True,
mode=i)
wavelet = extractor.extracted_features[0]
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
# Test multi wavelet
dat2 = dat.loc[:, ['Positive', 'Negative']].interpolate()
n_bank = 4
extractor = Fextractor()
extractor.multi_wavelet(fex_object=dat2,
min_freq=.1,
max_freq=2,
bank=n_bank,
mode='power',
ignore_sessions=False)
out = extractor.extracted_features[0]
assert n_bank * dat2.shape[1] == out.shape[1]
assert len(out) == len(dat2)
assert np.array_equal(out.sessions, dat2.sessions)
assert out.sampling_freq == dat2.sampling_freq
# Test Bag Of Temporal Features Extraction
facet_filled = facet.fillna(0)
assert isinstance(facet_filled, Facet)
extractor = Fextractor()
extractor.boft(facet_filled)
assert isinstance(extractor.extracted_features[0], DataFrame)
filters, histograms = 8, 12
assert extractor.extracted_features[0].shape[
1] == facet.columns.shape[0] * filters * histograms
# Test mean, min, and max Features Extraction
# assert isinstance(facet_filled.extract_mean(), Facet)
# assert isinstance(facet_filled.extract_min(), Facet)
# assert isinstance(facet_filled.extract_max(), Facet)
# Test if a method returns subclass.
facet = facet.downsample(target=10, target_type='hz')
assert isinstance(facet, Facet)
### Test Openface importer and subclass ###
# For OpenFace data file
filename = join(get_test_data_path(), 'OpenFace_Test.csv')
openface = Fex(read_openface(filename), sampling_freq=30)
# Test KeyError
class MyTestCase(unittest.TestCase):
def test1(self):
with self.assertRaises(KeyError):
Fex(read_openface(filename, features=['NotHere']),
sampling_freq=30)
# Test length
assert len(openface) == 100
# Test loading from filename
openface = Openface(filename=filename, sampling_freq=30)
openface.read_file()
# Test length?
assert len(openface) == 100
# Test PSPI calculation b/c diff from facet
assert len(openface.calc_pspi()) == len(openface)
# Test if a method returns subclass.
openface = openface.downsample(target=10, target_type='hz')
assert isinstance(openface, Openface)
# Check if file is missing columns
data_bad = dat.iloc[:, 0:10]
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Check if file has too many columns
data_bad = dat.copy()
data_bad['Test'] = 0
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Test clean
assert isinstance(dat.clean(), Fex)
assert dat.clean().columns is dat.columns
assert dat.clean().sampling_freq == dat.sampling_freq
# Test Decompose
n_components = 3
stats = dat.decompose(algorithm='pca', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=1,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='pca', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=0,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
def read_file(self, *args, **kwargs):
super(Fex, self).__init__(read_facet(self.filename, *args, **kwargs),
*args, **kwargs)
def test_fextractor():
filename = join(get_test_data_path(), 'iMotions_Test.txt')
df = read_facet(filename)
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
# Test Fextractor class
extractor = Fextractor()
dat = dat.interpolate() # interpolate data to get rid of NAs
f = .5
num_cyc = 3 # for wavelet extraction
# Test each extraction method
extractor.mean(fex_object=dat)
extractor.max(fex_object=dat)
extractor.min(fex_object=dat)
#extractor.boft(fex_object=dat, min_freq=.01, max_freq=.20, bank=1)
extractor.multi_wavelet(fex_object=dat)
extractor.wavelet(fex_object=dat, freq=f, num_cyc=num_cyc)
# Test ValueError
with pytest.raises(ValueError):
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
mode='BadValue')
# Test Fextracor merge method
newdat = extractor.merge(out_format='long')
assert newdat['sessions'].nunique() == 52
assert isinstance(newdat, DataFrame)
assert len(extractor.merge(out_format='long')) == 24960
assert len(extractor.merge(out_format='wide')) == 52
# Test summary method
extractor = Fextractor()
dat2 = dat.loc[:, ['Positive', 'Negative']].interpolate()
extractor.summary(fex_object=dat2, min=True, max=True, mean=True)
# [Pos, Neg] * [mean, max, min] + ['sessions']
assert extractor.merge(out_format='wide').shape[1] == dat2.shape[1] * 3 + 1
# Test wavelet extraction
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=False)
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True)
wavelet = extractor.extracted_features[0] # ignore_sessions = False
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
wavelet = extractor.extracted_features[1] # ignore_sessions = True
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
assert np.array_equal(wavelet.sessions, dat.sessions)
for i in ['filtered', 'phase', 'magnitude', 'power']:
extractor = Fextractor()
extractor.wavelet(fex_object=dat,
freq=f,
num_cyc=num_cyc,
ignore_sessions=True,
mode=i)
wavelet = extractor.extracted_features[0]
assert wavelet.sampling_freq == dat.sampling_freq
assert len(wavelet) == len(dat)
# Test multi wavelet
dat2 = dat.loc[:, ['Positive', 'Negative']].interpolate()
n_bank = 4
extractor = Fextractor()
extractor.multi_wavelet(fex_object=dat2,
min_freq=.1,
max_freq=2,
bank=n_bank,
mode='power',
ignore_sessions=False)
out = extractor.extracted_features[0]
assert n_bank * dat2.shape[1] == out.shape[1]
assert len(out) == len(dat2)
assert np.array_equal(out.sessions, dat2.sessions)
assert out.sampling_freq == dat2.sampling_freq
# Test Bag Of Temporal Features Extraction
filename = join(get_test_data_path(), 'iMotions_Test.txt')
facet = Facet(filename=filename, sampling_freq=30)
facet.read_file()
facet_filled = facet.fillna(0)
assert isinstance(facet_filled, Facet)
extractor = Fextractor()
extractor.boft(facet_filled)
assert isinstance(extractor.extracted_features[0], DataFrame)
filters, histograms = 8, 12
assert extractor.extracted_features[0].shape[
1] == facet.columns.shape[0] * filters * histograms
def test_fex():
# For iMotions-FACET data files
# test reading iMotions file < version 6
dat = Fex(read_facet(join(get_test_data_path(), 'iMotions_Test_v2.txt')),
sampling_freq=30)
# test reading iMotions file > version 6
filename = join(get_test_data_path(), 'iMotions_Test.txt')
df = read_facet(filename)
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
# Test Session ValueError
with pytest.raises(ValueError):
Fex(df, sampling_freq=30, sessions=sessions[:10])
# Test KeyError
with pytest.raises(KeyError):
Fex(read_facet(filename, features=['NotHere']), sampling_freq=30)
# Test length
assert len(dat) == 519
# Test Info
assert isinstance(dat.info(), str)
# Test sessions generator
assert len(np.unique(dat.sessions)) == len([x for x in dat.itersessions()])
# Test metadata propagation
assert dat['Joy'].sampling_freq == dat.sampling_freq
assert dat.iloc[:, 0].sampling_freq == dat.sampling_freq
# Test Downsample
assert len(dat.downsample(target=10)) == 52
# Test upsample
assert len(dat.upsample(target=60, target_type='hz')) == (len(dat) - 1) * 2
# Test interpolation
assert np.sum(dat.interpolate(method='linear').isnull().sum() == 0) == len(
dat.columns)
dat = dat.interpolate(method='linear')
# Test distance
d = dat.distance()
assert isinstance(d, Adjacency)
assert d.square_shape()[0] == len(dat)
# Test Copy
assert isinstance(dat.copy(), Fex)
assert dat.copy().sampling_freq == dat.sampling_freq
# Test baseline
assert isinstance(dat.baseline(baseline='median'), Fex)
assert isinstance(dat.baseline(baseline='mean'), Fex)
assert isinstance(dat.baseline(baseline='begin'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean()), Fex)
assert isinstance(dat.baseline(baseline='median', ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='mean', ignore_sessions=True), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='median', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline='mean', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), normalize='pct'), Fex)
assert isinstance(
dat.baseline(baseline='median', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline='mean', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline=dat.mean(),
ignore_sessions=True,
normalize='pct'), Fex)
# Test ValueError
with pytest.raises(ValueError):
dat.baseline(baseline='BadValue')
# Test summary
dat2 = dat.loc[:, ['Positive', 'Negative']].interpolate()
out = dat2.extract_summary(min=True, max=True, mean=True)
assert len(out) == len(np.unique(dat2.sessions))
assert np.array_equal(out.sessions, np.unique(dat2.sessions))
assert out.sampling_freq == dat2.sampling_freq
assert dat2.shape[1] * 3 == out.shape[1]
out = dat2.extract_summary(min=True,
max=True,
mean=True,
ignore_sessions=True)
assert len(out) == 1
assert dat2.shape[1] * 3 == out.shape[1]
# Check if file is missing columns
data_bad = dat.iloc[:, 0:10]
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Check if file has too many columns
data_bad = dat.copy()
data_bad['Test'] = 0
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Test clean
assert isinstance(dat.clean(), Fex)
assert dat.clean().columns is dat.columns
assert dat.clean().sampling_freq == dat.sampling_freq
# Test Decompose
n_components = 3
stats = dat.decompose(algorithm='pca', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=1,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='pca', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=0,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
def test_fex():
with pytest.raises(Exception):
fex = Fex().read_feat()
with pytest.raises(Exception):
fex = Fex().read_facet()
with pytest.raises(Exception):
fex = Fex().read_openface()
with pytest.raises(Exception):
fex = Fex().read_affectiva()
# For iMotions-FACET data files
# test reading iMotions file < version 6
filename = os.path.join(get_test_data_path(), 'iMotions_Test_v5.txt')
dat = Fex(read_facet(filename), sampling_freq=30)
# test reading iMotions file > version 6
filename = os.path.join(get_test_data_path(), 'iMotions_Test_v6.txt')
df = read_facet(filename)
# Test slicing functions.
assert df.aus().shape == (519, 20)
assert df.emotions().shape == (519, 12)
assert df.facebox().shape == (519, 4)
assert df.time().shape[-1] == 4
assert df.design().shape[-1] == 4
sessions = np.array([[x] * 10
for x in range(1 + int(len(df) / 10))]).flatten()[:-1]
dat = Fex(df, sampling_freq=30, sessions=sessions)
dat = dat[[
'Joy', 'Anger', 'Surprise', 'Fear', 'Contempt', 'Disgust', 'Sadness',
'Confusion', 'Frustration', 'Neutral', 'Positive', 'Negative'
]]
# Test Session ValueError
with pytest.raises(ValueError):
Fex(df, sampling_freq=30, sessions=sessions[:10])
# Test KeyError
with pytest.raises(KeyError):
Fex(read_facet(filename, features=['NotHere']), sampling_freq=30)
# Test length
assert len(dat) == 519
# Test sessions generator
assert len(np.unique(dat.sessions)) == len([x for x in dat.itersessions()])
# Test metadata propagation
assert dat[['Joy']].sampling_freq == dat.sampling_freq
assert dat.iloc[:, 0].sampling_freq == dat.sampling_freq
# Test Downsample
assert len(dat.downsample(target=10)) == 52
# Test upsample
assert len(dat.upsample(target=60, target_type='hz')) == (len(dat) - 1) * 2
# Test interpolation
assert dat.interpolate(method='linear').isnull().sum(
)['Positive'] < dat.isnull().sum()['Positive']
dat = dat.interpolate(method='linear')
# Test distance
d = dat[['Positive']].distance()
assert isinstance(d, Adjacency)
assert d.square_shape()[0] == len(dat)
# Test Copy
assert isinstance(dat.copy(), Fex)
assert dat.copy().sampling_freq == dat.sampling_freq
# Test rectification
rectified = df.rectification()
assert df[df.au_columns].isna().sum()[0] < rectified[
rectified.au_columns].isna().sum()[0]
# Test pspi
assert len(df.calc_pspi()) == len(df)
# Test baseline
assert isinstance(dat.baseline(baseline='median'), Fex)
assert isinstance(dat.baseline(baseline='mean'), Fex)
assert isinstance(dat.baseline(baseline='begin'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean()), Fex)
assert isinstance(dat.baseline(baseline='median', ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='mean', ignore_sessions=True), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), ignore_sessions=True),
Fex)
assert isinstance(dat.baseline(baseline='median', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline='mean', normalize='pct'), Fex)
assert isinstance(dat.baseline(baseline=dat.mean(), normalize='pct'), Fex)
assert isinstance(
dat.baseline(baseline='median', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline='mean', ignore_sessions=True, normalize='pct'),
Fex)
assert isinstance(
dat.baseline(baseline=dat.mean(),
ignore_sessions=True,
normalize='pct'), Fex)
# Test ValueError
with pytest.raises(ValueError):
dat.baseline(baseline='BadValue')
# Test summary
dat2 = dat.loc[:, ['Positive', 'Negative']].interpolate()
out = dat2.extract_summary(min=True, max=True, mean=True)
assert len(out) == len(np.unique(dat2.sessions))
assert np.array_equal(out.sessions, np.unique(dat2.sessions))
assert out.sampling_freq == dat2.sampling_freq
assert dat2.shape[1] * 3 == out.shape[1]
out = dat2.extract_summary(min=True,
max=True,
mean=True,
ignore_sessions=True)
assert len(out) == 1
assert dat2.shape[1] * 3 == out.shape[1]
# Check if file is missing columns
data_bad = dat.iloc[:, 0:10]
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Check if file has too many columns
data_bad = dat.copy()
data_bad['Test'] = 0
with pytest.raises(Exception):
_check_if_fex(data_bad, imotions_columns)
# Test clean
assert isinstance(dat.clean(), Fex)
assert dat.clean().columns is dat.columns
assert dat.clean().sampling_freq == dat.sampling_freq
# Test Decompose
n_components = 3
stats = dat.decompose(algorithm='pca', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=1,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=1, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='pca', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='ica', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
new_dat = dat + 100
stats = new_dat.decompose(algorithm='nnmf',
axis=0,
n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]
stats = dat.decompose(algorithm='fa', axis=0, n_components=n_components)
assert n_components == stats['components'].shape[1]
assert n_components == stats['weights'].shape[1]