def test_google_vision_face_batch():
obama_file = join(get_test_data_path(), 'image', 'obama.jpg')
people_file = join(get_test_data_path(), 'image', 'thai_people.jpg')
stims = [ImageStim(obama_file), ImageStim(people_file)]
ext = GoogleVisionAPIFaceExtractor(handle_annotations='first')
result = ext.transform(stims)
result = ExtractorResult.merge_stims(result)
assert 'face1_joyLikelihood' in result.columns
assert result['face1_joyLikelihood'][0] == 'VERY_LIKELY'
assert result['face1_joyLikelihood'][1] == 'VERY_LIKELY'
video = VideoStim(join(get_test_data_path(), 'video', 'obama_speech.mp4'))
conv = FrameSamplingFilter(every=10)
video = conv.transform(video)
result = ext.transform(video)
result = ExtractorResult.merge_stims(result)
assert 'face1_joyLikelihood' in result.columns
assert result.shape == (11, 137)
video = VideoStim(join(get_test_data_path(), 'video', 'small.mp4'))
video = conv.transform(video)
result = ext.transform(video)
result = ExtractorResult.merge_stims(result)
assert 'face1_joyLikelihood' not in result.columns
assert result.shape == (17, 7)
def test_batch_transformer():
img1 = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
img2 = ImageStim(join(get_test_data_path(), 'image', 'button.jpg'))
img3 = ImageStim(join(get_test_data_path(), 'image', 'obama.jpg'))
ext = DummyBatchExtractor()
res = ExtractorResult.merge_stims(ext.transform([img1, img2, img3]))
assert ext.num_calls == 1
assert res.shape == (3, 8)
ext = DummyBatchExtractor(batch_size=1)
res2 = ExtractorResult.merge_stims(ext.transform([img1, img2, img3]))
assert ext.num_calls == 3
assert res.equals(res2)
def test_google_vision_api_face_extractor_inits():
ext = GoogleVisionAPIFaceExtractor(num_retries=5)
assert ext.num_retries == 5
assert ext.max_results == 100
assert ext.service is not None
# Test parsing of individual response
filename = join(
get_test_data_path(), 'payloads', 'google_vision_api_face_payload.json')
response = json.load(open(filename, 'r'))
stim = ImageStim(join(get_test_data_path(), 'image', 'obama.jpg'))
res = ExtractorResult(response['faceAnnotations'], stim, ext)
df = res.to_df()
assert df['angerLikelihood'][0] == 'VERY_UNLIKELY'
assert df['landmark_LEFT_EYE_BOTTOM_BOUNDARY_y'][0] == 257.023
assert np.isnan(df['boundingPoly_vertex2_y'][0])
def test_google_vision_api_face_extractor_inits():
ext = GoogleVisionAPIFaceExtractor(num_retries=5)
assert ext.num_retries == 5
assert ext.max_results == 100
assert ext.service is not None
# Test parsing of individual response
filename = join(
get_test_data_path(), 'payloads', 'google_vision_api_face_payload.json')
response = json.load(open(filename, 'r'))
stim = ImageStim(join(get_test_data_path(), 'image', 'obama.jpg'))
res = ExtractorResult(response['faceAnnotations'], stim, ext)
df = res.to_df()
assert df['angerLikelihood'][0] == 'VERY_UNLIKELY'
assert df['landmark_LEFT_EYE_BOTTOM_BOUNDARY_y'][0] == 257.023
assert np.isnan(df['boundingPoly_vertex2_y'][0])
def _extract(self, stim):
time_bins = np.arange(0., stim.duration, 1.)
return ExtractorResult(np.array([1] * len(time_bins)),
stim,
self,
features=['constant'],
onsets=time_bins,
durations=[1.] * len(time_bins))
def test_convert_to_long():
audio_dir = join(get_test_data_path(), 'audio')
stim = AudioStim(join(audio_dir, 'barber.wav'))
ext = STFTAudioExtractor(frame_size=1., spectrogram=False,
freq_bins=[(100, 300), (300, 3000), (3000, 20000)])
timeline = ext.transform(stim)
long_timeline = to_long_format(timeline)
assert long_timeline.shape == (timeline.to_df().shape[0] * 3, 4)
assert 'feature' in long_timeline.columns
assert 'value' in long_timeline.columns
assert '100_300' not in long_timeline.columns
timeline = ExtractorResult.merge_features([timeline])
long_timeline = to_long_format(timeline)
assert 'feature' in long_timeline.columns
assert 'extractor' in long_timeline.columns
assert '100_300' not in long_timeline.columns
def test_extractor_result_to_series_converter():
data = [[2, 4], [1, 7], [6, 6], [8, 2]]
result = ExtractorResult(data,
None,
None,
features=['a', 'b'],
onsets=[2, 4, 6, 8])
stims = ExtractorResultToSeriesConverter().transform(result)
assert len(stims) == 4
stim = stims[2]
assert isinstance(stim, SeriesStim)
assert stim.data.shape == (2, )
assert list(stim.data) == [6, 6]
assert stim.onset == 6
assert stim.duration is None
assert stim.order == 2
def _extract(self, stim, name=None, n_rows=100, n_cols=3, max_time=1000):
data = np.random.randint(0, 1000, (n_rows, n_cols))
onsets = np.random.choice(n_rows * 2, n_rows, False)
if name is not None:
self.name = name
return ExtractorResult(data, stim, deepcopy(self), onsets=onsets)
def _extract(self, stim):
return ExtractorResult(np.array([[1]]),
stim,
self,
features=['constant'])