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_google_vision_face_batch():
stims = ['apple', 'obama', 'thai_people']
stim_files = [join(get_test_data_path(), 'image', '%s.jpg' % s)
for s in stims]
stims = [ImageStim(s) for s in stim_files]
ext = GoogleVisionAPIFaceExtractor(batch_size=5)
result = ext.transform(stims)
result = merge_results(result, format='wide', extractor_names=False,
handle_annotations='first')
assert result.shape == (2, 139)
assert 'joyLikelihood' in result.columns
assert result['joyLikelihood'][0] == 'VERY_LIKELY'
assert result['joyLikelihood'][1] == 'VERY_LIKELY'
video = VideoStim(join(VIDEO_DIR, 'obama_speech.mp4'))
conv = FrameSamplingFilter(every=10)
video = conv.transform(video)
result = ext.transform(video)
result = merge_results(result, format='wide', extractor_names=False)
assert 'joyLikelihood' in result.columns
assert result.shape == (22, 139)
video = VideoStim(join(VIDEO_DIR, 'small.mp4'))
video = conv.transform(video)
result = ext.transform(video)
result = merge_results(result, format='wide', extractor_names=False)
assert 'joyLikelihood' not in result.columns
assert len(result) == 0
def test_google_vision_face_batch():
stims = ['apple', 'obama', 'thai_people']
stim_files = [join(get_test_data_path(), 'image', '%s.jpg' % s)
for s in stims]
stims = [ImageStim(s) for s in stim_files]
ext = GoogleVisionAPIFaceExtractor(batch_size=5)
result = ext.transform(stims)
result = merge_results(result, format='wide', extractor_names=False,
handle_annotations='first')
assert result.shape == (2, 139)
assert 'joyLikelihood' in result.columns
assert result['joyLikelihood'][0] == 'VERY_LIKELY'
assert result['joyLikelihood'][1] == 'VERY_LIKELY'
video = VideoStim(join(VIDEO_DIR, 'obama_speech.mp4'))
conv = FrameSamplingFilter(every=10)
video = conv.transform(video)
result = ext.transform(video)
result = merge_results(result, format='wide', extractor_names=False)
assert 'joyLikelihood' in result.columns
assert result.shape == (22, 139)
video = VideoStim(join(VIDEO_DIR, 'small.mp4'))
video = conv.transform(video)
result = ext.transform(video)
result = merge_results(result, format='wide', extractor_names=False)
assert 'joyLikelihood' not in result.columns
assert len(result) == 0
def test_google_vision_api_face_extractor():
ext = GoogleVisionAPIFaceExtractor(num_retries=5)
filename = join(get_test_data_path(), 'image', 'obama.jpg')
stim = ImageStim(filename)
result = ext.transform(stim).to_df()
assert 'joyLikelihood' in result.columns
assert result['joyLikelihood'][0] == 'VERY_LIKELY'
assert result['face_detectionConfidence'][0] > 0.7
def test_google_vision_multiple_face_extraction():
filename = join(get_test_data_path(), 'image', 'thai_people.jpg')
stim = ImageStim(filename)
# Only first record
ext = GoogleVisionAPIFaceExtractor()
result1 = ext.transform(stim).to_df(handle_annotations='first')
assert 'joyLikelihood' in result1.columns
# All records
ext = GoogleVisionAPIFaceExtractor()
result2 = ext.transform(stim).to_df()
assert 'joyLikelihood' in result2.columns
assert result2.shape[0] > result1.shape[0]
def test_google_vision_api_face_extractor():
ext = GoogleVisionAPIFaceExtractor(num_retries=5)
assert ext.validate_keys()
filename = join(get_test_data_path(), 'image', 'obama.jpg')
stim = ImageStim(filename)
result = ext.transform(stim).to_df()
assert 'joyLikelihood' in result.columns
assert result['joyLikelihood'][0] == 'VERY_LIKELY'
assert float(result['face_detectionConfidence'][0]) > 0.7
ext = GoogleVisionAPIFaceExtractor(discovery_file='nogood')
assert not ext.validate_keys()
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'))
features, data = ext._parse_annotations(response['faceAnnotations'])
assert len(features) == len(data)
assert data[features.index('angerLikelihood')] == 'VERY_UNLIKELY'
assert data[features.index(
'landmark_LEFT_EYE_BOTTOM_BOUNDARY_y')] == 257.023
assert np.isnan(data[features.index('boundingPoly_vertex2_y')])
def test_convert_to_long_graph():
image_dir = join(get_test_data_path(), 'image')
stim = ImageStim(join(image_dir, 'obama.jpg'))
ext = GoogleVisionAPIFaceExtractor()
g = Graph([ext])
timeline = g.run(stim)
long_timeline = to_long_format(timeline)
assert 'feature' in long_timeline.columns
assert 'extractor' in long_timeline.columns
assert 'history' in long_timeline.columns
def extract_faces(video):
frame_sampling_filter = FrameSamplingFilter(hertz=1)
sampled_video = frame_sampling_filter.transform(video)
ext = GoogleVisionAPIFaceExtractor()
results = ext.transform(sampled_video)
res = merge_results(results,
metadata=False,
format='long',
extractor_names=False,
object_id=False)
res = res[res['feature'] == 'face_detectionConfidence']
res = res.drop(['order'], axis=1)
res = res.fillna(0)
res['value'] = np.round(res['value'])
res.rename(columns={
'value': 'modulation',
'feature': 'trial_type'
},
inplace=True)
res.to_csv('events/visual_face_events.csv')
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_multiple_face_extraction():
filename = join(get_test_data_path(), 'image', 'thai_people.jpg')
stim = ImageStim(filename)
# Only first record
ext = GoogleVisionAPIFaceExtractor()
result1 = ext.transform(stim).to_df(handle_annotations='first')
assert 'joyLikelihood' in result1.columns
# All records
ext = GoogleVisionAPIFaceExtractor()
result2 = ext.transform(stim).to_df()
assert 'joyLikelihood' in result2.columns
assert result2.shape[0] > result1.shape[0]
# obama_trump.py # inspired by https://github.com/tyarkoni/pliers # see also http://tyarkoni.github.io/pliers/ from pliers.extractors import GoogleVisionAPIFaceExtractor obama_img = 'img/obama.jpg' trump_img = 'img/trump.jpg' ext = GoogleVisionAPIFaceExtractor() obama = ext.transform(obama_img).to_df() trump = ext.transform(trump_img).to_df() print(obama['angerLikelihood']) print(obama['joyLikelihood']) print(trump['angerLikelihood']) print(trump['joyLikelihood'])
from pliers.extractors import GoogleVisionAPIFaceExtractor
ext = GoogleVisionAPIFaceExtractor()
result = ext.transform('/home/icarus/projects/pliers/pliers/tests/data/image/obama.jpg').to_df()
print result
