def test_indico_api_image_extractor():
ext = IndicoAPIImageExtractor(api_key=os.environ['INDICO_APP_KEY'],
models=['fer', 'content_filtering'])
stim1 = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
result1 = merge_results(ext.transform([stim1, stim1]),
extractor_names=False)
outdfKeysCheck = {
'object_id', 'fer_Surprise', 'fer_Neutral', 'fer_Sad', 'fer_Happy',
'fer_Angry', 'fer_Fear', 'content_filtering'
}
meta_columns = {
'source_file', 'history', 'class', 'filename', 'onset', 'duration',
'order'
}
assert set(result1.columns) - set(['stim_name'
]) == outdfKeysCheck | meta_columns
assert result1['content_filtering'][0] < 0.2
stim2 = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
result2 = ext.transform(stim2).to_df(timing=False, object_id=True)
assert set(result2.columns) == outdfKeysCheck
assert result2['fer_Happy'][0] > 0.7
url = 'https://via.placeholder.com/350x150'
stim = ImageStim(url=url)
result = ext.transform(stim).to_df()
assert result['fer_Neutral'][0] > 0.
def test_clarifai_api_extractor():
stim = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
ext = ClarifaiAPIExtractor()
assert ext.validate_keys()
result = ext.transform(stim).to_df()
assert result['apple'][0] > 0.5
assert result.ix[:, 5][0] > 0.0
result = ClarifaiAPIExtractor(max_concepts=5).transform(stim).to_df()
assert result.shape == (1, 9)
result = ClarifaiAPIExtractor(min_value=0.9).transform(stim).to_df(
object_id=False)
assert all(np.isnan(d) or d > 0.9 for d in result.values[0, 3:])
concepts = ['cat', 'dog']
result = ClarifaiAPIExtractor(select_concepts=concepts).transform(stim)
result = result.to_df()
assert result.shape == (1, 6)
assert 'cat' in result.columns and 'dog' in result.columns
url = 'https://tuition.utexas.edu/sites/all/themes/tuition/logo.png'
stim = ImageStim(url=url)
result = ClarifaiAPIExtractor(max_concepts=5).transform(stim).to_df()
assert result.shape == (1, 9)
assert result['symbol'][0] > 0.8
ext = ClarifaiAPIExtractor(api_key='nogood')
assert not ext.validate_keys()
def test_clarifai_api_extractor():
stim = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
ext = ClarifaiAPIImageExtractor()
assert ext.validate_keys()
result = ext.transform(stim).to_df()
assert result['apple'][0] > 0.5
assert result.ix[:, 5][0] > 0.0
result = ClarifaiAPIImageExtractor(max_concepts=5).transform(stim).to_df()
assert result.shape == (1, 9)
result = ClarifaiAPIImageExtractor(min_value=0.9).transform(stim).to_df(
object_id=False)
assert all(np.isnan(d) or d > 0.9 for d in result.values[0, 3:])
concepts = ['cat', 'dog']
result = ClarifaiAPIImageExtractor(
select_concepts=concepts).transform(stim)
result = result.to_df()
assert result.shape == (1, 6)
assert 'cat' in result.columns and 'dog' in result.columns
url = 'https://via.placeholder.com/350x150'
stim = ImageStim(url=url)
result = ClarifaiAPIImageExtractor(max_concepts=5).transform(stim).to_df()
assert result.shape == (1, 9)
assert result['graphic'][0] > 0.8
ext = ClarifaiAPIImageExtractor(api_key='nogood')
assert not ext.validate_keys()
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 'joyLikelihood' in result.columns
assert result['joyLikelihood'][0] == 'VERY_LIKELY'
assert result['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 '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 'joyLikelihood' not in result.columns
assert result.shape == (17, 7)
def test_indico_api_image_extractor():
ext = IndicoAPIImageExtractor(api_key=os.environ['INDICO_APP_KEY'],
models=['fer', 'content_filtering'])
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
result1 = ext.transform(stim1).to_df()
outdfKeysCheck = set(['onset',
'duration',
'fer_Surprise',
'fer_Neutral',
'fer_Sad',
'fer_Happy',
'fer_Angry',
'fer_Fear',
'content_filtering'])
assert set(result1.columns) == outdfKeysCheck
assert result1['content_filtering'][0] < 0.1
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
result2 = ext.transform(stim2).to_df()
assert set(result2.columns) == outdfKeysCheck
assert result2['fer_Happy'][0] > 0.7
def test_indico_api_image_extractor():
ext = IndicoAPIImageExtractor(api_key=os.environ['INDICO_APP_KEY'],
models=['fer', 'content_filtering'])
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
result1 = ExtractorResult.merge_stims(ext.transform([stim1, stim1]))
outdfKeysCheck = {
'onset',
'duration',
'fer_Surprise',
'fer_Neutral',
'fer_Sad',
'fer_Happy',
'fer_Angry',
'fer_Fear',
'content_filtering'}
meta_columns = {'source_file',
'history',
'class',
'filename'}
assert set(result1.columns) - set(['stim_name']) == outdfKeysCheck | meta_columns
assert result1['content_filtering'][0] < 0.2
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
result2 = ext.transform(stim2).to_df()
assert set(result2.columns) == outdfKeysCheck
assert result2['fer_Happy'][0] > 0.7
def test_compound_stim():
audio_dir = join(get_test_data_path(), 'audio')
audio = AudioStim(join(audio_dir, 'crowd.mp3'))
image1 = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
image2 = ImageStim(join(get_test_data_path(), 'image', 'obama.jpg'))
filename = join(get_test_data_path(), 'video', 'small.mp4')
video = VideoStim(filename)
text = ComplexTextStim(text="The quick brown fox jumped...")
stim = CompoundStim([audio, image1, image2, video, text])
assert len(stim.elements) == 5
assert isinstance(stim.video, VideoStim)
assert isinstance(stim.complex_text, ComplexTextStim)
assert isinstance(stim.image, ImageStim)
with pytest.raises(AttributeError):
stim.nonexistent_type
assert stim.video_frame is None
# Test iteration
len([e for e in stim]) == 5
imgs = stim.get_stim(ImageStim, return_all=True)
assert len(imgs) == 2
assert all([isinstance(im, ImageStim) for im in imgs])
also_imgs = stim.get_stim('image', return_all=True)
assert imgs == also_imgs
def test_clarifai_api_extractor_batch():
stim = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
stim2 = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
ext = ClarifaiAPIImageExtractor()
results = ext.transform([stim, stim2])
results = merge_results(results)
assert results['ClarifaiAPIImageExtractor#apple'][0] > 0.5 or \
results['ClarifaiAPIImageExtractor#apple'][1] > 0.5
def test_clarifai_api_extractor_batch():
image_dir = join(get_test_data_path(), 'image')
stim = ImageStim(join(image_dir, 'apple.jpg'))
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
ext = ClarifaiAPIExtractor()
results = ext.transform([stim, stim2])
results = merge_results(results)
assert results['ClarifaiAPIExtractor#apple'][0] > 0.5 or \
results['ClarifaiAPIExtractor#apple'][1] > 0.5
def test_tfhub_image_reshape():
stim = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
stim2 = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
ext = TFHubImageExtractor(MNET_URL,
reshape_input=(224, 224, 3),
features='feature_vector')
df = merge_results(ext.transform([stim, stim2]), extractor_names=False)
assert df.shape[0] == 2
assert all([len(v) == 1280 for v in df['feature_vector']])
def test_implicit_stim_iteration():
np.random.seed(100)
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
de = DummyExtractor()
results = de.transform([stim1, stim2])
assert len(results) == 2
assert isinstance(results[0], ExtractorResult)
def test_indico_api_extractor_rate_limit():
stim = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
stim2 = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
ext = IndicoAPIImageExtractor(models=['fer'], rate_limit=5)
ext._batch_size = 1
t1 = time.time()
ext.transform([stim, stim2])
t2 = time.time()
assert t2 - t1 >= 5
def test_transformations_on_compound_stim():
image1 = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
image2 = ImageStim(join(get_test_data_path(), 'image', 'obama.jpg'))
text = ComplexTextStim(text="The quick brown fox jumped...")
stim = CompoundStim([image1, image2, text])
ext = BrightnessExtractor()
results = ext.transform(stim)
assert len(results) == 2
assert np.allclose(results[0].data[0], 0.88784294)
def test_image_stim_bytestring():
path = join(get_test_data_path(), 'image', 'apple.jpg')
img = ImageStim(path)
assert img._bytestring is None
bs = img.get_bytestring()
assert isinstance(bs, str)
assert img._bytestring is not None
raw = bs.encode()
with open(path, 'rb') as f:
assert raw == base64.b64encode(f.read())
def test_microsoft_vision_api_text_converter():
conv = MicrosoftAPITextConverter()
img = ImageStim(join(IMAGE_DIR, 'button.jpg'))
text = conv.transform(img).text
assert 'Exit' in text
conv = MicrosoftAPITextConverter()
img = ImageStim(join(IMAGE_DIR, 'CC0', '28010844841_c5b81cb9cc_z.jpg'))
text = conv.transform(img).text
assert 'Santander\nSantander' in text
def test_merge_extractor_results_by_stims():
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
de = DummyExtractor()
results = [de.transform(stim1), de.transform(stim2)]
df = ExtractorResult.merge_stims(results)
assert df.shape == (200, 6)
assert set(df.columns.tolist()) == set(['onset', 'duration', 0, 1, 2, 'stim'])
assert set(df['stim'].unique()) == set(['obama.jpg', 'apple.jpg'])
def test_image_stim_bytestring():
path = join(get_test_data_path(), 'image', 'apple.jpg')
img = ImageStim(path)
assert img._bytestring is None
bs = img.get_bytestring()
assert isinstance(bs, str)
assert img._bytestring is not None
raw = bs.encode()
with open(path, 'rb') as f:
assert raw == base64.b64encode(f.read())
def test_microsoft_vision_api_adult_extractor():
ext = MicrosoftVisionAPIAdultExtractor()
img = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert res.shape == (1, 4)
assert res['adultScore'][0] < 0.5
img = ImageStim(join(IMAGE_DIR, 'CC0', '3333259349_0177d46bbf_z.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert res['adultScore'][0] > 0.1
assert res['racyScore'][0] > 0.1
def test_get_filename():
url = 'https://archive.org/download/999WavFiles/TANKEN.WAV'
audio = AudioStim(url=url)
with audio.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
url = 'https://archive.org/download/NIX-C-1987-11903/1987_11903L.jpg'
image = ImageStim(url=url)
with image.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
def test_get_filename():
url = 'http://www.bobainsworth.com/wav/simpsons/themodyn.wav'
audio = AudioStim(url=url)
with audio.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
url = 'https://via.placeholder.com/350x150'
image = ImageStim(url=url)
with image.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
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 = merge_results(ext.transform([img1, img2, img3]))
assert ext.num_calls == 1
assert res.shape == (3, 10)
ext = DummyBatchExtractor(batch_size=1)
res2 = merge_results(ext.transform([img1, img2, img3]))
assert ext.num_calls == 3
assert res.equals(res2)
def test_get_filename():
url = 'http://www.bobainsworth.com/wav/simpsons/themodyn.wav'
audio = AudioStim(url=url)
with audio.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
url = 'https://via.placeholder.com/350x150'
image = ImageStim(url=url)
with image.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
def test_microsoft_vision_api_tag_extractor():
ext = MicrosoftVisionAPITagExtractor()
img = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert 'fruit' in res.columns
assert 'apple' in res.columns
assert res['apple'][0] > 0.7
url = 'https://tuition.utexas.edu/sites/all/themes/tuition/logo.png'
stim = ImageStim(url=url)
result = ext.transform(stim).to_df()
assert result['plate'][0] > 0.1 # doesn't give great labels
def test_microsoft_vision_api_tag_extractor():
ext = MicrosoftVisionAPITagExtractor()
img = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert 'fruit' in res.columns
assert 'apple' in res.columns
assert res['apple'][0] > 0.7
url = 'https://via.placeholder.com/350x150'
stim = ImageStim(url=url)
result = ext.transform(stim).to_df()
assert result['typography'][0] > 0.1
def test_get_filename():
url = 'http://www.bobainsworth.com/wav/simpsons/themodyn.wav'
audio = AudioStim(url=url)
with audio.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
url = 'https://tuition.utexas.edu/sites/all/themes/tuition/logo.png'
image = ImageStim(url=url)
with image.get_filename() as filename:
assert exists(filename)
assert not exists(filename)
def test_merge_extractor_results():
np.random.seed(100)
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
de_names = ['Extractor1', 'Extractor2', 'Extractor3']
des = [DummyExtractor(name=name) for name in de_names]
results = [de.transform(stim1) for de in des]
results += [de.transform(stim2) for de in des]
df = merge_results(results, format='wide')
assert df.shape == (200, 18)
cols = [
'onset', 'duration', 'order', 'class', 'filename', 'history',
'stim_name', 'source_file'
]
assert not set(cols) - set(df.columns)
assert 'Extractor2#feature_3' in df.columns
df = merge_results(results, format='wide', extractor_names='drop')
assert df.shape == (200, 12)
assert not set(cols) - set(df.columns)
assert 'feature_3' in df.columns
df = merge_results(results, format='wide', extractor_names='multi')
assert df.shape == (200, 18)
_cols = [(c, np.nan) for c in cols]
assert not set(_cols) - set(df.columns)
assert ('Extractor2', 'feature_3') in df.columns
with pytest.raises(ValueError):
merge_results(results, format='long', extractor_names='multi')
df = merge_results(results, format='long', extractor_names='column')
assert df.shape == (1800, 12)
_cols = cols + ['feature', 'extractor', 'value']
assert not set(_cols) - set(df.columns)
row = df.iloc[523, :]
assert row['feature'] == 'feature_2'
assert row['value'] == 475
assert row['extractor'] == 'Extractor1'
df = merge_results(results, format='long', extractor_names='drop')
assert df.shape == (1800, 11)
assert set(_cols) - set(df.columns) == {'extractor'}
df = merge_results(results, format='long', extractor_names='prepend')
assert df.shape == (1800, 11)
row = df.iloc[523, :]
assert row['feature'] == 'Extractor1#feature_2'
def test_merge_extractor_results():
np.random.seed(100)
image_dir = join(get_test_data_path(), 'image')
stim1 = ImageStim(join(image_dir, 'apple.jpg'))
stim2 = ImageStim(join(image_dir, 'obama.jpg'))
de = DummyExtractor()
de_names = ['Extractor1', 'Extractor2', 'Extractor3']
results = [de.transform(stim1, name) for name in de_names]
results += [de.transform(stim2, name) for name in de_names]
df = merge_results(results)
assert df.shape == (355, 14)
cols = ['onset', 'class', 'filename', 'history', 'stim']
assert df.columns.levels[0].unique().tolist() == de_names + cols
assert df.columns.levels[1].unique().tolist() == ['duration', 0, 1, 2, '']
assert set(df['stim'].unique()) == set(['obama.jpg', 'apple.jpg'])
def test_microsoft_vision_api_category_extractor():
ext = MicrosoftVisionAPICategoryExtractor()
img = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert res.shape == (1, 1)
assert 'people_portrait' in res.columns
assert res['people_portrait'][0] > 0.5
def test_microsoft_vision_api_tag_extractor():
ext = MicrosoftVisionAPITagExtractor()
img = ImageStim(join(IMAGE_DIR, 'apple.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert 'fruit' in res.columns
assert 'apple' in res.columns
assert res['apple'][0] > 0.7
def test_microsoft_api_face_emotion_extractor():
ext = MicrosoftAPIFaceEmotionExtractor()
img = ImageStim(join(IMAGE_DIR, 'obama.jpg'))
res = ext.transform(img).to_df(timing=False, object_id=False)
assert res.shape == (1, 8)
assert res['face_emotion_happiness'][0] > 0.5
assert res['face_emotion_anger'][0] < 0.5
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_safe_search():
ext = GoogleVisionAPISafeSearchExtractor(num_retries=5)
filename = join(get_test_data_path(), 'image', 'obama.jpg')
stim = ImageStim(filename)
result = ext.transform(stim).to_df()
assert 'adult' in result.columns
assert result['violence'][0] == 'VERY_UNLIKELY'
