def test_tesseract_converter():
pytest.importorskip('pytesseract')
stim = ImageStim(join(IMAGE_DIR, 'button.jpg'), onset=4.2)
conv = TesseractConverter()
out_stim = conv.transform(stim)
assert out_stim.name == 'text[Exit]'
assert out_stim.history.source_class == 'ImageStim'
assert out_stim.history.source_name == 'button.jpg'
assert out_stim.onset == 4.2
def test_tesseract_converter():
pytest.importorskip('pytesseract')
image_dir = join(get_test_data_path(), 'image')
stim = ImageStim(join(image_dir, 'button.jpg'))
conv = TesseractConverter()
out_stim = conv.transform(stim)
assert out_stim.name == 'text[Exit]'
assert out_stim.history.source_class == 'ImageStim'
assert out_stim.history.source_name == 'button.jpg'
def test_big_pipeline():
pytest.importorskip('pygraphviz')
filename = join(get_test_data_path(), 'video', 'obama_speech.mp4')
video = VideoStim(filename)
visual_nodes = [(FrameSamplingFilter(every=15), [
(TesseractConverter(), [LengthExtractor()]),
VibranceExtractor(),
'BrightnessExtractor',
])]
audio_nodes = [(VideoToAudioConverter(),
[WitTranscriptionConverter(),
'LengthExtractor'], 'video_to_audio')]
graph = Graph()
graph.add_nodes(visual_nodes)
graph.add_nodes(audio_nodes)
results = graph.run(video, merge=False)
result = merge_results(results, format='wide', extractor_names='multi')
# Test that pygraphviz outputs a file
drawfile = next(tempfile._get_candidate_names())
graph.draw(drawfile)
assert exists(drawfile)
os.remove(drawfile)
assert ('LengthExtractor', 'text_length') in result.columns
assert ('VibranceExtractor', 'vibrance') in result.columns
# assert not result[('onset', '')].isnull().any()
assert 'text[negotiations]' in result['stim_name'].values
assert 'frame[90]' in result['stim_name'].values
def test_small_pipeline():
pytest.importorskip('pytesseract')
filename = join(get_test_data_path(), 'image', 'button.jpg')
stim = ImageStim(filename)
nodes = [(TesseractConverter(), [LengthExtractor()])]
graph = Graph(nodes)
result = list(graph.run([stim], merge=False))
history = result[0].history.to_df()
assert history.shape == (2, 8)
assert history.iloc[0]['result_class'] == 'TextStim'
result = merge_results(result, format='wide', extractor_names='prepend')
assert (0, 'text[Exit]') in result['stim_name'].values
assert 'LengthExtractor#text_length' in result.columns
assert result['LengthExtractor#text_length'].values[0] == 4
def test_big_pipeline():
filename = join(get_test_data_path(), 'video', 'obama_speech.mp4')
video = VideoStim(filename)
visual_nodes = [(FrameSamplingConverter(every=15), [
(TesseractConverter(), [LengthExtractor()]),
VibranceExtractor(), 'BrightnessExtractor',
])]
audio_nodes = [(VideoToAudioConverter(), [
WitTranscriptionConverter(), 'LengthExtractor'],
'video_to_audio')]
graph = Graph()
graph.add_nodes(visual_nodes)
graph.add_nodes(audio_nodes)
result = graph.run(video)
assert ('LengthExtractor', 'text_length') in result.columns
assert ('VibranceExtractor', 'vibrance') in result.columns
# assert not result[('onset', '')].isnull().any()
assert 'text[negotiations]' in result['stim'].values
assert 'frame[90]' in result['stim'].values
