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_small_pipeline2():
filename = join(get_test_data_path(), 'image', 'button.jpg')
nodes = [BrightnessExtractor(), VibranceExtractor()]
graph = Graph(nodes)
result = list(graph.run([filename], merge=False))
history = result[0].history.to_df()
assert history.shape == (1, 8)
result = merge_results(result, format='wide', extractor_names='multi')
assert ('BrightnessExtractor', 'brightness') in result.columns
brightness = result[('BrightnessExtractor', 'brightness')].values[0]
vibrance = result[('VibranceExtractor', 'vibrance')].values[0]
assert_almost_equal(brightness, 0.746965, 5)
assert ('VibranceExtractor', 'vibrance') in result.columns
assert_almost_equal(vibrance, 841.577274, 5)
def test_small_pipeline_json_spec2():
pytest.importorskip('pytesseract')
filename = join(get_test_data_path(), 'image', 'button.jpg')
stim = ImageStim(filename)
spec = join(get_test_data_path(), 'graph', 'simple_graph.json')
graph = Graph(spec=spec)
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='multi')
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_save_graph():
graph = Graph(
spec=join(get_test_data_path(), 'graph', 'simple_graph.json'))
filename = tempfile.mkstemp()[1]
graph.save(filename)
assert os.path.exists(filename)
same_graph = Graph(spec=filename)
os.remove(filename)
assert graph.to_json() == same_graph.to_json()
img = join(get_test_data_path(), 'image', 'button.jpg')
res = same_graph.run(img)
assert res['LengthExtractor#text_length'][0] == 4
def test_big_pipeline_json():
pytest.importorskip('pygraphviz')
filename = join(get_test_data_path(), 'video', 'obama_speech.mp4')
video = VideoStim(filename)
nodes = {
"roots": [{
"transformer":
"FrameSamplingFilter",
"parameters": {
"every": 15
},
"children": [{
"transformer": "TesseractConverter",
"children": [{
"transformer": "LengthExtractor"
}]
}, {
"transformer": "VibranceExtractor"
}, {
"transformer": "BrightnessExtractor"
}]
}, {
"transformer":
"VideoToAudioConverter",
"children": [{
"transformer": "WitTranscriptionConverter",
"children": [{
"transformer": "LengthExtractor"
}]
}]
}]
}
graph = Graph(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_node_arg_parsing():
n1, n2 = 'MyLovelyExtractor', ['MyLovelyExtractor']
args1 = Graph._parse_node_args(n1)
args2 = Graph._parse_node_args(n2)
assert args1 == args2 == {'transformer': 'MyLovelyExtractor'}
node = ('saliencyextractor', [])
args = Graph._parse_node_args(node)
assert set(args.keys()) == {'transformer', 'children'}
node = ('saliencyextractor', [('child1'), ('child2')], 'my_name')
args = Graph._parse_node_args(node)
assert set(args.keys()) == {'transformer', 'name', 'children'}
assert len(args['children']) == 2
node = {'transformer': '...', 'name': '...'}
args = Graph._parse_node_args(node)
assert args == node
def test_multiple_text_filters():
stim = TextStim(text='testing the filtering features')
filt1 = TokenizingFilter()
filt2 = WordStemmingFilter()
stemmed_tokens = filt2.transform(filt1.transform(stim))
full_text = ' '.join([s.text for s in stemmed_tokens])
assert full_text == 'test the filter featur'
stim = TextStim(text='ARTICLE ONE: Rights')
g = Graph()
g.add_node(LowerCasingFilter())
filt1 = LowerCasingFilter()
filt2 = PunctuationRemovalFilter()
filt3 = TokenizingFilter()
final_texts = filt3.transform(filt2.transform(filt1.transform(stim)))
assert len(final_texts) == 3
assert final_texts[0].text == 'article'
assert final_texts[0].order == 0
assert final_texts[1].text == 'one'
assert final_texts[2].text == 'rights'
assert final_texts[2].order == 2
def test_small_pipeline_json_spec():
pytest.importorskip('pytesseract')
filename = join(get_test_data_path(), 'image', 'button.jpg')
stim = ImageStim(filename)
nodes = {
"roots": [{
"transformer":
"TesseractConverter",
"children": [{
"transformer": "LengthExtractor",
"children": []
}]
}]
}
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='multi')
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_graph_scikit():
pytest.importorskip('pytesseract')
pytest.importorskip('sklearn')
image_dir = join(get_test_data_path(), 'image')
stim1 = join(image_dir, 'apple.jpg')
stim2 = join(image_dir, 'button.jpg')
graph_spec = join(get_test_data_path(), 'graph', 'simple_graph.json')
graph = Graph(spec=graph_spec)
trans = PliersTransformer(graph)
res = trans.fit_transform([stim1, stim2])
assert res.shape == (2, 1)
assert res[0][0] == 4 or res[1][0] == 4
meta = trans.metadata_
assert 'history' in meta.columns
assert meta['history'][1] == 'ImageStim->TesseractConverter/TextStim'
def test_within_pipeline():
pytest.importorskip('cv2')
pytest.importorskip('sklearn')
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import Normalizer
stim = join(get_test_data_path(), 'image', 'apple.jpg')
graph = Graph([BrightnessExtractor(), SharpnessExtractor()])
trans = PliersTransformer(graph)
normalizer = Normalizer()
pipeline = Pipeline([('pliers', trans), ('normalizer', normalizer)])
res = pipeline.fit_transform(stim)
assert res.shape == (1, 2)
assert np.isclose(res[0][0], 0.66393, 1e-5)
assert np.isclose(res[0][1], 0.74780, 1e-5)
meta = trans.metadata_
assert 'onset' in meta.columns
assert meta['class'][0] == 'ImageStim'
def test_to_json():
nodes = {
"roots": [{
"transformer":
"FrameSamplingFilter",
"parameters": {
"every": 15
},
"children": [{
"transformer": "TesseractConverter",
"children": [{
"transformer": "LengthExtractor"
}]
}, {
"transformer": "VibranceExtractor"
}, {
"transformer": "BrightnessExtractor"
}]
}, {
"transformer":
"VideoToAudioConverter",
"children": [{
"transformer": "WitTranscriptionConverter",
"children": [{
"transformer": "LengthExtractor"
}]
}]
}]
}
graph = Graph(nodes)
assert graph.to_json() == nodes
graph = Graph(
spec=join(get_test_data_path(), 'graph', 'simple_graph.json'))
simple_graph = {
"roots": [{
"transformer": "TesseractConverter",
"children": [{
"transformer": "LengthExtractor"
}]
}]
}
assert graph.to_json() == simple_graph
filename = join(get_test_data_path(), 'image', 'button.jpg')
res = graph.run(filename)
assert res['LengthExtractor#text_length'][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
```
from pliers.graph import Graph
# Define nodes
nodes = [
(FrameSamplingFilter(hertz=0.1),
['FaceRecognitionFaceLandmarksExtractor', 'BrightnessExtractor']),
(STFTAudioExtractor(freq_bins=[(100, 300)])),
('RevAISpeechAPIConverter',
[PredefinedDictionaryExtractor(['affect/V.Mean.Sum','subtlexusfrequency/Lg10WF']),
'VADERSentimentExtractor'])
]
# Initialize and execute Graph
g = Graph(nodes)
# Arguments to merge_results can be passed in here
df = g.transform(sherlock_video)
```
This short example demostrates a powerful way to express complex extraction workflows in *pliers*.
If you'd like to learn more about the Graph API, you can head over to the [documentation](http://tyarkoni.github.io/pliers/graphs.html).
# Where to go from here?
*Pliers* is a powerful, yet easy to use Python library for multi-modal feature extraction. In this short tutorial, you've seen how to use *pliers* to modify, convert and extract features from stimuli.
To see the full range of `Transformers` implemented in *pliers*, [refer to this listing](http://tyarkoni.github.io/pliers/transformers.html)
def test_stim_results():
stim = TextStim(text='some, example the text.')
g = Graph()
g.add_nodes(
['PunctuationRemovalFilter', 'TokenRemovalFilter', 'TokenizingFilter'],
mode='vertical')
final_stims = g.run(stim, merge=False)
assert len(final_stims) == 2
assert final_stims[1].text == 'text'
n = Node('PunctuationRemovalFilter', name='punc')
g = Graph([n])
g.add_nodes(['TokenizingFilter', 'LengthExtractor'], parent=n)
results = g.run(stim)
assert isinstance(results, pd.DataFrame)
assert results['LengthExtractor#text_length'][0] == 21
with pytest.raises(ValueError):
g.run(stim, invalid_results='fail')
def test_add_children():
graph = Graph()
de1, de2, de3 = DummyExtractor(), DummyExtractor(), DummyExtractor()
graph.add_nodes([de1, de2, de3])
assert len(graph.roots) == 3
assert all([isinstance(c, Node) for c in graph.roots])
def test_adding_nodes():
graph = Graph()
graph.add_children(['VibranceExtractor', 'BrightnessExtractor'])
assert len(graph.roots) == 2
assert len(graph.nodes) == 2
for r in graph.roots:
assert len(r.children) == 0
img = ImageStim(join(get_test_data_path(), 'image', 'button.jpg'))
results = graph.run(img, merge=False)
assert len(results) == 2
assert_almost_equal(results[0].to_df()['vibrance'][0], 841.577274, 5)
assert_almost_equal(results[1].to_df()['brightness'][0], 0.746965, 5)
graph = Graph()
graph.add_chain(['PunctuationRemovalFilter', 'LengthExtractor'])
txt = TextStim(text='the.best.text.')
results = graph.run(txt, merge=False)
assert len(results) == 1
assert results[0].to_df()['text_length'][0] == 11
with pytest.raises(ValueError):
graph.add_nodes(['LengthExtractor'], mode='invalid')
