def classify_images(self, keywords=[], limit=25):
"""
Worker task to retrieve a list of automatically categorized images from
Wikimedia Commons from a given list of keywords.
"""
if not len(keywords):
raise AssertionError
with app.app_context():
def supported_extractors():
extractors = []
extractors.append(SizeFeature())
extractors.append(ColorFeature())
extractors.append(HistogramFeature())
extractors.append(GradientFeature())
extractors.append(FaceFeature(app.config["FACE_CLASSIFIER"]))
extractors.append(GeoFeature())
extractors.append(FormatFeature())
extractors.append(WordsFeature.create_from(app.config["WORDS_CONFIG"]))
return extractors
def create_response_entry(label, sample):
return {"thumbnail": sample.thumbnail, "image": sample.url, "label": label, "title": sample.url}
def create_response(entries):
return {"current": 100, "total": 100, "result": entries}
# keep track of progress
progress_observer = ProgressObserver(self)
progress_observer.update(5)
# query dpedia for related images based on given keywords
if limit > app.config["QUERY_LIMIT"]:
limit = app.config["QUERY_LIMIT"]
searchterm = " ".join(keywords)
uris = fetch_uris_from_metadata(searchterm, limit, multiple=False)
progress_observer.update(20)
# download images and metadata into temp folder with unique task id
temp_folder = os.path.join(app.config["DOWNLOAD_DIRECTORY"], classify_images.request.id)
images_and_metadata(uris, temp_folder, False, observer=progress_observer)
progress_observer.update(80)
# load dataset and extract features
dataset = Dataset(logging=True)
dataset.read(root=temp_folder, extractors=supported_extractors(), unlabeled_data=True)
dataset_config = json.load(open(app.config["DATASET_CONFIG"]))
dataset.means = dataset_config["means"]
dataset.stds = dataset_config["stds"]
dataset.normalize()
progress_observer.update(90)
# predict labels using the trained classifier
classifier = joblib.load(app.config["WIKIMEDIA_CLASSIFIER"])
predictions = classifier.predict(dataset.data)
progress_observer.update(95)
# build response
suggestions = []
for index, sample in enumerate(dataset.samples):
label = np.asscalar(predictions[index])
entry = create_response_entry(label, sample)
suggestions.append(entry)
result = create_response(suggestions)
# cleanup temporary directory
delete_directory(temp_folder)
progress_observer.update(100)
return result
def classify_images(self, keywords=[], limit=25):
"""
Worker task to retrieve a list of automatically categorized images from
Wikimedia Commons from a given list of keywords.
"""
if not len(keywords):
raise AssertionError
with app.app_context():
def supported_extractors():
extractors = []
extractors.append(SizeFeature())
extractors.append(ColorFeature())
extractors.append(HistogramFeature())
extractors.append(GradientFeature())
extractors.append(FaceFeature(app.config['FACE_CLASSIFIER']))
extractors.append(GeoFeature())
extractors.append(FormatFeature())
extractors.append(
WordsFeature.create_from(app.config['WORDS_CONFIG']))
return extractors
def create_response_entry(label, sample):
return {
'thumbnail': sample.thumbnail,
'image': sample.url,
'label': label,
'title': sample.url
}
def create_response(entries):
return {'current': 100, 'total': 100, 'result': entries}
# keep track of progress
progress_observer = ProgressObserver(self)
progress_observer.update(5)
# query dpedia for related images based on given keywords
if limit > app.config['QUERY_LIMIT']:
limit = app.config['QUERY_LIMIT']
searchterm = ' '.join(keywords)
uris = fetch_uris_from_metadata(searchterm, limit, multiple=False)
progress_observer.update(20)
# download images and metadata into temp folder with unique task id
temp_folder = os.path.join(app.config['DOWNLOAD_DIRECTORY'],
classify_images.request.id)
images_and_metadata(uris,
temp_folder,
False,
observer=progress_observer)
progress_observer.update(80)
# load dataset and extract features
dataset = Dataset(logging=True)
dataset.read(root=temp_folder,
extractors=supported_extractors(),
unlabeled_data=True)
dataset_config = json.load(open(app.config['DATASET_CONFIG']))
dataset.means = dataset_config['means']
dataset.stds = dataset_config['stds']
dataset.normalize()
progress_observer.update(90)
# predict labels using the trained classifier
classifier = joblib.load(app.config['WIKIMEDIA_CLASSIFIER'])
predictions = classifier.predict(dataset.data)
progress_observer.update(95)
# build response
suggestions = []
for index, sample in enumerate(dataset.samples):
label = np.asscalar(predictions[index])
entry = create_response_entry(label, sample)
suggestions.append(entry)
result = create_response(suggestions)
# cleanup temporary directory
delete_directory(temp_folder)
progress_observer.update(100)
return result
assert all(len(x) == len(data[0]) for x in data)
with open(filename, 'w') as csv:
csv.write(','.join(captions) + '\n')
for row in range(len(data[0])):
csv.write(','.join(str(column[row]) for column in data) + '\n')
if __name__ == '__main__':
parser = ArgumentParser(description='Measure statistics of features '
'within the images of the same class to evaluate features.',
formatter_class=ArgumentDefaultsHelpFormatter)
parser.add_argument('features',
help='Path to the JSON file containing extracted features of the '
'dataset')
parser.add_argument('-o', '--output', default='<folder>/evaluation.csv',
help='Filename of the CSV file where p-values will be written to; '
'<folder> is the directory of the features file')
args = parser.parse_args()
folder = os.path.splitext(os.path.split(args.features)[0])[0]
args.output = args.output.replace('<folder>', folder)
dataset = Dataset()
dataset.load(args.features)
dataset.normalize()
print_chi(dataset)
print('Write CSV table to', args.output)
write_chi(args.output, dataset)
print('Done')
